Search

Accurate estimation of three-dimensional (3D) information from captured images is essential in numerous computer vision applications. Although binocular stereo vision has been extensively investigated for this task, its reliability is conditioned by the baseline between cameras. A larger baseline improves the resolution of disparity estimation but increases the probability of matching errors. This research presents a reliable method for disparity estimation through progressive baseline increases in multiocular vision. First, a robust rectification method for multiocular images is introduced, satisfying epipolar constraints and minimizing induced distortion. This method can improve rectification error by 25% for binocular images and 80% for multiocular images compared to well-known existing methods. Next, a dense disparity map is estimated by stereo matching from the rectified images with the shortest baseline. Afterwards, the disparity map for the subsequent images with an extended baseline is estimated within a short optimized interval, minimizing the probability of matching errors and further error propagation. This process is iterated until the disparity map for the images with the longest baseline is obtained. The proposed method increases disparity estimation accuracy by 20% for multiocular images compared to a similar existing method. The proposed approach enables accurate scene characterization and spatial point computation from disparity maps with improved resolution. The effectiveness of the proposed method is verified through exhaustive evaluations using well-known multiocular image datasets and physical scenes, achieving superior performance over similar existing methods in terms of objective measures. [ABSTRACT FROM AUTHOR]

Camellia oleifera is an oilseed crop with high economic value. The short optimum harvest period and high labour costs of C. oleifera harvesting have prompted research on intelligent robotic harvesting. This study focused on the determination of grabbing points for the robotic harvesting of C. oleifera fruits, providing a basis for the decision making of the fruit-picking robot. A relatively simple 2D convolutional neural network (CNN) and stereoscopic vision replaced the complex 3D CNN to realise the 3D positioning of the fruit. Apple datasets were used for the pretraining of the model and knowledge transfer, which shared a certain degree of similarity to C. oleifera fruit. In addition, a fully automatic coordinate conversion method has been proposed to transform the fruit position information in the image into its 3D position in the robot coordinate system. Results showed that the You Only Look Once (YOLO)v8x model trained using 1012 annotated samples achieved the highest performance for fruit detection, with mAP 50 of 0.96 on the testing dataset. With knowledge transfer based on the apple datasets, YOLOv8x using few-shot learning realised a testing mAP 50 of 0.95, reducing manual annotation. Moreover, the error in the 3D coordinate calculation was lower than 2.1 cm on the three axes. The proposed method provides the 3D coordinates of the grabbing point for the target fruit in the robot coordinate system, which can be transferred directly to the robot control system to execute fruit-picking actions. This dataset was published online to reproduce the results of this study. [Display omitted] • 3D positioning of grabbing points for Camellia oleifera fruit picking is addressed. • 2D CNN and binocular vision replace the complex 3D CNN for 3D positioning of fruit. • Knowledge transfer reduced the manual annotation work for deep learning. • Images with different lighting conditions enhance the robustness of the model. • Automatic coordinate conversion avoids the manual calibration work for robot control. [ABSTRACT FROM AUTHOR]

In recent years, the integration of polarimetric imaging into robotic perception systems has increased significantly, driven by the accessibility of affordable polarimetric sensors. This technology complements traditional color imaging by capturing and analyzing the polarization characteristics of light. This additional information provides robots with valuable insights into object shape, material composition, and other properties, ultimately enabling more robust manipulation tasks. This review aims to provide a comprehensive analysis of the principles behind polarimetric imaging and its diverse applications within the field of robotic perception. By exploiting the polarization state of light, polarimetric imaging offers promising solutions to three key challenges in robot vision: Surface segmentation; depth estimation through polarization patterns; and 3D reconstruction using polarimetric data. This review emphasizes the practical value of polarimetric imaging in robotics by demonstrating its effectiveness in addressing real-world challenges. We then explore potential applications of this technology not only within the core robotics field but also in related areas. Through a comparative analysis, our goal is to elucidate the strengths and limitations of polarimetric imaging techniques. This analysis will contribute to a deeper understanding of its broad applicability across various domains within and beyond robotics. [ABSTRACT FROM AUTHOR]

Direct laser deposition (DLD) requires high-energy input and causes poor stability and portability. To improve the deposited layer quality, conducting online measurements and feedback control of the dimensions, temperature, and other melt-pool parameters during deposition is essential. Currently, melt-pool dimension measurement is mainly based on machine vision methods, which can mostly detect only the deposition direction of a single melt pool, limiting their measurement range and applicability. We propose a binocular-vision-based online measurement method to detect the melt-pool width during DLD. The method uses a perspective transformation algorithm to align multicamera measurements into a single-coordinate system and a fuzzy entropy threshold segmentation algorithm to extract the melt-pool true contour. This effectively captures melt-pool width information in various deposition directions. A DLD measurement system was constructed, establishing an online model that maps the melt-pool width to the offline deposited layer width, validating the accuracy of the binocular vision system in measuring melt-pool width at different deposition angles. The method achieved high accuracy for melt-pool measurements within certain deposition angle ranges. Within the 30°–60° measurement range, the average error is 0.056 mm, with <3% error. The proposed method enhances the detectable range of melt-pool widths, improving cladding layers and parts. [ABSTRACT FROM AUTHOR]

Performance of gear transmissions affects the performance of mechanical equipment. It is necessary to develop more reliable gear pitch and tooth thickness accuracy detection methods in order to evaluate gear transmission performance and detect gear pitch and tooth thickness accuracy more accurately. Based on the basic theory of gears, binocular vision technology, and statistical principles, a new method that measures gear pitch and tooth thickness using machine vision is proposed: coaxial multi-ring detection (MCD). There is no contact, no damage, and a high degree of efficiency with this method. Using this method, we are able to detect the pitch and thickness accuracy of each gear tooth multiple times within the tooth width range and in multiple directions perpendicular to the gear axis. We statistically analyze the measurement results to determine the gear's most accurate detection results. The measurement method for gear machining accuracy is investigated using the coaxial multi-ring detection method. The statistical analysis of multiple measurement results is carried out, and the measurement results obtained are highly consistent with those of the gear detection center. In conclusion, the measurement results of this method are highly reliable, and they can be used as a reliable basis for evaluating gear transmission performance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Measurement Science & Instrumentation is the property of Journal of Measurement Science & Instrumentation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Recent advances have demonstrated that Language Vision Models (LVMs) surpass the existing State-of-the-Art (SOTA) in two-dimensional (2D) computer vision tasks, motivating attempts to apply LVMs to three-dimensional (3D) data. While LVMs are efficient and effective in addressing various downstream 2D vision tasks without training, they face significant challenges when it comes to point clouds, a representative format for representing 3D data. It is more difficult to extract features from 3D data and there are challenges due to large data sizes and the cost of the collection and labelling, resulting in a notably limited availability of datasets. Moreover, constructing LVMs for point clouds is even more challenging due to the requirements for large amounts of data and training time. To address these issues, our research aims to 1) apply the Grounded SAM through Spherical Projection to transfer 3D to 2D, and 2) experiment with synthetic data to evaluate its effectiveness in bridging the gap between synthetic and real-world data domains. Our approach exhibited high performance with an accuracy of 0.96, an IoU of 0.85, precision of 0.92, recall of 0.91, and an F1 score of 0.92, confirming its potential. However, challenges such as occlusion problems and pixel-level overlaps of multi-label points during spherical image generation remain to be addressed in future studies. [ABSTRACT FROM AUTHOR]

