Template-guided frequency attention and adaptive cross-entropy loss for UAV visual tracking

作     者：Yuanliang XUE Guodong JIN Tao SHEN Lining TAN Lianfeng WANG Yuanliang XUE;Guodong JIN;Tao SHEN;Lining TAN;Lianfeng WANG

作者机构：School of Nuclear EngineeringPLA Rocket Force University of EngineeringXi’an 710025China 

出 版 物：《Chinese Journal of Aeronautics》 (中国航空学报（英文版）)

年 卷 期：2023年第36卷第9期

页      面：299-312页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 082503[工学-航空宇航制造工程] 0835[工学-软件工程] 0825[工学-航空宇航科学与技术] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This study was co-supported by the National Natural Science Foundation of China(Nos.61673017 and 61403398) 

主　　题：Object tracking Unmanned Aerial Vehicle(UAV) Deep learning Siamese neural network 

摘      要：This paper addresses the problem of visual object tracking for Unmanned Aerial Vehicles(UAVs).Most Siamese trackers are used to regard object tracking as classification and regression ***,it is difficult for these trackers to accurately classify in the face of similar objects,background clutters and other common challenges in UAV ***,a reliable classifier is the key to improving UAV tracking *** this paper,a simple yet efficient tracker following the basic architecture of the Siamese neural network is proposed,which improves the classification ability from three ***,the frequency channel attention module is introduced to enhance the target features via frequency domain ***,a template-guided attention module is designed to promote information exchange between the template branch and the search branch,which can get reliable classification response ***,adaptive cross-entropy loss is proposed to make the tracker focus on hard samples that contribute more to the training process,solving the data imbalance between positive and negative *** evaluate the performance of the proposed tracker,comprehensive experiments are conducted on two challenging aerial datasets,including UAV123 and *** results demonstrate that the proposed tracker achieves favorable tracking performances in aerial benchmarks beyond 41 frames/*** conducted experiments in real UAV scenes to further verify the efficiency of our tracker in the real world.