Bertrand Vachon

Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey

Mixture of Gaussians is a widely used approach for background modeling to detect moving objects from static cameras. Numerous improvements of the original method developed by Stauffer and Grimson [1] have been proposed over the recent years and the purpose of this paper is to provide a survey and an original classification of these improvements. We also discuss relevant issues to reduce the computation time. Firstly, the original MOG are reminded and discussed following the challenges met in video sequences. Then, we categorize the different improvements found in the literature. We have classified them in term of strategies used to improve the original MOG and we have discussed them in term of the critical situations they claim to handle. After analyzing the strategies and identifying their limitations, we conclude with several promising directions for future research.

Type-2 Fuzzy Mixture of Gaussians Model: Application to Background Modeling

Background modeling is a key step of background subtraction methods used in the context of static camera. The goal is to obtain a clean background and then detect moving objects by comparing it with the current frame. Mixture of Gaussians Model [1] is the most popular technique and presents some limitations when dynamic changes occur in the scene like camera jitter, illumination changes and movement in the background. Furthermore, the MGM is initialized using a training sequence which may be noisy and/or insufficient to model correctly the background. All these critical situations generate false classification in the foreground detection mask due to the related uncertainty. To take into account this uncertainty, we propose to use a Type-2 Fuzzy Mixture of Gaussians Model. Results show the relevance of the proposed approach in presence of camera jitter, waving trees and water rippling.

Fuzzy integral for moving object detection

Detection of moving objects is the first step in many applications using video sequences like video-surveillance, optical motion capture and multimedia application. The process mainly used is the background subtraction which one key step is the foreground detection. The goal is to classify pixels of the current image as foreground or background. Some critical situations as shadows, illumination variations can occur in the scene and generate a false classification of image pixels. To deal with the uncertainty in the classification issue, we propose to use the Choquet integral as aggregation operator. Experiments on different data sets in video surveillance have shown a robustness of the proposed method against some critical situations when fusing color and texture features. Different color spaces have been tested to improve the insensitivity of the detection to the illumination changes. Then, the algorithm has been compared with another fuzzy approach based on the Sugeno integral and has proved its robustness.

A fuzzy approach for background subtraction

Background Subtraction is a widely used approach to detect moving objects from static cameras. Many different methods have been proposed over the recent years and can be classified following different mathematical model: determinist model, statistical model or filter model. The presence of critical situations i.e. noise, illumination changes and structural background changes introduce two main problems: The first one is the uncertainty in the classification of the pixel in foreground and background. The second one is the imprecision in the localization of the moving object. In this context, we propose a fuzzy approach for background subtraction. For this, we use the Choquet integral in the foreground detection and propose fuzzy adaptive background maintenance. Results show the pertinence of our approach.

Foreground Detection Using the Choquet Integral

Foreground Detection is a key step in background subtraction problem. This approach consists in the detection of moving objects from static cameras through a classification process of pixels as foreground or background. The presence of some critical situations i.e noise, illumination changes and structural background changes produces an uncertainty in the classification of image pixels which can generate false detections. In this context, we propose a fuzzy approach using the Choquet integral to avoid the uncertainty in the classification. The experiments on different video datasets have been realized by testing different color space and by fusing color and texture features. The proposed method is characterized through robustness against illumination changes, shadows and little background changes, and it is validated with the experimental results.

Fuzzy statistical modeling of dynamic backgrounds for moving object detection in infrared videos

Mixture of Gaussians (MOG) is the most popular technique for background modeling and presents some limitations when dynamic changes occur in the scene like camera jitter and movement in the background. Furthermore, the MOG is initialized using a training sequence which may be noisy and/or insufficient to model correctly the background. All these critical situations generate false classification in the foreground detection mask due to the related uncertainty. In this context, we present a background modeling algorithm based on Type-2 Fuzzy Mixture of Gaussians which is particularly suitable for infrared videos. The use of the Type-2 Fuzzy Set Theory allows to take into account the uncertainty. The results using the OTCBVS benchmark/test dataset videos show the robustness of the proposed method in presence of dynamic backgrounds.

Comparison of Background Subtraction Methods for a Multimedia Application

This article presents the Aqu@theque application and a comparison of background subtraction methods to improve the performance of this application. The Aqu@theque application consists in elaborating an information system dedicated to aquariums in an interactive learning area. In particular, this article presents our comparison of different background subtraction methods to detect fish in video sequences and the improvement for the Aqu@theque application.

Fuzzy foreground detection for infrared videos

We present a foreground detection algorithm based on a fuzzy integral that is particularly suitable for infrared videos. The proposed detection of moving objects is based on fusing intensity and textures using fuzzy integral. The detection results are then used to update the background in a fuzzy way. This method allows to robustly detect moving object in presence of cloudy and rainy conditions. Our theoretical and experimental results show that the proposed method gives similar results than the KaewTraKulPong and Bowden approach based on Mixture Of Gaussians (MOG) with less memory requirement and time consuming. The results using the OTCBVS benchmark/test dataset videos show the robustness of the proposed method.

COMPRESSION AND RECOGNITION OF SPATIO-TEMPORAL SEQUENCES FROM CONTEMPORARY BALLET

We aim at recognizing a set of dance gestures from contemporary ballet. Our input data are motion trajectories followed by the joints of a dancing body provided by a motion-capture system. It is obvious that direct use of the original signals is unreliable and expensive. Therefore, we propose a suitable tool for nonuniform sub-sampling of spatio-temporal signals. The key to our approach is the use of polygonal approximation to provide a compact and efficient representation of motion trajectories. Our dance gesture recognition method involves a set of Hidden Markov Models (HMMs), each of them being related to a motion trajectory followed by the joints. The recognition of such movements is then achieved by matching the resulting gesture models with the input data via HMMs. We have validated our recognition system on 12 fundamental movements from contemporary ballet performed by four dancers.

Range image generator including robot motion

The system here described has the capability of generating range images that include robot motion. The system has two main modules, the motion and the image generator. Motion is modeled using a Beziers curve method. To compute a range value corresponding to a pixel image, the robot position in the coordinated system is obtained from trajec-tory generation. In this way, distortion is produced in the image, or sequence of images, as a consequence of motion. The obtained range images represent scenes perceived by the robot from a specific location or during a specified dis-placement in a very “real” view.