Search

Accurate volume measurement is essential to the marine treasures in aquaculture. However, existing approaches cannot fully meet the growth and evaluation in the volume measurement of sea cucumbers. In this study, the binocular vision was introduced to efficiently and precisely in-situ measure the volume of sea cucumbers. Three modules also included target detection, segmentation, and volume estimation. In the first module, the target detection was used in the variable lighting and environmental conditions under the typical underwater. The reason was that object detection previously failed to monitor underwater environments, due to the fluctuation of light conditions, reflections, and debris in the water. YOLOv8 target detection model was introduced to integrate the multi-head self-attention mechanism, in order to enhance the detection accuracy in these unpredictable conditions. This attention mechanism was significantly improved to detect the sea cucumbers under the complex underwater landscape. A high-precision system was obtained to more effectively process information from different parts of images under these challenging circumstances. In the second module, instance segmentation was used to focus on the precise identification and segmentation of sea cucumber entities. A segmentation model of sea cucumber was constructed using the segment anything model (SAM) with an adapter mechanism. The SAM model was used to more accurately isolate the sea cucumber from its background, even in the presence of noise and other marine organisms in the water. The segmentation was successfully essential for the accuracy of subsequent steps, as the generated mask served as the input for the volume estimation. High-quality mask information was provided to ensure that the shape of the sea cucumber was captured with the necessary details for accurate volume reconstruction. In the third module of volume estimation, the 2D mask maps were input into 3D space to obtain a point cloud representation of sea cucumbers. Poisson surface reconstruction and voxelization were employed to reduce the distortion of the 3D model because point cloud data often suffered from sparsity and noise. Specifically, the sparse data and noise interference were avoided for the accurate 3D model. As such, the actual volume of sea cucumber was faithfully represented for precise measurement. The experimental results demonstrate that the superior performance of the improved detection model was achieved, compared with the existing algorithms. The 92.5% accuracy and a frame rate of 31 frames per second (fps) outperformed the rest, such as Faster RCNN, Cascade RCNN, YOLOv7, and YOLOv8. Additionally, the Poisson surface reconstruction also produced a closer shape approximation of the true sea cucumber, compared with the Alpha Shapes and Ball Pivoting. More accurate volume measurements were better performed at various depths. Specifically, the accuracy of volume measurement reached 94% at a distance of 100 cm, which was 22 percentage points higher than the minimum bounding box and 14 points higher than the Ball Pivoting. Reliable data was then provided to accurately measure the sea cucumber in aquaculture. In conclusion, high efficiency and precision were obtained to measure the sea cucumber volume after 3D reconstruction in underwater conditions. The finding can also offer reliable data to monitor the growth and assess value for more accurate and efficient aquaculture practices. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology 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.)

In order to realize the accurate evaluation of queue posture and action, aiming at the problem that it is difficult to accurately measure the three-dimensional human posture characteristics such as kick height in the training scene, this paper proposed a queue three-dimensional posture feature detection method based on binocular information. The method is divided into two stages; the 2D pose estimation stage and binocular stereo matching stage. In order to improve the accuracy of 2D human pose detection, it designed a 2D pose estimation model based on the improved HRNet network. Firstly, it introduced spatial channel attention in the back-bone network to enhance feature extraction capabilities. The feature fusion layer used an adaptive spatial feature fusion module to fuse multi-scale features of the network. Secondly, it used the unbiased data processing method to encode and decode the heat map to reduce the statistical error of the data. Finally, it adopted a coarse-to-fine multi-stage supervision method during model training to improve the detection accuracy of key points. Based on the 2D pose estimation model, it used the standard correlation matching function to achieve binocular stereo matching, and then obtained the 3D human pose through coordinate transformation. The experimental results show that the improved pose estimation network has better accuracy, the accuracy of the COCO dataset reaches 77.1%, and the detection accuracy of the self-made queue training dataset reaches 86.3%, which are respectively 2.2% and 3.1% higher than the original network. In the kick height experiment of the three-dimensional human body posture, the average relative error measured by the proposed method is 2.5%, which fully verifies the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of Technology 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 Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology 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 Zhengzhou University (Natural Science Edition) is the property of Journal of Zhengzhou University (Natural Science Edition) Editorial Office 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.)

