点击次数：

论文类型：期刊论文

发表时间：2015-09-01

发表刊物：MULTIMEDIA TOOLS AND APPLICATIONS

收录刊物：SCIE、EI、Scopus

卷号：74

期号：17

页面范围：7285-7329

ISSN号：1380-7501

关键字：Slow-motion video; Color image segmentation; Color similarity; Parallel computing

摘要：Along with the high-speed cameras are more and more widely applied, how to automatically segment the region of interest in the slow-motion video is a new issue. In this paper, a color slow-motion video segmentation method is proposed. The main strategy is based on region growing and pixel color difference. A rapid color similarity computing method is improved and applied for classifying different pixels. An algorithm based on four directions corrosion is proposed to automatically extract the seed points for the serialized video frames. Utilizing this method, the color frames of the slow-motion videos can be segmented in series automatically. Also, the multithreading mode of parallel computing is introduced in the entire segmentation process. This method is not complicated but automatic. The regions of interest in the slow-motion video frames can be segmented clearly. This novel method can provide support to the video related applications.