Conference Paper

A variational framework for image segmentation combining motion estimation and shape regularization

Dept. of Comput. Sci., Univ. of California, Los Angeles, CA, USA;
DOI: 10.1109/CVPR.2003.1211337 Conference: Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, Volume: 1
Source: DBLP

ABSTRACT Based on a geometric interpretation of the optic flow constraint equation, we propose a conditional probability on the spatio-temporal image gradient. We consistently derive a variational approach for the segmentation of the image domain into regions of homogeneous motion. The proposed energy functional extends the Mumford-Shah functional from gray value segmentation to motion segmentation. It depends on the spatio-temporal image gradient calculated from only two consecutive images of an image sequence. Moreover, it depends on motion vectors for a set of regions and a boundary separating these regions. In contrast to most alternative approaches, the problems of motion estimation and motion segmentation are jointly solved by minimizing a single functional. Numerical evaluation with both explicit and implicit (level set based) representations of the boundary shows the strengths and limitations of our approach.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Abstract In this technical report, we propose a novel technique to address motion estima- tion and tracking. Such technique represents the motion field using a regular grid of thin-plate splines, and the moving objects using an implicit function on the image plane that is a cubic interpolation of a ”level set function” defined on this grid. Optical flow is determined through the deformation,of the grid and conse- quently of the underlying image structures towards satisfying the constant bright- ness constraint. Tracking is performed,in similar fashion through the consistent recovery in the temporal domain,of the zero iso-surfaces of a level set that is the projection of the FFD implicit function according to the cubic spline formulation. Such an approach is a compromise,between dense motion estimation and parame- tric motion models, introduces smoothness in an implicit fashion, is intrinsic, and can cope with important object deformations. Promising results demonstrate the
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: An Abstract of the Thesis Presented in Partial Fulfillment of the Requirements for the Degree of Master of Science (in Spatial Information Science and Engineering) 2006 From being an expensive toy in the hands of governmental agencies, computers have
  • [Show abstract] [Hide abstract]
    ABSTRACT: The image segmentation method described in this paper has been developed as a pre-processing stage to be used in methodologies and tools for video/image indexing and retrieval by content. This method solves the problem of whole objects extraction from background and it produces images of single complete objects from videos or photos. The extracted images are used for calculating the object visual features necessary for both indexing and retrieval processes. The segmentation algorithm is based on the cooperation among an optical flow evaluation method, edge detection and region growing procedures. The optical flow estimator belongs to the class of differential methods. It permits to detect motions ranging from a fraction of a pixel to a few pixels per frame, achieving good results in presence of noise without the need of a filtering pre-processing stage and includes a specialised model for moving object detection. The first task of the presented method exploits the cues from motion analysis for moving areas detection. Objects and background are then refined using respectively edge detection and seeded region growing procedures. All the tasks are iteratively performed until objects and background are completely resolved. The method has been applied to a variety of indoor and outdoor scenes where objects of different type and shape are represented on variously textured background.


Available from