A 3-Step Algorithm Using Region-Based Active Contours for Video Objects Detection
- PDF / 2,187,821 Bytes
- 10 Pages / 600 x 792 pts Page_size
- 57 Downloads / 190 Views
A 3-Step Algorithm Using Region-Based Active Contours for Video Objects Detection ´ Stephanie Jehan-Besson Laboratoire I3S, CNRS UNSA, 2000 route des Lucioles, 06903 Sophia Antipolis, France Email: [email protected]
Michel Barlaud Laboratoire I3S, CNRS UNSA, 2000 route des Lucioles, 06903 Sophia Antipolis, France Email: [email protected]
Gilles Aubert Laboratoire J. A. Dieudonn´e, CNRS, Parc Valrose, 06108 Nice Cedex 2, France Email: [email protected] Received 26 July 2001 and in revised form 9 February 2002 We propose a 3-step algorithm for the automatic detection of moving objects in video sequences using region-based active contours. First, we introduce a very full general framework for region-based active contours with a new Eulerian method to compute the evolution equation of the active contour from a criterion including both region-based and boundary-based terms. This framework can be easily adapted to various applications, thanks to the introduction of functions named descriptors of the different regions. With this new Eulerian method based on shape optimization principles, we can easily take into account the case of descriptors depending upon features globally attached to the regions. Second, we propose a 3-step algorithm for detection of moving objects, with a static or a mobile camera, using region-based active contours. The basic idea is to hierarchically associate temporal and spatial information. The active contour evolves with successively three sets of descriptors: a temporal one, and then two spatial ones. The third spatial descriptor takes advantage of the segmentation of the image in intensity homogeneous regions. User interaction is reduced to the choice of a few parameters at the beginning of the process. Some experimental results are supplied. Keywords and phrases: detection of moving objects, video sequences analysis, region-based active contours, level-set method.
1. INTRODUCTION Automatic segmentation of video objects is still a matter of intensive research and is a crucial issue for the development of the new video coding standards MPEG-4 [1, 2] and MPEG-7 [3]. Indeed, object-based coding attracts now a considerable attention. Actually, it will open new areas of applications in the field of video production and multimedia interface. Generally speaking, two classes of approaches may be considered for segmentation: region-based approaches such as Markov random fields [4], and boundary-based approaches. Originally, active contours were boundary-based methods. Indeed, snakes [5], balloons [6], or geodesic active contours [7] are driven by the minimization of energy towards the edges of an image. However, for video objects detection, it is interesting to incorporate region-based information in the evolution equation of the active contour. In this context, we propose a generalized Eulerian framework for region-based active contours. This general frame-
work is then applied to the detection of moving objects from video sequences acquired with either a moving or a static camera. First, a g
Data Loading...
