Robust visual tracking via self‐similarity learning

In the field of visual tracking, trackers based on a convolutional neural network (CNN) have had significant achievements. The fully-convolutional Siamese (SiamFC) tracker is a typical representation of these CNN trackers and has attracted much attention. It models visual tracking as a similarity-learning problem. However, experiments showed that SiamFC was not so robust in some complex environments. This may be because the tracker lacked enough prior information about the target. Inspired by the key idea of a Staple tracker and Kalman filter, we constructed two more models to help compensate for SiamFC’s disadvantages. One model contained the target’s prior color information, and the other the target’s prior trajectory information. With these two models, we design a novel and robust tracking framework on the basis of SiamFC. We call it Histogram–Kalman SiamFC (HKSiamFC). We also evaluated HKSiamFC tracker’s performance on dataset of the online object tracking benchmark (OTB) and Temple Color (TC128), and it showed quite competitive performance when compared with the baseline tracker and several other state-of-the-art trackers.

Download Full-text

Visual tracking based on semantic and similarity learning

IET Computer Vision ◽

10.1049/iet-cvi.2018.5826 ◽

2019 ◽

Vol 13 (7) ◽

pp. 623-631

Author(s):

Yufei Zha ◽

Min Wu ◽

Zhuling Qiu ◽

Wangsheng Yu

Keyword(s):

Visual Tracking ◽

Similarity Learning

Download Full-text

Subpixel Mapping Algorithms Based on Block Structural Self-Similarity Learning

Mathematical Problems in Engineering ◽

10.1155/2017/5254024 ◽

2017 ◽

Vol 2017 ◽

pp. 1-8

Author(s):

Liwei Chen ◽

Tieshen Wang ◽

Haifeng Zhu

Keyword(s):

Spatial Distribution ◽

Block Structure ◽

Mapping Method ◽

Similarity Learning ◽

Remote Sensing Images ◽

Self Similarity ◽

Image Block ◽

Mapping Algorithms ◽

Mixed Pixels ◽

Subpixel Mapping

Subpixel mapping (SPM) algorithms effectively estimate the spatial distribution of different land cover classes within mixed pixels. This paper proposed a new subpixel mapping method based on image structural self-similarity learning. Image structure self-similarity refers to similar structures within the same scale or different scales in image itself or its downsampled image, which widely exists in remote sensing images. Based on the similarity of image block structure, the proposed method estimates higher spatial distribution of coarse-resolution fraction images and realizes subpixel mapping. The experimental results show that the proposed method is more accurate than existing fast subpixel mapping algorithms.

Download Full-text

Multi-Stream Deep Similarity Learning Networks for Visual Tracking

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2017/301 ◽

2017 ◽

Cited By ~ 10

Author(s):

Kunpeng Li ◽

Yu Kong ◽

Yun Fu

Keyword(s):

Visual Tracking ◽

Model Updating ◽

Feature Space ◽

Fine Tuning ◽

Similarity Learning ◽

Learning Networks ◽

Target Template ◽

Background Clutter ◽

Cluttered Background ◽

Background Context

Visual tracking has achieved remarkable success in recent decades, but it remains a challenging problem due to appearance variations over time and complex cluttered background. In this paper, we adopt a tracking-by-verification scheme to overcome these challenges by determining the patch in the subsequent frame that is most similar to the target template and distinctive to the background context. A multi-stream deep similarity learning network is proposed to learn the similarity comparison model. The loss function of our network encourages the distance between a positive patch in the search region and the target template to be smaller than that between positive patch and the background patches. Within the learned feature space, even if the distance between positive patches becomes large caused by the appearance change or interference of background clutter, our method can use the relative distance to distinguish the target robustly. Besides, the learned model is directly used for tracking with no need of model updating, parameter fine-tuning and can run at 45 fps on a single GPU. Our tracker achieves state-of-the-art performance on the visual tracking benchmark compared with other recent real-time-speed trackers, and shows better capability in handling background clutter, occlusion and appearance change.

Download Full-text

Online similarity learning for visual tracking

Information Sciences ◽

10.1016/j.ins.2016.05.019 ◽

2016 ◽

Vol 364-365 ◽

pp. 33-50 ◽

Cited By ~ 10

Author(s):

Sihua Yi ◽

Nan Jiang ◽

Bin Feng ◽

Xinggang Wang ◽

Wenyu Liu

Keyword(s):

Visual Tracking ◽

Similarity Learning

Download Full-text

Similarity learning for template-based visual tracking

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) ◽

10.1109/icmew.2014.6890723 ◽

2014 ◽

Author(s):

Xiuzhuang Zhou ◽

Lu Kou ◽

Hui Ding ◽

Xiaoyan Fu ◽

Yuanyuan Shang

Keyword(s):

Visual Tracking ◽

Similarity Learning

Download Full-text

Visual Tracking via Nonlocal Similarity Learning

IEEE Transactions on Circuits and Systems for Video Technology ◽

10.1109/tcsvt.2017.2708726 ◽

2018 ◽

Vol 28 (10) ◽

pp. 2826-2835 ◽

Cited By ~ 5

Author(s):

Qingshan Liu ◽

Jiaqing Fan ◽

Huihui Song ◽

Wei Chen ◽

Kaihua Zhang

Keyword(s):

Visual Tracking ◽

Similarity Learning ◽

Nonlocal Similarity

Download Full-text

MFCFSiam: A Correlation-Filter-Guided Siamese Network with Multifeature for Visual Tracking

Wireless Communications and Mobile Computing ◽

10.1155/2020/6681391 ◽

2020 ◽

Vol 2020 ◽

pp. 1-19

Author(s):

Chenpu Li ◽

Qianjian Xing ◽

Zhenguo Ma ◽

Ke Zang

Keyword(s):

Visual Tracking ◽

Correlation Filter ◽

Evaluation Criterion ◽

Visual Object ◽

Semantic Features ◽

Similarity Learning ◽

Feature Maps ◽

Siamese Network ◽

Histograms Of Oriented Gradients ◽

High Level

With the development of deep learning, trackers based on convolutional neural networks (CNNs) have made significant achievements in visual tracking over the years. The fully connected Siamese network (SiamFC) is a typical representation of those trackers. SiamFC designs a two-branch architecture of a CNN and models’ visual tracking as a general similarity-learning problem. However, the feature maps it uses for visual tracking are only from the last layer of the CNN. Those features contain high-level semantic information but lack sufficiently detailed texture information. This means that the SiamFC tracker tends to drift when there are other same-category objects or when the contrast between the target and the background is very low. Focusing on addressing this problem, we design a novel tracking algorithm that combines a correlation filter tracker and the SiamFC tracker into one framework. In this framework, the correlation filter tracker can use the Histograms of Oriented Gradients (HOG) and color name (CN) features to guide the SiamFC tracker. This framework also contains an evaluation criterion which we design to evaluate the tracking result of the two trackers. If this criterion finds the SiamFC tracker fails in some cases, our framework will use the tracking result from the correlation filter tracker to correct the SiamFC. In this way, the defects of SiamFC’s high-level semantic features are remedied by the HOG and CN features. So, our algorithm provides a framework which combines two trackers together and makes them complement each other in visual tracking. And to the best of our knowledge, our algorithm is also the first one which designs an evaluation criterion using correlation filter and zero padding to evaluate the tracking result. Comprehensive experiments are conducted on the Online Tracking Benchmark (OTB), Temple Color (TC128), Benchmark for UAV Tracking (UAV-123), and Visual Object Tracking (VOT) Benchmark. The results show that our algorithm achieves quite a competitive performance when compared with the baseline tracker and several other state-of-the-art trackers.

Download Full-text