Image Segmentation in Video Sequences

1999

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.

2008 15th IEEE International Conference on Image Processing, 2008

In this paper it is presented a robust segmentation process for detecting incidents on highways. This segmentation process is based on background subtraction and uses an efficient background model initialization and update to work 24/7. A crosscorrelation based shadow detection is also used for minimizing ghosts. It is also proposed a stopped vehicle detection system based on the pixel history cache. This methodology has proved to be quite robust in terms of different weather conditions, lighting and image quality. Some experiments carried out on some highway scenarios demonstrate the robustness of the proposed solution.

2010

In this paper, we conduct an investigation into background subtraction techniques using Gaussian Mixture Models (GMM) in the presence of large illumination changes and background variations. We show that the techniques used to date suffer from the trade-off imposed by the use of a common learning rate to update both the mean and variance of the component densities, which leads to a degeneracy of the variance and creates "saturated pixels". To address this problem, we propose a simple yet effective technique that differentiates between the two learning rates, and imposes a constraint on the variance so as to avoid the degeneracy problem. Experimental results are presented which show that, compared to existing techniques, the proposed algorithm provides more robust segmentation in the presence of illumination variations and abrupt changes in background distribution.

…, 2009

Real-time segmentation of moving regions in image sequences is a fundamental step in many vision systems including automated visual surveillance and human-machine interface. In this paper we present a framework for detecting some important but unknown knowledge like vehicle identification and traffic flow count. The objective is to monitor activities at traffic intersections for detecting congestions, and then predict the traffic flow which assists in regulating traffic. The present algorithm for vision-based detection and counting of vehicles in monocular image sequences for traffic scenes are recorded by a stationary camera. The method is based on the establishment of correspondences between regions and vehicles, as the vehicles move through the image sequence. Background subtraction is used which improves the adaptive background mixture model and makes the system learn faster and more accurately, as well as adapt effectively to changing environments. The resulting system robustly identifies vehicles at intersection, rejecting background and tracks vehicles over a specific period of time. Real-life traffic video sequences are used to illustrate the effectiveness of the proposed algorithm.

Turkish Journal of Electrical Engineering and Computer Science, 2011

The paper presents a vehicle counting method based on invariant moments and shadow aware foreground masks. Estimation of the background and the segmentation of foreground regions can be done using either the Mixture of Gaussians model (MoG) or an improved version of the Group Based Histogram (GBH) technique. The work demonstrates that, even though the improved GBH method delivers performance just as good as MoG, considering computational efficiency, MoG is more suitable. Shadow aware binary masks for each frame are formed by using background subtraction and shadow removal in the Hue Saturation and Value (HSV) domain. To determine new vehicles in the subsequent frame (in addition to those in the current frame), invariant moments are used. For vehicles which are the same model and brand, color information and distance between center of mass and an imaginary reference line need to be considered. As for classification, the paper proposes a new method based on perspective projection of the scene geometry. The classification is grouped into three major tracks: bikes, saloon cars, and long vehicles. For each category, a lower and an upper bounding curve are developed to show the extent of their associated modality regions.

Artificial Intelligence Review, 2017

Foreground detection or moving object detection is a fundamental and critical task in video surveillance systems. Background subtraction using Gaussian Mixture Model (GMM) is a widely used approach for foreground detection. Many improvements have been proposed over the original GMM developed by Stauffer and Grimson (IEEE Computer Society conference on computer vision and pattern recognition,

This paper proposes an accurate and fast background subtraction technique for object tracking in still camera videos. Regions of motion in a frame are first estimated by comparing the current frame to a previous one. A samplingresampling based Bayesian learning technique is then used on the estimated regions to perform background subtraction and accurately determine the exact pixels which correspond to moving objects. An obvious advantage in terms of processing time is gained as the Bayesian learning steps are performed only on the estimated motion regions, which typically constitute only a small fraction of the frame. The technique has been used on a variety of indoor and outdoor sequences, to track both slow and fast moving objects, under different lighting conditions and varying object-background contrast. Results demonstrate that the technique achieves high degrees of sensitivity with considerably lower time complexity as compared to existing techniques based on mixture modeling of the background.

Journal of Imaging

Moving foreground detection is a very important step for many applications such as human behavior analysis for visual surveillance, model-based action recognition, road traffic monitoring, etc. Background subtraction is a very popular approach, but it is difficult to apply given that it must overcome many obstacles, such as dynamic background changes, lighting variations, occlusions, and so on. In the presented work, we focus on this problem (foreground/background segmentation), using a type-2 fuzzy modeling to manage the uncertainty of the video process and of the data. The proposed method models the state of each pixel using an imprecise and adjustable Gaussian mixture model, which is exploited by several fuzzy classifiers to ultimately estimate the pixel class for each frame. More precisely, this decision not only takes into account the history of its evolution, but also its spatial neighborhood and its possible displacements in the previous frames. Then we compare the proposed method with other close methods, including methods based on a Gaussian mixture model or on fuzzy sets. This comparison will allow us to assess our method's performance, and to propose some perspectives to this work.

Journal of Visual Languages & Computing, 2014

Video surveillance on highway is a hot topic and a great challenge in Intelligent Transportation Systems. In such applications requiring objects extraction, cast shadows induce shape distortions and object fusions interfering performance of high level algorithms. Shadow elimination allows to improve the performances of video object extraction, classification and tracking. In other hand, it is very important to recognize the type of a detected object in order to track reliably and estimate traffic parameters correctly. This paper presents two approaches to enhance automatic traffic surveillance systems. The first deals with the elimination of shadows and the second concerns the classification of vehicles, based on robust vision and image processing. For moving shadow elimination, a contrast model is proposed to describe and remove dynamic shadows based on the idea that a shadow transformation is a change in contrast. For vehicles classification, Hu moments are calculated in a manner to reduce the perspective effects and used to describe vehicles in knowledge base. Experimental results on the various challenging video sequences show that the proposed approach outperforms classification methods of related works (with a classification accuracy of 96.96%), and that the shadow elimination approach performs better than compared works (with detection rate of 95-99% and discrimination rate of 85.7-89%).

2004

Identifying moving objects from a video sequence is a fundamental and critical task in many computer-vision applications. A common approach is to perform background subtraction, which identifies moving objects from the portion of a video frame that differs significantly from a background model. There are many challenges in developing a good background subtraction algorithm. First, it must be robust against changes in illumination. Second, it should avoid detecting non-stationary background objects such as swinging leaves, rain, snow, and shadow cast by moving objects. Finally, its internal background model should react quickly to changes in background such as starting and stopping of vehicles. In this paper, we compare various background subtraction algorithms for detecting moving vehicles and pedestrians in urban traffic video sequences. We consider approaches varying from simple techniques such as frame differencing and adaptive median filtering, to more sophisticated probabilistic modeling techniques. While complicated techniques often produce superior performance, our experiments show that simple techniques such as adaptive median filtering can produce good results with much lower computational complexity.