Multiple Kernels Based Object Tracking Using Histograms of Oriented Gradients

Jia, Hui-Xing; Zhang, Yujin

doi:10.3724/sp.j.1004.2009.01283

Cited by 9 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, MSTA cannot deal with the sheltering problem since it use the overall information. Document [6] introduces a multi-core tracking algorithm based on MSTA. And its general idea is to segment target first, as shown in Fig.…”

Section: Mean Shift Tracing Algorithm Combined With Lbpmentioning

confidence: 99%

Object Update-Based Mean Shift Tracing Algorithm Combined with LBP

Liu

Sun

Wang

2014

AMM

View full text Add to dashboard Cite

This paper proposed a novel solution to track human face obscured largely in an image on the basis of Mean Shift Tracing Algorithm (MSTA). The improved approach aims to update the target model in real-time during the whole tracking process to avoid target losing. Local Binary Pattern (LBP) theory is chosen to improve the original MSTA here. The experimental result shows that our new solution has a better performance in target tracking under situations like face rotation and occlusion as well as in fast acquisition when faces reappear on the screen.

show abstract

Section: Mean Shift Tracing Algorithm Combined With Lbpmentioning

confidence: 99%

Object Update-Based Mean Shift Tracing Algorithm Combined with LBP

Liu

Sun

Wang

2014

AMM

View full text Add to dashboard Cite

show abstract

“…Additionally, as motivated by works [8][10] [22], Differ from structure preserved methods [8] [22] and fusion of multiple cues [10], we provide a solution for spatial information preserved metric, which uses multi-patches weighted texture histogram to describe similarity between the target and candidate. In order to keep the spatial pattern of the target, we decompose the target region into 4 small patches and use the distribution of each patches' location and texture histogram with weight coefficient to represent the target's spatial pattern and texture feature.…”

Section: Spatial Pattern Preserved Similarity Metricmentioning

confidence: 99%

“…He proposed a cluster based Gaussian distribution color model. Jia [8] introduced the histogram of gradient (HOG) feature into kernel based tracking method, which is robust to illumination and small deformation. But it is weak in characterizing the spatial structural information of tracked objects, and the single-cue is often affected by the background distraction.…”

Section: Introductionmentioning

confidence: 99%

Robust mean-shift tracker with local saliency feature and spatial pattern preserved metric

Liu

Zheng

Qiao

et al. 2013

Proceedings 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC)

View full text Add to dashboard Cite

Robust object tracking in crowded and cluttered dynamic scenes is a very difficult task in robotic vision due to complex and changeable environment and similar features between the background and foreground. In this paper, we present an improved mean-shift tracker which uses discriminative local saliency feature and a new spatial pattern preserved similarity metric method to overcome above difficulties in mean-shift based tracking approaches. The local saliency feature, which is composed of contrast color, texture and gradient around the target, is proposed to find the most distinguished features between the target and background, and it could enhance the tracking performance greatly in the cluttered and complex environment. Another important benefit of this feature is that the saliency map form could be easily embedded into the meanshift framework. The new similarity metric try to preserve the spatial pattern to reduce the similarity errors caused by different spatial structure. It is beneficial to the mean-shift tracker to face the targets and scenes which has identical texture and color feature and with different spatial patterns. Finally, the efficiency of the proposed improved mean-shift tracker is validated through the plenty experimental results and analysis.

show abstract

“…Additionally, various multi-part models have been proposed to enforce a particular spatial structure on the object. Maggio et al [14] propose a multi-part target representation based on the computation of seven semi-overlapping color histograms; Calfield et al [15] combine the background exclusion constraint with multi-part appearance models; Jia and Zhang [16] propose a multiple kernel based object tracking method which divides the object into blocks and extracts kernel weighted histograms of oriented gradients for each block. Yan et al [17] proposed a novel multiple subtemplates based tracking algorithm, where each subtemplate corresponding to a separate tracker.…”

Section: Introductionmentioning

confidence: 99%

Robust Spatial-Color Feature with New Similarity Measure and Adaptive Template Update for Mean-Shift Tracking

Shen

Dong

Lü

et al. 2013

AMM

View full text Add to dashboard Cite

In this paper, we analyze the object tracking task of mean-shift algorithm. A spatial-color and similarity based mean-shift tracking algorithm is proposed. The spatial-color feature is used to replace the color histogram, and an enhanced algorithm is derived by adopting a new similarity measure. We also introduce Lucas-Kanade algorithm to design a template update strategy, propose a template update algorithm for mean-shift. Experimental results show that these two improved mean-shift tracking algorithms have high tracking accuracy and good robustness to the change of appearance of the object.

show abstract

Multiple Kernels Based Object Tracking Using Histograms of Oriented Gradients

Cited by 9 publications

References 5 publications

Object Update-Based Mean Shift Tracing Algorithm Combined with LBP

Object Update-Based Mean Shift Tracing Algorithm Combined with LBP

Robust mean-shift tracker with local saliency feature and spatial pattern preserved metric

Robust Spatial-Color Feature with New Similarity Measure and Adaptive Template Update for Mean-Shift Tracking

Contact Info

Product

Resources

About