论文信息 - QIMERA: A SOFTWARE PLATFORM FOR VIDEO OBJECT SEGMENTATION AND TRACKING

QIMERA: A SOFTWARE PLATFORM FOR VIDEO OBJECT SEGMENTATION AND TRACKING

In this paper we present an overview of an ongoing collaborative project in the field of video object segmentation and tracking. The objective of the project is to develop a flexible modular software architecture that can be used as test-bed for segmentation algorithms. The background to the project is described, as is the first version of the software system itself. Some sample results for the first segmentation algorithm developed using the system are presented and directions for future work are discussed.

[1] Ferran Marqués,et al. Tracking areas of interest for content-based functionalities in segmentation-based video coding , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[2] Noel E. O'Connor,et al. Supervised Semantic Object Segmentation and Tracking via EM-based Estimation of Mixture Density Parameters , 1998, NMBIA.

[3] Levent Onural,et al. Utilization of the recursive shortest spanning tree algorithm for video-object segmentation by 2-D affine motion modeling , 2000, IEEE Trans. Circuits Syst. Video Technol..