| 潘磊,程科,束鑫,张明.基于压缩传感和加权主色的镜头边界检测算法[J].光电子激光,2015,26(6):1118~1124 |
| 基于压缩传感和加权主色的镜头边界检测算法 |
| A shot boundary detection algorithm based on compressive sensing and weighted major color |
| 投稿时间：2015-02-10 |
| DOI： |
| 中文关键词: 镜头边界检测(SBD) 压缩传感(CS) 加权主色(WMC) 类Bhattacharyya相似度 |
| 英文关键词:shot boundary detection (SBD) compressive sensing (CS) weighted major color (W MC) Bhattacharyya-like similarity |
| 基金项目:国家自然科学基金(61103128,61471182,61170120,61305058)、江苏省自然科学基金(BK20130473,BK20130471,BK20140419)、江苏省科技创新与成果转化(重大科技成果转化 )(BA2012129)和江苏大学现代农业装备与技术省部共建教育 部重点实验室开放基金(NZ201303)资助项目 (1.江苏科技大学 计算机科学与工程学院,江苏 镇江 212003； 2.江苏 大学 现代农业装备与技术省部共建教育部重点实验室,江苏 镇江 212013) |
|
| 摘要点击次数: 793 |
| 全文下载次数: 0 |
| 中文摘要: |
| 针对现有算法存在计算量大、对摄像机和物体运动 敏感等缺点,提出一种基于压缩传感(CS)和加权主色(WMC)的镜头边界检测(SBD)算法(CSWMC )。首先通过直方图特征得到粗略的镜头 边界集合；然后利用CS将该集合中的帧及其前后帧的高维特征投影到低维空间,采用调节余 弦相似度得到基 于夹角的第一判定指标；继而定义一种新的图像主色权值和基于该权值的类Bhattacharyya 相似度,得到基于颜色 相似度的第二判定指标；以两种判定指标的乘积作为最终判定指标,并设计一种朴素但有效 的策略进行SBD。 实验结果表明,与常用方法相比,所提算法具有更高的查全率和精确率,能够更加有效进行 SBD。 |
| 英文摘要: |
| Shot boundary detection (SBD) is regarded as one of the most criti cal issues in content-based video retrieval technology.The existing algorithms are sensitive to the motions caused by cameras and objects,and also need huge amount of computation.With regard to these disadvantages,a shot bounda ry detection algorithm based on compressive sensing and weighted major color (CSWMC) is proposed.Firstly,a c oarse set of shot boundaries is obtained by comparison of frames′ histogram features,then the high dimensio nal features of the frames in the set and their neighboring frames are projected to low dimensional space,and afte r that,the first decision criterion based on angle similarity is generated by the computation of adjusted cosine sim ilarity.Secondly,a novel weighted value for image major color is defined and applied to the calculation of a new B hattacharyya-like similarity,which is used as the second decision criterion ba sed on color similarity.Finally,the product of the two decision criteria is computed as the ultimate one.At the same time,a naive yet e ffective strategy is designed for boundary detection.The experimental results demonstrate that the proposed algor ithm has higher recall rate and precision rate,and could perform shot boundary detection more effectively than those state-of-the-art methods. |
| 查看全文 下载PDF阅读器 |
| 关闭 |
|
|
|
|
|