Search

Detecting parcels accurately and efficiently has always been a challenging task when unloading from trucks onto conveyor belts because of the diverse and complex ways in which parcels are stacked. Conventional methods struggle to quickly and accurately classify the various shapes and surface patterns of unordered parcels. In this paper, we propose a parcel-picking surface detection method based on deep learning and image processing for the efficient unloading of diverse and unordered parcels. Our goal is to develop a systematic image processing algorithm that emphasises the boundaries of parcels regardless of their shape, pattern, or layout. The core of the algorithm is the utilisation of RGB-D technology for detecting the primary boundary lines regardless of obstacles such as adhesive labels, tapes, or parcel surface patterns. For cases where detecting the boundary lines is difficult owing to narrow gaps between parcels, we propose using deep learning-based boundary line detection through the You Only Look at Coefficients (YOLACT) model. Using image segmentation techniques, the algorithm efficiently predicts boundary lines, enabling the accurate detection of irregularly sized parcels with complex surface patterns. Furthermore, even for rotated parcels, we can extract their edges through complex mathematical operations using the depth values of the specified position, enabling the detection of the wider surfaces of the rotated parcels. Finally, we validate the accuracy and real-time performance of our proposed method through various case studies, achieving mAP (50) values of 93.8% and 90.8% for randomly sized and rotationally covered boxes with diverse colours and patterns, respectively. [ABSTRACT FROM AUTHOR]

Background: The planetary rover is an essential platform for planetary exploration. Visual semantic segmentation is significant in the localization, perception, and path planning of the rover autonomy. Recent advances in computer vision and artificial intelligence brought about new opportunities. A systematic literature review (SLR) can help analyze existing solutions, discover available data, and identify potential gaps. Methods: A rigorous SLR has been conducted, and papers are selected from three databases (IEEE Xplore, Web of Science, and Scopus) from the start of records to May 2022. The 320 candidate studies were found by searching with keywords and bool operators, and they address the semantic terrain segmentation in the navigation vision of planetary rovers. Finally, after four rounds of screening, 30 papers were included with robust inclusion and exclusion criteria as well as quality assessment. Results: 30 studies were included for the review, and sub-research areas include navigation (16 studies), geological analysis (7 studies), exploration efficiency (10 studies), and others (3 studies) (overlaps exist). Five distributions are extendedly depicted (time, study type, geographical location, publisher, and experimental setting), which analyzes the included study from the view of community interests, development status, and reimplementation ability. One key research question and six sub-research questions are discussed to evaluate the current achievements and future gaps. Conclusions: Many promising achievements in accuracy, available data, and real-time performance have been promoted by computer vision and artificial intelligence. However, a solution that satisfies pixel-level segmentation, real-time inference time, and onboard hardware does not exist, and an open, pixel-level annotated, and the real-world data-based dataset is not found. As planetary exploration projects progress worldwide, more promising studies will be proposed, and deep learning will bring more opportunities and contributions to future studies. Contributions: This SLR identifies future gaps and challenges by proposing a methodical, replicable, and transparent survey, which is the first review (also the first SLR) for semantic terrain segmentation in the navigation vision of planetary rovers. [ABSTRACT FROM AUTHOR]

Object detection and tracking in camera images is a fundamental technology for computer vision and is used in various applications. In particular, object tracking using high-speed cameras is expected to be applied to real-time control in robotics. Therefore, it is required to increase tracking speed and detection accuracy. Currently, however, it is difficult to achieve both of those things simultaneously. In this paper, we propose a tracking method that combines multiple methods: correlation filter-based object tracking, deep learning-based object detection, and motion detection with background subtraction. The algorithms work in parallel and assist each other's processing to improve the overall performance of the system. We named it the "Mutual Assist tracker of feature Filters and Detectors (MAFiD method)". This method aims to achieve both high-speed tracking of moving objects and high detection accuracy. Experiments were conducted to verify the detection performance and processing speed by tracking a transparent capsule moving at high speed. The results show that the tracking speed was 618 frames per second (FPS) and the accuracy was 86% for Intersection over Union (IoU). The detection latency was 3.48 ms. These experimental scores are higher than those of conventional methods, indicating that the MAFiD method achieved fast object tracking while maintaining high detection performance. This proposal will contribute to the improvement of object-tracking technology. [ABSTRACT FROM AUTHOR]

