Online dual dictionary learning for visual object tracking
- Authors: Cheng, Xu , Zhang, Yifeng , Zhou, Lin , Lu, Guojun
- Date: 2021
- Type: Text , Journal article
- Relation: Journal of Ambient Intelligence and Humanized Computing Vol. 12, no. 12 (2021), p. 10881-10896
- Full Text: false
- Reviewed:
- Description: Sparse representation method has been widely applied to visual tracking. Most of existing tracking algorithms based on sparse representation exploit the l0 or l1-norm for solving the sparse coefficients. However, it makes the execution of solution very time consuming. In this paper, we propose an effective dual dictionary learning model for visual tracking. The dictionary model is composed of discriminative dictionary and analytic dictionary; they work together to perform the representation and discrimination simultaneously. First, we exploit the object states of the first ten frames of a video to initialize the dual dictionary. In the tracking phase, the dual dictionary model is updated alternatively. Second, the local and global information of the object are integrated into the dual dictionary learning model. Sparse coefficients of the patch are used to encode the local structural information of the object. Furthermore, all the sparse coefficients within one object state form a global object representation. We develop a likelihood function that takes an adaptive threshold into consideration to de-noise the global representation. In addition, the object template is updated via an online scheme to adapt the object appearance changes. The experiments on a number of common benchmark test sets show that our approach is more effective than the existing methods. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature.
Siamese network for object tracking with multi-granularity appearance representations
- Authors: Zhang, Zhuoyi , Zhang, Yifeng , Cheng, Xu , Lu, Guojun
- Date: 2021
- Type: Text , Journal article
- Relation: Pattern Recognition Vol. 118, no. (2021), p.
- Full Text: false
- Reviewed:
- Description: A reliable tracker has the ability to adapt to change of objects over time, and is robust and accurate. We build such a tracker by extracting semantic features using robust Siamese networks and multi-granularity color features. It incorporates a semantic model that can capture high quality semantic features and an appearance model that can describe object at pixel, local and global levels effectively. Furthermore, we propose a novel selective traverse algorithm to allocate weights to semantic models and appearance models dynamically for better tracking performance. During tracking, our tracker updates appearance representations for objects based on the recent tracking results. The proposed tracker operates at speeds that exceed the real-time requirement, and outperforms nearly all other state-of-the-art trackers on OTB-2013/2015 and VOT-2016/2017 benchmarks. © 2021 Elsevier Ltd
An Attention-Based Approach for Single Image Super Resolution
- Authors: Liu, Yuan , Wang, Yuancheng , Li, Nan , Cheng, Xu , Zhang, Yifeng , Huang, Yongming , Lu, Guojun
- Date: 2018
- Type: Text , Conference proceedings , Conference paper
- Relation: 2018 24th International Conference on Pattern Recognition, ICPR 2018; Beijing, China; 20th-24th August 2018 Vol. 2018, p. 2777-2784
- Full Text:
- Reviewed:
- Description: The main challenge of single image super resolution (SISR) is the recovery of high frequency details such as tiny textures. However, most of the state-of-the-art methods lack specific modules to identify high frequency areas, causing the output image to be blurred. We propose an attention-based approach to give a discrimination between texture areas and smooth areas. After the positions of high frequency details are located, high frequency compensation is carried out. This approach can incorporate with previously proposed SISR networks. By providing high frequency enhancement, better performance and visual effect are achieved. We also propose our own SISR network composed of DenseRes blocks. The block provides an effective way to combine the low level features and high level features. Extensive benchmark evaluation shows that our proposed method achieves significant improvement over the state-of-the-art works in SISR.