With the development of Industry 4.0 and the implementation of the 14th Five-Year Plan, intelligent manufacturing has become a significant trend in the steel industry, which can propel the steel industry toward a more intelligent, efficient, and sustainable direction. At present, the operation mode of unmanned warehouse area for slabs and coils has become relatively mature, while the positioning accuracy requirement of bars is getting more stringent because they are stacked in the warehouse area according to the stacking position and transferred by disk crane. Meanwhile, the traditional laser ranging and line scanning method cannot meet the demand for precise positioning of the whole bundle of bars. To deal with the problems above, this paper applies machine vision technology to the unmanned warehouse area of bars, proposing a binocular vision-based measurement method. On the one hand, a 3D reconstruction model with sub-pixel interpolation is established to improve the accuracy of 3D reconstruction in the warehouse area. On the other hand, a feature point matching algorithm based on motion trend constraint is established by means of multi-sensor data fusion, thus improving the accuracy of feature point matching. Finally, a high-precision unmanned 3D reconstruction of the bar stock area is completed. [ABSTRACT FROM AUTHOR]

Monocular vision-based 3D scene understanding has been an integral part of many machine vision applications. Always, the objective is to measure the depth using a single RGB camera, which is at par with the depth cameras. In this regard, monocular vision-guided autonomous navigation of robots is rapidly gaining popularity among the research community. We propose an effective monocular vision-assisted method to measure the depth of an Unmanned Aerial Vehicle (UAV) from an impending frontal obstacle. This is followed by collision-free navigation in unknown GPS-denied environments. Our approach deals upon the fundamental principle of perspective vision that the size of an object relative to its field of view(FoV) increases as the center of projection moves closer towards the object. Our contribution involves modeling the depth followed by its realization through scale-invariant SURF features. Noisy depth measurements arising due to external wind, or the turbulence in the UAV, are rectified by employing a constant velocity-based Kalman filter model. Necessary control commands are then designed based on the rectified depth value to avoid the obstacle before collision. Rigorous experiments with SURF scale-invariant features reveal an overall accuracy of 88.6% with varying obstacles, in both indoor and outdoor environments. [ABSTRACT FROM AUTHOR]

Real-time 3D scanning of a scene or object using multiple depth cameras is often required in many applications but is still a challenging task for the computer vision community, especially when the object or scene is partially occluded and dynamic. If active depth sensors are used in this case, their resulting depth map quality gets degraded due to interference between active radiations from each depth sensor. Passive 3D sensors like stereo cameras can avoid the issue of interference as they do not emit any active radiation, but they face correspondence problems. Since releasing the commodity depth sensor Microsoft Kinect, researchers are getting more interested in active depth-sensing. However, Kinect sensors have some easily noticeable limitations concerning 3D reconstruction such as: they can provide depth maps for a limited range, their field of view is restricted and holes are observed in the depth map due to occlusion. The above-mentioned limitations can be overcome if multiple Kinect sensors are used simultaneously instead of a single Kinect sensor. Still, the challenge here is to avoid interference between these sensors. We present a comprehensive review of possible solutions to avoid interference between multiple Kinect sensors. Furthermore, we introduce the Kinect technology in detail along with applications where multiple Kinect sensors are used in the literature. We expect that this paper will be helpful to the researchers who want to use multiple Kinect sensors in sharing the workplace in their research. [ABSTRACT FROM AUTHOR]

Some traditional robots are based on offline programming reciprocal motion, and with the continuous upgrades in vision technology, more and more tasks are being replaced with machine vision. At present, the main method of target recognition used in palletizers is the traditional SURF algorithm, but this method of grasping leads to low accuracy due to the influence of too many mis-matched points. Due to the accuracy of robot target localization with binocular-based vision being low, an improved random sampling consistency algorithm for performing complete parallel robot target localization and grasping under the guidance of multi-vision is proposed. Firstly, the improved RANSAC algorithm, based on the SURF algorithm, was created based on the SURF algorithm; next, the parallax gradient method was applied to iterate the matched point pairs several times to further optimize the data; then, the 3D reconstruction was completed using the improved algorithm via the program technique; finally, the obtained data were input into the robot arm, and the camera's internal and external parameters were obtained using the calibration method so that the robot could accurately locate and grasp objects. The experiments show that the improved algorithm shows better recognition accuracy and grasping success with the multi-vision approach. [ABSTRACT FROM AUTHOR]

Deep learning has gained a lot of attention in the last decade for its use in computer vision. However, a barrier to use deep learning in an agricultural context is the need for large datasets. Agricultural processes are situated in uncontrolled environments, making data collection even harder than in other contexts. Factors such as plant growth, weather conditions, and illumination are largely uncontrolled, making it hard to collect all possible variations in a dataset. This study demonstrates how synthetic generated data can aid to overcome the current barrier and it exemplifies this in the context of automating the detection and localisation of Calendula flowers. To this end, a pipeline was created that utilises photogrammetry and a flower field simulator to create synthetic data of a flower field. Next, the synthetic data is used to train a deep neural network to detect flowers and the transfer from simulation to reality (sim-to-real) is demonstrated on real data. Although the flower detector has not been trained on real data, it reaches an F1 score of up to 86% on the test sets of real data. Subsequently, a stereo vision camera system utilises this detection model to accurately determine the 3D positions of the flowers. The localisation results in an error of 6.9 ± 5.1 mm for the prediction of the flower height. In conclusion, leveraging the potential of synthetic data and sim-to-real capabilities can lower the costs of collecting large datasets in uncontrolled environments and can accelerate the development of precision agricultural applications. [Display omitted] • Limited datasets and large possible variations limit deep learning in agriculture. • Synthetic training data is created using photogrammetry and a game engine. • Detection model is trained on synthetically generated data. • Sim-to-real is validated for the detection of real Calendula flowers. • Localisation of flowers is demonstrated towards automated Calendula harvesting. [ABSTRACT FROM AUTHOR]

