Real-Time Obstacle Detection Method in the Driving Process of Driverless Rail Locomotives Based on DeblurGANv2 and Improved YOLOv4

Abstract

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%.

Real-Time Obstacle Detection with YOLOv8 in a WSN Using UAV Aerial Photography

“…A further improved YOLOv4 model was proposed for small object detection in surveillance drones, achieving 2% better mean average precision (mAP) results on the VisDrone dataset while maintaining the same speed as the original YOLOv4 [19]. A study [20] proposed a real-time obstacle detection method for coal mine environments, addressing low illumination, motion blur, and other challenges. It combined DeblurGANv2 for image deblurring, a modified YOLOv4 with MobileNetv2 for faster detection, and SANet attention modules for better accuracy.…”

Research on Automatic Counting of Drill Pipes for Underground Gas Drainage in Coal Mines Based on YOLOv7-GFCA Model

“…The position loss function is represented the ratio between the predicted box A of the rig chuck and the manually marked real box B by Equation (11).…”

“…At present, a significant amount of research is conducted by many scholars on coal mine underground targets using target detection technology, leading to the achievement of certain research results [11][12][13]. However, targets such as miners, safety equipment, and coal blocks are mainly detected in the literature [11][12][13], and the drilling rig targets in the gas drainage environment are not studied.…”

Dark Light Image-Enhancement Method Based on Multiple Self-Encoding Prior Collaborative Constraints

“…Currently, digital image processing technologies centered around network frameworks are gradually shining brightly in various aspects of human life, such as unmanned driving [1], industrial production [2], video surveillance [3], military applications, remote sensing monitoring [4] and other fields. However, the application premise of these technologies is to obtain accurate and clear digital images for recognition and judgment, so as to carry out a series of downstream tasks of computer vision.…”