光学精密工程2023，Vol.31Issue(22)：3345-3356,12.DOI:10.37188/OPE.20233122.3345
针对目标遮挡的自适应特征匹配网络
Adaptive feature matching network for object occlusion
摘要
Abstract
An adaptive feature-matching network is proposed to solve the common problem of object occlu-sion in object tracking.By calculating the pixel-level similarity between the query and memory frames,the network encodes the similarity relationship between an object and its background and obtains a pixel-level similarity matrix.By separating the query and memory frames,the network calculates the multi-dimen-sional similarity to focus on more areas in the query frame and adaptively weighs the memory frame through the calculated similarity matrix to improve the accuracy and robustness of object tracking.Addi-tionally,the feature memory network selects and saves the memory frames,provides additional apparent information for feature matching,and allows the network to implicitly learn the moving trend of an object to achieve better tracking results.Experimental results show that this method performs well on GOT-10k,LaSOT,and other datasets.On GOT-10k datasets,compared with the STMTrack algorithm,the value of the proposed algorithm is improved by 1.8%.The visualization results show that the proposed algo-rithm is more robust in meeting the challenges of object occlusion and disappearance.关键词
目标遮挡/自适应/特征匹配/记忆网络Key words
object occlusion/self-adaption/feature matching/memory network分类
计算机与自动化引用本文复制引用
毛琳,苏宏阳,杨大伟..针对目标遮挡的自适应特征匹配网络[J].光学精密工程,2023,31(22):3345-3356,12.基金项目
国家自然科学基金资助项目(No.61673084) （No.61673084）
辽宁省自然科学基金资助项目(No.20170540192,No.20180550866,No.2020-MZLH-24) （No.20170540192,No.20180550866,No.2020-MZLH-24）
