期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2015
期号：NCET
页码：268
出版社：S&S Publications
摘要：Video object segmentation and tracking framework for smart visual surveillance cameras is proposed withtwo major contributions. First, motion detection algorithm is proposed for video object segmentation. Second cellularautomata segmentation is proposed for video object tracking. The edges of the image are determined using Sobel and cannymethod. The Canny edge detector is an edge detection operator that uses a multi-stage algorithm to detect a wide range ofedges in images. The Sobel operator is based on convolving the image with a small, separable, and integer valued filter inhorizontal and vertical direction and is therefore relatively inexpensive in terms of computations. In motion segmentationoptical flow measurement is used for tracking object from video. Mathematical Morphology (MM) is a tool for extractingimage components that are useful for representation and description. Morphological technique removes unwanted motionsin the video and enhances the segmentation result. Morphological opening is used to remove small object andmorphological closing is used to fill the holes. Cellular automata is the graphical cut method. It is used to tracking aparticular object from video. In this paper focused on improving the accuracy of image segmentation by using optical flowmethod, hence it improves the segmentation performance.
