Paper
12 March 2019 A fast and accurate moving target detection method
Author Affiliations +
Proceedings Volume 11023, Fifth Symposium on Novel Optoelectronic Detection Technology and Application; 1102315 (2019) https://doi.org/10.1117/12.2521230
Event: Fifth Symposium on Novel Optoelectronic Detection Technology and Application, 2018, Xi'an, China
Abstract
This paper proposes a significant moving target detection method combining time difference and optical flow field filter for scenes with complex backgrounds such as streets and traffic intersections. Firstly, the gradation change region of the sequence image is obtained by using the cumulative frame difference, then the Lucas-Kanade optical flow algorithm is introduced to obtain the optical flow field of the gray-scale change region. Finally, the optical flow time filter is used to filter the interference motion in the image background. The method can not only detect the motion area quickly and accurately, but also distinguish the spurious interference motion from the salient target (such as people, cars, etc.). So it detects the moving target in a complex background easily.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ningming Wang "A fast and accurate moving target detection method", Proc. SPIE 11023, Fifth Symposium on Novel Optoelectronic Detection Technology and Application, 1102315 (12 March 2019); https://doi.org/10.1117/12.2521230
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Optical flow

Target detection

Detection and tracking algorithms

Image filtering

Optical filters

Evolutionary algorithms

Motion detection

Back to Top