An efficient pattern-less background modeling based on scale invariant local states

Yuk, Jacky S-C.; Wong, Kwan-Yee K.

doi:10.1109/avss.2011.6027338

Cited by 6 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In both cases or the cases in between, the foreground regions became more distinguishable from the background, and this improves the foreground/background segmentation results. Figure 5 shows the foreground/background segmentation results, and table 2 lists the F -Score [13] of the results. The F -Score is defined as 2T P 2T P +F P +F N , where T P , F P and F N are true positive, false positive and false negative, respectively.…”

Section: Resultsmentioning

confidence: 99%

“…Any of these cases enhances the foreground to be more distinctive from the background, and therefore, improves the foreground/background segmentation results. In this paper, a texture-based PLPM background modeling [13] was used for illustration. The main reason to choose PLPM is that texture-based background modeling is usually more tolerant to outdoor scenes, and PLPM can perform the foreground/background segmentation in a very efficient manner.…”

Section: Foreground/background Segmentationmentioning

confidence: 99%

“…where G(x, σ s ) is the same spatial Guassisn function in (13). δ(x) is a delta function, δ(x) = 1 when pixel x is on foreground region, and ε = 0.01 for regularization.…”

Section: Foreground Transmission Refinementmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Background Defogging with Foreground Decremental Preconditioned Conjugate Gradient

Yuk

Wong

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

The quality of outdoor surveillance videos are always degraded by bad weathers, such as fog, haze, and snowing. The degraded videos not only provide poor visualizations, but also increase the difficulty of vision-based analysis such as foreground/background segmentation. However, haze/fog removal has never been an easy task, and is often very time consuming. Most of the existing methods only consider a single image, and no temporal information of a video is used. In this paper, a novel adaptive background defogging method is presented. It is observed that most of the background regions between two consecutive video frames do not vary too much. Based on this observation, each video frame is firstly defogged by a background transmission map which is generated adaptively by the proposed foreground decremental preconditioned conjugate gradient (FDPCG). It is shown that foreground/background segmentation can be improved dramatically with such background-defogged video frames. With the help of a foreground map, the defogging of foreground regions is then completed by 1) foreground transmission estimation by fusion, and 2) transmission refinement by the proposed foreground incremental preconditioned conjugate gradient (FIPCG). Experimental results show that the proposed method can effectively improve the visualization quality of surveillance videos under heavy fog and snowing weather. Comparing with the state-of-the-art image defogging methods, the proposed method is much more efficient.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Foreground/background Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Background Defogging with Foreground Decremental Preconditioned Conjugate Gradient

Yuk

Wong

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

show abstract

“…We believe SILTP represents the state of the art in background modeling and hence compare our re- sults to this method. Scale-invariant local states [11] is a slight variation in the representation of the SILTP feature. For comparison, we use SILTP results from Liao et al because in Yuk and Wong [11], human judgement 2 was used to vary a size threshold parameter for each video.…”

Section: Resultsmentioning

confidence: 99%

“…Scale-invariant local states [11] is a slight variation in the representation of the SILTP feature. For comparison, we use SILTP results from Liao et al because in Yuk and Wong [11], human judgement 2 was used to vary a size threshold parameter for each video. We believe results from the latter fall under a different category of human-assisted backgrounding and hence do not compare to our method where no video-specific hand-tuning of parameters was done.…”

Section: Resultsmentioning

confidence: 99%

Background modeling using adaptive pixelwise kernel variances in a hybrid feature space

Narayana

Hanson

Learned-Miller

2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Recent work on background subtraction has shown developments on two major fronts. In one, there has been increasing sophistication of probabilistic models, from mixtures of Gaussians at each pixel [7], to kernel density estimates at each pixel [1], and more recently to joint domainrange density estimates that incorporate spatial information [6]. Another line of work has shown the benefits of increasingly complex feature representations, including the use of texture information, local binary patterns, and recently scale-invariant local ternary patterns [4]. In this work, we use joint domain-range based estimates for background and foreground scores and show that dynamically choosing kernel variances in our kernel estimates at each individual pixel can significantly improve results. We give a heuristic method for selectively applying the adaptive kernel calculations which is nearly as accurate as the full procedure but runs much faster. We combine these modeling improvements with recently developed complex features [4] and show significant improvements on a standard backgrounding benchmark.

show abstract

A New Approach for the Extraction of Moving Objects

Farou

Séridi

Akdag

2013

Modeling Approaches and Algorithms for Advanced Computer Applications

View full text Add to dashboard Cite

An efficient pattern-less background modeling based on scale invariant local states

Cited by 6 publications

References 11 publications

Adaptive Background Defogging with Foreground Decremental Preconditioned Conjugate Gradient

Adaptive Background Defogging with Foreground Decremental Preconditioned Conjugate Gradient

Background modeling using adaptive pixelwise kernel variances in a hybrid feature space

A New Approach for the Extraction of Moving Objects

Contact Info

Product

Resources

About