Nathalie Peyrard

EM procedures using mean field-like approximations for Markov model-based image segmentation

This paper deals with Markov random field model-based image segmentation. This involves parameter estimation in hidden Markov models for which one of the most widely used procedures is the EM algorithm. In practice, difficult- ies arise due to the dependence structure in the models and approximations are required to make the algorithm tractable. We propose a class of algorithms in which the idea is to deal with systems of independent variables. This corresponds to approximations of the pixels interactions similar to the mean field approximation. It follows algorithms that have the advantage of taking the Markovian structure into account while preserving the good features of EM. In addition, this class, that includes new and already known procedures, is presented in a unified framework, showing that apparently distant algorithms come from similar approximation principles. We illustrate the algorithms performance on synthetic and real images. These experiments point out the ability of our procedures to take the spatial information into account. Our algorithms often show significant improvement when comparing with the EM algorithm applied with no account of the spatial structure and with the ICM algorithm, based on maximization of the pseudo-likelihood and commonly used in image segmentation.

Hidden Markov random field model selection criteria based on mean field-like approximations

Hidden Markov random fields appear naturally in problems such as image segmentation, where an unknown class assignment has to be estimated from the observations at each pixel. Choosing the probabilistic model that best accounts for the observations is an important first step for the quality of the subsequent estimation and analysis. A commonly used selection criterion is the Bayesian Information Criterion (BIC) of Schwarz (1978), but for hidden Markov random fields, its exact computation is not tractable due to the dependence structure induced by the Markov model. We propose approximations of BIC based on the mean field principle of statistical physics. The mean field theory provides approximations of Markov random fields by systems of independent variables leading to tractable computations. Using this principle, we first derive a class of criteria by approximating the Markov distribution in the usual BIC expression as a penalized likelihood. We then rewrite BIC in terms of normalizing constants, also called partition functions, instead of Markov distributions. It enables us to use finer mean field approximations and to derive other criteria using optimal lower bounds for the normalizing constants. To illustrate the performance of our partition function-based approximation of BIC as a model selection criterion, we focus on the preliminary issue of choosing the number of classes before the segmentation task. Experiments on simulated and real data point out our criterion as promising: It takes spatial information into account through the Markov model and improves the results obtained with BIC for independent mixture models.

Motion-based selection of relevant video segments for video summarisation

We present a method for motion-based video segmentation and segment classification as a step towards video summarization. The sequential segmentation of the video is performed by detecting changes in the dominant image motion, assumed to be related to camera motion and represented by a 2D affine model. The detection is achieved by analysing the temporal variations of some coefficients of the 2D affine model (robustly) estimated. The obtained video segments supply reasonable temporal units to be further classified. For the second stage, we adopt a statistical representation of the residual motion content of the video scene, relying on the distribution of temporal co-occurrences of local motion-related measurements. Pre-identified classes of dynamic events are learned off-line from a training set of video samples of the genre of interest. Each video segment is then classified according to a Maximum Likelihood criterion. Finally, excerpts of the relevant classes can be selected for video summarization. Experiments regarding the two steps of the method are presented on different video genres leading to very encouraging results while only low-level motion information is considered.

Detection of meaningful events in videos based on a supervised classification approach

In this paper, we consider the challenging problem of unusual event detection in video surveillance systems. The proposed approach makes a step toward generic and automatic detection of unusual events in terms of velocity and acceleration. At first, the moving objects in the scene are detected and tracked. A better representation of moving objects trajectories is then achieved by means of appropriate pre-processing techniques. A supervised Support Vector Machine method is then used to train the system with one or more typical sequences, and the resulting model is then used for testing the proposed method with other typical sequences (different scenes and scenarios). Experimental results are shown to be promising. The presented approach is capable of determining similar unusual events as in the training sequences.We present a supervised method for the detection and retrieval of relevant events in videos according to dynamic content. We adopt a statistical representation where residual and camera motion informations are characterized by probabilistic models. In an off-line stage, the models associated to pre-identified classes of meaningful dynamic events are learned from a given training set of video samples. Then, a classification and selection algorithm is applied on each segment of a temporal segmentation of the video to process, by exploiting this statistical framework. Only the segments associated to classes defined as relevant in terms of dynamic event can then be selected. The efficiency of the proposed method is evaluated on sport videos for which categories of relevant events can be explicitly defined.

Content-Based Video Segmentation using Statistical Motion Models

We present in this paper an original approach for content-based video segmentation using motion information. The method is generic and does not require any knowledge about the type of the processed video. Its relies on the analysis of the temporal evolution of the dynamic content of the video. The motion content is characterised by a probabilistic Gibbsian modelling of the distribution of local motion-related measurements. The designed statistical framework provides a well formalised similarity measure according to motion activity that we exploit to derive criteria for segmentation decision. Then, the considered merging criteria are sequentially applied between every two successive temporal units of the video to progressively form homogeneous segments in term of motion content. Experiments on real video documents demonstrate the ability of the proposed approach to provide a concise and meaningful overview of a video.