航空学报2025，Vol.46Issue(23)：59-71,13.DOI:10.7527/S1000-6893.2025.32017
基于特征协同重构的RGB-T无人机目标跟踪
RGB-T UAV object tracking based on feature-cooperative reconstruction
摘要
Abstract
RGB-T Unmanned Aerial Vehicle(UAV)object tracking enhances tracking robustness in complex environ-ments by fusing complementary information from visible light and thermal infrared modalities.However,existing meth-ods neglect the noise interference caused by modality gaps,which weakens the effectiveness of cross-modal feature complementarity and degrades the power of feature representation;thereby,limiting the performance of RGB-T UAV trackers.To address this issue,a feature-cooperative reconstruction-based tracker is proposed,the core of which is to develop a feature-cooperative reconstruction module,consisting of a cross-modal interaction encoder and a feature re-construction decoder.Specifically,the cross-modal interaction encoder employs an adaptive feature interaction strat-egy to extract critical complementary information from the auxiliary modality while effectively suppressing cross-modal noise interference.The feature reconstruction decoder then utilizes the query features from the encoder to guide the reconstruction of features,preserving modality-specific information while incorporating cross-modal complementary de-tails to enhance feature representation.Additionally,to improve target localization accuracy in dynamic scenes,a cross-modal location cue fusion module is proposed to integrate search regions from different modalities,providing more precise localization cues.Finally,extensive experimental evaluations on two RGB-T UAV object tracking bench-mark datasets(i.e.,VTUAV and HiAL)as well as the LasHeR dataset are conducted.The results demonstrate that the proposed method significantly outperforms existing methods.Notably,compared to HMFT,the proposed method improves tracking success rate and precision on the VTUAV dataset by 9.9%and 9.0%,respectively.关键词
无人机/目标跟踪/Transformer/跨模态特征交互/特征协同重构/跨模态位置线索融合Key words
UAV/object tracking/Transformer/cross-modal feature interaction/feature-cooperative reconstruc-tion/cross-modal location cue fusion分类
航空航天引用本文复制引用
GAO Dong,LAI Pujian,WANG Shilei,CHENG Gong..基于特征协同重构的RGB-T无人机目标跟踪[J].航空学报,2025,46(23):59-71,13.基金项目
国家自然科学基金(61772425) （61772425）
陕西省自然科学基金(2021JC-16) National Natural Science Foundation of China(61772425) （2021JC-16）
Shaanxi Province Natural Science Foundation(2021JC-16) （2021JC-16）