Autonomous path planning represents a cornerstone technology for enabling planetary rovers to carry out exploration missions on extraterrestrial planets. This technology facilitates planetary rovers in navigating safely and efficiently toward their mission goal. However, the special conditions of extraterrestrial planetary environments pose significant challenges for autonomous path planning compared with those faced by ground-based mobile robots. These challenges include communication delays and bandwidth limitations between the planetary rover and the ground control station, limited light, unknown and unpredictable terrain, distinct environmental features, and the difficulty of accurately modeling interactions between the rover wheels and the ground. Therefore, addressing how to generate a safe, efficient, and reasonable traversable path for a planetary rover under conditions of incomplete environmental data and uncertain positioning is a focal point of current research. This paper reviews advancements in perception map construction and autonomous path planning for planetary rovers, examining both research progress and engineering applications. First, this paper summarizes advances in perception map construction methods that rely on binocular vision. This method uses stereo vision to generate parallax maps, which in turn help construct a digital elevation model of the planet’s surface. Stereo matching algorithms are typically used to acquire parallax maps. The discussion includes an analysis of two main types of methods: region-based matching algorithms and feature-based matching algorithms. Second, the paper classifies existing autonomous path-planning methods for planetary rovers into two categories: those based on cost evaluation and those leveraging machine learning. As a typical representative of cost-evaluation–based path planning methods, the optional arc-based autonomous path planning method is spotlighted for its algorithmic principles and iterative applications in ongoing planetary rover missions. Furthermore, the potential of A* heuristic search algorithm, rapidly-exploring random tree star (RRT*) algorithm, and fast marching method(FMM) algorithms for enhancing planetary rover path planning is explored in a categorical manner. The application of machine learning in autonomous path planning for planetary rovers is also reviewed. Such methods are classified into two groups: end-to-end path planning methods and auxiliary approaches leveraging machine learning. Ultimately, based on the above analysis of the key technologies of planetary rover autonomous path planning, the paper identifies and discusses future research directions for improving autonomous path planning methods for planetary rovers. These include enhancing perception capabilities, improving optional arc paths, reducing slippage, integrating multiple path planning methods, and strengthening the use of machine learning.

Copyright of Journal of Test & Measurement Technology is the property of Publishing Center of North University of China 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.)

Binocular image stereo matching is a key technology to realize autonomous obstacle avoidance and visual reconnaissance of unmanned auxiliary transport vehicles in coal mines. However, factors such as high dust and unstable lighting conditions in coal mines can lead to Salt-and-pepper noise in the images collected by the visual sensor, resulting in a high stereo matching error rate. Therefore, a Census stereo matching algorithm based on the combination of threshold and weight is proposed to reduce the impact of Salt-and-pepper noise on stereo matching. The main contributions include: ① threshold processing is carried out on the gray values of all pixels in the support window to remove the pixels with maximum and minimum gray values in the support window and solve the impact of outlier on the weighted fusion; ② the four diagonal pixels corresponding to the center point are weighted and fused to replace the center point pixel. Select pixel points along the four diagonal lines intersecting at the center pixel, with step sizes ranging from 1 to 3. According to the corresponding steps, weights of 0.7, 0.2, and 0.1 are assigned. Multiply the valid pixel points among these 12 points by their respective weights, then divide by the sum of the valid weights. This process yields the reference value of the center pixel point after weighted processing, addressing the issue of traditional algorithms' dependency on the center pixel of the Census transform window. Consequently, this approach enhances matching precision. The experimental results show that the average error rate calculated by the proposed algorithm is reduced by 5.64% compared to traditional Census algorithms, and reduced by 1.71% compared to the mean-based Census algorithm. What's more, the average error rate under different noise levels calculated by the proposed algorithm is reduced by 15.93% compared to the traditional Census algorithm, and reduced by 16.62% compared to the mean-based one. In non-occluded areas, the error matching rate of our algorithm is reduced by 17.19% compared to the traditional Census algorithm and 18.11% compared to the mean-based Census algorithm. The proposed Census stereo matching algorithm, which combines threshold and weight, effectively enhances the robustness against noise, reduces the error rate, and improves matching accuracy.

Copyright of Journal of Tiangong University is the property of Journal of Tianjin Polytechnic University 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 Graphics is the property of Journal of Graphics Editorial Office 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 Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control 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 Xi'an Jiaotong University is the property of Editorial Office of Journal of Xi'an Jiaotong University 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 Coal Science & Technology (0253-2336) is the property of Coal Science & Technology 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.)