In this study, we used image recognition technology to explore different ways to improve the safety of construction workers. Three object recognition scenarios were designed for safety at a construction site, and a corresponding object recognition model was developed for each scenario. The first object recognition model checks whether there are construction workers at the site. The second object recognition model assesses the risk of falling (falling off a structure or falling down) when working at an elevated position. The third object recognition model determines whether the workers are appropriately wearing safety helmets and vests. These three models were newly created using the image data collected from the construction sites and synthetic image data collected from the virtual environment based on transfer learning. In particular, we verified an artificial intelligence model based on a virtual environment in this study. Thus, simulating and performing tests on worker falls and fall injuries, which are difficult to re-enact by humans, are efficient algorithm verification methods. The verification and synthesis data acquisition method based on a virtual environment is one of the main contributions of this study. This paper describes the overall application development approach, including the structure and method used to collect the construction site image data, structure of the training image dataset, image dataset augmentation method, and the artificial intelligence backbone model applied for transfer learning. [ABSTRACT FROM AUTHOR]

Because of the development of image processing using cameras and the subsequent development of artificial intelligence technology, various fields have begun to develop. However, it is difficult to implement an image processing algorithm that requires a lot of calculations on a light board. This paper proposes a method using real-time deep learning object recognition algorithms in lightweight embedded boards. We have developed an algorithm suitable for lightweight embedded boards by appropriately using two deep neural network architectures. The first architecture requires small computational volumes, although it provides low accuracy. The second architecture uses large computational volumes and provides high accuracy. The area is determined using the first architecture, which processes semantic segmentation with relatively little computation. After masking the area using the more accurate deep learning architecture, object detection is implemented with improved accuracy, as the image is filtered by segmentation and the cases that have not been recognized by various variables, such as differentiation from the background, are excluded. OpenCV (Open source Computer Vision) is used to process input images in Python, and images are processed using an efficient neural network (ENet) and You Only Look Once (YOLO). By running this algorithm, the average error can be reduced by approximately 2.4 times, allowing for more accurate object detection. In addition, object recognition can be performed in real time for lightweight embedded boards, as a rate of about 4 FPS (frames per second) is achieved. [ABSTRACT FROM AUTHOR]

Roads make a huge contribution to the economy and act as a platform for transportation. Potholes in roads are one of the major concerns in transportation infrastructure. A lot of research has proposed using computer vision techniques to automate pothole detection that include a wide range of image processing and object detection algorithms. There is a need to automate the pothole detection process with adequate accuracy and speed and implement the process easily and with low setup cost. In this paper, we have developed efficient deep learning convolution neural networks (CNNs) to detect potholes in real-time with adequate accuracy. To reduce the computational cost and improve the training results, this paper proposes a modified VGG16 (MVGG16) network by removing some convolution layers and using different dilation rates. Moreover, this paper uses the MVGG16 as a backbone network for the Faster R-CNN. In addition, this work compares the performance of YOLOv5 (Large (Yl), Medium (Ym), and Small (Ys)) models with ResNet101 backbone and Faster R-CNN with ResNet50(FPN), VGG16, MobileNetV2, InceptionV3, and MVGG16 backbones. The experimental results show that the Ys model is more applicable for real-time pothole detection because of its speed. In addition, using the MVGG16 network as the backbone of the Faster R-CNN provides better mean precision and shorter inference time than using VGG16, InceptionV3, or MobilNetV2 backbones. The proposed MVGG16 succeeds in balancing the pothole detection accuracy and speed. [ABSTRACT FROM AUTHOR]

Low-light image enhancement is one of the most challenging tasks in computer vision, and it is actively researched and used to solve various problems. Most of the time, image processing achieves significant performance under normal lighting conditions. However, under low-light conditions, an image turns out to be noisy and dark, which makes subsequent computer vision tasks difficult. To make buried details more visible, and reduce blur and noise in a low-light captured image, a low-light image enhancement task is necessary. A lot of research has been applied to many different techniques. However, most of these approaches require much effort or expensive equipment to perform low-light image enhancement. For example, the image has to be captured in a raw camera file in order to be processed, and the addressing method does not perform well under extreme low-light conditions. In this paper, we propose a new convolutional network, Attention U-net (the integration of an attention gate and a U-net network), which is able to work on common file types (.PNG, .JPEG, .JPG, etc.) with primary support from deep learning to solve the problem of surveillance camera security in smart city inducements without requiring the raw image file from the camera, and it can perform under the most extreme low-light conditions. [ABSTRACT FROM AUTHOR]

