A lightweight vehicles detection network model based on YOLOv5

Detecting and counting on road vehicles is a key task in intelligent transport management and surveillance systems. The applicability lies both in urban and highway traffic monitoring and control, particularly in difficult weather and traffic conditions. In the past, the task has been performed through data acquired from sensors and conventional image processing toolbox. However, with the advent of emerging deep learning based smart computer vision systems the task has become computationally efficient and reliable. The data acquired from road mounted surveillance cameras can be used to train models which can detect and track on road vehicles for smart traffic analysis and handling problems such as traffic congestion particularly in harsh weather conditions where there are poor visibility issues because of low illumination and blurring. Different vehicle detection algorithms focusing the same issue deal only with on or two specific conditions. In this research, we address detecting vehicles in a scene in multiple weather scenarios including haze, dust and sandstorms, snowy and rainy weather both in day and nighttime. The proposed architecture uses CSPDarknet53 as baseline architecture modified with spatial pyramid pooling (SPP-NET) layer and reduced Batch Normalization layers. We also augment the DAWN Dataset with different techniques including Hue, Saturation, Exposure, Brightness, Darkness, Blur and Noise. This not only increases the size of the dataset but also make the detection more challenging. The model obtained mean average precision of 81% during training and detected smallest vehicle present in the image

/pdf/traffic-management-multi-scale-vehicle-detection-in-varying-2634hytr.pdf

Traffic Management: Multi-Scale Vehicle Detection in Varying Weather Conditions Using YOLOv4 and Spatial Pyramid Pooling Network

In the industrial field, the anthropomorphism of grasping robots is the trend of future development, however, the basic vision technology adopted by the grasping robot at this stage has problems such as inaccurate positioning and low recognition efficiency. Based on this practical problem, in order to achieve more accurate positioning and recognition of objects, an object detection method for grasping robot based on improved YOLOv5 was proposed in this paper. Firstly, the robot object detection platform was designed, and the wooden block image data set is being proposed. Secondly, the Eye-In-Hand calibration method was used to obtain the relative three-dimensional pose of the object. Then the network pruning method was used to optimize the YOLOv5 model from the two dimensions of network depth and network width. Finally, the hyper parameter optimization was carried out. The simulation results show that the improved YOLOv5 network proposed in this paper has better object detection performance. The specific performance is that the recognition precision, recall, mAP value and F1 score are 99.35%, 99.38%, 99.43% and 99.41% respectively. Compared with the original YOLOv5s, YOLOv5m and YOLOv5l models, the mAP of the YOLOv5_ours model has increased by 1.12%, 1.2% and 1.27%, respectively, and the scale of the model has been reduced by 10.71%, 70.93% and 86.84%, respectively. The object detection experiment has verified the feasibility of the method proposed in this paper.

Object Detection Method for Grasping Robot Based on Improved YOLOv5

In this work, we introduce the problem of cross-modal visuo-tactile object recognition with robotic active exploration. With this term, we mean that the robot observes a set of objects with visual perception and, later on, it is able to recognize such objects only with tactile exploration, without having touched any object before. Using a machine learning terminology, in our application we have a visual training set and a tactile test set, or vice versa. To tackle this problem, we propose an approach constituted by four steps: finding a visuo-tactile common representation, defining a suitable set of features, transferring the features across the domains, and classifying the objects. We show the results of our approach using a set of 15 objects, collecting 40 visual examples and five tactile examples for each object. The proposed approach achieves an accuracy of 94.7%, which is comparable with the accuracy of the monomodal case, i.e., when using visual data both as training set and test set. Moreover, it performs well compared to the human ability, which we have roughly estimated carrying out an experiment with ten participants.

/pdf/a-transfer-learning-approach-to-cross-modal-object-2gw4p8n01o.pdf

A Transfer Learning Approach to Cross-Modal Object Recognition: From Visual Observation to Robotic Haptic Exploration.

In this paper, a novel grasp detection neural network Squeeze-and-Excitation ResUNet (SE-ResUNet) is developed, where the residual block with the channel attention is integrated. The proposed framework can not only generate the grasp pose from the RGB-D images, but also predict the quality score of each grasp pose. The experimental results show that the accuracy on the Cornell dataset and the Jacquard dataset is 98.2% and 95.7%, respectively. And the processing speed for the RGB-D images can reach 30fps, which shows the good real-time performance. In the comparison study, better performance is also obtained by the proposed method, which improves the accuracy and time efficiency. Finally, it is also demonstrated by physical grasping on the Baxter robot, where the average grasp success rate is 96.3%. Video is available at https://youtu.be/UfzVPJRt1Fg.

