飞控与探测2023，Vol.6Issue(4)：84-94,11.
基于注意力机制和改进YOLOv3的红外弱小目标检测
Infrared Small Target Detection Based on Improved YOLOv3 and Attention Mechanism
摘要
Abstract
Infrared dim and small target detection technology is one of the core technologies of infrared detection sys-tems.Aiming at the low target detection rate caused by low contrast,low signal-to-noise ratio,and sparse texture features in remote complex scenes,a fusion of attention mechanism and improved YOLOv3 infrared dim target de-tection algorithm is proposed.First,based on YOLOv3,the smallest detection head is replaced with a larger detec-tion head,which can effectively improve the detection probability of small targets in infrared images with ensuring the inference speed as much as possible.Then,the Infrared Attention module is added before the detection head to realize the information exchange between channels and focus on the important target features.Finally,use Complete IoU Loss instead of Intersection over Union Loss to achieve better training of the model.The experimental results show that the YOLOv3 DCA proposed can complete the detection of infrared small targets in various scenarios.The accuracy,recall,F1,and average accuracy of detecting infrared dim small targets by the optimized YOLOv3 algo-rithm are 91.8%,88.8%,93.0%,and 88.8%,respectively.The average accuracy is about 7%higher than the YOLOv3 baseline,and the average accuracy is currently the best compared to the SSD,CenterNet,and YOLOv4 models.关键词
红外弱小目标/目标检测/YOLOv3/深度学习/注意力机制Key words
infrared dim and small target/target detection/YOLOv3/deep learning/attention mechanism分类
信息技术与安全科学引用本文复制引用
冯伟,薛如翔,傅志凌,席永辉,钮赛赛,肖婷,王喆..基于注意力机制和改进YOLOv3的红外弱小目标检测[J].飞控与探测,2023,6(4):84-94,11.基金项目
中国航天科技集团有限公司第八研究院产学研合作基金(SAST2021-007) （SAST2021-007）
中国科技国防计划(2021-JCJQ-JJ-0041) （2021-JCJQ-JJ-0041）
上海市科技计划项目(21511100800) （21511100800）
国家自然科学基金(62076094) （62076094）