The aim of this article is to introduce a novel approach to identifying flow regimes and void fractions in microchannel flow boiling, which is based on binary image segmentation using digital image processing and deep learning. The proposed image processing pipeline uses adaptive thresholding, blurring, gamma correction, contour detection, and histogram comparison to separate vapor from liquid areas, while the deep learning method uses a customized version of a convolutional neural network (CNN) called U-net to extract meaningful features from video frames. Both approaches enabled the automatic detection of flow boiling conditions, such as bubbly, slug, and annular flow, as well as automatic void fraction calculation. Especially CNN demonstrated its ability to deliver fast and dependable results, presenting an appealing substitute to manual feature extraction. The U-net-based CNN was able to segment flow boiling images with a Dice score of 99.1% and classify the above flow regimes with an overall classification accuracy of 91%. In addition, the neural network was able to predict resistance sensor readings from image data and assign them to a flow state with a mean squared error (MSE) < 10−6. [ABSTRACT FROM AUTHOR]

New processing methods based on artificial intelligence (AI) and deep learning are replacing traditional computer vision algorithms. The more advanced systems can process huge amounts of data in large computing facilities. In contrast, this paper presents a smart video surveillance system executing AI algorithms in low power consumption embedded devices. The computer vision algorithm, typical for surveillance applications, aims to detect, count and track people's movements in the area. This application requires a distributed smart camera system. The proposed AI application allows detecting people in the surveillance area using a MobileNet-SSD architecture. In addition, using a robust Kalman filter bank, the algorithm can keep track of people in the video also providing people counting information. The detection results are excellent considering the constraints imposed on the process. The selected architecture for the edge node is based on a UpSquared2 device that includes a vision processor unit (VPU) capable of accelerating the AI CNN inference. The results section provides information about the image processing time when multiple video cameras are connected to the same edge node, people detection precision and recall curves, and the energy consumption of the system. The discussion of results shows the usefulness of deploying this smart camera node throughout a distributed surveillance system. [ABSTRACT FROM AUTHOR]

Recent advancements in computer vision technology, developments in sensors and sensor-collecting approaches, and the use of deep and transfer learning approaches have excelled in the development of autonomous vehicles. On-road vehicle detection has become a task of significant importance, especially due to exponentially increasing research on autonomous vehicles during the past few years. With high-end computing resources, a large number of deep learning models have been trained and tested for on-road vehicle detection recently. Vehicle detection may become a challenging process especially due to varying light and weather conditions like night, snow, sand, rain, foggy conditions, etc. In addition, vehicle detection should be fast enough to work in real time. This study investigates the use of the recent YOLO version, YOLOx, to detect vehicles in bad weather conditions including rain, fog, snow, and sandstorms. The model is tested on the publicly available benchmark dataset DAWN containing images containing four bad weather conditions, different illuminations, background, and number of vehicles in a frame. The efficacy of the model is evaluated in terms of precision, recall, and mAP. The results exhibit the better performance of YOLOx-s over YOLOx-m and YOLOx-l variants. YOLOx-s has 0.8983 and 0.8656 mAP for snow and sandstorms, respectively, while its mAP for rain and fog is 0.9509 and 0.9524, respectively. The performance of models is better for snow and foggy weather than rainy weather sandstorms. Further experiments indicate that enhancing image quality using multiscale retinex improves YOLOx performance. [ABSTRACT FROM AUTHOR]

Sign language recognition, an essential interface between the hearing and deaf-mute communities, faces challenges with high false positive rates and computational costs, even with the use of advanced deep learning techniques. Our proposed solution is a stacked encoded model, combining artificial intelligence (AI) with the Internet of Things (IoT), which refines feature extraction and classification to overcome these challenges. We leverage a lightweight backbone model for preliminary feature extraction and use stacked autoencoders to further refine these features. Our approach harnesses the scalability of big data, showing notable improvement in accuracy, precision, recall, F1-score, and complexity analysis. Our model's effectiveness is demonstrated through testing on the ArSL2018 benchmark dataset, showcasing superior performance compared to state-of-the-art approaches. Additional validation through an ablation study with pre-trained convolutional neural network (CNN) models affirms our model's efficacy across all evaluation metrics. Our work paves the way for the sustainable development of high-performing, IoT-based sign-language-recognition applications. [ABSTRACT FROM AUTHOR]