In view of the problems of high-cost and accumulation of errors in the existing attitude measurement methods of roadheader, an attitude measurement algorithm based on the principle of double-vector attitude determination is proposed. By constructing and sensing the gravity-vector and light-vector respectively in the roadway excavation environment, using inertial inclination measurement and binocular vision measurement techniques, the attitude of the roadheader carrier coordinate frame relative to the roadway navigation coordinate frame can be realized based on the mathematical expression of vector elements in the navigation coordinate frame and the roadheader carrier coordinate frame. A measuring device that consists of an inclinometer and a binocular camera measures the indicated laser and gravity-vectors, and then the attitude of the roadheader can be solved using the double-vector attitude determination algorithm. The static repeatability measurement experiment is designed, and the experimental results show that the repeatability measurement precision of the attitude angles is 0.066 2°. The simulation analysis of the errors that may be introduced using the Monte Carlo method, which shows that the effect of the errors on the yaw, pitch and roll angles are 0.786 4°, 0.454 8° and 0.476 5°, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology 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 Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) 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 Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control 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.)

Intelligent digging and anchoring equipment in underground coal mines is the key to improve the mining imbalance problem in the industry, and the precise positioning of digging and anchoring equipment is the prerequisite to realize its intelligence. Compared with other traditional positioning methods, the vision-based pose measurement method has been initially applied in underground coal mines for its advantages of no contact and no cumulative error. Aiming at the problems of complex structure of cooperative target and cumbersome calibration of the current visual positioning method of the digging anchor equipment in the face of the underground coal mine, combining with the characteristics of the original laser pointers in the face of the digging, a visual positioning method of the digging and anchoring equipment based on the information of a single laser beam is proposed. By analyzing the laser pointer spot and beam image features, the method proposes a laser spot center extraction method based on two-dimensional inverse tangent function fitting and a laser beam centerline extraction method based on Hough straight line detection, and constructs a binocular visual position solving model based on the point and line features, which results in the real-time position of the anchor digging equipment in the roadway. Finally, in order to verify the feasibility and accuracy of the proposed feature extraction method and visual positioning method, experiments were conducted in the laboratory by building a platform to simulate the working condition environment of the digging face. The results show that the visual localization method of digging and anchoring equipment based on the information of mining laser pointers has high accuracy of position measurement. Within the test range of 50 m, the average measurement errors of the body position along the X-axis, Y-axis and Z-axis under the roadway coordinate system are 25.44, 58.64 and 31.08 mm, respectively, and the maximum errors are 55.16, 127.39 and 63.57 mm, respectively; and the average measurement errors of the pitch angle, yaw angle and roll angle of the body attitude under the roadway coordinate system are 0.22°, 0.22°, 0.41°, and their maximum errors are 0.29°, 0.37°, 0.58°, respectively. The maximum errors are 0.29°, 0.37° and 0.58°, respectively. It meets the requirement of positioning accuracy for the construction of underground roadway in coal mine.

To further improve the disparity prediction accuracy of stereo matching algorithm in the ill-posed regions such as repeating textures, no texture, and edge, an improved dense multi-scale feature guided aggregation network (DGNet) based on PSMNet was proposed. Firstly, a dense multi-scale feature extraction module was designed based on the dense atrous spatial pyramid pooling structure. This module extracted region-level features of different scales by using atrous convolution of different expansion rates, and effectively fused image features of different scales through dense connection, so that the network can capture contextual information. Secondly, the initial cost volume was obtained by concatenating left feature maps with their corresponding right feature maps across each disparity level. Then, a dense multi-scale feature guided cost aggregation module was proposed, which adaptively fused the cost volume and dense multi-scale features while aggregating the cost volume, so that the subsequent decoding layers can decode more accurate and high-resolution geometry information with the guidance of multi-scale context information. Finally, the high-resolution cost volume with global optimization was input into the regression module to obtain the disparity map. Comprehensive experimental results demonstrated that the mismatching rate of the proposed algorithm on KITTI 2015 and KITTI 2012 datasets was respectively reduced to 1.76% and 1.24%, and the endpoint error on SceneFlow dataset was reduced to 0.56 px. Compared with existing stereo matching algorithms such as GWCNet and CPOP-Net, the proposed algorithm performs well in the ill-posed regions. [ABSTRACT FROM AUTHOR]

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology 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.)

