Paper
16 February 2022 Siamese dual path aggregation network for object tracking
Author Affiliations +
Proceedings Volume 12083, Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021); 120830N (2022) https://doi.org/10.1117/12.2623408
Event: Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021), 2021, Kunming, China
Abstract
Siamese trackers have attracted great attention on visual object tracking due to their real-time speed and high accuracy. In this paper, we propose a dual path aggregation network (SiamDPAN) for high-performance tracking. First, we build a multi-level similarity maps aggregation (MSA) structure, which predicts and fuses the similarity maps from multi-level features. Second, we propose a mask path aggregation module (MPA) for better capturing the appearance changes of objects by propagating maps in low-layers. We conduct sufficient ablation studies to demonstrate the effectiveness of our proposed tracker. We only train our network with two datasets, achieving 0.436 EAO and 0.351 EAO on VOT2016 and VOT2018.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yijun Tian, Huiqian Du, and Zhifeng Ma "Siamese dual path aggregation network for object tracking", Proc. SPIE 12083, Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021), 120830N (16 February 2022); https://doi.org/10.1117/12.2623408
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Optical tracking

Feature extraction

Head

Video

Visualization

Detection and tracking algorithms

Video surveillance

Back to Top