Dual Deep Network for Visual Tracking
From MaRDI portal
Publication:4618752
DOI10.1109/TIP.2017.2669880zbMATH Open1409.94083arXiv1612.06053WikidataQ38380641 ScholiaQ38380641MaRDI QIDQ4618752FDOQ4618752
Authors: Zhizhen Chi, Hongyang Li, Hu-Chuan Lu, Ming-Hsuan Yang 
Publication date: 5 February 2019
Published in: IEEE Transactions on Image Processing (Search for Journal in Brave)
Abstract: Visual tracking addresses the problem of identifying and localizing an unknown target in a video given the target specified by a bounding box in the first frame. In this paper, we propose a dual network to better utilize features among layers for visual tracking. It is observed that features in higher layers encode semantic context while its counterparts in lower layers are sensitive to discriminative appearance. Thus we exploit the hierarchical features in different layers of a deep model and design a dual structure to obtain better feature representation from various streams, which is rarely investigated in previous work. To highlight geometric contours of the target, we integrate the hierarchical feature maps with an edge detector as the coarse prior maps to further embed local details around the target. To leverage the robustness of our dual network, we train it with random patches measuring the similarities between the network activation and target appearance, which serves as a regularization to enforce the dual network to focus on target object. The proposed dual network is updated online in a unique manner based on the observation that the target being tracked in consecutive frames should share more similar feature representations than those in the surrounding background. It is also found that for a target object, the prior maps can help further enhance performance by passing message into the output maps of the dual network. Therefore, an independent component analysis with reference algorithm (ICA-R) is employed to extract target context using prior maps as guidance. Online tracking is conducted by maximizing the posterior estimate on the final maps with stochastic and periodic update. Quantitative and qualitative evaluations on two large-scale benchmark data sets show that the proposed algorithm performs favourably against the state-of-the-arts.
Full work available at URL: https://arxiv.org/abs/1612.06053
Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Cited In (1)
This page was built for publication: Dual Deep Network for Visual Tracking
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4618752)
