This study presents a simple and effective Mask R-CNN algorithm for more rapid detection of vehicles and pedestrians. The method is of practical value for anticollision warning systems in intelligent driving. Deep neural networks with more layers have greater capacity but also have to perform more complicated calculations. To overcome this disadvantage, this study adopts a Resnet-86 network as a backbone that differs from the backbone structure of Resnet-101 in the Mask R-CNN algorithm within practical conditions. The results show that the Resnet-86 network can reduce the operation time and greatly improve accuracy. The detected vehicles and pedestrians are also screened out based on the Microsoft COCO dataset. The new dataset is formed by screening and supplementing COCO dataset, which makes the training of the algorithm more efficient. Perhaps, the most important part of our research is that we propose a new algorithm, Side Fusion FPN. The parameters in the algorithm have not increased, the amount of calculation has increased by less than 0.000001, and the mean average precision (mAP) has increased by 2.00 points. The results show that, compared with the algorithm of Mask R-CNN, our algorithm decreased the weight memory size by 9.43%, improved the training speed by 26.98%, improved the testing speed by 7.94%, decreased the value of loss by 0.26, and increased the value of mAP by 17.53 points.

/pdf/fast-vehicle-and-pedestrian-detection-using-improved-mask-r-k062ojx3kl.pdf

Fast Vehicle and Pedestrian Detection Using Improved Mask R-CNN

To improve the satisfaction and acceptance of automatic driving, we propose a deep reinforcement learning (DRL)-based autonomous car-following (CF) decision-making strategy using naturalist driving data (NDD). This study examines the traits of CF behavior using 1341 pairs of CF events taken from the Next Generation Simulation (NGSIM) data. Furthermore, in order to improve the random exploration of the agent’s action, the dynamic characteristics of the speed-acceleration distribution are established in accordance with NDD. The action’s varying constraints are achieved via a normal distribution 3σ boundary point-to-fit curve. A multiobjective reward function is designed considering safety, efficiency, and comfort, according to the time headway (THW) probability density distribution. The introduction of a penalty reward in mechanical energy allows the agent to internalize negative experiences. Next, a model of agent-environment interaction for CF decision-making control is built using the deep deterministic policy gradient (DDPG) method, which can explore complicated environments. Finally, extensive simulation experiments validate the effectiveness and accuracy of our proposal, and the driving strategy is learned through real-world driving data, which is better than human data.

/pdf/a-decision-making-strategy-for-car-following-based-on-2eqo0042.pdf

A Decision-Making Strategy for Car Following Based on Naturalist Driving Data via Deep Reinforcement Learning

A novel Single-shot Multi-scale detection network with feature fusion and multi-scale attention mechanism is proposed for autonomous driving. The proposed model is referred to as a Single-shot Multi-scale Attentive Detector (SSAD) and it would build feature relations of the feature map in the spatial space. The proposed network highlights pedestrian and vehicle regions on the extracted feature map and also suppresses irrelevant regions, from the global relation information and thereby providing reliable guidance for autonomous driving, while detecting smaller and occluded targets. SSAD design is simple, accurate and computationally efficient. Evaluation results of the proposed network on multiple datasets have achieved considerable and promising results. Experimental results show that the SSAD network when tested on Pascal Voc-2007, INRIA, Caltech, and City Persons datasets, outperforms many state-of-the-art (SOTA) detectors. 

SSAD: Single-Shot Multi-Scale Attentive Detector for Autonomous Driving

Forward Collision Warning System is an important part of vehicle active safety system, it can reduce the occurrence of rear-end collision accidents with high fatality rate and improve the safety of driving. At present, there are still some outstanding issues to be addressed among the existing forward collision warning systems, such as the high cost of information acquisition based on LiDAR and other high-definition sensors, and the poor real-time performance of target detection based on vision. In view of the aforementioned issues and in order to improve the detection accuracy and real-time requirements of the target detection function of the early warning system, this paper proposes an enhanced deep learning model-based vehicle target detection method, and improves the key techniques of target detection, ranging and speed measurement and early warning strategy in the warning system. Then, a target positioning scheme by visual fusion method is employed to improve the accuracy of distance detection, followed by an improved multi-target tracking algorithm.to realize the speed estimation of the front vehicle. Finally, the proposed forward collision warning strategy is demonstrated through real world case studies and results are given in the end.

Vehicle Forward Collision Warning Based on Improved Deep Neural Network

This study aims to reduce the severity of injuries caused by and the frequency of rear-end vehicle collisions. A better collision prediction method is proposed by means of millimeter-wave radar sensors able to rapidly detect potential collisions and alert drivers. Implementation of the system would bring about a reduction in accidents and potentially reduce the severity of the accidents that cannot be avoided. The proposed collision avoidance system adopted millimeter-wave radar sensors to collect information on vehicle’s rear surroundings. The designed experimental device has several unique features. The device has a wide monitoring range, incorporates a continuous detection process, and contains a rapid warning system. A series of real-world experiments were performed on cars (Model: Tercel 1.5, Toyota) to demonstrate the monitoring efficiency and warning frequency of this device under several operating conditions. This study furthered the development of a safe technology for avoidance of rear-end collisions, and this offers a novel system which can be used in a variety of vehicles to reduce the frequency of rear-end vehicle collisions.

Sheng Chien Chiu

Papers

Safe Technology with a Novel Rear Collision Avoidance System of Vehicles