scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Tensor Voting Based Foreground Object Extraction

TL;DR: A novel foreground extraction technique for static cameras which works for indoor as well as outdoor scenes is proposed and is robust to background motion, noise, illumination fluctuations, scene and lighting changes.
Abstract: Robust foreground extraction is necessary for good performance of any computer vision application such as tracking or video surveillance. In this paper, we propose a novel foreground extraction technique for static cameras which works for indoor as well as outdoor scenes. We model colors in a background frame by Gaussians using non-iterative tensor voting framework. For input frame, we compare color features of each pixel against background model and those that do not follow the model are classified as foreground pixels. We update background model to account for scene and lighting changes over time. In the case of significant background motion, we incorporate motion vectors within tensor voting framework to reduce misclassification. Experiments show that our approach is robust to background motion, noise, illumination fluctuations, scene and lighting changes.
Citations
More filters
Journal ArticleDOI
TL;DR: This work reviews and explains a number of high impact theoretical modifications in a self-contained manner and including possible future directions of work on the theoretical aspects of tensor voting.
Abstract: Tensor voting is a computational framework that addresses the problem of perceptual organisation. It was designed to convey human perception principles into a unified framework that can be adapted to extract visually salient elements from possibly noisy or corrupted images. The original formulation featured some concerns that made it difficult or impractical to be applied directly. Therefore, several partial or total theoretical reformulations or augmentations have been proposed. These almost parallel publication were presented in different directions, with different priorities and even in a different notation. Thus, the authors observed the need for a coherent description and comparison of the different proposals. This work, after describing the original approach of tensor voting, reviews and explains a number of high impact theoretical modifications in a self-contained manner and including possible future directions of work. The authors have selected and organised a number of formulations and unified the way the problem is addressed across the different proposals. The aim of this study is to contribute with a modern comprehensive source of information on the theoretical aspects of tensor voting.

9 citations

Journal ArticleDOI
TL;DR: In the experiment for extracting pavement cracks, the original pavement image is processed by the proposed method which is combined with the significant curve feature threshold procedure, and the result displays the faint crack signals submerged in the complicated background efficiently and clearly.
Abstract: An adaptive tensor voting algorithm combined with texture spectrum is proposed. The image texture spectrum is used to get the adaptive scale parameter of voting field. Then the texture information modifies both the attenuation coefficient and the attenuation field so that we can use this algorithm to create more significant and correct structures in the original image according to the human visual perception. At the same time, the proposed method can improve the edge extraction quality, which includes decreasing the flocculent region efficiently and making image clear. In the experiment for extracting pavement cracks, the original pavement image is processed by the proposed method which is combined with the significant curve feature threshold procedure, and the resulted image displays the faint crack signals submerged in the complicated background efficiently and clearly.
References
More filters
Proceedings ArticleDOI
23 Jun 1999
TL;DR: This paper discusses modeling each pixel as a mixture of Gaussians and using an on-line approximation to update the model, resulting in a stable, real-time outdoor tracker which reliably deals with lighting changes, repetitive motions from clutter, and long-term scene changes.
Abstract: A common method for real-time segmentation of moving regions in image sequences involves "background subtraction", or thresholding the error between an estimate of the image without moving objects and the current image. The numerous approaches to this problem differ in the type of background model used and the procedure used to update the model. This paper discusses modeling each pixel as a mixture of Gaussians and using an on-line approximation to update the model. The Gaussian, distributions of the adaptive mixture model are then evaluated to determine which are most likely to result from a background process. Each pixel is classified based on whether the Gaussian distribution which represents it most effectively is considered part of the background model. This results in a stable, real-time outdoor tracker which reliably deals with lighting changes, repetitive motions from clutter, and long-term scene changes. This system has been run almost continuously for 16 months, 24 hours a day, through rain and snow.

7,660 citations


"Tensor Voting Based Foreground Obje..." refers methods in this paper

  • ...Our approach is accurate and robust to background motion, noise, illumination fluctuations, scene and lighting changes....

    [...]

