Robust Visual Tracking Revisited: From Correlation Filter to Template Matching

Liu, Fanghui; Gong, Chen; Huang, Xiaolin; Zhou, Tao; Yang, Jie; Tao, Dacheng

doi:10.1109/tip.2018.2813161

Cited by 65 publications

(27 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar approach was employed in CFLB [12] and BACF [15], forcing the parameters corresponding to background to be exactly zero. In addition, DCFbased tracking methods have also been extended to support long-term memory [46], multi-kernel method [47], structural constraints [48], support vector representation [49], sparse representation [50] and enhanced robustness [51], [52], [53], [54], [55], [56]. Furthermore, adaptive decontamination of the training set [57] was proposed to achieve adaptive multiframe learning in the DCF paradigm, which improved the generalisation performance.…”

Section: Related Workmentioning

confidence: 99%

Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking

Feng

et al. 2019

IEEE Trans. on Image Process.

360

187

View full text Add to dashboard Cite

With efficient appearance learning models, Discriminative Correlation Filter (DCF) has been proven to be very successful in recent video object tracking benchmarks and competitions. However, the existing DCF paradigm suffers from two major issues, i.e., spatial boundary effect and temporal filter degradation. To mitigate these challenges, we propose a new DCF-based tracking method. The key innovations of the proposed method include adaptive spatial feature selection and temporal consistent constraints, with which the new tracker enables joint spatial-temporal filter learning in a lower dimensional discriminative manifold. More specifically, we apply structured spatial sparsity constraints to multi-channel filers. Consequently, the process of learning spatial filters can be approximated by the lasso regularisation. To encourage temporal consistency, the filter model is restricted to lie around its historical value and updated locally to preserve the global structure in the manifold. Last, a unified optimisation framework is proposed to jointly select temporal consistency preserving spatial features and learn discriminative filters with the augmented Lagrangian method. Qualitative and quantitative evaluations have been conducted on a number of well-known benchmarking datasets such as OTB2013, OTB50, OTB100, Temple-Colour, UAV123 and VOT2018. The experimental results demonstrate the superiority of the proposed method over the state-of-the-art approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking

Feng

et al. 2019

IEEE Trans. on Image Process.

360

187

View full text Add to dashboard Cite

show abstract

“…Recent semisupervised methods [12], [30], [31], [32], [33] often assume that the object mask is known in the first frame, followed by a tracking method to segment it in the subsequent frames. In order to alleviate the drift problem [34] in tracking stage, Fan et al [10] annotated the object mask in a few frames, and adopted a local mask transfer method to propagate the source annotation to terminal images in both forward and backward directions. Recently, many deep learning based approaches [6], [12], [35], [33], [32], [36] have been developed for semisupervised VOS, making significant progress.…”

Section: Related Work a Semi-supervised Vosmentioning

confidence: 99%

Unsupervised Online Video Object Segmentation With Motion Property Understanding

Zhuo

Cheng

Zhang

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Unsupervised video object segmentation aims to automatically segment moving objects over an unconstrained video without any user annotation. So far, only few unsupervised online methods have been reported in literature and their performance is still far from satisfactory, because the complementary information from future frames cannot be processed under online setting. To solve this challenging problem, in this paper, we propose a novel Unsupervised Online Video Object Segmentation (UOVOS) framework by construing the motion property to mean moving in concurrence with a generic object for segmented regions. By incorporating salient motion detection and object proposal, a pixel-wise fusion strategy is developed to effectively remove detection noise such as dynamic background and stationary objects. Furthermore, by leveraging the obtained segmentation from immediately preceding frames, a forward propagation algorithm is employed to deal with unreliable motion detection and object proposals. Experimental results on several benchmark datasets demonstrate the efficacy of the proposed method. Compared to the state-of-the-art unsupervised online segmentation algorithms, the proposed method achieves an absolute gain of 6.2%. Moreover, our method achieves better performance than the best unsupervised offline algorithm on the DAVIS-2016 benchmark dataset. Our code is available on the project website: https://github.com/visiontao/uovos.

show abstract

“…However, it is complex and has a low tracking rate. Liu et al [25] proposed a novel template-matching tracking algorithm. The algorithm obtains the most accurate results from previous tracking results by using k-nearest neighbors, but it simply uses a simple machine learning algorithm to classify samples, resulting in poor performance and low accuracy.…”

Section: Related Workmentioning

confidence: 99%

A Novel Changing Athlete Body Real-Time Visual Tracking Algorithm Based on Distractor-Aware SiamRPN and HOG-SVM

et al. 2020

View full text Add to dashboard Cite

Athlete detection in sports videos is a challenging task due to the dynamic and cluttered background. Distractor-aware SiamRPN (DaSiamRPN) has a simple network structure and can be utilized to perform long-term tracking of large data sets. However, similarly to the Siamese network, the tracking results heavily rely on the given position in the initial frame. Hence, there is a lack of solutions for some complex tracking scenarios, such as running and changing of bodies of athletes, especially in the stage from squatting to standing to running. The Haar feature-based cascade classifier is involved to catch the key frame, representing the video frame of the most dramatic changes of the athletes. DaSiamRPN is implemented as the tracking method. In each frame after the key frame, a detection window is given based on the bounding box generated by the DaSiamRPN tracker. In the new detection window, a fusion method (HOG-SVM) combining features of Histograms of Oriented Gradients (HOG) and a linear Support-Vector Machine (SVM) is proposed for detecting the athlete, and the tracking results are updated in real-time by fusing the tracking results of DaSiamRPN and HOG-SVM. Our proposed method has reached a stable and accurate tracking effect in testing on men’s 100 m video sequences and has realized real-time operation.

show abstract

Robust Visual Tracking Revisited: From Correlation Filter to Template Matching

Cited by 65 publications

References 47 publications

Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking

Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking

Unsupervised Online Video Object Segmentation With Motion Property Understanding

A Novel Changing Athlete Body Real-Time Visual Tracking Algorithm Based on Distractor-Aware SiamRPN and HOG-SVM

Contact Info

Product

Resources

About