.png){kind=icon}
.png){kind=icon}
Return
Space moving target detection and tracking method in complex background
.png){kind=icon}
PRE
AI
DOI：10.1016/j.infrared.2018.03.007.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The background of the space-borne detectors in real space-based environment is extremely complex and the signal-to-clutter ratio is very low (SCR approximate to 1), which increases the difficulty for detecting space moving targets. In order to solve this problem, an algorithm combining background suppression processing based on two-dimensional least mean square filter (TDLMS) and target enhancement based on neighborhood gray-scale difference (GSD) is proposed in this paper. The latter can filter out most of the residual back-ground clutter processed by the former such as cloud edge. Through this procedure, both global and local SCR have obtained substantial improvement, indicating that the target has been greatly enhanced. After removing the detector's inherent clutter region through connected domain processing, the image only contains the target point and the isolated noise, in which the isolated noise could be filtered out effectively through multi-frame association. The proposed algorithm in this paper has been compared with some state-of-the-art algorithms for moving target detection and tracking tasks. The experimental results show that the performance of this algorithm is the best in terms of SCR gain, background suppression factor (BSF) and detection results. (C) 2018 Elsevier BV. All rights reserved.
Keywords:
Weak point target
Low SCR
Complex background
GSD
TDLMS
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
3.4
Papers:
5.8K
Citations:
1.2W