Video object extraction based on a comparative study of efficient edge detection techniques

Abstract EN

Segmentation of objects serves as a key of image analysis and pattern recognition.

The main focus of the paper is related to the development of efficient algorithms for automatic segmentation of objects in image sequences.

Fast, automatic and robust segmentation are necessary in many aspects of multimedia applications due to its capability that it can automatically detect objects appearance and in addition it can be used for object tracking system.

The extraction of semantically meaningful video object for tracking and surveillance application can be obtained in the process of implementing the proposed algorithms.

Further in this paper a comparative study between video object extraction based on change detection and model matching techniques is given.

Experimental results prove the effectiveness of the proposed algorithms.