Aiming at the problems of slow image acquisition and processing speed, large CPU load and low image resolution in traditional binocular vision-based distance measurement of trees and obstacles, a forest target ranging system based on binocular vision is designed to realize the rapid measurement of the distance of forest targets such as trees and obstacles. The binocular camera and FPGA (Field Programmable Gate Array) are used as the image acquisition and processing platform of the system, and the gigabit Ethernet is used to transmit the image to the PC. Then, MATLAB is used to complete the binocular calibration of the system, so as to obtain the internal and external parameters of the binocular camera. Finally, based on VS2022 platform, stereo matching is performed through SGBM (Semi-Global Block Matching) algorithm and BM (Block Matching) algorithm to obtain disparity map and depth map, so that the current distance between trees and obstacles can be obtained through the 3D coordinate information of key points of trees and obstacles. The results show that the relative error of tree and obstacle distance measurement results of SGBM and BM algorithms is less than 2% in the range of 1. 4 m, and the processing speed of the two algorithms for frame is 130 ms and 119 ms, respectively. The results show that the binocular visual ranging system can realize the rapid processing of image data, and it can complete the ranging of forest targets such as trees and obstacles more accurately, providing a reference for the application of computer vision technology in forest resource investigation. [ABSTRACT FROM AUTHOR]

Stereo vision allows machines to perceive their surroundings, with plane identification serving as a crucial aspect of perception. The accuracy of identification constrains the applicability of stereo systems. Some stereo vision cameras are cost-effective, compact, and user-friendly, resulting in widespread use in engineering applications. However, identification errors limit their effectiveness in quantitative scenarios. While certain calibration methods enhance identification accuracy using camera distortion models, they rely on specific models tailored to a camera's unique structure. This article presents a calibration method that is not dependent on any particular distortion model, capable of correcting plane position and orientation identified by any algorithm, provided that the identification error is biased. A high-precision mechanical calibration platform is designed to acquire accurate calibration data while using the same detected material in real measurement scenarios. Experimental comparisons confirm the efficacy of plane pose correction on PCL-RANSAC, with the average relative error of distance reduced by 5.4 times and the average absolute error of angle decreasing by 41.2%. [ABSTRACT FROM AUTHOR]

Ergonomics focuses on the analysis of the interaction between human beings and their working environment. During the riding of a motorbike, ergonomics studies the rider's posture on the motorbike. An incorrect posture can lead to physical and psychological discomfort, and can affect the perception of risk and the handling of the motorcycle. It is important for motorcyclists to adopt a good riding posture, for their health and road safety. The aim of this work is to propose a fast, cheap, and sufficiently robust method for the 3D reconstruction of the posture assumed by a motorcyclist. The stereo vision and the application of OpenPose made it possible to obtain a 3D reconstruction of the key points, and their evolution over time. The evaluation of the distances between the 3D key points, which represent the length of the various parts of the body, appears to remain sufficiently stable over time, and faithful to the real distances, as taken on the motorcyclist themself. The 3D reconstruction obtained can be applied in different fields: ergonomics, motorsport training, dynamics, and fluid dynamics analysis. [ABSTRACT FROM AUTHOR]

Many works have been done in stereo vision due to its critical importance to the different uses and various areas of computer vision. Recently, the popularity of research on the local block matching algorithm is difficult to compete with the convolutional neural network (CNN) approach, whereby the latter method can achieve higher accuracy at the expense of time consumption. However, the simplicity of the local block matching algorithm is easier to be implemented in real applications at a lower cost. Therefore, this paper presents a new study that improved computation and cost aggregation using a progressive approach. A new algorithm to aid in searching locally similar blocks called the ranking-gradient-similarity multi-block strategy (RGSMB) has been presented, improving processing time and accuracy. A new cost computation has been introduced in the proposed algorithm, which fully utilises the information from the limited local window region by combining the cost from three different constraints, including a Ranking constraint, a Gradient constraint, and a Similarity constraint. The proposed algorithm can accomplish remarkable accuracy by combining with multi-block matching (MBM), which is developed to diminish the conventional cost aggregation's constrained shape limitation. We evaluate the RGSMB algorithm's performance and other CNN methods for comparison. KITTI 2012 dataset of 194 and 195 image pairs and the KITTI 2015 dataset of 200 image pairs were used for training and testing. The results indicate that the proposed algorithm is better than the existing approaches, with a higher matching rate using the KITTI benchmark dataset. Compared to existing local block matching algorithms, the average errors of the RGS are less than the CT approach by nearly 9%, which is the 2nd ranked in this analysis. Also, the RGSMB has average errors of 21% less than the S 7 + correlation when comparing with existing CNN methods. It was also observed that the RGSMB could estimate the disparity value more accurately in the depth discontinuities and homogenous regions. [ABSTRACT FROM AUTHOR]

To solve the problem of online detection of coal-carrying rate in gangue, an approach based on particle queuing and binocular machine vision was proposed. First, a queuing device was applied to line up the coal and gangue particles. A binocular camera was used to obtain images of coal and gangue from above the belt. Through image segmentation, the coal and gangue particle regions were divided from the belt background. Then, the Semi-Global Block Matching (SGBM) algorithm was used to obtain the height information matrix of each region. At the same time, the projected area of the particles was calculated from the area of the divided regions. It was converted from pixel units to physical units by capturing an image of a ruler. The height matrix and projected area were combined to construct a mechanism-based volume model by integral principle. Finally, the calculated volume of coal and gangue were multiplied by their respective empirical density to get the mass of particles. The coal-carrying rate in gangue was obtained by dividing the mass of coal by the total mass. The average relative error of the proposed method is 2.79%. It not only overcomes the prediction error caused by particle stacking, but also improves the computational efficiency of image processing, and the "white-box model" is also easy to understand. [ABSTRACT FROM AUTHOR]

During the production, transportation and storage of nonwoven fabric mask, there are many damages caused by human or nonhuman factors. Therefore, checking the defects of nonwoven fabric mask in a timely manner to ensure the reliability and integrity, which plays a positive role in the safe use of nonwoven fabric mask. At present, the wide application of machine vision technology provides a technical mean for the defect detection of nonwoven fabric mask. On the basis of the pre-treatment of the defect images, it can effectively simulate the contour fluctuation grading and gray value change of the defect images, which is helpful to realize the segmentation, classification and recognition of nonwoven fabric mask defect features. First, in order to accurately obtain the image information of the nonwoven fabric mask, the binocular vision calibration method of the defect detection system is discussed. On this basis, the defect detection mechanism of the nonwoven fabric mask is analyzed, and the model of image processing based on spatial domain and Hough transform is established, respectively. The original image of the nonwoven fabric mask is processed by region processing and edge extraction. Second, the defect detection algorithm of nonwoven fabric mask is established and the detection process is designed. Finally, a fast defect detection system for nonwoven fabric mask is designed, and the effectiveness of the detection method for nonwoven fabric mask is analyzed with an example. The results show that this detection method has positive engineering significance for improving the detection efficiency of defects in nonwoven fabric mask. [ABSTRACT FROM AUTHOR]

