文献类型：会议论文

中文题名：Effective Approach to Camera Zoom Detection Based on Visual Attention

作者：Huang Jing-hua;Yang Yan-song

第一作者：黄静华

机构：[1]Institute of Information Technology,Beijing Union University,Beijing,China,100101;[2]School of Mechanic;

第一机构：北京联合大学智慧城市学院

会议论文集：9th International Conference on Signal Processing(第九届国际信号处理学术会议)(ICSP'08)论文集

会议日期：20081026

会议地点：北京

主办单位：中国电子学会

语种：英文

摘要：An effective approach based on geometric constraint of the motion vector field is proposed to detect camera zoom operation.The approach exploits the valid motion vectors to estimate the center of focus (COF) for zoom,and then calculates the average distance from the COF to valid motion vectors to identify zoom operation.To reduce the influence of object motion,Visual attention mechanism is employed to select valid motion vectors.Experimental results show that the proposed approach achieves a good performance.