| 考场异常行为检测算法 |
| |
| 引用本文： | 戴金波,龙曼丽,赵宏伟,陈奋君.考场异常行为检测算法[J].吉林大学学报(工学版),2012(Z1):236-240. |
| |
| 作者姓名： | 戴金波 龙曼丽 赵宏伟 陈奋君 |
| |
| 作者单位： | 吉林大学计算机科学与技术学院;长春师范学院计算机科学与技术学院;吉林大学公共外语教育学院 |
| |
| 基金项目： | 国家自然科学基金项目(61101155);吉林省科技发展计划资助项目(20101504) |
| |
| 摘 要： | 以智能视频监控理论为依据,结合考试现场特点,提出了一种能够进行考场异常行为检测的高效算法。该算法从考生信息结构和内容方面作了科学设计,提出了行为覆盖区、3维考场关注度等概念。仿真实验针对分析器的准确率和效率两方面进行,并特别比较了本算法设计的分析器和普通方式分析器的效率。实验结果表明,本算法能很好地挖掘视频帧间的历史关系,与未采用本算法的普通方式相比检测效率有较大提高。
|
| 关 键 词： | 计算机应用 行为覆盖区 Latent SVM 行为模型 三维考场关注度 |
Algorithm of the exam abnormal behavior detection |
| |
| DAI Jin-bo,LONG Man-li,ZHAO Hong-wei,CHEN Fen-jun.Algorithm of the exam abnormal behavior detection[J].Journal of Jilin University:Eng and Technol Ed,2012(Z1):236-240. |
| |
| Authors: | DAI Jin-bo LONG Man-li ZHAO Hong-wei CHEN Fen-jun |
| |
| Affiliation: | 1(1.College of Computer Science and Technology,Jilin University,Changchun 130012,China;2.Department of Computer Science and Technology,Changchun Normal University,Changchun 130032,China;3.School of Foreign Language Education,Jilin University,Changchun 130012,China) |
| |
| Abstract: | A efficient algorithm was presented for abnormal behavior detection in examroom based on intelligent video surveillance theory and examroom characters.The concepts of Behavior Coverage Region and Three-Dimensional Attention(TDA) were given in this algorithm from the structure and content of examinee information.And the efficiency between analyzer designed by this algorithm and ordinal methods had been compared after the simulation experiments to analyzer's accuracy and efficiency.The result suggested that this algorithm can reveal the history relationship of video inter-frame and can also accelerate greatly comparing with ordinal methods. |
| |
| Keywords: | computer application action coverage area(ACA) latent SVM viewpoint action model(MVAM) three-dimensional attention(TDA) |
| 本文献已被 CNKI 等数据库收录！ |
