第6期 王倩倩，等：深度自编码与自更新稀疏组合的异常事件检测算法 ·1203· tion[C]//Proceedings of 2013 2nd IAPR Asian Confer- Conference on Image Analysis and Processing.Catania, ence on Pattern Recognition.Naha,Japan,2013: Italy,2017:779-789 110-114. [22]RUSSAKOVSKY O,DENG Jia,SU Hao,et al.ImageN- [11]胡正平，张乐，尹艳华.时空深度特征AP聚类的稀疏表 et large scale visual recognition challenge[J].Internation- 示视频异常检测算法[J].信号处理，2019,35(3) al journal of computer vision,2015,115(3):211-252. 386-395 [23]MAHADEVAN V.LI Weixin.BHALODIA V.et al.An- HU Zhengping,ZHANG Le,YIN Yanhua.Video anom- omaly detection in crowded scenes[C]//Proceedings of aly detection by AP clustering sparse representation based 2010 IEEE Computer Society Conference on Computer on spatial-temporal deep feature model[J].Journal of sig- Vision and Pattern Recognition.San Francisco,USA, nal processing,2019,35(3):386-395. 2010:1975-1981. [12]HASAN M,CHOI J,NEUMANN J,et al.Learning tem- [24]BRADLEY A P.The use of the area under the ROC curve poral regularity in video sequences[C]//Proceedings of the in the evaluation of machine learning algorithms[J].Pat- IEEE Conference on Computer Vision and Pattern Recog- tern recognition,1997,30(7):1145-1159 nition.Las Vegas,USA,2016:733-742. [25]LIU Yusha,LI Chunliang,POCZOS B.Classifier two- [13]WEI Hao,LI Kai,LI Haichang.et al.Detecting video an- sample test for video anomaly detections[C]//Proceedings omaly with a stacked convolutional LSTM framework[Cl// of the 29th British Machine Vision Conference.New- Proceedings of 12th International Conference on Com- castle.UK.2018:71 puter Vision Systems.Thessaloniki,Greece,2019: [26]MEHRAN R.OYAMA A.SHAH M.Abnormal crowd 330-342. behavior detection using social force model[C]//Proceed- [14]CONG Yang,YUAN Junsong,LIU Ji.Sparse reconstruc- ings of 2009 IEEE Conference on Computer Vision and tion cost for abnormal event detection[C]//Proceedings of Pattern Recognition.Miami,USA,2009:935-942. 2011 IEEE Conference on Computer Vision and Pattern [27]WANG Siqi,ZHU En,YIN Jianping,et al.Anomaly de- Recognition.Providence,USA,2011:3449-3456. tection in crowded scenes by SL-HOF descriptor and [15]ZHAO Bin,LI Feifei,XING E P.Online detection of un- foreground classification[C]//Proceedings of 2016 23rd usual events in videos via dynamic sparse coding[Cl//Pro- International Conference on Pattern Recognition.Cancun. ceedings of 2011 IEEE Conference on Computer Vision Mexico,.2016:3398-3403 and Pattern Recognition.Providence,USA,2011: 作者简介： 3313-3320. [16]LU Cewu,SHI Jianping,JIA Jiaya.Abnormal event de- 王倩倩，硕士研究生，主要研究方 tection at 150 FPS in MATLAB[C]//Proceedings of the 向为视频中的异常事件检测与行人重 IEEE International Conference on Computer Vision. 识别。 Sydney,Australia,2013:2720-2727. [17]LUO Weixin,LIU Wen,GAO Shenghua.A revisit of sparse coding based anomaly detection in stacked RNN framework[C]//Proceedings of the IEEE International Conference on Computer Vision.Venice,Italy,2017: 苗夺谦，教授，博士生导师，主要 341-349. 研究方向为人工智能、机器学习、大数 [18]SAJID H,CHEUNG S C S.Universal multimode back- 据分析、粒度计算。主持完成国家自 ground subtraction[J].IEEE transactions on image pro- 然科学基金项目6项，在研国家重点 cessing,2017,26(7):3249-3260. 研发计划项目1项、公安部重点计划 [19]ZIVKOVIC Z.Improved adaptive Gaussian mixture mod- 项目I项。荣获CAAI吴文俊人工智 el for background subtraction[Cl//Proceedings of the 17th 2 能自然科学奖二等奖、国家教学成果 International Conference on Pattern Recognition.Cam- 二等奖，授权专利12项。发表学术论文100余篇，出版教材 bridge,UK.2004:28-31. 和学术著作10部。 [20]FARNEBACK G.Two-frame motion estimation based on 张远健，博士研究生，主要研究方 polynomial expansion[C]//Proceedings of the 13th Scand- 向为粒度计算、不确定性。 inavian Conference on Image Analysis.Halmstad, Sweden.2003:363-370. [21]SMEUREANU S,IONESCU R T,POPESCU M,et al. Deep appearance features for abnormal behavior detec- tion in video[C]//Proceedings of the 19th Internationaltion[C]//Proceedings of 2013 2nd IAPR Asian Confer￾ence on Pattern Recognition. Naha, Japan, 2013: 110−114. 