Infrared Moving Small Target Detection Based on Consistency of Sparse Trajectory

被引:4
|
作者
Wu, Mo [1 ,2 ]
Yang, Xiubin [1 ,2 ]
Fu, Zongqiang [1 ,2 ]
He, Haoyang [3 ]
Du, Jiamin [1 ,2 ]
Xu, Tingting [1 ,2 ]
Tu, Ziming [1 ,2 ]
机构
[1] Chinese Acad Sci, Changchun Inst Opt, Fine Mech & Phys, Changchun 130033, Peoples R China
[2] Univ Chinese Acad Sci, Daheng Coll, Beijing 100039, Peoples R China
[3] Beijing Inst Technol, Sch Opt & Photon, Beijing 100081, Peoples R China
基金
中国国家自然科学基金;
关键词
Trajectory; Optical flow; Feature extraction; Optical variables measurement; Object detection; Geoscience and remote sensing; Three-dimensional displays; Infrared moving small target; optical flow consistency; similarity measure; sparse trajectory; trajectory growth; LOCAL CONTRAST;
D O I
10.1109/LGRS.2023.3257850
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Infrared search and track (IRST) systems require reliable detection of small targets in complex backgrounds. Outlier-based methods are prone to high false positive rates due to the resemblance of point-like background features to small targets. The difference image-based method is an effective approach for suppressing point-like background interference; however, it has limitations in detecting slow-moving targets. In this letter, a novel sparse trajectory is proposed for moving target detection in IR videos. With a trajectory growing strategy, two kinds of trajectories from difference images, namely, short sparse trajectories and long sparse trajectories, are correlated to avoid the slow-moving targets being dismissed. The strategy matches the trajectories based on the sparse trajectory intensity composed of similarity measures and optical flow consistency. Finally, real targets are extracted from candidate trajectories using trajectory filtering. Experimental results show that, in the scene with point-like background features, our method achieves the best detection rate and lowest false alarm compared to the state-of-the-art methods.
引用
收藏
页数:5
相关论文
empty
未找到相关数据