Digital Video Sequence Segmentation Using Self-organising Maps

摘要：

Digital video sequence segmentation is an important, step in the construction of efficient and userfriendly video archives. In this paper, we employ the self-organising maps (SOM) 6 to segment a digital video sequence into shots. The SOM is capable of learning the characteristics of various shots and clustering them accordingly. We represent the image frames by 6-bit color-coded histograms. We make use of the Chi-square distances between histograms of neighboring frames as the primary features to train the SOM and to segment the video sequences. We present results to demonstrate the reliable performance of our proposed approach.

作者: P. N. Suganthan Xiang Cao

作者单位: School of Electrical and Electronic Engineering Nanyang Technological University Nanyang Avenue, Singapore 639798

会议类型: 国际会议

会议名称: 8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)

会议地点: 上海

会议语种:英文

页码: 1447-1451

在线出版日期: 2001-11-14（万方平台首次上网日期，不代表论文的发表时间）