SE-ResUNet: A Novel Robotic Grasp Detection Method

Image classification has always been a hot research direction in the world, and the emergence of deep learning has promoted the development of this field. Convolutional neural networks (CNNs) have gradually become the mainstream algorithm for image classification since 2012, and the CNN architecture applied to other visual recognition tasks (such as object detection, object localization, and semantic segmentation) is generally derived from the network architecture in image classification. In the wake of these successes, CNN-based methods have emerged in remote sensing image scene classification and achieved advanced classification accuracy. In this review, which focuses on the application of CNNs to image classification tasks, we cover their development, from their predecessors up to recent state-of-the-art (SOAT) network architectures. Along the way, we analyze (1) the basic structure of artificial neural networks (ANNs) and the basic network layers of CNNs, (2) the classic predecessor network models, (3) the recent SOAT network algorithms, (4) comprehensive comparison of various image classification methods mentioned in this article. Finally, we have also summarized the main analysis and discussion in this article, as well as introduce some of the current trends.

Review of Image Classification Algorithms Based on Convolutional Neural Networks

With the rapid development of machine learning, its powerful function in the machine vision field is increasingly reflected. The combination of machine vision and robotics to achieve the same precise and fast grasping as that of humans requires high-precision target detection and recognition, location and reasonable grasp strategy generation, which is the ultimate goal of global researchers and one of the prerequisites for the large-scale application of robots. Traditional machine learning has a long history and good achievements in the field of image processing and robot control. The CNN (convolutional neural network) algorithm realizes training of large-scale image datasets, solves the disadvantages of traditional machine learning in large datasets, and greatly improves accuracy, thereby positioning CNNs as a global research hotspot. However, the increasing difficulty of labeled data acquisition limits their development. Therefore, unsupervised learning, self-supervised learning and reinforcement learning, which are less dependent on labeled data, have also undergone rapid development and achieved good performance in the fields of image processing and robot capture. According to the inherent defects of vision, this paper summarizes the research achievements of tactile feedback in the fields of target recognition and robot grasping and finds that the combination of vision and tactile feedback can improve the success rate and robustness of robot grasping. This paper provides a systematic summary and analysis of the research status of machine vision and tactile feedback in the field of robot grasping and establishes a reasonable reference for future research.

/pdf/object-detection-recognition-and-robot-grasping-based-on-3omlo05jkl.pdf

Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey

The purpose of mobile robot path planning is to produce the optimal safe path. However, mobile robots have poor real-time obstacle avoidance in local path planning and longer paths in global path planning. In order to improve the accuracy of real-time obstacle avoidance prediction of local path planning, shorten the path length of global path planning, reduce the path planning time, and then obtain a better safe path, we propose a real-time obstacle avoidance decision model based on machine learning (ML) algorithms, an improved smooth rapidly exploring random tree (S-RRT) algorithm, and an improved hybrid genetic algorithm-ant colony optimization (HGA-ACO). Firstly, in local path planning, the machine learning algorithms are used to train the datasets, the real-time obstacle avoidance decision model is established, and cross validation is performed. Secondly, in global path planning, the greedy algorithm idea and B-spline curve are introduced into the RRT algorithm, redundant nodes are removed, and the reverse iteration is performed to generate a smooth path. Then, in path planning, the fitness function and genetic operation method of genetic algorithm are optimized, the pheromone update strategy and deadlock elimination strategy of ant colony algorithm are optimized, and the genetic-ant colony fusion strategy is used to fuse the two algorithms. Finally, the optimized path planning algorithm is used for simulation experiment. Comparative simulation experiments show that the random forest has the highest real-time obstacle avoidance prediction accuracy in local path planning, and the S-RRT algorithm can effectively shorten the total path length generated by the RRT algorithm in global path planning. The HGA-ACO algorithm can reduce the iteration number reasonably, reduce the search time effectively, and obtain the optimal solution in path planning.

/pdf/intelligent-optimization-algorithm-based-path-planning-for-a-2sec4beu3y.pdf

Intelligent Optimization Algorithm-Based Path Planning for a Mobile Robot.

Robot manipulator trajectory planning is one of the core robot technologies, and the design of controllers can improve the trajectory accuracy of manipulators. However, most of the controllers designed at this stage have not been able to effectively solve the nonlinearity and uncertainty problems of the high degree of freedom manipulators. In order to overcome these problems and improve the trajectory performance of the high degree of freedom manipulators, a manipulator trajectory planning method based on a radial basis function (RBF) neural network is proposed in this work. Firstly, a 6-DOF robot experimental platform was designed and built. Secondly, the overall manipulator trajectory planning framework was designed, which included manipulator kinematics and dynamics and a quintic polynomial interpolation algorithm. Then, an adaptive robust controller based on an RBF neural network was designed to deal with the nonlinearity and uncertainty problems, and Lyapunov theory was used to ensure the stability of the manipulator control system and the convergence of the tracking error. Finally, to test the method, a simulation and experiment were carried out. The simulation results showed that the proposed method improved the response and tracking performance to a certain extent, reduced the adjustment time and chattering, and ensured the smooth operation of the manipulator in the course of trajectory planning. The experimental results verified the effectiveness and feasibility of the method proposed in this paper.

Qiang Bai

Papers

Review of Image Classification Algorithms Based on Convolutional Neural Networks

Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey

Object Detection Method for Grasping Robot Based on Improved YOLOv5

Intelligent Optimization Algorithm-Based Path Planning for a Mobile Robot.

Trajectory Planning of Robot Manipulator Based on RBF Neural Network