Paper
1 August 2023 Siamese tracker based on hybrid dilated convolution and global cross-correlation
DongYun Xu, JianMing Gu, Yun Gao
Author Affiliations +
Proceedings Volume 12754, Third International Conference on Computer Vision and Pattern Analysis (ICCPA 2023); 127541A (2023) https://doi.org/10.1117/12.2684192
Event: 2023 3rd International Conference on Computer Vision and Pattern Analysis (ICCPA 2023), 2023, Hangzhou, China
Abstract
Backbone networks and cross correlation operations are two important modules of the current mainstream Siamese network tracking framework. However, backbone networks based on dilated convolutions have a checkerboard effect while expanding the receptive field. The size of the depth-wise cross correlation features matching area and the number of channels activated affect the discrimination ability of the object boundary. Aiming at the problems of checkerboard effect and depth-wise cross correlation operation, proposes a Siamese tracker based on hybrid dilated convolution and global cross correlation, which uses hybrid expansion convolution to improve the checkerboard effect, improve the effectiveness of feature extraction, the global cross-correlation operation is used to promote the accuracy of the matching between the template feature and the search region feature. Evaluated on VOT2018, OTB100, UAV123 and other public test sets, the performance of this proposed method is better than that of mainstream Siamese network tracking algorithms, and the tracking effect is effectively improved.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
DongYun Xu, JianMing Gu, and Yun Gao "Siamese tracker based on hybrid dilated convolution and global cross-correlation", Proc. SPIE 12754, Third International Conference on Computer Vision and Pattern Analysis (ICCPA 2023), 127541A (1 August 2023); https://doi.org/10.1117/12.2684192
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Convolution

Detection and tracking algorithms

Feature extraction

Semantics

Image processing

Ablation

Feature fusion

Back to Top