Curvelet transform based moving object segmentation

Khare, Manish; Srivastava, Rajneesh; Khare, Ashish; Jeon, Moongu

doi:10.1109/icip.2013.6738840

Cited by 8 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wavelet Transform [147][162] [144], Curvelet Transform [260], Walsh Transform [495][497] [496], Hadamard Transform [29], Slant Transform [178] and Gabor Transform [560][562] [543]. Pratically, FTT processes blocks much faster in comparison with DCT.…”

Section: Features In a Transform Domainmentioning

confidence: 99%

“…-Wavelet Transform Features: First, Huang and Hsieh [205][207] proposed the use of Discrete Wavelet Transform (DWT) to obtain features that are used in a change detection based method for interframe-difference but DWT is not suitable for video applications as the use of DWT makes the method shift sensitive [260]. In an other work, Gao et al [147][148][149] [150] proposed a Marr wavelet kernel and a background subtraction technique based on Binary Discrete Wavelet Transforms (BDWT).…”

Section: Features From Frequency Domain Transformmentioning

confidence: 99%

“…-Curvelet Transform Features: Because the wavelet transform can not describe curve discontinuities and can present inaccurate segmentation of moving object due to non-removal of noise in consecutive frames, Khare et al [260] proposed to use curvelet transform. Thus, moving objects are detected with a change detection applied on curvelet coefficients of two consecutive frames.…”

Section: Features From Frequency Domain Transformmentioning

confidence: 99%

“…Thus, moving objects are detected with a change detection applied on curvelet coefficients of two consecutive frames. Experimental results [260] show that the change detection based on curvelet transform is more robust to noise than the change detection with Discrete Wavelet Transform (DWT) [205].…”

Section: Features From Frequency Domain Transformmentioning

confidence: 99%

See 3 more Smart Citations

On the Role and the Importance of Features for Background Modeling and Foreground Detection

Bouwmans¹,

Silva²,

Marghes³

et al. 2016

Preprint

View full text Add to dashboard Cite

Background modeling has emerged as a popular foreground detection technique for various applications in video surveillance. Background modeling methods have become increasing efficient in robustly modeling the background and hence detecting moving objects in any visual scene. Although several background subtraction and foreground detection have been proposed recently, no traditional algorithm today still seem to be able to simultaneously address all the key challenges of illumination variation, dynamic camera motion, cluttered background and occlusion. This limitation can be attributed to the lack of systematic investigation concerning the role and importance of features within background modeling and foreground detection. With the availability of a rather large set of invariant features, the challenge is in determining the best combination of features that would improve accuracy and robustness in T. Bouwmans Lab. MIA,

show abstract

Section: Features In a Transform Domainmentioning

confidence: 99%

Section: Features From Frequency Domain Transformmentioning

confidence: 99%

Section: Features From Frequency Domain Transformmentioning

confidence: 99%

Section: Features From Frequency Domain Transformmentioning

confidence: 99%

See 2 more Smart Citations

On the Role and the Importance of Features for Background Modeling and Foreground Detection

Bouwmans¹,

Silva²,

Marghes³

et al. 2016

Preprint

View full text Add to dashboard Cite

show abstract

“…[1,2]. Object tracking requires the segmentation [3][4][5] of object from scene followed by tracking. A good tracking algorithms should have following attributes [1]:…”

Section: Introductionmentioning

confidence: 99%

Contourlet transform based human object tracking

et al. 2015

Self Cite

View full text Add to dashboard Cite

Human object tracking is a challenging problem in video processing applications, and is an important step toward development of surveillance system. In this paper, we have proposed a new method for tracking of a human object in video sequence which is based on Contourlet transform. We have chosen Contourlet transform as it has high directionality and represents salient features of image such as edges, curves and contours in better way as compared with wavelet transform. The proposed method is simple and does not require any other parameter except Contourlet coefficients. Results after applying the proposed method for human object tracking is compared with other state-of-theart methods in terms of visual as well as quantitative performance measures viz. Euclidean distance and Mahalanobis distance. The proposed method is found to be better than other methods.

show abstract