Paper
20 April 2023 Lightweight Siamese network-based single-target tracking algorithm for pedestrians
Cong Sun, Yubing Dong, Mingjing Li, Dong Pan
Author Affiliations +
Proceedings Volume 12602, International Conference on Electronic Information Engineering and Computer Science (EIECS 2022); 126022U (2023) https://doi.org/10.1117/12.2668485
Event: International Conference on Electronic Information Engineering and Computer Science (EIECS 2022), 2022, Changchun, China
Abstract
Aiming at the problem of slow running speed of pedestrian single-target tracking task using SiamBAN algorithm under limited hardware conditions, this paper proposes a lightweight pedestrian single-target tracking network GhostSiamBAN. Specifically, we use GhostModule to build a new lightweight backbone network to replace the original Resnet50. The evaluation on OTB2015 and VOT2018 shows that our method can well balance the tracking accuracy and speed. Compared with SiamBAN, the test results of pedestrian single target tracking sequence on Nvidia GTX 1050 show that the average running speed of our method is about 26fps with an accuracy loss of about 5.46%, and the speed is increased by nearly 271.4%
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Cong Sun, Yubing Dong, Mingjing Li, and Dong Pan "Lightweight Siamese network-based single-target tracking algorithm for pedestrians", Proc. SPIE 12602, International Conference on Electronic Information Engineering and Computer Science (EIECS 2022), 126022U (20 April 2023); https://doi.org/10.1117/12.2668485
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Detection and tracking algorithms

Convolution

Education and training

Feature extraction

Video

Deep learning

Mobile devices

Back to Top