With the improvement of industrial automation and technological progress, the number of robots continues to increase, application scenarios are becoming more and more complex, and the requirements for automation and intelligence of robots are also increasing. Due to the development of computer technology and artificial intelligence based on machine vision technical robots has received great attention inthe field of research and production. With the growth of demand, rapid and accurate identification and positioning of objects in any posture in complex spatial environments have become a research hotspot. Based on the image feature processing technology, this paper studies the autonomous target recognition and grasping of industrial robots, establishes the coordinate system of the vision system, derives the projection matrix, and builds a parallel binocular stereo vision system. The method adopted in this paper is that the claw at the end of the robot grips the object to move to different poses, which is used as the theoretical pose of the object, and the grasping result of the visual system is used as the actual pose. The two are compared to solve the grasping errors, a total of 8 comparison experiments were made, and these experimental data were collected and decomposed to draw conclusions. Experiments show that the attitude errors in the X, Y, and Z directions are 1.08°, 1.01°, and 0.92°, respectively. Compared with the previous image positioning errors, it can be found that the errors in the actual robot positioning process are too large, which is mainly caused by the uncalibrated robot; the method used can accurately, quickly, and stably realize the recognition and positioning of the target and meet the needs of the robot for real-time grasping. [ABSTRACT FROM AUTHOR]

Real-time detection of the distance between trains is an important way to ensure the safety of rail transit and improve train capacity. In particular, the distance measurement between trains on curved rails is difficult to distance measurement. In order to calculate and optimize the real-time distance measurement formula of the train at the curve, a method of distance measurement of the train at the curve based on machine vision is proposed. In this method, monocular camera is used for track image acquisition, OpenCV algorithm is used to process and analyze the acquired images, and neural network method is used to fit the track line of curved rail, realizing the dynamic extraction of track feature points. The distance formula between trains can be calculated and optimized by building a mathematical model. The experimental results show that the overall error rate of the testing system is less than 9.11% when the duration interval is 40~50 ms. The method for the spacing measurement can be integrated together with other information in the collected images for the information fusion and referred as an important condition in the rail system for a train running. [ABSTRACT FROM AUTHOR]

Introduction: The frequency and the trend of smartphone use increase rapidly, and 85% of Malaysians owns a smartphone and spend an average of 187 minutes per day to use the smartphone. Aims: To evaluate the potential effects of smartphone use on Accommodation and Vergence of the users. Methods: A total of 18 articles were selected in this review following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines, and the research question was formulated based on the population, intervention, control, and outcomes (PICO) method. This review was registered with PROSPERO (reference number: CRD42022293325). Data Sources: Databases namely PubMed, Web of Science, and Science-Direct were used in the article search using appropriate keywords, phrases, and Medical Subject Heading (MeSH) terms. The inclusion criteria of this review were journal articles published from January 2010 until December 2021 with full articles or abstract in English available. Results: Accommodative function has been reported to changed significantly with 20 minutes of smartphone use, with reduced amplitude, facility, relative and increased lag. In addition, vergence function has been reported to be altered significantly with receded near point of convergence. Conclusion: Smartphone use has an effect on the accommodation and vergence parameters among adults. Assessments of accommodation and vergence parameters need to be conducted in patients with the symptoms of Computer Vision Syndrome to prevent vision problems. Future reviews are required in younger cohorts with various smartphone features. [ABSTRACT FROM AUTHOR]

The core aim of motion-recognition technology is to detect moving targets and extract the target's movement characteristics, classifying these so as to judge the corresponding action category. Moving target detection and tracking form the core of computer vision research topics in military visual guidance, robot visual navigation, industrial product detection, medical diagnosis, traffic monitoring, and virtual reality, and is also very important in terms of practical value and the broad prospects for development in other fields. However, in human behavior recognition algorithms, the background, light, environment, and other factors make identification accuracy difficult to obtain and unstable, with limited application scenarios. Because traditional target detection and tracking is based on monocular vision algorithm robustness, which is poor, this makes it difficult to detect and track moving targets in complex environments. In recent years, with the maturity of target detection and visual range-finding technology, pure static target visual barium distance or the depth of target detection cannot meet the demand of the market. Therefore, we need the efficient collection of deep information in moving target detection systems. Binocular stereo vision technology, as a hot research field in computer vision, can be widely used in the field of sports to achieve target detection and ranging functions. In view of this, this paper adopted a stereoscopic vision for use in target detection and tracking methods. This paper proposes a stereo-matching method based on hierarchical network minimum segmentation, where the method uses three-dimensional images from two layers of the pyramid decomposition by splitting the global optimal search strategy into a minimum at the top of the image to match with the initial parallax at the bottom of the image through regional gray correlation matching. Both reduce the search space of the stereo matching and improve matching accuracy. At the same time, this paper uses the motion of a football shot to prospect this recognition method, which can identify the target area. The Snake contour model method was also utilized to extract the target contour. This method has the following three characteristics: when ambient light changes slowly and suddenly, it can correctly detect moving targets; when the object is lit with cast shadows, the moving target can be detected correctly and is not affected by the shadows. When rigid target motion and deformation occur, it can correctly extract the target contour. [ABSTRACT FROM AUTHOR]

With the development of computer vision technology, its applications in forestry are steadily becoming wider. To address the problems of inconvenience in transporting unmanned aerial vehicles (UAVs), as well as the complex operation of large instruments for measurement, a new method based on multi-vision image segmentation and coordinate fusion (MISF) is proposed in this paper for measuring the size of standing trees. In MISF, after images of a standing tree are captured using a camera from multiple angles, a semantic segmentation method based on deep learning is used to segment the main body of the standing tree and automatically detect the edge feature points. Next, the effects of visual field splicing and fusion are analyzed collaboratively using the correlations among images, so as to restore the three-dimensional spatial information of the feature points of the tree to be measured. Lastly, the size attributes of the standing tree, such as height, diameter at breast height (DBH), and crown width, are automatically measured. The urban environment measurement experiment showed that the relative errors of tree height, DBH, and crown width measured using the proposed method, i.e., MISF, were 1.89%, 2.42%, and 3.15%, respectively, representing a significant enhancement compared with binocular measurement. On the one hand, the experimental results exhibited a high degree of measurement accuracy; therefore, MISF can be used for the management inventory of typical forests. On the other hand, MISF cannot be used if a tree's images cannot be acquired due to environmental or other reasons. [ABSTRACT FROM AUTHOR]

