Adaptive background mixture models for real-time tracking
23 Jun 1999-Vol. 2, pp 246-252
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.
Citations
More filters
TL;DR: In this paper, the authors prove that under some suitable assumptions, it is possible to recover both the low-rank and the sparse components exactly by solving a very convenient convex program called Principal Component Pursuit; among all feasible decompositions, simply minimize a weighted combination of the nuclear norm and of the e1 norm.
Abstract: This article is about a curious phenomenon. Suppose we have a data matrix, which is the superposition of a low-rank component and a sparse component. Can we recover each component individuallyq We prove that under some suitable assumptions, it is possible to recover both the low-rank and the sparse components exactly by solving a very convenient convex program called Principal Component Pursuit; among all feasible decompositions, simply minimize a weighted combination of the nuclear norm and of the e1 norm. This suggests the possibility of a principled approach to robust principal component analysis since our methodology and results assert that one can recover the principal components of a data matrix even though a positive fraction of its entries are arbitrarily corrupted. This extends to the situation where a fraction of the entries are missing as well. We discuss an algorithm for solving this optimization problem, and present applications in the area of video surveillance, where our methodology allows for the detection of objects in a cluttered background, and in the area of face recognition, where it offers a principled way of removing shadows and specularities in images of faces.
6,783 citations
TL;DR: This paper focuses on motion tracking and shows how one can use observed motion to learn patterns of activity in a site and create a hierarchical binary-tree classification of the representations within a sequence.
Abstract: Our goal is to develop a visual monitoring system that passively observes moving objects in a site and learns patterns of activity from those observations. For extended sites, the system will require multiple cameras. Thus, key elements of the system are motion tracking, camera coordination, activity classification, and event detection. In this paper, we focus on motion tracking and show how one can use observed motion to learn patterns of activity in a site. Motion segmentation is based on an adaptive background subtraction method that models each pixel as a mixture of Gaussians and uses an online approximation to update the model. The Gaussian distributions are then evaluated to determine which are most likely to result from a background process. This yields a stable, real-time outdoor tracker that reliably deals with lighting changes, repetitive motions from clutter, and long-term scene changes. While a tracking system is unaware of the identity of any object it tracks, the identity remains the same for the entire tracking sequence. Our system leverages this information by accumulating joint co-occurrences of the representations within a sequence. These joint co-occurrence statistics are then used to create a hierarchical binary-tree classification of the representations. This method is useful for classifying sequences, as well as individual instances of activities in a site.
3,631 citations
Cites background from "Adaptive background mixture models ..."
...…would involve attaching them to poles, trees, and buildings.1 For indoor settings, this would involve attaching to walls and furniture for indoor sites, such as the Intelligent Room.2 For this article, we explore the monitoring of an outdoor site by connecting a set of video cameras to an…...
[...]
TL;DR: W/sup 4/ employs a combination of shape analysis and tracking to locate people and their parts and to create models of people's appearance so that they can be tracked through interactions such as occlusions.
Abstract: W/sup 4/ is a real time visual surveillance system for detecting and tracking multiple people and monitoring their activities in an outdoor environment. It operates on monocular gray-scale video imagery, or on video imagery from an infrared camera. W/sup 4/ employs a combination of shape analysis and tracking to locate people and their parts (head, hands, feet, torso) and to create models of people's appearance so that they can be tracked through interactions such as occlusions. It can determine whether a foreground region contains multiple people and can segment the region into its constituent people and track them. W/sup 4/ can also determine whether people are carrying objects, and can segment objects from their silhouettes, and construct appearance models for them so they can be identified in subsequent frames. W/sup 4/ can recognize events between people and objects, such as depositing an object, exchanging bags, or removing an object. It runs at 25 Hz for 320/spl times/240 resolution images on a 400 MHz dual-Pentium II PC.
2,870 citations
Cites background from "Adaptive background mixture models ..."
...However, one could replace it with a more robust but slow detection algorithm such as in [14], [10]....
[...]
TL;DR: This survey reviews recent trends in video-based human capture and analysis, as well as discussing open problems for future research to achieve automatic visual analysis of human movement.
