Paper
18 November 2022 Satellite video target tracking based on kernel correlation filtering and trajectory prediction
Xiongfeng Liu, Haixing Shang
Author Affiliations +
Proceedings Volume 12473, Second International Conference on Optics and Communication Technology (ICOCT 2022); 124730Q (2022) https://doi.org/10.1117/12.2653638
Event: Second International Conference on Optics and Communication Technology (ICOCT 2022), 2022, Hefei, China
Abstract
There are various problems in the current target tracking of satellite videos, such as the small size of moving targets, few textures, and easy occlusion. To solve the problem of tracking failure caused by occlusion of moving objects, a tracking algorithm based on kernel correlation filtering and trajectory prediction is proposed in this paper. The algorithm in this paper uses the motion characteristics of moving objects in satellite video to predict the trajectory and uses the trajectory prediction algorithm to predict the trajectory of the target when it is occluded. Combined with the kernel correlation filtering algorithm, the target can still be accurately tracked after it is occluded. Experiments on satellite video datasets show that the algorithm in this paper can effectively solve the problem of tracking failure caused by the occlusion of moving objects, and the speed is also very fast.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiongfeng Liu and Haixing Shang "Satellite video target tracking based on kernel correlation filtering and trajectory prediction", Proc. SPIE 12473, Second International Conference on Optics and Communication Technology (ICOCT 2022), 124730Q (18 November 2022); https://doi.org/10.1117/12.2653638
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Detection and tracking algorithms

Video

Satellites

Image filtering

Electronic filtering

Target detection

Optical tracking

Back to Top