Back to Search
Start Over
Joint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks.
- Source :
-
International Journal of Computer Vision . Feb2022, Vol. 130 Issue 2, p550-566. 17p. - Publication Year :
- 2022
-
Abstract
- Visual tracking of generic objects is one of the fundamental but challenging problems in computer vision. Here, we propose a novel fully convolutional Siamese network to solve visual tracking by directly predicting the target bounding box in an end-to-end manner. We first reformulate the visual tracking task as two subproblems: a classification problem for pixel category prediction and a regression task for object status estimation at this pixel. With this decomposition, we design a simple yet effective Siamese architecture based classification and regression framework, termed SiamCAR, which consists of two subnetworks: a Siamese subnetwork for feature extraction and a classification-regression subnetwork for direct bounding box prediction. Since the proposed framework is both proposal- and anchor-free, SiamCAR can avoid the tedious hyper-parameter tuning of anchors, considerably simplifying the training. To demonstrate that a much simpler tracking framework can achieve superior tracking results, we conduct extensive experiments and comparisons with state-of-the-art trackers on a few challenging benchmarks. Without bells and whistles, SiamCAR achieves leading performance with a real-time speed. Furthermore, the ablation study validates that the proposed framework is effective with various backbone networks, and can benefit from deeper networks. Code is available at https://github.com/ohhhyeahhh/SiamCAR. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09205691
- Volume :
- 130
- Issue :
- 2
- Database :
- Academic Search Index
- Journal :
- International Journal of Computer Vision
- Publication Type :
- Academic Journal
- Accession number :
- 155281204
- Full Text :
- https://doi.org/10.1007/s11263-021-01559-4