A New Deep Model for Detecting Multiple Moving Targets in Real Traffic Scenarios: Machine Vision-Based Vehicles

Abstract

When performing multiple target detection, it is difficult to detect small and occluded targets in complex traffic scenes. To this end, an improved YOLOv4 detection method is proposed in this work. Firstly, the network structure of the original YOLOv4 is adjusted, and the 4× down-sampling feature map of the backbone network is introduced into the neck network of the YOLOv4 model to splice the feature map with 8× down-sampling to form a four-scale detection structure, which enhances the fusion of deep and shallow semantics information of the feature map to improve the detection accuracy of small targets. Then, the convolutional block attention module (CBAM) is added to the model neck network to enhance the learning ability for features in space and on channels. Lastly, the detection rate of the occluded target is improved by using the soft non-maximum suppression (Soft-NMS) algorithm based on the distance intersection over union (DIoU) to avoid deleting the bounding boxes. On the KITTI dataset, experimental evaluation is performed and the analysis results demonstrate that the proposed detection model can effectively improve the multiple target detection accuracy, and the mean average accuracy (mAP) of the improved YOLOv4 model reaches 81.23%, which is 3.18% higher than the original YOLOv4; and the computation speed of the proposed model reaches 47.32 FPS. Compared with existing popular detection models, the proposed model produces higher detection accuracy and computation speed.

Vehicle and Pedestrian Target Detection Model Under Complex Traffic Conditions

“…Zhang et al [9] introduced the YOLOv7-RAR recognition algorithm, which employed the Res3Unit structure to reconstruct the backbone network of YOLOv7, added the mixed attention mechanism module ACmix, and utilized a Gauss receptive fieldbased label allocation scheme between the feature fusion region and the probe head. Xu et al [10] adjusted the YOLOv4 network structure, incorporated a convolutional block attention module, and adopted a soft non-maximum suppression algorithm based on distance intersection, thereby improving the accuracy and computational speed of multi-target detection. Chen et al [11] introduced a deep learning-based edge node traffic detection scheme.…”