The existing classification methods for Panax notoginseng taproots suffer from low accuracy, low efficiency, and poor stability. In this study, a classification model based on image feature fusion is established for Panax notoginseng taproots. The images of Panax notoginseng taproots collected in the experiment are preprocessed by Gaussian filtering, binarization, and morphological methods. Then, a total of 40 features are extracted, including size and shape features, HSV and RGB color features, and texture features. Through BP neural network, extreme learning machine (ELM), and support vector machine (SVM) models, the importance of color, texture, and fusion features for the classification of the main roots of Panax notoginseng is verified. Among the three models, the SVM model performs the best, achieving an accuracy of 92.037% on the prediction set. Next, iterative retaining information variables (IRIVs), variable iterative space shrinkage approach (VISSA), and stepwise regression analysis (SRA) are used to reduce the dimension of all the features. Finally, a traditional machine learning SVM model based on feature selection and a deep learning model based on semantic segmentation are established. With the model size of only 125 kb and the training time of 3.4 s, the IRIV-SVM model achieves an accuracy of 95.370% on the test set, so IRIV-SVM is selected as the main root classification model for Panax notoginseng. After being optimized by the gray wolf optimizer, the IRIV-GWO-SVM model achieves the highest classification accuracy of 98.704% on the test set. The study results of this paper provide a basis for developing online classification methods of Panax notoginseng with different grades in actual production. [ABSTRACT FROM AUTHOR]

Computer vision, biomedical image processing and deep learning are related fields with a tremendous impact on the interpretation of medical images today. Among biomedical image sensing modalities, ultrasound (US) is one of the most widely used in practice, since it is noninvasive, accessible, and cheap. Its main drawback, compared to other imaging modalities, like computed tomography (CT) or magnetic resonance imaging (MRI), consists of the increased dependence on the human operator. One important step toward reducing this dependence is the implementation of a computer-aided diagnosis (CAD) system for US imaging. The aim of the paper is to examine the application of contrast enhanced ultrasound imaging (CEUS) to the problem of automated focal liver lesion (FLL) diagnosis using deep neural networks (DNN). Custom DNN designs are compared with state-of-the-art architectures, either pre-trained or trained from scratch. Our work improves on and broadens previous work in the field in several aspects, e.g., a novel leave-one-patient-out evaluation procedure, which further enabled us to formulate a hard-voting classification scheme. We show the effectiveness of our models, i.e., 88% accuracy reported against a higher number of liver lesion types: hepatocellular carcinomas (HCC), hypervascular metastases (HYPERM), hypovascular metastases (HYPOM), hemangiomas (HEM), and focal nodular hyperplasia (FNH). [ABSTRACT FROM AUTHOR]

Drilling operations are an essential part of furniture from MDF laminated boards required for product assembly. Faults in the process might introduce adverse effects to the furniture. Inspection of the drilling quality can be challenging due to a big variety of board surface textures, dust, or woodchips in the manufacturing process, milling cutouts, and other kinds of defects. Intelligent computer vision methods can be engaged for global contextual analysis with local information attention for automated object detection and segmentation. In this paper, we propose blind and through drilled holes segmentation on textured wooden furniture panel images using the UNet encoder-decoder modifications enhanced with residual connections, atrous spatial pyramid pooling, squeeze and excitation module, and CoordConv layers for better segmentation performance. We show that even a lightweight architecture is capable to perform on a range of complex textures and is able to distinguish the holes drilling operations' semantical information from the rest of the furniture board and conveyor context. The proposed model configurations yield better results in more complex cases with a not significant or small bump in processing time. Experimental results demonstrate that our best-proposed solution achieves a Dice score of up to 97.89% compared to the baseline U-Net model's Dice score of 94.50%. Statistical, visual, and computational properties of each convolutional neural network architecture are addressed. [ABSTRACT FROM AUTHOR]