Visual Odometry (VO) is a fundamental technique to enhance the navigation capabilities of planetary exploration rovers. By processing the images acquired during the motion, VO methods provide estimates of the relative position and attitude between navigation steps with the detection and tracking of two‐dimensional (2D) image keypoints. This method allows one to mitigate trajectory inconsistencies associated with slippage conditions resulting from dead‐reckoning techniques. We present here an independent analysis of the high‐resolution stereo images of the NASA Mars 2020 Perseverance rover to retrieve its accurate localization on sols 65, 66, 72, and 120. The stereo pairs are processed by using a 3D‐to‐3D stereo‐VO approach that is based on consolidated techniques and accounts for the main nonlinear optical effects characterizing real cameras. The algorithm is first validated through the analysis of rectified stereo images acquired by the NASA Mars Exploration Rover Opportunity, and then applied to the determination of Perseverance's path. The results suggest that our reconstructed path is consistent with the telemetered trajectory, which was directly retrieved onboard the rover's system. The estimated pose is in full agreement with the archived rover's position and attitude after short navigation steps. Significant differences (~10–30 cm) between our reconstructed and telemetered trajectories are observed when Perseverance traveled distances larger than 1 m between the acquisition of stereo pairs. [ABSTRACT FROM AUTHOR]

As a research hotspot in computer vision, 3D object detection has wide application prospects. In the field of autonomous driving, the perception system with three-dimensional object detection function enables the vehicle to perceive the surrounding environment, make the vehicle more intelligent, and play a role in assisting driving. Aiming at two commonly used sensors: monocular camera and lidar, combined with deep learning, this paper separately studies the 3D target detection algorithm of PointPillars based on attention mechanism and the 3D target detection method based on monocular vision. The results show that the detection performance based on monocular vision still has advantages and can be used as an effective supplement to Lidar based three-dimensional target detection, improving the robustness of the sensing system. [ABSTRACT FROM AUTHOR]

Stereopsis is the three-dimensional perception capability, which is possible when binocular vision is present. Development of binocular vision system ends around 7-year-old, and after this time brain connections are already set, therefore, it will be difficult to recover stereopsis. Early diagnosis of Stereoscopic Visual Alterations (SVA) in the childhood is paramount to receive an appropriate treatment as soon as possible. Currently, to detect SVA, ophthalmologists commonly carry out tests based on cards. All these tests are based on the random-dot-stereogram principle, with different seconds of arc images, which allows doctors to graduate stereopsis. Some limits of this tests have been identified, such as monocular clues (e.g., the contours of the objects), or the non-standardized range levels depending on the test. This paper presents a novel concept of measuring stereopsis based on computer vision techniques. The system detects SVA in patients and calculates the degree of the perceived depth. As early diagnosis of SVA may suppose a therapeutic possibility, this platform is aimed at children by using stereoscopic models with varied and attractive designs. To validate the proposal, an early-stage prototype has been implemented and an objective evaluation of the measurement accuracy and reliability has been carried out with satisfactory results. [ABSTRACT FROM AUTHOR]

The bearing stratum of high-rise and ultra-high-rise buildings in southwest China has inevitably faced moderately weathered red mudstone. It was a waste of the potential bearing stratum calculated according to the specification, as the bearing stratum obtained from laboratory and in situ tests was much higher than the values suggested by the specification. Rock mass surface deformation detection is of great significance in the safety management of a foundation project. Some correlation between surface deformation and failure characteristics may exist that could help to understand the bearing stratum of the moderately weathered red mudstone. This research was conducted to study the progressive failure characteristics of the moderately weathered red mudstone through surface deformation. In situ load, triaxial, and binocular visual technology were employed for data acquisition. The proposed conjecture was illustrated and verified by a group of experiments from three construction sites. Five stages could be described as the progressive failure of the moderately weathered red mudstone: compaction, elasticity, elastoplasticity, plasticity, and failure. Furthermore, the surface displacement increment fluctuates with the loading time and fades into the distance. Therefore, this research could provide a robust, practical application for analyzing the progressive failure of moderately weathered red mudstone. [ABSTRACT FROM AUTHOR]

In order to further improve the functional requirements and performance indicators of the industrial robot assembly system and more accurately realize the measurement and recognition of the target position of the assembly line by the vision system, this article constructs a robot assembly line system based on obstacle detection and robot arm obstacle path planning based on machine vision technology and further improves the intelligence and accuracy of the assembly line system through the design and optimization of the system software module. Through the experimental verification of the positioning error based on the eye-to-hand binocular vision system and eye-in-hand monocular vision system, the system proposed in this article meets the design accuracy requirements of less than 0.1 mm in x/y direction and less than 1 mm in depth direction and verifies the feasibility and high accuracy of the system. [ABSTRACT FROM AUTHOR]

The functional performance of concrete structures degrades over time as a result of continuous loads, stress fatigue, and external environmental changes. Thus, periodic diagnoses and inspections are essential because such conditions can eventually lead to disaster. Hence, the detection of cracks in concrete is a key component of structural management. In recent years, deep-learning-based computer vision technologies have emerged as a promising trend and have been actively used for crack detection. Unfortunately, the performance of existing crack detection technologies decreases under environmental conditions that vary widely. To resolve this issue, we propose a new deep neural network that applies an optimal mixing ratio of training data to improve recognition performance alongside an adversarial learning-based balanced ensemble discriminator network. Furthermore, a method to reconstruct the 3-dimensional shape of cracks is proposed using a stereo-vision-based triangulation measurement technique that determines the size of detected cracks. Experimental results show that the proposed algorithm achieved a crack detection performance with a mean intersection-over-union of 84.53% and an F1 score of 82.91%. The proposed inspection technology for concrete structures is expected to be implemented in the future in connection with various automation techniques. [ABSTRACT FROM AUTHOR]

This article aims to explore an effective method for reducing vehicle collisions at unsignalized intersections. First, a monocular-binocular vision switching system is built to enable machine vision-based detection of obstacle vehicles in the left and right front directions. Then, the motion state and trajectory of each obstacle vehicle are predicted, and the intersection points of the trajectories of the obstacle vehicle and the ego vehicle are calculated. On this basis, a cross-conflict judgment model based on trajectories and collision times and a safety assessment model based on safety distance are established. Finally, the conflict judgment and safety assessment for the obstacle vehicles are simulated. The results of the simulation demonstrate that the monocular-binocular vision switching system proposed in this article can achieve a detection accuracy of 95%, a ranging accuracy of 96%, and a cross-conflict detection accuracy of 97%, while ensuring a maximum detection area, which can meet the requirements of traffic safety assurance at unsignalized intersections. [ABSTRACT FROM AUTHOR]