To confront the difficulties for moving vehicles in measuring the actual heights at various highway height limit facilities, this paper proposes a binocular camera height limit target real-time monitoring algorithm. First, an analysis of the height limit scenarios and facilities is made and a large- scale multi-scenario highway height limit dataset is built. Second, the target region is obtained by the detection and tracking algorithm based on deep learning. The binocular disparity is processed by a multi-step and multi-scale filtering algorithm to obtain the high-confidence height limit facility disparity data and thus calculate the distance and height information. Finally, the robust output strategy is adopted and alarms will be activated based on the real-time collected distance and height results. After multi-scenario height limit experiments, the target detection accuracy stands at 98.77%, the missed detection rateat 0. 87%, the false detection rate at 0. 36%, and the average height measurement error within 60 m below 4%. The results show that our algorithm achieves automatic detection and computation of highway height limit targets, as well as real-time and robust delivery of distance and height measurements and early warnings. [ABSTRACT FROM AUTHOR]

The environmental perception of intelligent vehicles is an important part of achieving autonomous driving, and object detection is one of the crucial functions of the environmental perception systems. Accurate and rapid detection of targets nearby is essentail for the smart vehicles. The faster and more accurately the detection algorithm can detect surrounding targets, the better. However, the detection speed and accuracy of existing perception algorithms still need improving. The distance information between the surrounding objects and the vehicle itself during its operation should also be obtained. The widely used YOLO series of algorithms, as representatives of one-stage object detection methods, have achieved a satisfactory balance between speed and detection accuracy, but there is stiil great potential for further improvement. This paper proposes an end-to-end object detection algorithm based on YOLO algorithm improvement-dual YOLO, which detects and measures the major participants in road traffic ( cars, pedestrians, cyclists) . The attention mechanism acts in the same way as humans observe things, focusing on more important information. The basic idea of combining attention mechanism with convolutional neural networks is to allow the network to concentrate on effective feature information in the image and ignore invalid information, thus improving the overall detection precision. Its mechanism of action is achieved by changing the weights of neurons in the network. This paper is based on the improvement of YOLOV5 algorithm, adding a channel attention mechanism to the backbone network to increase the learning weight of the neural network for effective features, thereby enhancing detection accuracy. In the meantime, a distance measurement module for binocular cameras is introduced to obtain target distance information. The basic principle of binocular camera ranging is triangulation, which employs the visual difference between two cameras to determine the distance of an object. Firstly, the camera is calibrated and distortion is corrected, and then stereo matching using the Semi Global Block Matching (SGBM) algorithm is performed to obtain disparity. Finally, the distance information of the target is calculated. The test results show the dual YOLO object detection algorithm achieves a detection speed of 60 fps and an average accuracy of 85. 99% in identifying the major participants in road traffic, which are far more superior to other algorithms in detecting cyclists and pedestrians. The proposed algorithm well meets the real-time detection and distance measurement requirements of intelligent vehicles. [ABSTRACT FROM AUTHOR]