Deep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than other 3D deep learning methods, and even worse than their 2D version. In this paper, we propose to improve 3D deep learning results by transferring the pretrained weights learned in 2D networks to their corresponding 3D version. Using an industrial object recognition context, we have analyzed different combinations of 3D convolutional networks (VGG16, ResNet, Inception ResNet, and EfficientNet), comparing the recognition accuracy. The highest accuracy is obtained with EfficientNetB0 using extrusion with an accuracy of 0.9217, which gives comparable results to state-of-the art methods. We also observed that the transfer approach enabled to improve the accuracy of the Inception ResNet 3D version up to 18% with respect to the score of the 3D approach alone. [ABSTRACT FROM AUTHOR]

Single-Sample Face Recognition (SSFR) is a computer vision challenge. In this scenario, there is only one example from each individual on which to train the system, making it difficult to identify persons in unconstrained environments, mainly when dealing with changes in facial expression, posture, lighting, and occlusion. This paper discusses the relevance of an original method for SSFR, called Multi-Block Color-Binarized Statistical Image Features (MB-C-BSIF), which exploits several kinds of features, namely, local, regional, global, and textured-color characteristics. First, the MB-C-BSIF method decomposes a facial image into three channels (e.g., red, green, and blue), then it divides each channel into equal non-overlapping blocks to select the local facial characteristics that are consequently employed in the classification phase. Finally, the identity is determined by calculating the similarities among the characteristic vectors adopting a distance measurement of the K-nearest neighbors (K-NN) classifier. Extensive experiments on several subsets of the unconstrained Alex and Robert (AR) and Labeled Faces in the Wild (LFW) databases show that the MB-C-BSIF achieves superior and competitive results in unconstrained situations when compared to current state-of-the-art methods, especially when dealing with changes in facial expression, lighting, and occlusion. The average classification accuracies are 96.17% and 99% for the AR database with two specific protocols (i.e., Protocols I and II, respectively), and 38.01% for the challenging LFW database. These performances are clearly superior to those obtained by state-of-the-art methods. Furthermore, the proposed method uses algorithms based only on simple and elementary image processing operations that do not imply higher computational costs as in holistic, sparse or deep learning methods, making it ideal for real-time identification. [ABSTRACT FROM AUTHOR]

Deep learning methods have achieved outstanding results in many image processing and computer vision tasks, such as image segmentation. However, they usually do not consider spatial dependencies among pixels/voxels in the image. To obtain better results, some methods have been proposed to apply classic spatial regularization, such as total variation, into deep learning models. However, for some challenging images, especially those with fine structures and low contrast, classical regularizations are not suitable. We derived a new regularization to improve the connectivity of segmentation results and make it applicable to deep learning. Our experimental results show that for both deep learning methods and unsupervised methods, the proposed method can improve performance by increasing connectivity and dealing with low contrast and, therefore, enhance segmentation results. [ABSTRACT FROM AUTHOR]

Nowadays, autonomous vehicle is an active research area, especially after the emergence of machine vision tasks with deep learning. In such a visual navigation system for autonomous vehicle, the controller captures images and predicts information so that the autonomous vehicle can safely navigate. In this paper, we first introduced small and medium-sized obstacles that were intentionally or unintentionally left on the road, which can pose hazards for both autonomous and human driving situations. Then, we discuss Markov random field (MRF) model by fusing three potentials (gradient potential, curvature prior potential, and depth variance potential) to segment the obstacles and non-obstacles into the hazardous environment. Since the segment of obstacles is done by MRF model, we can predict the information to safely navigate the autonomous vehicle form hazardous environment on the roadway by DNN model. We found that our proposed method can segment the obstacles accuracy from the blended background road and improve the navigation skills of the autonomous vehicle. [ABSTRACT FROM AUTHOR]