Abstract: This survey reviews advances in human motion capture and analysis from 2000 to 2006, following a previous survey of papers up to 2000 [T.B. Moeslund, E. Granum, A survey of computer vision-based human motion capture, Computer Vision and Image Understanding, 81(3) (2001) 231-268.]. Human motion capture continues to be an increasingly active research area in computer vision with over 350 publications over this period. A number of significant research advances are identified together with novel methodologies for automatic initialization, tracking, pose estimation, and movement recognition. Recent research has addressed reliable tracking and pose estimation in natural scenes. Progress has also been made towards automatic understanding of human actions and behavior. This survey reviews recent trends in video-based human capture and analysis, as well as discussing open problems for future research to achieve automatic visual analysis of human movement.
2,738 citations
26 Jun 2000
TL;DR: A novel non-parametric background model that can handle situations where the background of the scene is cluttered and not completely static but contains small motions such as tree branches and bushes is presented.
Abstract: Background subtraction is a method typically used to segment moving regions in image sequences taken from a static camera by comparing each new frame to a model of the scene background. We present a novel non-parametric background model and a background subtraction approach. The model can handle situations where the background of the scene is cluttered and not completely static but contains small motions such as tree branches and bushes. The model estimates the probability of observing pixel intensity values based on a sample of intensity values for each pixel. The model adapts quickly to changes in the scene which enables very sensitive detection of moving targets. We also show how the model can use color information to suppress detection of shadows. The implementation of the model runs in real-time for both gray level and color imagery. Evaluation shows that this approach achieves very sensitive detection with very low false alarm rates.
2,432 citations
Cites background or methods from "Adaptive background mixture models ..."
...A comparison between the proposed model and a Gaussian mixture model [6, 7 ] was also presented....
[...]
...In this section we describe a set of experiments performed to compare the detection performance of the proposed background model as described in section 2 and a mixture of Gaussian model as described in [6, 7 ]....
[...]
...In [6, 7 ] a generalization to the previous approach was presented....
[...]
References
More filters
49,597 citations
Journal Article•
4,506 citations
TL;DR: Pfinder is a real-time system for tracking people and interpreting their behavior that uses a multiclass statistical model of color and shape to obtain a 2D representation of head and hands in a wide range of viewing conditions.
Abstract: Pfinder is a real-time system for tracking people and interpreting their behavior. It runs at 10 Hz on a standard SGI Indy computer, and has performed reliably on thousands of people in many different physical locations. The system uses a multiclass statistical model of color and shape to obtain a 2D representation of head and hands in a wide range of viewing conditions. Pfinder has been successfully used in a wide range of applications including wireless interfaces, video databases, and low-bandwidth coding.
4,280 citations
Book•
[...]
TL;DR: Robot Vision as discussed by the authors is a broad overview of the field of computer vision, using a consistent notation based on a detailed understanding of the image formation process, which can provide a useful and current reference for professionals working in the fields of machine vision, image processing, and pattern recognition.
Abstract: From the Publisher:
This book presents a coherent approach to the fast-moving field of computer vision, using a consistent notation based on a detailed understanding of the image formation process. It covers even the most recent research and will provide a useful and current reference for professionals working in the fields of machine vision, image processing, and pattern recognition.
An outgrowth of the author's course at MIT, Robot Vision presents a solid framework for understanding existing work and planning future research. Its coverage includes a great deal of material that is important to engineers applying machine vision methods in the real world. The chapters on binary image processing, for example, help explain and suggest how to improve the many commercial devices now available. And the material on photometric stereo and the extended Gaussian image points the way to what may be the next thrust in commercialization of the results in this area.
Chapters in the first part of the book emphasize the development of simple symbolic descriptions from images, while the remaining chapters deal with methods that exploit these descriptions. The final chapter offers a detailed description of how to integrate a vision system into an overall robotics system, in this case one designed to pick parts out of a bin.
The many exercises complement and extend the material in the text, and an extensive bibliography will serve as a useful guide to current research.
Errata (164k PDF)
3,783 citations
Proceedings Article•
[...]
TL;DR: A scheme is developed for classifying the types of motion perceived by a humanlike robot and equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented.
Abstract: A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >
2,000 citations
"Adaptive background mixture models ..." refers methods in this paper
...These labeled foreground pixels can then be segmented into regions by a two-pass, connected components algorithm [3]....
[...]