https://doi.org/10.1140/epjd/s10053-022-00505-4
Regular Article - Optical Phenomena and Photonics
Infrared moving small target detection and tracking algorithm based on feature point matching
1
College of Communication and Art Design, University of Shanghai for Science and Technology, 200093, Shanghai, China
2
School of Computer Science and Technology, Huazhong University of Science and Technology, 430074, Wuhan, China
Received:
5
June
2022
Accepted:
14
September
2022
Published online:
9
October
2022
The detection and tracking of the small target in infrared video are among the most critical technologies in computer vision applications. These include video surveillance and infrared imaging precision guidance. Recently, more and more infrared small target detection and tracking algorithms have been proposed. However, most existing algorithms have complex processing problems, high false alarm rates, and low detection accuracy. To achieve accurate detection and tracking of infrared small targets, this paper proposes an algorithm for detection and tracking of infrared small targets using infrared small target feature point and gradient information. Feature point detection is used to detect possible targets, and possible targets are further processed through direction gradient calculation. Then, in the adjacent sequence images, it is matched according to the local features of adjacent frames. According to the characteristics of infrared small target motion, this paper proposes a target motion generation trajectory to verify the accuracy of the detection algorithm. Finally, compared with other algorithms, it is concluded that the algorithm in this paper has a higher detection rate and a lower false detection rate.
Copyright comment Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to EDP Sciences, SIF and Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