With the increasing number of drones, the danger of their illegal use has become relevant. This has necessitated the creation of automatic drone protection systems. One of the important tasks solved by these systems is the reliable detection of drones near guarded objects. This problem can be solved using various methods. From the point of view of the price–quality ratio, the use of video cameras for a drone detection is of great interest. However, drone detection using visual information is hampered by the large similarity of drones to other objects, such as birds or airplanes. In addition, drones can reach very high speeds, so detection should be done in real time. This paper addresses the problem of real-time drone detection with high accuracy. We divided the drone detection task into two separate tasks: the detection of moving objects and the classification of the detected object into drone, bird, and background. The moving object detection is based on background subtraction, while classification is performed using a convolutional neural network (CNN). The experimental results showed that the proposed approach can achieve an accuracy comparable to existing approaches at high processing speed. We also concluded that the main limitation of our detector is the dependence of its performance on the presence of a moving background. [ABSTRACT FROM AUTHOR]

Behavioural research of pigs can be greatly simplified if automatic recognition systems are used. Systems based on computer vision in particular have the advantage that they allow an evaluation without affecting the normal behaviour of the animals. In recent years, methods based on deep learning have been introduced and have shown excellent results. Object and keypoint detector have frequently been used to detect individual animals. Despite promising results, bounding boxes and sparse keypoints do not trace the contours of the animals, resulting in a lot of information being lost. Therefore, this paper follows the relatively new approach of panoptic segmentation and aims at the pixel accurate segmentation of individual pigs. A framework consisting of a neural network for semantic segmentation as well as different network heads and postprocessing methods will be discussed. The method was tested on a data set of 1000 hand-labeled images created specifically for this experiment and achieves detection rates of around 95% (F1 score) despite disturbances such as occlusions and dirty lenses. [ABSTRACT FROM AUTHOR]

Noise reduction is one of the most important and still active research topics in low-level image processing due to its high impact on object detection and scene understanding for computer vision systems. Recently, we observed a substantially increased interest in the application of deep learning algorithms. Many computer vision systems use them, due to their impressive capability of feature extraction and classification. While these methods have also been successfully applied in image denoising, significantly improving its performance, most of the proposed approaches were designed for Gaussian noise suppression. In this paper, we present a switching filtering technique intended for impulsive noise removal using deep learning. In the proposed method, the distorted pixels are detected using a deep neural network architecture and restored with the fast adaptive mean filter. The performed experiments show that the proposed approach is superior to the state-of-the-art filters designed for impulsive noise removal in color digital images. [ABSTRACT FROM AUTHOR]

In recent years, computer vision technology has been widely used in the field of medical image processing. However, there is still a big gap between the existing breast mass detection methods and the real-world application due to the limited detection accuracy. It is known that humans locate the regions of interest quickly and further identify whether these regions are the targets we found. In breast cancer diagnosis, we locate all the potential regions of breast mass by glancing at the mammographic image from top to bottom and from left to right, then further identify whether these regions are a breast mass. Inspired by the process of human detection of breast mass, we proposed a novel breast mass detection method to detect breast mass on a mammographic image by stimulating the process of human detection. The proposed method preprocesses the mammographic image via the mathematical morphology method and locates the suspected regions of breast mass by the image template matching method. Then, it obtains the regions of breast mass by classifying these suspected regions into breast mass and background categories using a convolutional neural network (CNN). The bounding box of breast mass obtained by the mathematical morphology method and image template matching method are roughly due to the mathematical morphology method, which transforms all of the brighter regions into approximate circular areas. For regression of a breast mass bounding box, the optimal solution should be searched in the feasible region and the Particle Swarm Optimization (PSO) is suitable for solving the problem of searching the optimal solution within a certain range. Therefore, we refine the bounding box of breast mass by the PSO algorithm. The proposed breast mass detection method and the compared detection methods were evaluated on the open database Digital Database for Screening Mammography (DDSM). The experimental results demonstrate that the proposed method is superior to all of the compared detection methods in detection performance. [ABSTRACT FROM AUTHOR]

Continually improving crowd counting neural networks have been developed in recent years. The accuracy of these networks has reached such high levels that further improvement is becoming very difficult. However, this high accuracy lacks deeper semantic information, such as social roles (e.g., student, company worker, or police officer) or location-based roles (e.g., pedestrian, tenant, or construction worker). Some of these can be learned from the same set of features as the human nature of an entity, whereas others require wider contextual information from the human surroundings. The primary end-goal of developing recognition software is to involve them in autonomous decision-making systems. Therefore, it must be foolproof, which is, it must have good semantic understanding of the input. In this study, we focus on counting pedestrians in helicopter footage and introduce a dataset created from helicopter videos for this purpose. We use semantic segmentation to extract the required additional contextual information from the surroundings of an entity. We demonstrate that it is possible to increase the pedestrian counting accuracy in this manner. Furthermore, we show that crowd counting and semantic segmentation can be simultaneously achieved, with comparable or even improved accuracy, by using the same crowd counting neural network for both tasks through hard parameter sharing. The presented method is generic and it can be applied to arbitrary crowd density estimation methods. A link to the dataset is available at the end of the paper. [ABSTRACT FROM AUTHOR]