ObjectiveThe width of maize stalks is an important indicator affecting the lodging resistance of maize. The measurement of maize stalk width has many problems, such as cumbersome manual collection process and large errors in the accuracy of automatic equipment collection and recognition, and it is of great application value to study a method for in-situ detection and high-precision identification of maize stalk width.MethodsThe ZED2i binocular camera was used and fixed in the field to obtain real-time pictures from the left and right sides of maize stalks together. The picture acquisition system was based on the NVIDIA Jetson TX2 NX development board, which could achieve timed shooting of both sides view of the maize by setting up the program. A total of maize original images were collected and a dataset was established. In order to observe more features in the target area from the image and provide assistance to improve model training generalization ability, the original images were processed by five processing methods: image saturation, brightness, contrast, sharpness and horizontal flipping, and the dataset was expanded to 3500 images. YOLOv8 was used as the original model for identifying maize stalks from a complex background. The coordinate attention (CA) attention mechanism can bring huge gains to downstream tasks on the basis of lightweight networks, so that the attention block can capture long-distance relationships in one direction while retaining spatial information in the other direction, so that the position information can be saved in the generated attention map to focus on the area of interest and help the network locate the target better and more accurately. By adding the CA module multiple times, the CA module was fused with the C2f module in the original Backbone, and the Bottleneck in the original C2f module was replaced by the CA module, and the C2fCA network module was redesigned. Replacing the loss function Efficient IoU Loss(EIoU) splits the loss term of the aspect ratio into the difference between the predicted width and height and the width and height of the minimum outer frame, which accelerated the convergence of the prediction box, improved the regression accuracy of the prediction box, and further improved the recognition accuracy of maize stalks. The binocular camera was then calibrated so that the left and right cameras were on the same three-dimensional plane. Then the three-dimensional reconstruction of maize stalks, and the matching of left and right cameras recognition frames was realized through the algorithm, first determine whether the detection number of recognition frames in the two images was equal, if not, re-enter the binocular image. If they were equal, continue to judge the coordinate information of the left and right images, the width and height of the bounding box, and determine whether the difference was less than the given Ta. If greater than the given Ta, the image was re-imported; If it was less than the given Ta, the confidence level of the recognition frame of the image was determined whether it was less than the given Tb. If greater than the given Tb, the image is re-imported; If it is less than the given Tb, it indicates that the recognition frame is the same maize identified in the left and right images. If the above conditions were met, the corresponding point matching in the binocular image was completed. After the three-dimensional reconstruction of the binocular image, the three-dimensional coordinates (Ax, Ay, Az) and (Bx, By, Bz) in the upper left and upper right corners of the recognition box under the world coordinate system were obtained, and the distance between the two points was the width of the maize stalk. Finally, a comparative analysis was conducted among the improved YOLOv8 model, the original YOLOv8 model, faster region convolutional neural networks (Faster R-CNN), and single shot multiBox detector (SSD)to verify the recognition accuracy and recognition accuracy of the model.Results and DiscussionsThe precision rate (P)、recall rate (R)、average accuracy mAP0.5、average accuracy mAP0.5:0.95 of the improved YOLOv8 model reached 96.8%、94.1%、96.6% and 77.0%. Compared with YOLOv7, increased by 1.3%、1.3%、1.0% and 11.6%, compared with YOLOv5, increased by 1.8%、2.1%、1.2% and 15.8%, compared with Faster R-CNN, increased by 31.1%、40.3%、46.2%、and 37.6%, and compared with SSD, increased by 20.6%、23.8%、20.9% and 20.1%, respectively. Respectively, and the linear regression coefficient of determination R2, root mean square error RMSE and mean absolute error MAE were 0.373, 0.265 cm and 0.244 cm, respectively. The method proposed in the research can meet the requirements of actual production for the measurement accuracy of maize stalk width.ConclusionsIn this study, the in-situ recognition method of maize stalk width based on the improved YOLOv8 model can realize the accurate in-situ identification of maize stalks, which solves the problems of time-consuming and laborious manual measurement and poor machine vision recognition accuracy, and provides a theoretical basis for practical production applications.

Mining robots are a component of mining production, concerning multiple stages such as mining, transportation, production, maintenance, safety control, and rescue, The degree of production automation directly affects the production safety, economic and social benefits of enterprises, With the rapid development and popularization of artificial intelligence in China, mine intelligence has become an important research field, Especially with the promulgation of some policies and regulations in China, intelligent unmanned mining technology has become a key part of mining production in the field of gold mining, To understand the connotation, status, and development trend of intelligent mining robots, this article reviews the underground intelligent robot technologies matching mining operations, including neural networks, binocular vision, and digital twins, from the perspective of the relationship between key technologies and practical engineering applications of intelligent mining robots in China, From the 4 perspectives of basic theories, critical technologies, engineering applications, and overall design system theories, this article reviews the relevant research, On this basis, the current development trend of domestic intelligent mining robots and the future development trend of smart mining models are summarized, [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]

Based on binocular vision technology, a target detection and ranging technology suitable for unmanned feeding equipment is studied.A high-precision target detection and recognition and binocular ranging method was designed, and related simulation experiments were carried out. The experimental results show that the average accuracy of the improved recognition and positioning algorithm is 99.53%. When the binocular camera is 40 cm to 90 cm away from the feeding device, the relative error of ranging is between 0.59% and 1.26%, which can effectively assist the short-distance positioning feeding device. It better meets the docking function requirements of the feeding device and the silo, and has positive significance for enhancing the automation level of the feeding device. [ABSTRACT FROM AUTHOR]