Non-destructive measurement of fish biomass is the key to achieving intelligent farming in aquaculture. Among them, the prerequisite can be the accurate estimation of the full length of fish. In this study, an accurate estimation was proposed for the full length of fish using 3D pose fitting. A summary was given on the previous estimations of fish length in recent years. Taking the Takifugu rubripes as the research object, the accurate estimation of the body length was realized in a non-contact situation. Firstly, the original image was corrected and stereo matched to obtain the depth image using binocular stereoscopic vision technology, and then the foreground segmentation of the fish body was performed by SOLOV2. Secondly, an independent classifier was designed to automatically acquire the fish side images for the full-length estimation. A comparison was made on the classification effects of three classifiers (SVM, Resnet18 and ResNet34). Finally, the ResNet34 network was selected as the image classification with the highest priority of accuracy, while maintaining a short inference time for the single image. As such, the accuracy reached 95.3%, and the inference time was 0.040s in the NVIDIA Geforce RTX 3090 SLI. Thus, the images were efficiently classified to improve the data quality, where the 2135 images of 121 fish were automatically filtered for the subsequent full-length estimation. The image data was fully used to couple the plane features and depth information of the fish images. 3D pose fitting of fish in the x-y and x-z planes was also performed to achieve the full-length estimation of fish. The results showed that the linearity fit was good with R² of 0.90, indicating better linearity between the manually measured and the estimated total length. When the estimated total length and body weight were fitted with the multiplicative power formula, the fit was good with an R² of 0.88, indicating a better correlation. The error analysis showed that the mean absolute error of the estimated full length was about -10.5mm, the mean relative error was 2.67%, the standard deviation of accuracy was 9.45%, and the relative error of the single full-length prediction data fell in the range of -6.68% to 12.12%, demonstrating a higher accuracy and stability. The estimated full length was also taken with the manually measured length as the exact value. Only image data was as the input, where the biological characteristics (such as body size and pigmentation) were the primary judgment factors for the applicability. The length was estimated during fish entering the developmental stage, where the biological characteristics were similar to those of adult fish. Meanwhile, the applicability range of this model for Takifugu rubripes was at least 187-650 mm full-length, according to the growth process and the applicability range of the multiplicative power formula in the existing studies. This finding can provide important technical support for the non-contact fish biomass estimation in the aquaculture process, particularly for the information management, fish growth condition assessment and baiting control of aquaculture. [ABSTRACT FROM AUTHOR]

As people pay more and more attention to a healthy diet, it has become a consensus to eat more coarse grains. The development of its edible value is of great significance for a healthy human diet and has attracted the attention of many scholars and food processing companies. However, due to the differences in protein composition and structure between corn flour and wheat protein, it is difficult to form a network structure during processing, and the viscoelasticity and flexibility are poor. Based on this, this paper proposes a machine vision-based noodle positioning monitoring method to achieve noodle alignment monitoring in the noodle processing process. First, the images are captured by binocular cameras and preprocessed. Further, feature detection and matching algorithms are used to recover the pose information between binocular cameras, and then the recognition targets are matched. Finally, noodle alignment monitoring during noodle processing is achieved. Experiments show that the detection accuracy of the method proposed in this paper is much higher than the traditional manual detection, which can improve the noodle quality and reduce labor costs. [ABSTRACT FROM AUTHOR]

New approaches to 3D vision are enabling new advances in artificial intelligence and autonomous vehicles, a better understanding of how animals navigate the 3D world, and new insights into human perception in virtual and augmented reality. Whilst traditional approaches to 3D vision in computer vision (SLAM: simultaneous localization and mapping), animal navigation (cognitive maps), and human vision (optimal cue integration) start from the assumption that the aim of 3D vision is to provide an accurate 3D model of the world, the new approaches to 3D vision explored in this issue challenge this assumption. Instead, they investigate the possibility that computer vision, animal navigation, and human vision can rely on partial or distorted models or no model at all. This issue also highlights the implications for artificial intelligence, autonomous vehicles, human perception in virtual and augmented reality, and the treatment of visual disorders, all of which are explored by individual articles. This article is part of a discussion meeting issue 'New approaches to 3D vision'. [ABSTRACT FROM AUTHOR]

At present, there are still problems of inaccurate labeling, inaccurate target matching, and excessively complex image processing of machine vision in spatial structure displacement measurement. Therefore, machine vision measurement technology is combined with deep learning algorithm to construct a precise displacement measurement model for largespan spatial structure of buildings based on machine vision technology and deep learning. First. the binocular stereo vision technology based on machine vision is expounded to analyze the deficiencies in measuring displacement of large-scale spatial structures. Second. related concepts of Convolutional Neural Networks (CNNs) are introduced, and You Only Look Once v2 (YOLOv2) is selected as the recognition algorithm of sphere joints iii the long-span spatial structure of buildings. Finally. a displacement measurement system for long-span spatial structures is constructed based on CNN models and YOLOv] algorithm. Images of various spatial structures collected through the Internet and shot by smartphones constitute the data set to test the performance of YOLOv2 recognition algorithm and three kinds of CNN models, namely the AlexNet model, Darkneti 9 model, and Resnet] 52 model. The experimental results demonstrate that the Recall of Darknet19 model is up to 93.9%, and the Intersection Over Union (IOU) is 82.02%, which are at least 3.6% and 4.4% higher than those of the other two niodels, respectively. Besides, the Darknet]9 model performs better in the task of identifying and locating sphere joints in spatial structures. In addition. when the Darknet 19 model is trained about 20,000 times, the Recall of the YOLOv2 recognition algorithm reaches 94.69%, and the IOU attains 84.98 %. Moreover, the average recognition accuracy of YOLOv2 algorithm is 2.3% higher than other recognition algorithms, which has a high recognition level. Furthermore. the relative error of displacement measurement in the single direction of each stage of the measurement modeldesigned here is controlled within 12%, which can meet the requirements of displacement measurement of spatial structure. The purpose of this work is to provide essential technical support for the upgrading of displacement measurement technology of large-span spatial structure of buildings and the improvement of measurement accuracy. [ABSTRACT FROM AUTHOR]

