Visual object tracking using spatial Context Information and Global tracking skills

Li, Shuxiao; Wu, Ou; Zhu, Chengfei; Chang, Hongxing

doi:10.1016/j.cviu.2013.10.001

Cited by 13 publications

(14 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been proven in [ 6 ] that

is bounded by [0, s ]. Thus, we can limit the value range of

by dividing s to get the CR features map, which can be described as

.…”

Section: The Proposed Methodsmentioning

confidence: 99%

“…However, traditional DCF trackers such as [ 2 ] are affected by boundary effects, while other improved DCF trackers [ 3 , 4 ] suffer from a large amount of calculations or unsatisfied model updating strategy, which cannot meet the requirements of target tracking when the computing resources are strictly restricted. In order to achieve balance between performance and efficiency of the tracker, we borrow the idea of mean shift tracking algorithms [ 5 , 6 ] to build a new color ratio feature (CR), and propose a DCF-based tracker embedded with CR features, namely CRCF tracker [ 7 ], which can achieve robust performance with real-time speed. Although our previous works have made great progress, nevertheless, a simple moving average update scheme of CRCF tracker cannot deal with the problem of occlusion and large appearance variation, and usually leads to model contamination and tracking drift.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient and Practical Correlation Filter Tracking

Zhu

Jiang

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Visual tracking is a basic task in many applications. However, the heavy computation and low speed of many recent trackers limit their applications in some computing power restricted scenarios. On the other hand, the simple update scheme of most correlation filter-based trackers restricts their robustness during target deformation and occlusion. In this paper, we explore the update scheme of correlation filter-based trackers and propose an efficient and adaptive training sample update scheme. The training sample extracted in each frame is updated to the training set according to its distance between existing samples measured with a difference hashing algorithm or discarded according to tracking result reliability. In addition, we expand our new tracker to long-term tracking. On the basis of the proposed model updating mechanism, we propose a new tracking state discrimination mechanism to accurately judge tracking failure, and resume tracking after the target is recovered. Experiments on OTB-2015, Temple Color 128 and UAV123 (including UAV20L) demonstrate that our tracker performs favorably against state-of-the-art trackers with light computation and runs over 100 fps on desktop computer with Intel i7-8700 CPU(3.2 GHz).

show abstract

“…It has been proven in [ 6 ] that

is bounded by [0, s ]. Thus, we can limit the value range of

by dividing s to get the CR features map, which can be described as

.…”

Section: The Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient and Practical Correlation Filter Tracking

Zhu

Jiang

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The work in [28] addresses this drawback by employing a pyramidal decomposition to capture distant targets between consecutive frames. An extension of the main algorithm is proposed in [29], which may handle cases where the color of the target is similar with the color of the background and the displacements are large. The disambiguation between target and background is achieved by a model incorporating information about the spatial context of the target and large displacements are handled by increasing the candidate scales.…”

Section: Mean Shift Trackingmentioning

confidence: 99%

“…where r i = number of correctly tracked pixels in frame i number of target pixels in frame i , (29) and the average F-measure:…”

mentioning

confidence: 99%

Visual tracking using spatially weighted likelihood of Gaussian mixtures

Karavasilis

Nikou

Likas

2015

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…Recently, Li et al combines spatial context inforamtion to meanshift [59]. This algorithm is robustness when target moves fast.…”

Section: Alg2 Finishedmentioning

confidence: 99%

A review of visual moving target tracking

Zheng

Liu

2016

Multimed Tools Appl

106

View full text Add to dashboard Cite

Recently, computer vision and multimedia understanding become important research domains in computer science. Meanwhile, visual tracking of moving target, one of most important application in computer vision, becomes a highlight today. So, this paper reviews research and technology in this domain. First, background and application of visual tracking is introduced. Then, visual tracking methods are classified by different thinking and technologies. Their positiveness, negativeness and improvement are analyzed deeply. Finally, difficulty in this domain is summarized and future prospect of related fields is presented.

show abstract

Visual object tracking using spatial Context Information and Global tracking skills

Cited by 13 publications

References 33 publications

Efficient and Practical Correlation Filter Tracking

Efficient and Practical Correlation Filter Tracking

Visual tracking using spatially weighted likelihood of Gaussian mixtures

A review of visual moving target tracking

Contact Info

Product

Resources

About