Fast multi-scale target detection in apron based on variable resolution mechanism

In the apron target detection, the target size is very small, and a large number of fine particle characteristics are lost in the compression process, resulting in recognition errors. Fine granularity directly affects the accuracy of target recognition. However, due to the limited energy consumption, computational power of equipment, and the insufficient feature extraction of small targets by universal target detection algorithms, the improvement of speed and accuracy of such algorithms is restricted. This paper presents a real-time detection algorithm which is named DT-YOLOV4 (difficult targets-YOLO V4) for apron target detection. By using the variable resolution mechanism, the algorithm detects the compressed image once, and then identifies the difficult targets twice. Finally, the unimportant channels in the network are trimmed based on the scaling factor of the batch normalization layer. The trimmed and slimmed algorithm has a higher speed. The test results on our airport-image data set show that the map (mean average precision) index of DT-YOLOV4 algorithm is about 21% higher than that of YOLO V4 algorithm, and the detection speed reaches 84 FPS (Frames Per Second), which is about equal to 83 FPS of YOLO V4.