The use of gestures is one of the main forms of human machine interaction (HMI) in many fields, from advanced robotics industrial setups, to multimedia devices at home. Almost every gesture detection system uses computer vision as the fundamental technology, with the already well-known problems of image processing: changes in lighting conditions, partial occlusions, variations in color, among others. To solve all these potential issues, deep learning techniques have been proven to be very effective. This research proposes a hand gesture recognition system based on convolutional neural networks and color images that is robust against environmental variations, has a real time performance in embedded systems, and solves the principal problems presented in the previous paragraph. A new CNN network has been specifically designed with a small architecture in terms of number of layers and total number of neurons to be used in computationally limited devices. The obtained results achieve a percentage of success of 96.92% on average, a better score than those obtained by previous algorithms discussed in the state of the art. [ABSTRACT FROM AUTHOR]

Computer Vision is a cross-research field with the main purpose of understanding the surrounding environment as closely as possible to human perception. The image processing systems is continuously growing and expanding into more complex systems, usually tailored to the certain needs or applications it may serve. To better serve this purpose, research on the architecture and design of such systems is also important. We present the End-to-End Computer Vision Framework, an open-source solution that aims to support researchers and teachers within the image processing vast field. The framework has incorporated Computer Vision features and Machine Learning models that researchers can use. In the continuous need to add new Computer Vision algorithms for a day-to-day research activity, our proposed framework has an advantage given by the configurable and scalar architecture. Even if the main focus of the framework is on the Computer Vision processing pipeline, the framework offers solutions to incorporate even more complex activities, such as training Machine Learning models. EECVF aims to become a useful tool for learning activities in the Computer Vision field, as it allows the learner and the teacher to handle only the topics at hand, and not the interconnection necessary for visual processing flow. [ABSTRACT FROM AUTHOR]

Weeds are one of the most important factors affecting agricultural production. The waste and pollution of farmland ecological environment caused by full-coverage chemical herbicide spraying are becoming increasingly evident. With the continuous improvement in the agricultural production level, accurately distinguishing crops from weeds and achieving precise spraying only for weeds are important. However, precise spraying depends on accurately identifying and locating weeds and crops. In recent years, some scholars have used various computer vision methods to achieve this purpose. This review elaborates the two aspects of using traditional image-processing methods and deep learning-based methods to solve weed detection problems. It provides an overview of various methods for weed detection in recent years, analyzes the advantages and disadvantages of existing methods, and introduces several related plant leaves, weed datasets, and weeding machinery. Lastly, the problems and difficulties of the existing weed detection methods are analyzed, and the development trend of future research is prospected. [ABSTRACT FROM AUTHOR]

Automated robotic platforms are an important part of precision agriculture solutions for sustainable food production. Agri-robots require robust and accurate guidance systems in order to navigate between crops and to and from their base station. Onboard sensors such as machine vision cameras offer a flexible guidance alternative to more expensive solutions for structured environments such as scanning lidar or RTK-GNSS. The main challenges for visual crop row guidance are the dramatic differences in appearance of crops between farms and throughout the season and the variations in crop spacing and contours of the crop rows. Here we present a visual guidance pipeline for an agri-robot operating in strawberry fields in Norway that is based on semantic segmentation with a convolution neural network (CNN) to segment input RGB images into crop and not-crop (i.e., drivable terrain) regions. To handle the uneven contours of crop rows in Norway's hilly agricultural regions, we develop a new adaptive multi-ROI method for fitting trajectories to the drivable regions. We test our approach in open-loop trials with a real agri-robot operating in the field and show that our approach compares favourably to other traditional guidance approaches. [ABSTRACT FROM AUTHOR]

