Aiming at the problems of error warning, low detection efficiency, and inability to meet the requirements of lightweight deployment in current track obstacle detection algorithms based on computer vision, the detection method of obstacles in the dangerous area of electric locomotive driving based on improved YOLOV4-Tiny (MSE-YOLOV4-Tiny) was proposed. The obstacle image dataset was constructed to provide a testing environment for various target detection algorithms. The method of perspective transformation, sliding window and least square cubic polynomial was used to fit the track line. By finding the area where the track was located and extending a certain distance to the outside of the track, the dangerous area of the electric locomotive running was obtained. A 3-scale detection structure was formed by increasing the shallow detection scale on the detection layer, so as to improve the detection accuracy of the network for smaller targets such as stones. The improved SKNet (ECA_SKNet) attention mechanism module was added to the output ends of the three scales of the backbone network, and the weight was re-assigned to realize feature reconstruction, thus further improving the detection accuracy of the target. By adding the Spatial Pyramid Pooling (SPP) module, the local and global features of the image were fused to improve the accurate localization ability and detection accuracy of the network. A comparative experiment was carried out on the dataset constructed in this paper. The experimental results show that the problem of false warnings caused by taking the target in the safe area as an obstacle can be effectively solved by dividing the danger area of electric locomotive driving. Compared with the original YOLOv4-Tiny algorithm, the MSE-YOLOv4-Tiny algorithm has a 3.97% increase in mAP while maintaining a higher detection speed and a smaller model memory. It has better detection performance and can be used for autonomous driving electric locomotive obstacle detection to provide technical support.
In order to improve the detection accuracy of an algorithm in the complex environment of a coal mine, including low-illumination, motion-blur, occlusions, small-targets, and background-interference conditions; reduce the number of model parameters; improve the detection speed of the algorithm; and make it meet the real-time detection requirements of edge equipment, a real-time obstacle detection method in the driving of driverless rail locomotives based on DeblurGANv2 and improved YOLOv4 is proposed in this study. A blurred image was deblurred using DeblurGANv2. The improved design was based on YOLOv4, and the lightweight feature extraction network MobileNetv2 was used to replace the original CSPDarknet53 network to improve the detection speed of the algorithm. There was a high amount of background interference in the target detection of the coal mine scene. In order to strengthen the attention paid to the target, the SANet attention module was embedded in the Neck network to improve the detection accuracy of the algorithm under low-illumination, target-occlusion, small-target, and other conditions. To further improve the detection accuracy of the algorithm, the K-means++ algorithm was adopted to cluster prior frames, and the focal loss function was introduced to increase the weight loss of small-target samples. The experimental results show that the deblurring of the motion-blurred image can effectively improve the detection accuracy of obstacles and reduce missed detections. Compared with the original YOLOv4 algorithm, the improved YOLOv4 algorithm increases the detection speed by 65.85% to 68 FPS and the detection accuracy by 0.68% to 98.02%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.