[Objective] The width of maize stalks is an important indicator affecting the lodging resistance of maize. The measurement of maize stalk width has many problems, such as cumbersome manual collection process and large errors in the accuracy of automatic equipment collection and recognition, and it is of great application value to study a method for in-situ detection and high-precision identification of maize stalk width. [Methods] The ZED2i binocular camera was used and fixed in the field to obtain real-time pictures from the left and right sides of maize stalks together. The picture acquisition system was based on the NVIDIA Jetson TX2 NX development board, which could achieve timed shooting of both sides view of the maize by setting up the program. A total of maize original images were collected and a dataset was established. In order to observe more features in the target area from the image and provide assistance to improve model training generalization ability, the original images were processed by five processing methods: image saturation, brightness, contrast, sharpness and horizontal flipping, and the dataset was expanded to 3500 images. YOLOv8 was used as the original model for identifying maize stalks from a complex background. The coordinate attention (CA) attention mechanism can bring huge gains to downstream tasks on the basis of lightweight networks, so that the attention block can capture long-distance relationships in one direction while retaining spatial information in the other direction, so that the position information can be saved in the generated attention map to focus on the area of interest and help the network locate the target better and more accurately. By adding the CA module multiple times, the CA module was fused with the C2f module in the original Backbone, and the Bottleneck in the original C2f module was replaced by the CA module, and the C2fCA network module was redesigned. Replacing the loss function Efficient IoU Loss(EIoU) splits the loss term of the aspect ratio into the difference between the predicted width and height and the width and height of the minimum outer frame, which accelerated the convergence of the prediction box, improved the regression accuracy of the prediction box, and further improved the recognition accuracy of maize stalks. The binocular camera was then calibrated so that the left and right cameras were on the same three-dimensional plane. Then the three-dimensional reconstruction of maize stalks, and the matching of left and right cameras recognition frames was realized through the algorithm, first determine whether the detection number of recognition frames in the two images was equal, if not, re-enter the binocular image. If they were equal, continue to judge the coordinate information of the left and right images, the width and height of the bounding box, and determine whether the difference was less than the given Ta. If greater than the given Ta, the image was re-imported; If it was less than the given Ta, the confidence level of the recognition frame of the image was determined whether it was less than the given Tb. If greater than the given Tb, the image is re-imported; If it is less than the given Tb, it indicates that the recognition frame is the same maize identified in the left and right images. If the above conditions were met, the corresponding point matching in the binocular image was completed. After the three-dimensional reconstruction of the binocular image, the three-dimensional coordinates (Ax, Ay, Az) and (Bx, By, Bz) in the upper left and upper right corners of the recognition box under the world coordinate system were obtained, and the distance between the two points was the width of the maize stalk. Finally, a comparative analysis was conducted among the improved YOLOv8 model, the original YOLOv8 model, faster region convolutional neural networks (Faster R-CNN), and single shot multiBox detector (SSD)to verify the recognition accuracy and recognition accuracy of the model. [Results and Discussions] The precision rate (P)、recall rate (R)、average accuracy mAP0.5、average accuracy mAP0.5:0.95 of the im‐ proved YOLOv8 model reached 96.8%、94.1%、96.6% and 77.0%. Compared with YOLOv7, increased by 1.3%、1.3%、1.0% and 11.6%, compared with YOLOv5, increased by 1.8%、2.1%、1.2% and 15.8%, compared with Faster R-CNN, increased by 31.1%、 40.3%、46.2%、and 37.6%, and compared with SSD, increased by 20.6%、23.8%、20.9% and 20.1%, respectively. Respectively, and the linear regression coefficient of determination R², root mean square error RMSE and mean absolute error MAE were 0.373, 0.265 cm and 0.244 cm, respectively. The method proposed in the research can meet the requirements of actual production for the mea‐ surement accuracy of maize stalk width. [Conclusions] In this study, the in-situ recognition method of maize stalk width based on the improved YOLOv8 model can realize the accurate in-situ identification of maize stalks, which solves the problems of time-consuming and laborious manual measurement and poor machine vision recognition accuracy, and provides a theoretical basis for practical production applications. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control 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 Food & Machinery is the property of Food & Machinery Editorial Office 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 Chinese Journal of Liquid Crystal & Displays is the property of Chinese Journal of Liquid Crystal & Displays 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.)

To explore the abnormal changes of local brain function in patients with high myopia (HM) during the resting state by a combining amplitude of low frequency fluctuations (ALFF) and degree centrality (DC) method. A total of 45 HM patients were selected as the HM group, and 46 subjects with normal binocular vision were selected as the control group. All subjects underwent a resting-state functional magnetic resonance imaging scan. Altered local brain function was analyzed by using combined ALFF and DC. Comparison between groups was performed by two-sample t test based on voxel level. The results showed that compared with the control group, (1) there were widespread ALFF differences between groups throughout the left Inferior frontal gyms, orbital part; right calcarine fissure and surrounding cortex; right anterior cingulate and paracingulate gyri; left thalamus; left inferior parietal, but supramarginal and angular gyri; right inferior parietal, but supramarginal and angular gyri and left paracentral lobule (P<0.05) ; (2) there were widespread DC differences between groups throughout the right inferior temporal gyrus; left inferior temporal gyrus; right anterior cingulate and paracingulate gyri; left superior frontal gyrus, medial orbital; left calcarine fissure and surrounding cortex; right fusiform gyrus; left inferior parietal, but supramarginal and angular gyri and left paracentral lobule (P< 0.05). The combination of low-frequency amplitude and degree centrality has high application value in the judgment of brain neuronal activity and brain functional network changes in HM patients. [ABSTRACT FROM AUTHOR]

