混合注意力机制的异常行为识别

doi:10.3778/j.issn.1002-8331.2109-0360

摘要/Abstract

摘要： 随着人工智能的快速发展，基于计算机视觉的人体异常行为识别受到极大的关注，并被广泛应用到智能安防等领域。针对人们在加油站等重要场所抽烟以及司机驾驶途中打电话等违规行为，提出一种混合注意力机制的异常行为识别方法。利用引入的卷积块注意力模块重点关注输入对象的显著性特征，并对输入信息进行精细化的分配和处理，在突出重要信息的同时弱化无关信息。为提升网络模型的特征挖掘能力及增强网络的信息交互性，利用提出的卷积特征提取模块进一步提取识别对象的高层语义特征，并将其与低层细节特征进行融合以达到多尺度特征交互的目的。此外，为了减少网络训练过程中错误标签造成的损失，采用标签平滑对交叉熵损失函数进行修正以此来驱动模型的学习过程。实验结果表明，所提出的模型优于当前的主流网络，可有效检测出异常行为。

关键词: 异常行为检测, 注意力机制, 卷积块注意力模块, 卷积特征提取模块, 标签平滑

Abstract: With the rapid development of artificial intelligence, human abnormal behaviour recognition based on computer vision has received great attention and is widely used in fields such as intelligent security. For violations such as people smoking in important places such as petrol stations and drivers talking on the phone while driving, this paper proposes a hybrid attentional mechanism for abnormal behaviour recognition. The introduced convolutional block attention module is used to focus on the salient features of the input objects, and the input information is finely allocated and processed to highlight important information while weakening irrelevant information. To enhance the feature mining capability of the network model and the interactivity of the network, the proposed convolutional feature extraction module is used to further extract the high-level semantic features of the recognised objects and fuse them with the low-level detailed features to achieve multi-scale feature interaction. In addition, in order to reduce the loss caused by mislabelling during network training, this paper uses label smoothing to correct the cross-entropy loss function to drive the learning process of the model. Experimental results show that the proposed model outperforms current mainstream networks and can effectively detect anomalous behaviour.

Key words: abnormal behavior detection, attention mechanism, convolution block attention module, convolution feature extraction module, label smoothing

孙晓虎, 余阿祥, 申栩林, 李洪均. 混合注意力机制的异常行为识别[J]. 计算机工程与应用, 2023, 59(5): 140-147.

SUN Xiaohu, YU Axiang, SHEN Xulin, LI Hongjun. Abnormal Behavior Recognition Based on Hybrid Attention Mechanism[J]. Computer Engineering and Applications, 2023, 59(5): 140-147.

参考文献

[1] ZHAI B.Research on detection method of abnormal behavior of people in video surveillance[C]//Proc of the 5th International Conference on Electrical and Electronics Engineering and Computer Science，Beijing，2018：289-293.
[2] WANG X，SONG H S，CUI H.Pedestrian abnormal event detection based on muti-feature fusion in traffic video[J].Optik，2018，154：22-32.
[3] SAQLAIN S M，GHANI A，KHAN I，et al.Image analysis using human body geometry and size proportion science for action classification[J].Applied Sciences，2020，10（16）：5453.
[4] GAO X J.Abnormal behavior detection and warning based on deep intelligent video analysis for geriatric patients[J].Journal of Medical Imaging and Health Informatics，2021，11（2）：345-352.
[5] XIONG H.Abnormal behavior recognition in the internet environment based on condition monitoring[J].Agro Food Industry Hi Tech，2017，28（1）：2210-2215.
[6] KO K E，SIM K B.Deep convolutional framework for abnormal behavior detection in a smart surveillance system[J].Engineering Applications of Artificial Intelligence，2018，67：226-234.
[7] JIA S，HUI F，LI S，et al.Long short-term memory and convolutional neural network for abnormal driving behaviour recognition[J].IET Intelligent Transport Systems，2020，14（5）：306-312.
[8] LI C，ZHONG Q Y，XIE D.Skeleton-based action recognition with convolutional neural networks[C]//Proc of IEEE International Conference on Multimedia and Expo，2017：597-600.
[9] WANG L，XIONG Y，WANG Z，et al.Towards good practices for very deep two-stream convnets[J].Computer Vision and Pattern Recognition，2015：1-5.
[10] 苏江毅，宋晓宁，吴小俊，等.多模态轻量级图卷积人体骨架行为识别方法[J].计算机科学与探索，2021，15（4）：733-742.
SU J Y，SONG X N，WU X J，et al.Skeleton based action recognition algorithm on multi-modal lightweight graph convolutional network[J].Journal of Frontiers of Computer Science and Technology，2021，15（4）：733-742.
[11] 胡薰尹，管业鹏.基于3D-LCRN视频异常行为识别方法[J].哈尔滨工业大学学报，2019，51（11）：183-193.
HU X Y，GUAN Y P.A 3D-LCRN based video abnormal behavior recognition[J].Journal of Harbin Institute of Technology，2019，51（11）：183-193.
[12] DU W，WANG Y，QIAO Y.RPAN：an end-to-end recurrent pose-attention network for action recognition in videos[C]//Proc of the 16th IEEE International Conference on Computer Vision，2017：3745-3754.
[13] SONG S J，LAN C L，XING J L.An end-to-end spatio-temporal attention model for human action recognition from skeleton data[C]//Proc of the 31st AAAI Conference on Artificial Intelligence，2017：4263-4270.
[14] WANG Q，WU B，ZHU P，et al.ECA-Net：efficient channel attention for deep convolutional neural networks[C]//Proc of 2020 IEEE Conference on Computer Vision and Pattern Recognition，2020：11534-11542.
[15] JADERBERG M，SIMONYAN K，ZISSERMAN A.Spatial transformer networks[C]//Advances in Neural Information Processing Systems，2015：1-9.
[16] HU J，SHEN L，SUN G，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，42（8）：2011-2023.
[17] LI H，XIONG P，AN J，et al.Pyramid attention network for semantic segmentation[J].arXiv：1805.10180v3，2018.
[18] WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module[J].arXiv：1807.06521，2018.
[19] FU J，LIU J，TIAN H，et al.Dual attention network for scene segmentation[C]//Proc of IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：3146-3154.
[20] HUANG Z，WANG X，HUANG L，et al.CCNet：criss-cross attention for semantic segmentation[C]//Proc of IEEE/CVF International Conference on Computer Vision，2020：603-612.
[21] MULLER R，KORNBLITH S，HINTON G.When does label smoothing help?[C]//33rd Conference on Neural Information Processing Systems，Vancouver，2019.
[22] HE K M，ZHANG X Y，REN S Q，et al.Delving deep into rectifiers：surpassing human-level performance on ImageNet classification[C]//Processing of the IEEE International Conference on Computer Vision，2015：1026-1034.