Image deblurring has been a challenging ill-posed problem in computer vision. Gaussian blur is a common model for image and signal degradation. The deep learning-based deblurring methods have attracted much attention due to their advantages over the traditional methods relying on hand-designed features. However, the existing deep learning-based deblurring techniques still cannot perform well in restoring the fine details and reconstructing the sharp edges. To address this issue, we have designed an effective end-to-end deep learning-based non-blind image deblurring algorithm. In the proposed method, a multi-stream bottom-top-bottom attention network (MBANet) with the encoder-to-decoder structure is designed to integrate low-level cues and high-level semantic information, which can facilitate extracting image features more effectively and improve the computational efficiency of the network. Moreover, the MBANet adopts a coarse-to-fine multi-scale strategy to process the input images to improve image deblurring performance. Furthermore, the global information-based fusion and reconstruction network is proposed to fuse multi-scale output maps to improve the global spatial information and recurrently refine the output deblurred image. The experiments were done on the public GoPro dataset and the realistic and dynamic scenes (REDS) dataset to evaluate the effectiveness and robustness of the proposed method. The experimental results show that the proposed method generally outperforms some traditional deburring methods and deep learning-based state-of-the-art deblurring methods such as scale-recurrent network (SRN) and denoising prior driven deep neural network (DPDNN) in terms of such quantitative indexes as peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) and human vision. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) is the state-of-the-art machine learning technology, which shows superior performance in computer vision, bioinformatics, natural language processing, and other areas. Especially as a modern image processing technology, DL has been successfully applied in various tasks, such as object detection, semantic segmentation, and scene analysis. However, with the increase of dense scenes in reality, due to severe occlusions, and small size of objects, the analysis of dense scenes becomes particularly challenging. To overcome these problems, DL recently has been increasingly applied to dense scenes and has begun to be used in dense agricultural scenes. The purpose of this review is to explore the applications of DL for dense scenes analysis in agriculture. In order to better elaborate the topic, we first describe the types of dense scenes in agriculture, as well as the challenges. Next, we introduce various popular deep neural networks used in these dense scenes. Then, the applications of these structures in various agricultural tasks are comprehensively introduced in this review, including recognition and classification, detection, counting and yield estimation. Finally, the surveyed DL applications, limitations and the future work for analysis of dense images in agriculture are summarized. [ABSTRACT FROM AUTHOR]

The visual inspection of massive civil infrastructure is a common trend for maintaining its reliability and structural health. However, this procedure, which uses human inspectors, requires long inspection times and relies on the subjective and empirical knowledge of the inspectors. To address these limitations, a machine vision-based autonomous crack detection method is proposed using a deep convolutional neural network (DCNN) technique. It consists of a fully convolutional neural network (FCN) with an encoder and decoder framework for semantic segmentation, which performs pixel-wise classification to accurately detect cracks. The main idea is to capture the global context of a scene and determine whether cracks are in the image while also providing a reduced and essential picture of the crack locations. The visual geometry group network (VGGNet), a variant of the DCCN, is employed as a backbone in the proposed FCN for end-to-end training. The efficacy of the proposed FCN method is tested on a publicly available benchmark dataset of concrete crack images. The experimental results indicate that the proposed method is highly effective for concrete crack classification, obtaining scores of approximately 92% for both the recall and F1 average. [ABSTRACT FROM AUTHOR]

Computer vision systems have the potential to provide automated, non-invasive monitoring of livestock animals, however, the lack of public datasets with well-defined targets and evaluation metrics presents a significant challenge for researchers. Consequently, existing solutions often focus on achieving task-specific objectives using relatively small, private datasets. This work introduces a new dataset and method for instance-level detection of multiple pigs in group-housed environments. The method uses a single fully-convolutional neural network to detect the location and orientation of each animal, where both body part locations and pairwise associations are represented in the image space. Accompanying this method is a new dataset containing 2000 annotated images with 24,842 individually annotated pigs from 17 different locations. The proposed method achieves over 99% precision and over 96% recall when detecting pigs in environments previously seen by the network during training. To evaluate the robustness of the trained network, it is also tested on environments and lighting conditions unseen in the training set, where it achieves 91% precision and 67% recall. The dataset is publicly available for download. [ABSTRACT FROM AUTHOR]