During the underwater cruise of the autonomous underwater vehicle based on binocular vision, the images acquired by the binocular camera have low contrast and color distortion due to the attenuation effect of the water and the scattering effect of the suspended particles on the light, which leads to the low accuracy of underwater obstacle localization. In view of the above problems, this study adopts the red channel prior restoration algorithm to improve the quality of underwater imaging, obtains the binocular disparity map of obstacles according to the calibration parameters of the binocular camera, and proposes an underwater obstacle localization method based on depth disparity map fusion. The proposed method fuses the depth disparity map and the underwater restoration contour map, performs convex polygon detection on the fused image, obtains the contour of the obstacle, and extracts the effective depth information of the obstacle based on the contour information to realize the spatial positioning of the obstacle. The experimental results of underwater binocular localization show that the method can make the binocular stereo matching more ideal and effectively improve the accuracy of underwater obstacle localization. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Forensic Medicine / Fayixue Zazhi is the property of Journal of Forensic Medicine Editorial Office 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.)

A material positioning algorithm for binocular vision was proposed, aiming at the problem of three-dimensional spatial positioning in the process of grasping materials by mechanical arm. Firstly, based on the principle of binocular vision imaging, the hand eye matrix was constructed to complete the transformation from binocular camera coordinate system to robot coordinate system. Secondly, the attention mechanism was embedded into the CSP structure of the backbone network, and a yolov5s + CBAM was used to improve the network structure. On the self-made material data set, the map is 99. 1% and the FPS is 71, which can realize the accurate detection of the position of material grab point. Finally, aiming at the problem of depth information acquisition error caused by grab point stereo matching error, an improved sgbm algorithm based on gray value ranging was proposed to obtain depth information. Through experimental detection, the average ranging error is 5. 16 mm. Combined with target detection, the three-dimensional coordinate positioning of material grab point can be realized. [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]

Machine vision has a certain theoretical basis in target detection and recognition for sorting robot of coal mine belt conveyor. But current target recognition of sorting robot of coal mine belt conveyor is mainly aimed at coal-gangue recognition. There are few kinds of research on the recognition of foreign object targets causing conveyor belt penetration and tearing, and also few kinds of research on the precise positioning of target foreign object. In order to solve the above problems, a foreign object recognition and positioning system based on machine vision for sorting robots of coal mine belt conveyor is designed. The system can recognize and position different types and shapes of foreign objects on the conveyor belt. The image information of the foreign objects on the conveyor belt in real-time is obtained by adopting binocular vision, and the image is preprocessed. Image information is enhanced based on the Canny operator. The gray stretching method is used to improve image edge information to highlight the edge features of foreign objects on coal mine belt conveyor. The morphological method is used to extract foreign object shape features, and establish foreign object image feature sample library. The image feature matching method is used to solve the existing area of foreign objects to realize the detection, classification and recognition of foreign objects. On the basis of the successful recognition of foreign object type, the region of interest (ROI) of the target foreign object is established based on the edge feature value of the target foreign object. The coordinate conversion relationship is built between the camera, conveyor belt and target foreign object. The fast multi-target centroid calculation method is used to obtain the centroid coordinate of the target foreign object, so as to realize the positioning of the target foreign object. The experimental result of the system prototype shows that the foreign object recognition rate of foreign object recognition and positioning system for sorting robot of coal mine belt conveyor is not affected by the size, material, color and other factors, the system can realize the image acquisition, process, feature extraction, recognition and positioning of the target foreign object of coal mine conveyor belt. The recognition rate is above 92.5%, and the average error of the target foreign object positioning is about 3%.

Stereo matching based on convolutional neural network has made great progress. Existing methods still suffer from mismatching in weak texture regions, details and edges. Based on the cost volume commonly used in stereo matching, a stereo matching network with adaptive multi-scale cost volume construction and aggregation was proposed. Firstly, the proposed method fully fused the multi-scale features to obtain the recombined features. Then, a learnable feature enhancement module was used to recover the detail information for multi-scale cost volumes. Finally, after intra-scale aggregation based on global attention, an adaptive multi-scale weighting method was proposed for inter-scale aggregation to screen the matching features adapted to the disparity regression of each scale. Massive experiments on the Scene Flow and KITTI2015 datasets show that the proposed method achieves competitive performance with smaller network size which verifies the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of Technology 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 Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics 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 Automobile Technology & Material is the property of Automobile Technology & Material Editorial Office 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.)

