Camouflaged Object Detection Based on Improved YOLO v5 Algorithm

• Published in: Ji suan ji ke xue Vol. 48; no. 10; pp. 226 - 232
• Main Authors: Wang, Yang, Cao, Tie-yong, Yang, Ji-bin, Zheng, Yun-fei, Fang, Zheng, Deng, Xiao-tong, Wu, Jing-wei, Lin, Jia
• Format: Journal Article
• Language: Chinese
• Published: Chongqing Guojia Kexue Jishu Bu 01.10.2021; Editorial office of Computer Science
• Subjects: Algorithms; Camouflage; camouflaged object|object detection|attention mechanism|yolo|aggregation network; Feature extraction; Feature maps; Object recognition; Recall
• ISSN: 1002-137X
• DOI: 10.11896/jsjkx.210100058

Since the camouflage object is highly similar to the surrounding environment with a rather small size, the general detection algorithm is not fully applicable to the camouflaged object detection task, which makes the detection of camouflaged object more challenging than the general detection task.In order to solve this problem, the existing methods are analyzed in this paper and a detection algorithm for camouflage object is proposed based on the YOLO v5 algorithm.A new feature extraction network combined with attention mechanism is designed to highlight the feature information of the camouflage target.The original path aggregation network is improved so that the high, middle and lowly level feature map information is fully fused.The semantic information of the target is strengthened by nonlinear pool module, and the detection feature map size is increased to improve the detection recall rate of the small size target.On a public camouflage target dataset, the proposed algorithm is tested with 7 algorithms.The