胡正平, 张乐, 尹艳华. 时空深度特征 AP 聚类的稀疏表 示视频异常检测算法 [J]. 信号处理, 2019, 35(3): 386–395. HU Zhengping, ZHANG Le, YIN Yanhua. Video anom￾aly detection by AP clustering sparse representation based on spatial-temporal deep feature model[J]. Journal of sig￾nal processing, 2019, 35(3): 386–395. [11] HASAN M, CHOI J, NEUMANN J, et al. Learning tem￾poral regularity in video sequences[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recog￾nition. Las Vegas, USA, 2016: 733−742. [12] WEI Hao, LI Kai, LI Haichang, et al. Detecting video an￾omaly with a stacked convolutional LSTM framework[C]// Proceedings of 12th International Conference on Com￾puter Vision Systems. Thessaloniki, Greece, 2019: 330−342. [13] CONG Yang, YUAN Junsong, LIU Ji. Sparse reconstruc￾tion cost for abnormal event detection[C]//Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2011: 3449−3456. [14] ZHAO Bin, LI Feifei, XING E P. Online detection of un￾usual events in videos via dynamic sparse coding[C]//Pro￾ceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2011: 3313−3320. [15] LU Cewu, SHI Jianping, JIA Jiaya. Abnormal event de￾tection at 150 FPS in MATLAB[C]//Proceedings of the IEEE International Conference on Computer Vision. Sydney, Australia, 2013: 2720−2727. [16] LUO Weixin, LIU Wen, GAO Shenghua. A revisit of sparse coding based anomaly detection in stacked RNN framework[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy, 2017: 341−349. [17] SAJID H, CHEUNG S C S. Universal multimode back￾ground subtraction[J]. IEEE transactions on image pro￾cessing, 2017, 26(7): 3249–3260. [18] ZIVKOVIC Z. Improved adaptive Gaussian mixture mod￾el for background subtraction[C]//Proceedings of the 17th International Conference on Pattern Recognition. Cam￾bridge, UK, 2004: 28−31. [19] FARNEBÄCK G. Two-frame motion estimation based on polynomial expansion[C]//Proceedings of the 13th Scand￾inavian Conference on Image Analysis. Halmstad, Sweden, 2003: 363−370. [20] SMEUREANU S, IONESCU R T, POPESCU M, et al. Deep appearance features for abnormal behavior detec￾tion in video[C]//Proceedings of the 19th International [21] Conference on Image Analysis and Processing. Catania, Italy, 2017: 779−789. RUSSAKOVSKY O, DENG Jia, SU Hao, et al. ImageN￾et large scale visual recognition challenge[J]. Internation￾al journal of computer vision, 2015, 115(3): 211–252. [22] MAHADEVAN V, LI Weixin, BHALODIA V, et al. An￾omaly detection in crowded scenes[C]//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, USA, 2010: 1975−1981. [23] BRADLEY A P. The use of the area under the ROC curve in the evaluation of machine learning algorithms[J]. Pat￾tern recognition, 1997, 30(7): 1145–1159. [24] LIU Yusha, LI Chunliang, PÓCZOS B. Classifier two￾sample test for video anomaly detections[C]//Proceedings of the 29th British Machine Vision Conference. New￾castle, UK, 2018: 71. [25] MEHRAN R, OYAMA A, SHAH M. Abnormal crowd behavior detection using social force model[C]//Proceed￾ings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 935−942. [26] WANG Siqi, ZHU En, YIN Jianping, et al. Anomaly de￾tection in crowded scenes by SL-HOF descriptor and foreground classification[C]//Proceedings of 2016 23rd International Conference on Pattern Recognition. Cancun, Mexico, 2016: 3398−3403. [27] 作者简介： 王倩倩，硕士研究生，主要研究方 向为视频中的异常事件检测与行人重 识别。 苗夺谦，教授，博士生导师，主要 研究方向为人工智能、机器学习、大数 据分析、粒度计算。主持完成国家自 然科学基金项目 6 项，在研国家重点 研发计划项目 1 项、公安部重点计划 项目 1 项。荣获 CAAI 吴文俊人工智 能自然科学奖二等奖、国家教学成果 二等奖，授权专利 12 项。发表学术论文 100 余篇，出版教材 和学术著作 10 部。 张远健，博士研究生，主要研究方 向为粒度计算、不确定性。 第 6 期 王倩倩，等：深度自编码与自更新稀疏组合的异常事件检测算法 ·1203·