Proceedings ArticleDOI
23 Aug 2004
TL;DR: An efficient adaptive algorithm using Gaussian mixture probability density is developed using Recursive equations to constantly update the parameters and but also to simultaneously select the appropriate number of components for each pixel.
Abstract: Background subtraction is a common computer vision task. We analyze the usual pixel-level approach. We develop an efficient adaptive algorithm using Gaussian mixture probability density. Recursive equations are used to constantly update the parameters and but also to simultaneously select the appropriate number of components for each pixel.

2,045 citations


"Tensor Voting Based Foreground Obje..." refers methods in this paper

  • ...Our approach is accurate and robust to background motion, noise, illumination fluctuations, scene and lighting changes....

    [...]

Journal ArticleDOI
TL;DR: This work addresses the problem of obtaining dense surface information from a sparse set of 3D data in the presence of spurious noise samples, and proposes to impose additional perceptual constraints such as good continuity and "cosurfacity" to not only infer surfaces, but also to detect surface orientation discontinuities, as well as junctions, all at the same time.
Abstract: We address the problem of obtaining dense surface information from a sparse set of 3D data in the presence of spurious noise samples. The input can be in the form of points, or points with an associated tangent or normal, allowing both position and direction to be corrupted by noise. Most approaches treat the problem as an interpolation problem, which is solved by fitting a surface such as a membrane or thin plate to minimize some function. We argue that these physical constraints are not sufficient, and propose to impose additional perceptual constraints such as good continuity and "cosurfacity". These constraints allow us to not only infer surfaces, but also to detect surface orientation discontinuities, as well as junctions, all at the same time. The approach imposes no restriction on genus, number of discontinuities, number of objects, and is noniterative. The result is in the form of three dense saliency maps for surfaces, intersections between surfaces (i.e., 3D curves), and 3D junctions, respectively. These saliency maps are then used to guide a "marching" process to generate a description (e.g., a triangulated mesh) making information about surfaces, space curves, and 3D junctions explicit. The traditional marching process needs to be refined as the polarity of the surface orientation is not necessarily locally consistent. These three maps are currently not integrated, and this is the topic of our ongoing research. We present results on a variety of computer-generated and real data, having varying curvature, of different genus, and multiple objects.

187 citations


"Tensor Voting Based Foreground Obje..." refers background in this paper

  • ...We do not assume any other training data except a single background (only) frame....

    [...]

Proceedings ArticleDOI
10 Oct 2005
TL;DR: This paper introduces a novel approach to detect moving objects in a noisy background that combines a modified adaptive Gaussian mixture model for background subtraction and optical flow methods supported by temporal differencing in order to achieve robust and accurate extraction of the shapes of moving objects.
Abstract: Segmentation of moving objects in image sequences is a fundamental step in many computer vision applications such as mineral processing industry and automated visual surveillance. In this paper, we introduce a novel approach to detect moving objects in a noisy background. Our approach combines a modified adaptive Gaussian mixture model (GMM) for background subtraction and optical flow methods supported by temporal differencing in order to achieve robust and accurate extraction of the shapes of moving objects. The algorithm works well for image sequences having many moving objects with different sizes as demonstrated by experimental results on real image sequences.

113 citations

Proceedings ArticleDOI
15 Dec 2003
TL;DR: A robust and efficient background subtraction algorithm for a vision-based user interface that removes effectively interferences of lighting changes by exploiting pixel-wise statistical characteristics and threshold values in the well-known two color spaces.
Abstract: In this paper, we propose a robust and efficient background subtraction algorithm for a vision-based user interface. We separate a user of interest as precisely as possible from the acquired images in order to convey the user's intension properly into the system through the vision-based user interface. Although the background subtraction techniques have been adopted in many vision-based interfaces to extract or track moving objects of interest in the images, they still suffer from the changes of lighting, such as shadows and highlighting. The proposed method removes effectively such interferences of lighting changes by exploiting pixel-wise statistical characteristics and threshold values in the well-known two color spaces (RGB and normalized RGB). According to experimental results, the proposed algorithm can be applied to various applications requiring real-time segmentation from the image sequences on the fly.

37 citations


"Tensor Voting Based Foreground Obje..." refers methods in this paper

  • ...Our approach is accurate and robust to background motion, noise, illumination fluctuations, scene and lighting changes....

    [...]