[1]肖 剑,刘天元,吴祥,等.基于前景对象检测和回归的视频异常检测方法[J].南京师大学报(自然科学版),2024,(02):117-128.[doi:10.3969/j.issn.1001-4616.2024.02.014]
　Xiao Jian,Liu Tianyuan,Wu Xiang,et al.Foreground Object Detection and Regression-based Video Anomaly Detection Method[J].Journal of Nanjing Normal University(Natural Science Edition),2024,(02):117-128.[doi:10.3969/j.issn.1001-4616.2024.02.014]
点击复制

基于前景对象检测和回归的视频异常检测方法()
分享到：

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

卷:
期数:
2024年02期
页码:
117-128
栏目:
计算机科学与技术
出版日期:
2024-06-15

文章信息/Info

Title:
Foreground Object Detection and Regression-based Video Anomaly Detection Method
文章编号:
1001-4616(2024)02-0117-12
作者:
肖 剑1; 刘天元2; 吴祥1; 吉根林1
(1.南京师范大学计算机与电子信息学院/人工智能学院,江苏 南京 210023)
(2.香港理工大学工业及系统工程学系,香港 999077)
Author(s):
Xiao Jian1; Liu Tianyuan2; Wu Xiang1; Ji Genlin1
(1.School of Computer and Electronic Information/Artificial Intelligence,Nanjing Normal University,Nanjing 210023,China)
(2.Department of Industrial and Systems Engineering,The Hong Kong Polytechnic University,Hongkong 999077,China)
关键词:
视频异常检测; 伪异常; 监督学习; 回归; 时空立方体
Keywords:
video anomaly detection; pseudo anomaly; supervised learning; regression; spatio-temporal cube
分类号:
TP391
DOI:
10.3969/j.issn.1001-4616.2024.02.014
文献标志码:
A
摘要:
视频异常检测在智能安防领域具有广泛的应用. 基于生成模型的方法以其强大的生成能力受到学术界广泛关注. 然而,这类方法通常涉及较多的参数,且往往依赖于大量的训练数据,这限制了其在实际应用场景中的适用性. 本文提出了一种基于前景对象检测和回归的视频异常检测方法(FODR-VAD). 首先,利用目标检测器检测前景对象并构建以对象为中心的时空立方体. 其次,采用随机乱序的方法构造伪异常数据. 最后,将单分类视频异常检测问题转换为回归任务,在有监督学习范式下优化特征表示. 在模型训练参数量小于1 M,使用不到一半训练集的前提下,所提出的方法在UCSD Ped2、CUHK Avenue和ShanghaiTech数据集上的Micro-AUC分别是99.09%、88.16% 和78.47%. 结果表明,所提出方法在保证较高异常检测能力的同时,可显著降低对训练数据的需求量.
Abstract:
Video anomaly detection finds wide applications in the field of intelligent security. Methods based on generative models have garnered extensive attention in academia due to their powerful generative capabilities. However,such methods typically involve a large number of parameters and often rely on a vast amount of training data,limiting their applicability in real-world scenarios. This paper proposes a video anomaly detection method based on foreground object detection and regression(FODR-VAD). Firstly,foreground objects are detected using an object detector,and spatiotemporal cubes centered around these objects are constructed. Secondly,pseudo-anomalous data is created using a random shuffling approach. Finally,the video anomaly detection problem is transformed into a regression task,optimizing feature representation under the supervised learning paradigm. With the model parameter count less than 1 million and using less than half of the training set,the proposed method achieves Micro-AUC scores of 99.09%,88.16%,and 78.47% on the UCSD Ped2,CUHK Avenue,and ShanghaiTech datasets,respectively. The results demonstrate that the proposed method significantly reduces the requirement for training data while ensuring high anomaly detection capability.

参考文献/References:

