Detection method of obstacles in the dangerous area of electric locomotive driving based on MSE-YOLOv4-Tiny

Abstract

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.

Coal gangue detection and recognition method based on multiscale fusion lightweight network SMS‐YOLOv3

“…Using a nonlinear method, the size of the receptive field can automatically change according to the incentive factors, which can automatically adjust the size of the receptive field with the difference of input scale. SKNet network consists of multiple SK convolution units stacked, in which The SK convolution operation is divided into three parts: split, fuse, and select, as shown in Figure 3 42 …”

“…SKNet network consists of multiple SK convolution units stacked, in which The SK convolution operation is divided into three parts: split, fuse, and select, as shown in Figure 3. 42 SKNet convolution is no longer an attention mechanism limited to channel level and space level, but an attention mechanism is applied to convolution cores of different sizes, thus allowing the network to adaptively adjust its structure. Furthermore, SK convolution is also a lightweight plug-and-play module that does not add too much computation to the network while bringing accuracy gains.…”

Error analysis of precision measurement with monocular vision

“…It can be observed that the second-order difference of the sequence H i ¢ is independent of i, indicating that the first-order difference of the sequence H i ¢ is an arithmetic sequence. According to equation (18)…”

“…This approach has several advantages, including lower cost, greater flexibility, mature algorithms, high accuracy, and reliability. As a result, monocular vision systems find wide application in diverse fields, including robot navigation [15][16][17], obstacle distance measurement [18][19][20][21], and pose estimation [22][23][24].…”

LF-YOLOv4: a lightweight detection model for enhancing the fusion of image features of surface defects in lithium batteries

“…Currently, deep learning object detection algorithms are mainly divided into two categories. Among them, one is onestage detection algorithms based on regression, mainly represented by single shot multibox detector (SSD) [14], you only look once (YOLO) [15,16], and the other is two-stage detection algorithms based on candidate region, mainly represented by Region CNN (RCNN) [17], Faster RCNN [18,19], Mask RCNN [20]. Given the same detection accuracy, one stage detection algorithms are widely used in industries, such as steel quality inspection, battery quality inspection, vehicle inspection, circuit board quality inspection, sawn timber quality inspection, and insulator equipment inspection, due to their advantages of fast speed and low hardware dependency.…”