文献类型：期刊文献

英文题名：RLPGB-Net: Reinforcement Learning of Feature Fusion and Global Context Boundary Attention for Infrared Dim Small Target Detection

作者：Wang, Zhe[1];Zang, Tao[1];Fu, Zhiling[1];Yang, Hai[2];Du, Wenli[1]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China

年份：2023

卷号：61

外文期刊名：IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

收录：;EI(收录号：20233414601697);WOS:【SCI-EXPANDED(收录号:WOS:001064718000005)】；

基金：This work was supported in part by the Shanghai Science and Technology Program "Federated based cross-domain and cross-task incremental learning" under Grant 21511100800, in part by the Natural Science Foundation of China under Grant 62076094, in part by the Chinese Defense Program of Science and Technology under Grant 2021-JCJQ-JJ-0041,and in part by the China Aerospace Science and Technology Corporation Industry-University-Research Cooperation Foundation of the Eighth Research Institute under Grant SAST2021-007.

语种：英文

外文关键词：Global context boundary attention (GB); infrared dim target; pyramid feature fusion; reinforcement learning

摘要：In infrared scenes, humans can easily observe objects in the scene with their eyes, even dim ones. To make the robot have the same visual ability, this article proposes a pyramid-feature fusion target detection network, called RLPGB-Net, which combines reinforcement learning with aerial targets in the infrared scene. It makes use of the powerful decision-making ability of reinforcement learning to give corresponding weights to the extracted features and highlight the significant features of infrared dim small targets. In reinforcement learning, we use priori strategy guidance and long-term training methods to train weight-regulating agents. To eliminate the local influence on the detection results, such as bright interference points similar to the target, and to solve the problem of dim target detection effectively, the global context boundary attention (GB) module is introduced to eliminate the disadvantage of local comparison using the global characteristics of different dimensions. At the same time, it can prevent the edge information of the refined target from being submerged in the background. Experimental results on the SAITD and SIRST datasets show the effectiveness of the proposed method.