An Interactive System for Video Object Segmentation

• Main Authors: Ping-Che Chen, 陳秉哲
• Other Authors: Yi-Ping Hung
• Format: Others
• Language: en_US
• Published: 2002
• Online Access: http://ndltd.ncl.edu.tw/handle/01836425769421399162

碩士 === 國立臺灣大學 === 資訊工程學研究所 === 90 === Video object segmentation is to extract an object from an image sequence. Single image segmentation is very hard; generally human intervention is re-quired for correct results. The motion information in an image sequence makes video object segmentation easier. However, there is still no algorithm that can automatically segment video objects precisely. Furthermore, it is in-efficient to perform single image segmentation for each image in the image sequence independently, for both supervised and unsupervised approaches. Therefore, it is important to utilize the temporal coherence between images in an image sequence. We proposed a video object segmentation system that combines both supervised single image segmentation and interactive video object tracking. The user uses a single image segmentation tool to extract the video object in one or more images, and use the interactive tracking tool to find the video object in the remaining images. The tracking tool is hierarchical, from higher detail level to lower detail level. The user can interactively correct the track-ing result between two tracking operations to ensure the correctness. The experimental results show that this system is simple to use and the user is able to obtain accurate results.