Background subtraction based on phase and distance transform under sudden illumination change

Conference PaperinProceedings / ICIP ... International Conference on Image Processing · October 2010with6 Reads
DOI: 10.1109/ICIP.2010.5650111 · Source: IEEE Xplore
Conference: Image Processing (ICIP), 2010 17th IEEE International Conference on
  • 8.98 · Shanghai Jiao Tong University
  • 27.63 · Shanghai Jiao Tong University
  • 26.88 · Shanghai Jiao Tong University
Abstract
Effective foreground detection under sudden illumination change is an active research topic. However, most existing background subtraction approaches, which are intensity based, fail to handle this situation. In this paper, we propose a novel background modeling method that overcomes this limitation by relying on statistical models which use pixel phase instead of intensities. We first extract the phase feature of the pixel using Gabor filters. Then, a phase based background subtraction approach is proposed. In this approach, each phase feature is modeled independently by a mixture of Gaussian models and updated with a novel scheme. Since foreground pixels are scattered in the preliminary detection result, distance transform is implemented on the binary image which transforms the image into a distance map. We segment the distance image with a threshold and get the final result. Experiments on two challenging sequences demonstrate the effectiveness and robustness of our method.
    • "We turned the light off at frame t 0 + 2 and succeed to locate the foreground object although two opposite intensity variation occurred (turning down the light in the room and up in the corridor). [6, 7] but either suppose that the change is global or do not work in environments when videos are projected in the background . As a result, we propose to tackle this problem with stereo imaging. "
    [Show abstract] [Hide abstract] ABSTRACT: Vision-based background subtraction algorithms model the intensity variation across time to classify a pixel as foreground. Unfortunately, such algorithms are sensitive to appearance changes of the background such as sudden changes of illumination or when videos are projected in the background. In this work, we propose an algorithm to extract foreground silhouettes without modeling the intensity variation across time. Using a camera pair, the stereo mismatch is processed to produce a dense disparity based on a Total Variation (TV) framework. Experimental results show that with sudden changes of background appearance, our proposed TV disparity-based extraction outperforms intensity-based algorithms and existing stereo-based approaches based on temporal depth variation and stereo mismatch.
    Full-text · Conference Paper · Sep 2012
    • "The limitation of this approach is then it can only handle illumination changes that can be represented as a linear combination of the training images. An alternative approach is to build the background model using illumination invariant features including simple intensity normalization [4], normalized color space [6] and noncolor features such as edges [8], texture [15, 20], phase [21], contours [9], etc. Simple normalization cannot handle local changes while normalized color space typically diminishes the dynamic range and can handle only small changes in illumination like shadows. Fusing color and non-color features is a challenging problem in its own right due to the availability and variability of these features over different surfaces. "
    [Show abstract] [Hide abstract] ABSTRACT: Background subtraction is important for many vision applications. Existing techniques can adapt to gradual changes in illumination but fail to cope with sudden changes often seen in indoor environment. In this paper, we propose a novel background subtraction technique that models the change of illumination as a regression function of spatial image coordinates. Such spatial dependency is significant when light sources are close to or within the scene. The regression function is learned from highly probable background regions and applied to the rest of the background models to compensate for the illumination change. While a single regression function is adequate for a smooth Lambertian surface, multiple regression functions are needed to handle depth discontinuities, shadows, and non-Lambertian surfaces. The change of illumination is first segmented and different regression functions are applied to different segments. Experimental results comparing our techniques with other schemes show better foreground segmentation during illumination change.
    Full-text · Conference Paper · Nov 2011 · Recent Patents on Computer Science
  • [Show abstract] [Hide abstract] ABSTRACT: Background modeling is currently used to detect moving objects in video acquired from static cameras. Numerous statistical methods have been developed over the recent years. The aim of this paper is firstly to provide an extended and updated survey of the recent researches and patents which concern statistical background modeling and secondly to achieve a comparative evaluation. For this, we firstly classified the statistical methods in term of category. Then, the original methods are reminded and discussed following the challenges met in video sequences. We classified their respective improvements in term of strategies used. Furthermore, we discussed them in term of the critical situations they claim to handle. Finally, we conclude with several promising directions for future research. The survey also discussed relevant patents.
    Full-text · Article · Sep 2011
Show more

  • undefined · undefined
  • undefined · undefined
  • undefined · undefined