|
|
论文:2015,Vol:33,Issue(3):462-466 |
|
|
引用本文： |
|
|
马利克, 彭进业, 冯晓毅. 基于聚散熵及运动目标检测的监控视频关键帧提取[J]. 西北工业大学学报 |
|
|
Ma Like, Peng Jinye, Feng Xiaoyi. Surveillance Key Frame Extraction Based on Aggregation Dispersion Entropy and Moving Target Detection[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于聚散熵及运动目标检测的监控视频关键帧提取 |
|
| 马利克1,2, 彭进业1, 冯晓毅1 |
|
1. 西北工业大学 电子信息学院, 陕西 西安 710072;
2. 陕西省人民警察培训学校, 陕西 西安 710054 |
| 摘要: |
| 针对公安监控视频检索中根据运动目标准确标注视频关键帧的问题,提出一种基于聚散熵及运动目标检测的监控视频关键帧提取算法。首先通过对视频内容的分析,提出监控视频聚散熵的概念。其次根据聚散熵对监控视频进行子镜头划分,再次根据运动目标检测对子镜头进行划分,从而提取视频关键帧。最后列举出算法在几种典型视频数据库中的实验结果及结果分析。实验结果表明该算法在关键帧提取的准确性和鲁棒性上都有良好表现,该算法针对公安监控视频检索需求,在缩短公安视频侦查时间及智能检索中起到支撑作用。 |
| 关键词:
监控视频
关键帧
聚散熵
运动目标检测
|
|
| Surveillance Key Frame Extraction Based on Aggregation Dispersion Entropy and Moving Target Detection |
|
| Ma Like1,2, Peng Jinye1, Feng Xiaoyi1 |
|
1. Department of Electronics and Engineering, Northwestern Polytechnical University, Xi'an 710072, China;
2. The People's Police Training School of Shaanxi Province, Xi'an 710054, China |
| Abstract: |
| Key frame extraction is an important step in surveillance video retrieval. We propose a surveillance key frame extraction algorithm which is based on the aggregation dispersion entropy and moving target detection. Firstly, the concept of the aggregation dispersion entropy was defined to distinguish the presence of moving objects in video. Secondly, the aggregation dispersion entropy was used to divide surveillance video into several shots. And then the shots were splitted into sub-shots by the moving target detection. So the key frames could be got though the sub-shots. Finally, the algorithm of key frame extraction was given. The experimental results and their discussions were given; they showed that this algorithm has good performance both in accuracy and robustness for several different databases. Also, it is the demand of surveillance video retrieval in police use. And it is expected to be of further use in police video investigation. |
| Key words:
algorithms
entropy
image retrieval
monitoring
pixels
probability
target tracking
vectors
aggregation dispersion entropy
key frame
moving target detection
surveillance video
|
|
| 收稿日期: 2014-10-09
修回日期:
|
| DOI: |
| 基金项目: 高等学校博士学科点专项科研基金(20116102110027)与国家自然科学基金(61075014)资助 |
| 通讯作者:
Email： |
| 作者简介: 马利克(1977—),西北工业大学博士研究生,主要从事图像处理、模式识别及视频处理等研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Wang Yao, Ostermann J, Zhang Yaqin. 视频处理与通信[M]. 侯正信,译. 北京:电子工业出本社, 2003 Wang Yao, Ostermann J, Zhang Yaqin. Video Processing and Communication[M]. Hou Zhengxin, Translator. Beijing: Publishing House of Electronics Industry, 2003 (in Chinese)
[2] 雷少帅. 基于内容的视频检索关键技术研究[D]. 太原:太原理工大学,2012 Lei Shaoshuai. Besearch on Some Key Techniques of Video Retrieval Based on Content[D]. taiyuan: Taiyuan University of Technology (in Chinese)
[3] Zhan Chaohui, Duan Xiaohui, Xu Shuoyu. An Improved Moving Object Detection Algorithm Based on Frame Difference and Edge Detection[C]//International Conference on Image and Graphics (ICIG), 2007: 519-523
[4] Zhao Chunhui, Liu Wei, Wang Yi, Cheng Yongmei. A Fast Algorithm for Moving Objects Detection Based on Model Switching[C]//International Conference on Audio, Language and Image Processing (ICALIP), 2008: 143-146
[5] Mukherjee D, Wu Q M J, Nguyen T M. Multiresolution Based Gaussian Mixture Model for Background Suppression[J]. IEEE Trans on Image Processing, 2013, 22(12):5022-5035
[6] Yang Yun, Liu Yunyi. An Improved Background and Foreground Modeling Using Kernel Density Estimation in Moving Object Detection[C]//Computer Science and Network Technology (ICCSNT), 2011: 1050-1054
[7] Gonzalez R C, Woods R E. 数字图像处理[M]. 阮秋奇,译.2版. 北京: 电子工业出版社, 2005 Gonzalez R C, Woods R E. Digital Image Processing[M]. Ruan Qiuqi, translator.2nd Edition. Beijing: Publishing House of Electronics Industry, 2005 (in Chinese)
[8] Worf W. Key Frame Selection by Motion Analysis[C]//IEEE International Conference on Acoustics, Speech and Signal Processing. Atlanta, USA: IEEE Computer Society, 1996 |
|
|
|
|
|
|
|
