Direct incremental model-based image motion segmentation for video analysis

Abstract

Dynamic analysis of image sequences is an important task in object-oriented video applications. It often relies on the segmentation of each image of the sequence into region entities of apparent homogeneous motion. In this paper, we present an original motion segmentation algorithm based on 2D polynomial motion models, a multiresolution robust estimator to compute these motion models, and appropriate local observations supplying both motion relevant information and their reliability.Motion segmentation is formulated as a contextual statistical labeling problem exploiting multiscale Markov Random Field (MRF) models. One of its main features is that it avoids time consuming alternate iterations between motion model estimation and spatial support identification. An original detection step allows us to estimate and to update the number of required motion models, and thus to handle the appearance of new objects. Numerous experiments performed with real indoor and outdoor image sequences demonstrate the efficiency of the method.

Vehicle detection and tracking with affine motion segmentation in stereo video

“…The algorithm was originally proposed in [5]. The aim of the motion segmentation is to extract moving regions in a video sequence.…”

Solving ill-posed Image Processing problems using Data Assimilation

“…The advantage of equation (36) is that W can be estimated even for high velocity norms. Equation (37) is an approximation and only well suited for low velocity except if incremental algorithms [12,19] or scale-space methods [1] are considered. In this paper, we choose however to consider the optical flow constraint (37) in order to illustrate the tasks to be applied for going from an ill-posed Image Processing problem to a Data Assimilation system, compare it with state-of-the-art methods, and prove the advantage of Data Assimilation when processing noisy acquisitions including missing data.…”

Decision Fusion for Object Detection and Tracking Using Mobile Cameras

“…This error function is minimized using an Iterative-ReweightedLeast-Squares procedure, with 0 as an initial value for ∆θ k [1]. This estimation algorithm allows us to get a robust and accurate estimation of the dominant motion model between two images.…”

“…Parametric motion model: The parametric motion model θ w represent the projection of the 3D motion field of the static background [1], where θ w denotes the modeled velocity vector field and θ the set of model parameters. The parametric motion model is defined at pixel p = (x,y) as:…”