[1]CAI R,ZHANG H,LIU W,et al. Appearance-motion memory consistency network for video anomaly detection[C]//Proceedings of the AAAI Conf on Artificial Intelligence. Menlo Park:AAAI,2021,35(2):938-946.
[2]周航,詹永照,毛启容. 基于时空融合图网络学习的视频异常事件检测[J]. 计算机研究与发展,2021,58(1):48-59.
[3]HASAN M,CHOI J,NEUMANN J,et al. Learning temporal regularity in video sequences[C]//Proceedings of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2016:733-742.
[4]ASTRID M,ZAHEER M Z,LEE S I. Synthetic temporal anomaly guided end-to-end video anomaly detection[C]//Proceedings of the IEEE/CVF Int Conf on Computer Vision. Piscataway,NJ:IEEE,2021:207-214.
[5]GONG D,LIU L,LE V,et al. Memorizing normality to detect anomaly:memory-augmented deep autoencoder for unsupervised anomaly detection[C]//Proceedings of the IEEE/CVF Int Conf on Computer Vision. Piscataway,NJ:IEEE,2019:1705-1714.
[6]ASTRID M,ZAHEER M Z,LEE J Y,et al. Learning not to reconstruct anomalies[DB/OL].(2021-10-24)[2024-04-08]http://airxiv.org/abs/2110.09742.
[7]LIU W,LUO W,LIAN D,et al. Future frame prediction for anomaly detection-a new baseline[C]//Proceedings of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2018:6536-6545.
[8]YANG Z,WU P,LIU J,et al. Dynamic local aggregation network with adaptive clusterer for anomaly detection[C]//European Conf on Computer Vision. Berlin:Springer,2022:404-421.
[9]PARK H,NOH J,HAM B. Learning memory-guided normality for anomaly detection[C]//Proceedings of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2020:14372-14381.
[10]GEORGESCU M I,BARBALAU A,IONESCU R T,et al. Anomaly detection in video via self-supervised and multi-task learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE. 2021:12742-12752.
[11]MUNAWAR A,VINAYAVEKHIN P,DE MAGISTRIS G. Limiting the reconstruction capability of generative neural network using negative learning[C]//2017 IEEE 27th Int Workshop on Machine Learning for Signal Processing(MLSP). Piscataway,NJ:IEEE,2017:1-6.
[12]MAHADEVAN V,LI W,BHALODIA V,et al. Anomaly detection in crowded scenes[C]//2010 IEEE Computer Society Conf on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2010:1975-1981.
[13]LU C,SHI J,JIA J. Abnormal event detection at 150 fps in matlab[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway,NJ:IEEE. 2013:2720-2727.
[14]LUO W,LIU W,GAO S. A revisit of sparse coding based anomaly detection in stacked rnn framework[C]//Proceedings of the IEEE Int Conf on Computer Vision. Piscataway,NJ:IEEE,2017:341-349.
[15]TANG Y,ZHAO L,ZHANG S,et al. Integrating prediction and reconstruction for anomaly detection[J]. Pattern recognition letters,2020,129(1):123-130.
[16]LIU Z,NIE Y,LONG C,et al. A hybrid video anomaly detection framework via memory-augmented flow reconstruction and flow-guided frame prediction[C]//Proceedings of the IEEE/CVF Int Conf on Computer Vision. Piscataway,NJ:IEEE,2021:13588-13597.
[17]SULTANI W,CHEN C,SHAH M. Real-world anomaly detection in surveillance videos[C]//Proceedings of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2018:6479-6488.
[18]LANDI F,SNOEK C G M,CUCCHIARA R. Anomaly locality in video surveillance[J/OL]. arXiv Preprint arXiv:1901.10364,2019.
[19]PANG G,YAN C,SHEN C,et al. Self-trained deep ordinal regression for end-to-end video anomaly detection[C]//Proceedings of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2020:12173-12182.
[20]JING L,TIAN Y. Self-supervised visual feature learning with deep neural networks:a survey[J]. IEEE transactions on pattern analysis and machine intelligence,2020,43(11):4037-4058.
[21]REDMON J,FARHADI A. Yolov3:an incremental improvement[J]. arXiv Preprint arXiv:1804.02767,2018.
[22]GEORGESCU M I,IONESCU R T,KHAN F S,et al. A background-agnostic framework with adversarial training for abnormal event detection in video[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence,Piscataway,NJ:IEEE,2021,44(9):4505-4523.
[23]LU Y,CAO C,ZHANG Y,et al. Learnable locality-sensitive hashing for video anomaly detection[J]. IEEE transactions on circuits and systems for video technology,2022,33(2):963-976.
[24]SHI C,SUN C,WU Y,et al. Video anomaly detection via sequentially learning multiple pretext tasks[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway,NJ:IEEE. 2023:10330-10340.
[25]LIU Z,ZHOU Y,XU Y,et al. Simplenet:a simple network for image anomaly detection and localization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE. 2023:20402-20411.
[26]CAI T T,FRANKLE J,SCHWAB D J,et al. Are all negatives created equal in contrastive instance discrimination?[J/OL]. arXiv Preprint arXiv:2010.06682,2020.

备注/Memo

备注/Memo:
收稿日期:2023-09-26.
基金项目:国家自然科学基金项目(41971343).
通讯作者:吉根林,博士,教授,博士生导师,研究方向:大数据分析与挖掘技术. E-mail:glji@njnu.edu.cn
更新日期/Last Update: 2024-06-15