Curvelet transform-based technique for tracking of moving objects

Nigam, Swati; Khare, Ashish

doi:10.1049/iet-cvi.2011.0023

Cited by 20 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They trained linear classifier online based on sparse representation. Nigam et al fused both gradient and color features based on particle filter, and presented their tracking method [22]. There were also many research based on sparse representation, which was an effective mid-level feature.…”

Section: Related Workmentioning

confidence: 99%

Distributed dynamic target tracking method by block diagonalization of topological matrix

Zhou

2015

J Supercomput

View full text Add to dashboard Cite

Today, movement recognition becomes a highlight in visual analysis. One problem in movement recognition is that existing characteristics of moving objects cannot be applied to recognize moving targets with similar color components and different color structures, which can be easily recognized by human vision. So, in this paper, a novel target tracking method is presented by both color topology and movement features. First, color topology of moving targets is extracted based on analysis of visual mechanism in human vision. In this way, the topology is processed as block diagonal matrix and divided to sub-topological matrices. Then, moving targets are recognized by both similarity of color topological matrices and movement features. Finally, a distributed dynamic tracking method is presented by the division of moving targets because of the huge computation of movement recognition and topological similarity. Experimental results show the high accuracy and real-time of the proposed method.

show abstract

Section: Related Workmentioning

confidence: 99%

Distributed dynamic target tracking method by block diagonalization of topological matrix

Zhou

2015

J Supercomput

View full text Add to dashboard Cite

show abstract

“…Then the occlusion parameter is presented as follows [19] O p = Q l=1 H l (15) where Q represents the maximum level of greyscale, and Q = 4096 in experiments for analysing each level of greyscale finely. According to (14) and (15), when the half occlusion occurs, the O p is about 0.5. When if the three quarters of an object are occluded, we consider the occlusion occurs.…”

Section: First Stepmentioning

confidence: 99%

Tracking with scattering descriptor

Tian

Jiao

Shang

2014

IET Computer Vision

View full text Add to dashboard Cite

This study proposes a new method to track the moving object based on undecimated scattering transform (UST). The UST removes the down-sampling operation from the traditional scattering transform to produce a complete representation. Based on the UST, the structural information of object can be captured, which is a highly discriminative representation and facilitates the tracker to distinguish the object from background. The update parameter of tracking model is adaptively adjusted by the correlation coefficient. Occlusion identification is achieved by using a new cascaded model, which can correctly find occlusion and avoid the drift. Experimental results demonstrate that the proposed method is able to track the object accurately and reliably in realistic videos where the appearance and motion change drastically over time.

show abstract

“…Motion segmentation is a basic step for many computer vision applications and it is specially very useful in robotics, video surveillance, video indexing, traffic monitoring and the many other applications. [1][2][3] Image segmentation has been researched for more than four decades 4 but robust segmentation techniques which can address the challenges of motion segmentation are still needed. Several problems arise while segmenting the video sequences because of changing background, clutter, occlusion, varying lighting conditions, automatic operation, and real time processing requirements, etc.…”

Section: Introductionmentioning

confidence: 99%

Adaptive real-time motion segmentation technique based on statistical background model

Kushwaha

Sharma²,

Khare

et al. 2014

The Imaging Science Journal

Self Cite

View full text Add to dashboard Cite

Motion segmentation is a crucial step for video analysis and has many applications. This paper proposes a method for motion segmentation, which is based on construction of statistical background model. Variance and Covariance of pixels are computed to construct the model for scene background. We perform average frame differencing with this model to extract the objects of interest from the video frames. Morphological operations are used to smooth the object segmentation results. The proposed technique is adaptive to the dynamically changing background because of change in the lighting conditions and in scene background. The method has the capability to relearn the background to adapt these variations. The immediate advantage of the proposed method is its high processing speed of 30 frames per second on large sized (high resolution) videos. We compared the proposed method with other five popular methods of object segmentation in order to prove the effectiveness of the proposed technique. Experimental results demonstrate the novelty of the proposed method in terms of various performance parameters. The method can segment the video stream in real-time, when background changes, lighting conditions vary, and even in the presence of clutter and occlusion

show abstract

Curvelet transform-based technique for tracking of moving objects

Cited by 20 publications

References 32 publications

Distributed dynamic target tracking method by block diagonalization of topological matrix

Distributed dynamic target tracking method by block diagonalization of topological matrix

Tracking with scattering descriptor

Adaptive real-time motion segmentation technique based on statistical background model

Contact Info

Product

Resources

About