[Objectives] In this study, a method of detecting the external quality on freeze-dried strawberry based on binocular stereo vision was developed, in order to realize the nondestructive testing and grading of freeze-dried strawberry. [Methods]The binocular stereo vision technology was used to obtain the parallax data of each pixel in the freeze-dried strawberry image through the pixel matching algorithm, its three-dimensional model was established, and the volume of the model, color, shape and texture quality indexes of the image were calculated as the characteristic parameters. Then the successive projections algorithm (SPA)was used to screen the optimal characteristic parameters, and the external quality grade recognition model of freeze-dried strawberry was established with the unfiltered and filtered characteristic parameters respectively. In addition, the discrimination and grading effects of each model were compared. Finally, the optimal recognition model was selected to develop the external quality grading software of freeze-dried strawberry and verified. [Results]The total classification accuracy of the support vector machines (SVM) and the partial least squares discriminant analysis (PLS-DA) prediction models was 91.7% and 86.7%, respectively. The total classification accuracy of SVM model and PLS-DA model based on the feature parameters (volume and red component meanfiltered by SPA algorithm was 95.0% and 81.7% respectively. Finally, the external quality recognition software of freeze-dried strawberry was developed by using the SVM model constructed by the characteristic parameters screened by SPA algorithm, with the total accuracy of 90.8%. [Conclusions]The SVM hierarchical prediction model based on the feature parameters filtered by SPA had the better prediction effect, and the total accuracy of modeling set and prediction set were 97.8% and 95.0% respectively. In addition, the software developed based on the aforementioned model could realize the detection of the external quality of freeze-dried strawberry. [ABSTRACT FROM AUTHOR]

The traditional relocation method of aerial photogrammetry data contains errors, and its algorithm has high power consumption and tends to be time-consuming, so the traditional relocation method was improved by the method of plane baseline target. The plane baseline target was designed with 9 feature points as the frame, and the aerial camera measurement structure diagram was constructed in combination with the binocular vision camera. Based on measurement structure, the aerial photogrammetry was carried out, with the data of all position points on the photographed object surface obtained through the movement of the camera and the plane baseline target, and the data conversion matrix of the camera coordinate system and the world coordinate system was calculated. The least squares method that was used to deal with the measurement error realized the relocation of aerial photogrammetry data. The experimental results show that the measurement error of this method is as low as 0.01 mm, the operating power consumption is between 65~75 W, and the average time is 8.5 s, lower than those of the traditional method. The method has certain application value in geological exploration.

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]

Copyright of Journal of National University of Defense Technology / Guofang Keji Daxue Xuebao is the property of NUDT Press 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 Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) 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.)

In order to improve the automation degree of strawberry harvesting operation, a strawberry harvester based on image recognition technology was designed. Through binocular vision, the spatial coordinates of strawberries were located and the initial images were obtained. The system achieves image recognition based on Lab color space, and locates the harvesting point with strawberry contour image and symmetry axis so as to determine the spatial harvesting position of strawberries. A two-stage structure, which first clamps the strawberry stem for positioning and then cutting it off, and three groups of screw slider mechanisms were adopted to complete the structure design of harvesting manipulator. The success rate of the recognition system can reach 98.48% through measurement. The recognition accuracy and positioning accuracy of the system are good, and the manipulator is simple in structure and reliable in operation, which can meet the requirements of harvesting. The study can provide a reference for automatic strawberry harvesting in greenhouse. [ABSTRACT FROM AUTHOR]

The wave height is the most basic element of wave information, and accurate measurement of wave heights plays a crucial role in both understanding wave theory and verifying numerical models. An improved optical measurement system was proposed based on the principle of binocular stereo vision, which breaks through the limitations of traditional measurement devices such as wave gauges and other single-point measurements, and improves the commonly used optical measurement method relying solely on images by involving the water wave theory into the data post-processing procedure. Through the identification and reconstruction of the unidirectional regular wave surface in a towing tank and the comparison of the results with the wave gauges and theoretical incoming wave parameters for validation, the research shows that, the measuring system has an error of about 1% in the measurement of a wide-area wave surface. Finally, a preliminary attempt was made on the irregular wave surface identification. [ABSTRACT FROM AUTHOR]

Copyright of Ordnance Industry Automation is the property of Editorial Board for Ordnance Industry Automation 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.)