With the development of computer vision technology, target measurement methods have been widely used in robot automatic obstacle avoidance, vehicle-assisted driving and other systems. There are many target measurement technologies available, but most of them are based on binocular or trinocular vision, or based on monocular vision with other auxiliary equipment, or based on monocular vision to measure horizontal target. The first two technologies achieve precise positioning by increasing the amount of data and sacrificing processing speed, while the third only studies the measurement method of the horizontal target. To address the complexity of the multi-equipment measurement methods and the limitation of the monocular measurement methods for horizontal target, this paper proposes a novel monocular vision measurement method for the non-horizontal target. According to the principle of camera imaging, internal and external parameters of the camera and analogue-to-digital conversion principle, the imaging relationship model for measuring the relative height and target distance of non-horizontal target is deduced, and the solvability of the model is demonstrated by mathematics. The experimental results verify the correctness and feasibility of this method. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the development of semiconductor assembly technology, the continuous requirement for the improvement of chip quality caused an increasing pressure on the assembly manufacturing process. The defects of chip pin had been mostly verified by manual inspection, which has low efficiency, high cost, and low reliability. In this paper, we propose a vision measurement method to detect the chip pin defects, such as the pin warping and collapse that heavily influence the quality of chip assembly. This task is performed by extracting the corner feature of the chip pins, computing the corresponding point pairs in the binocular sequence images, and reconstructing the target features of the chip. In the corner feature step, the corner detection of the pins using the gradient correlation matrices (GCM), and the feature point extraction of the chip package body surface using the crossing points of the fitting lines are introduced, respectively. After obtaining the corresponding point pairs, the feature points are utilized to reconstruct the three dimensional (3D) coordinate information in the binocular vision measurement system, and the key geometry dimension of the pins is computed, which reflects whether the quality of the chip pins is up to the standard. The proposed method is evaluated on the chip data, and the effectiveness is also verified by the comparison experiments. [ABSTRACT FROM AUTHOR]

Get in-depth understanding of each part of visual pathway yields insights to conquer the challenges that classic computer vision is facing. Here, we first report the bioinspired striate cortex with binocular and orientation selective receptive field based on the crossbar array of self-powered memristors which is solution-processed monolithic all-perovskite system with each cross-point containing one CsFAPbI3 solar cell directly stacking on the CsPbBr2I memristor. The plasticity of self-powered memristor can be modulated by optical stimuli following triplet-STDP rules. Furthermore, plasticity of 3 × 3 flexible crossbar array of self-powered memristors has been successfully modulated based on generalized BCM learning rule for optical-encoded pattern recognition. Finally, we implemented artificial striate cortex with binocularity and orientation selectivity based on two simulated 9 × 9 self-powered memristors networks. The emulation of striate cortex with binocular and orientation selectivity will facilitate the brisk edge and corner detection for machine vision in the future applications. Designing efficient bio-inspired vision systems remains a challenge. Here, the authors report a bio-inspired striate visual cortex with binocular and orientation selective receptive field based on self-powered memristor to enable machine vision with brisk edge and corner detection in the future applications. [ABSTRACT FROM AUTHOR]

To guide grape picking robots to recognize and classify the grapes with different maturity quickly and accurately in the complex environment of the orchard, and to obtain the spatial position information of the grape clusters, an algorithm of grape maturity detection and visual pre-positioning based on improved YOLOv4 is proposed in this study. The detection algorithm uses Mobilenetv3 as the backbone feature extraction network, uses deep separable convolution instead of ordinary convolution, and uses the h-swish function instead of the swish function to reduce the number of model parameters and improve the detection speed of the model. At the same time, the SENet attention mechanism is added to the model to improve the detection accuracy, and finally the SM-YOLOv4 algorithm based on improved YOLOv4 is constructed. The experimental results of maturity detection showed that the overall average accuracy of the trained SM-YOLOv4 target detection algorithm under the verification set reached 93.52%, and the average detection time was 10.82 ms. Obtaining the spatial position of grape clusters is a grape cluster pre-positioning method based on binocular stereo vision. In the pre-positioning experiment, the maximum error was 32 mm, the mean error was 27 mm, and the mean error ratio was 3.89%. Compared with YOLOv5, YOLOv4-Tiny, Faster_R-CNN, and other target detection algorithms, which have greater advantages in accuracy and speed, have good robustness and real-time performance in the actual orchard complex environment, and can simultaneously meet the requirements of grape fruit maturity recognition accuracy and detection speed, as well as the visual pre-positioning requirements of grape picking robots in the orchard complex environment. It can reliably indicate the growth stage of grapes, so as to complete the picking of grapes at the best time, and it can guide the robot to move to the picking position, which is a prerequisite for the precise picking of grapes in the complex environment of the orchard. [ABSTRACT FROM AUTHOR]

• 3D shape generation using relatively basic optical equipment and tools. • Integration of monocular and binocular vision attributes. • Unique and localised edges with sub-pixel accuracy with the improved algorithm. • Single-image based depth mapping process incorporating defocus and texture. • Spatial resolution and depth of field crucial for measurement accuracy. Aiming at an in-depth material characterisation, the present study introduces a technique to capture the 3D shape change of specimens during static and dynamic tensile tests. The hybrid optical technique integrates stereovision and monocular cues. Stereovision imaging coupled with digital image correlation enables precise surface deformation measurements. The data is supplemented with accurate specimen edge coordinates identified via an improved sub-pixel edge detection method. Finally, a depth-mapping algorithm based on computer vision strategy is implemented, which uses monocular cues such as defocus and texture to estimate the shape change of the specimen side profile with high reliability. The sequence of steps allows a complete 3D shape reconstruction of the sample. The accuracy is sensitive to the spatial resolution of the images and lighting conditions, which are particularly challenging for the dynamic tests. However, combining monocular and binocular imaging significantly improves the reconstruction. The application of the technique is successfully demonstrated on flat and round tensile specimens, proving its potential in determining heterogeneous deformations using relatively basic optical equipment. The proposed technique is additionally instrumental in characterising the mechanical behaviour of materials even under very large plastic deformations. The effectiveness and accuracy of the approach are verified by a relative error assessment of the final cross-sectional area and dimensions of the fractured specimens. [ABSTRACT FROM AUTHOR]

• YOLOv8 enables intelligent stereo vision for blast-induced fragmentation analysis. • AI and computer vision automate and enhance fragmentation assessment. • Blender & real explosion datasets ensure accurate results. • High accuracy & effective segmentation validate the method. • Reducing manual interventions and enhancing mining efficiency. Rock fragmentation assessment is a critical aspect of evaluating blasting operations in the mining industry, offering insights for optimising procedures and subsequent mining processes. Traditional methods, such as sieving, while accurate, are costly and time-consuming. Digital image analysis methods have emerged as alternatives, yet they face challenges in accurately handling fragments of varying sizes. Recent advancements in computer vision, particularly deep learning techniques, offer promising solutions to automate and refine fragmentation analysis. This paper introduces a novel intelligent stereo vision approach utilising YOLOv8, an advanced deep learning model, for blast-induced fragmentation size distribution assessment at the Golgohar open-pit mine in Iran. By training YOLOv8 with an automated self-labelled dataset and evaluating its performance against real mine site data, this research aims to enhance the accuracy and efficiency of blast fragmentation analysis. The proposed method leverages stereo images and machine learning to provide precise measurements, leading to improved optimisation of blasting parameters and potential economic benefits compared to traditional methods. Through rigorous validation processes and case studies across diverse scenarios, the proposed approach demonstrates robustness and reliability in assessing blast fragmentation, offering a practical and efficient solution for the mining industry's evolving needs. [ABSTRACT FROM AUTHOR]

