Siamese High-Level Feature Refine Network for Visual Object Tracking
Autor: | Md. Maklachur Rahman, Seock Ho Kim, Lamyanba Laishram, Soon Ki Jung, Rishad Ahmed |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
Computer Networks and Communications
Computer science feature refine network lcsh:TK7800-8360 02 engineering and technology Tracking (particle physics) Discriminative model 0202 electrical engineering electronic engineering information engineering Computer vision siamese network Electrical and Electronic Engineering Representation (mathematics) business.industry lcsh:Electronics 020206 networking & telecommunications Hardware and Architecture Control and Systems Engineering Salient Feature (computer vision) Video tracking Signal Processing visual object tracking Eye tracking 020201 artificial intelligence & image processing Artificial intelligence business attention mechanism |
Zdroj: | Electronics, Vol 9, Iss 1918, p 1918 (2020) Electronics Volume 9 Issue 11 |
ISSN: | 2079-9292 |
Popis: | Siamese network-based trackers are broadly applied to solve visual tracking problems due to its balanced performance in terms of speed and accuracy. Tracking desired objects in challenging scenarios is still one of the fundamental concerns during visual tracking. This research paper proposes a feature refined end-to-end tracking framework with real-time tracking speed and considerable performance. The feature refine network has been incorporated to enhance the target feature representation power, utilizing high-level semantic information. Besides, it allows the network to capture the salient information to locate the target and learns to represent the target feature in a more generalized way advancing the overall tracking performance, particularly in the challenging sequences. But, only the feature refine module is unable to handle such challenges because of its less discriminative ability. To overcome this difficulty, we employ an attention module inside the feature refine network that strengths the tracker discrimination ability between the target and background. Furthermore, we conduct extensive experiments to ensure the proposed tracker&rsquo s effectiveness using several popular tracking benchmarks, demonstrating that our proposed model achieves state-of-the-art performance over other trackers. |
Databáze: | OpenAIRE |
Externí odkaz: |
načítá se...