Multi-view region proposal network predictive learning for tracking

• Published in: Multimedia systems Vol. 29; no. 1; pp. 333 - 346
• Main Authors: Guo, Wen, Li, Dong, Liang, Bowen, Shan, Bin
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2023; Springer Nature B.V
• Subjects: Algorithms; Computer Communication Networks; Computer Graphics; Computer Science; Computer vision; Cryptology; Data Storage Representation; Deep learning; Machine learning; Multimedia Information Systems; Operating Systems; Optical tracking; Optimization; Performance evaluation; Regular Paper; Representations; Support vector machines; Visual discrimination; Prediction learning; Visual tracking; Multi-view multi-expert learning; Region proposal prediction
• ISSN: 0942-4962; 1432-1882
• DOI: 10.1007/s00530-022-01001-w

Visual tracking is one of the most challenging problems in computer vision. Most state-of-the-art visual trackers suffer from three challenging problems: nondiverse discriminate feature representation, coarse object locator, and limited quantities of positive samples. In this paper, a multi-view multi-expert region proposal prediction algorithm for tracking is proposed to solve the above problems concurrently in one framework. The proposed algorithm integrates multiple views and exploits powerful multiple sources of information, which can solve nondiverse discriminate feature representation problem effectively. It builds multiple SVM classifier models on the expanded bounding boxes and adds the regional suggestion network module to accurately optimize it to predict optimal object location, which naturally alleviates the coarse object locator and limited quantities of positive samples problems at the same time. A comprehensive evaluation of the proposed approach on various benchmark sequences has been performed. The evaluation results demonstrate our method can significantly improve the tracking performance by combining the advantages of lightweight region proposal network predictive learning model and multi-view expert groups. The experimental results demonstrate the proposed approach outperforms other state-of-the-art visual trackers.