In an era of increasing screen consumption, the requirement for binocular vision is demanding, leading to the emergence of syndromes such as the computer vision syndrome (CVS) or visual discomfort reported by virtual reality (VR) users. Heterophoria (phoria) is a latent eye misalignment (with a prevalence up to 35%) that appears in conditions that disrupt binocular vision and may affect the quality of binocular fusion. Collinear facilitation (CF), the mechanism for grouping contour elements, is a process that reveals lateral interactions by improving the visibility of a target by flankers placed collinearly. An abnormal pattern of CF has been observed in strabismic amblyopia. We hypothesize that phoria may affect CF in the horizontal meridian (HM) due to latent eye misalignment and its impact on binocular fusion. Fully corrected participants (phoria group and controls) completed a standard CF experiment for horizontal and vertical meridians during binocular and monocular viewing. Phoric observers exhibited (1) an asymmetry and an abnormal pattern of CF only for the HM, during both monocular and binocular viewing, (2) poor binocular summation between the monocular inputs, and (3) no binocular advantage of the CF. Phoria affects the CF in a way that is reminiscent of meridional amblyopia without being attributed to abnormal refraction. The abnormal pattern of CF in monocular viewing suggests that phoria could be a binocular developmental disorder that affects monocular spatial interactions. We suggest that the results could contribute to explain the visual discomfort experienced with VR users or symptoms when presenting CVS. [ABSTRACT FROM AUTHOR]

The use of automation has dramatically increased in various industries and domains including our daily lives. The manufacturing industry is no exception, as it continuously seeks to produce high-quality products at scale. A system devoid of a vision system can be considered a relatively blind tool that cannot cope with the uncertainty of handling components of different geometries that are in different positions. The growing use of vision systems is helping several application areas and contributing significantly in various stages of the production cycle and making the process more efficient and confident. This study aims to evaluate, through techniques of pattern recognition statistics, the use of a low-cost vision system that allows the accurate recognition of the target position without the aid of additional devices. We use metal parts that have the same thickness. These parts are measured using digital static pictures and are compared with the measurements performed using appropriately calibrated metrology tools. The experimental results validate the application of the proposed system in a real-world welding process. [ABSTRACT FROM AUTHOR]

Aiming at the problem that existing stereo matching algorithms is difficult to match in shadow, object edge and illumination reflection regions and has a large number of error results, this paper designed a detachable loss self-attention net (LSAnet) to search for the difficult matching regions in images. Each network layer of LSAnet densely connected with each other, it used atrous convolution to increase the receptive field, and carried out dynamic supervised training with the loss distribution generated by stereo matching algorithm as the label, and finally generated a mask for difficult matching areas to assist stereo matching network for better optimization. At the same time, it improved the classical feature matching cost volume structure in stereo matching network, which reduced the computational load of subsequent 3D convolution and improved the matching efficiency. Experimental results show that the proposed algorithm has higher accuracy than the benchmark algorithm, and can improve the robustness of the algorithm for matching difficult regions. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to study six degrees-of-freedom (6DOF) pose measurement of reflective metal casts by machine vision, analyze the problems existing in the positioning of metal casts by stereo vision sensor in unstructured environment and put forward the visual positioning and grasping strategy that can be used in industrial robot cell. Design/methodology/approach: A multikeypoints detection network Binocular Attention Hourglass Net is constructed, which can complete the two-dimensional positioning of the left and right cameras of the stereo vision system at the same time and provide reconstruction information for three-dimensional pose measurement. Generate adversarial networks is introduced to enhance the image of local feature area of object surface, and the three-dimensional pose measurement of object is completed by combining RANSAC ellipse fitting algorithm and triangulation method. Findings: The proposed method realizes the high-precision 6DOF positioning and grasping of reflective metal casts by industrial robots; it has been applied in many fields and solves the problem of difficult visual measurement of reflective casts. The experimental results show that the system exhibits superior recognition performance, which meets the requirements of the grasping task. Research limitations/implications: Because of the chosen research approach, the research results may lack generalizability. The proposed method is more suitable for objects with plane positioning features. Originality/value: This paper realizes the 6DOF pose measurement of reflective casts by vision system, and solves the problem of positioning and grasping such objects by industrial robot. [ABSTRACT FROM AUTHOR]

The pushing robot working in the complex farming environment encounters several problems. For example, the precision of its navigation path extraction is low, and its working quality is greatly affected by the weather. In view of this, a method of farm operation path extraction based on machine vision is proposed in this study in order to solve the problems above and realize the autonomous and intelligent operation of the robot. First of all, the RGB images of the working area in front of the robot are obtained by using an RGB camera installed on the machine. Then, the collected images are preprocessed by means of sky removal, denoising and grayscale transformation. After that, the image is segmented to obtain the front fence, feed belt and ground data. Finally, the navigation path is obtained by extracting the features of the feed belt. The test results show that the absolute deviation of the pushing robot at different initial lateral distances is less than ±15 cm, and the deviation between the actual navigation route and the target route is within the expected range. The absolute value of the maximum lateral deviation in five test areas is 8.9 cm, and the absolute value of the average maximum lateral deviation is 7.6 cm. These experimental results show that the pushing robot can work stably without disturbing the feeding of cows. Particle swarm optimization is used to optimize the parameters of the PID and find the optimal parameters. This makes the system balanced and more responsive. Through this test, it is found that the initial direction of the robot will have a certain impact on the path production and tracking efficiency, and this effect is more significant when the robot changes the working area or turns. In which case, the trajectory of the robot should be in such a way that it immediately faces the next row at a small angular deviation, thus ensuring smoother motion. The method proposed in this study can provide support for the automatic navigation of pushing robots in dairy farms. [ABSTRACT FROM AUTHOR]

Distance estimation can be achieved by using active sensors or with the help of passive sensors such as cameras. The stereo vision system is generally composed of two cameras to mimic the human binocular vision. In this paper, a Python‐based algorithm is proposed to find the parameters of each camera, rectify the images, create the disparity maps and finally use these maps for distance measurements. Experiments using real‐time images, which were captured from our stereo vision system, of different obstacles positioned at multiple distances (60–200 cm) prove the effectiveness of the proposed program and show that the calculated distance to the obstacle is relatively accurate. The accuracy of distance measurement is up to 99.83%. The processing time needed to calculate the distance between the obstacle and the cameras is less than 0.355 s. [ABSTRACT FROM AUTHOR]