生物启发的人群突发局部聚集感知神经网络

doi:10.3778/j.issn.1002-8331.2203-0090

摘要/Abstract

摘要： 公共场所中的人群突发局部聚集常是异常事件发生的先兆，由于其随机性强，前兆特征不明显，现有的传统计算机视觉技术较难对其有效检测。基于蝗虫视觉系统的神经结构特性与小叶巨型运动检测器（lobula giant movement detector，LGMD）危险感知机理，提出一种人群突发局部聚集行为检测的LGMD改进型神经网络模型。该模型感知人群活动在视野域中引发的视觉信号，基于哺乳动物视网膜视觉信号处理机制整合视觉运动线索，借助LGMD神经元危险感知机理构建尖峰阈值机制调谐神经网络输出，以感知人群活动中的突发聚集行为。不同场景下的人群活动视频实验结果表明，提出的神经网络能有效检测视野域中人群突发局部聚集行为并对其预警。该文涉及生物视神经机理启发的人群活动动态视觉信息加工处理，可为智能视频监控中的人群活动检测与行为分析提供新思想、新方法。

关键词: 异常事件检测, 人群聚集, LGMD模型, 人群行为分析, 智能视频监控

Abstract: The suddenly localized crowd gathering behavior in public places is often a precursor of abnormal events, but it is difficult to be effectively detected by existing traditional computer vision techniques due to its strong randomness and inconspicuous characteristics of precursors. This paper proposes a modified LGMD-based neural network model for detecting suddenly localized crowd gathering behaviors, based on the structural properties of locust vision systems and the hazardous perception mechanism of lobula giant movement detector（LGMD）. This model perceives visual signals triggered by the crowd activity in the field of view, and then integrates the motion cues collected by each pixel based on the specific neural mechanism in mammalian retinas. Finally, a spiking threshold mechanism is built to tune the output membrane potentials of the neural network, by means of the hazardous perception mechanism of LGMD neuron. The experimental results of crowd activity videos in different scenes show that the proposed neural network can effectively detect suddenly localized crowd gathering behaviors in the field of view and generate warning signals. This paper involves the processing for dynamic visual information of crowd activities inspired by the optic nerve mechanism of biological vision systems, which can provide novel methods and creative ideas for crowd activity detections and behavior analyses for future intelligent video surveillance.

Key words: abnormal event detection, crowd gathering, LGMD model, crowd behavior analysis, intelligent video surveillance

刘倡, 胡滨. 生物启发的人群突发局部聚集感知神经网络[J]. 计算机工程与应用, 2022, 58(16): 164-174.

LIU Chang, HU Bin. Bio-Inspired Neural Network for Perceiving Suddenly Localized Crowd Gathering[J]. Computer Engineering and Applications, 2022, 58(16): 164-174.

参考文献

[1] 徐涛，田崇阳，刘才华.基于深度学习的人群异常行为检测综述[J].计算机科学，2021，48（9）：125-134.
XU T，TIAN C Y，LIU C H.Deep learning for abnormal crowd behavior detection：a review[J].Computer Science，2021，48（9）：125-134.
[2] BRIASSOULI A，KOMPATSIARIS I.Spatiotemporally localized new event detection in crowds[C]//2011 IEEE International Conference on Computer Vision Workshops，2011：928-933.
[3] GU X，CUI J，ZHU Q.Abnormal crowd behavior detection by using the particle entropy[J].Optik，2014，125（14）：3428-3433.
[4] WANG T，SNOUSSI H.Detection of abnormal visual events via global optical flow orientation histogram[J].IEEE Transactions on Information Forensics and Security，2014，9（6）：988-998.
[5] RAO A S，GUBBI J，MARUSIC S，et al.Crowd event detection on optical flow manifolds[J].IEEE Transactions on Cybernetics，2015，46（7）：1524-1537.
[6] XU F，RAO Y，WANG Q.An unsupervised abnormal crowd behavior detection algorithm[C]//2017 International Conference on Security，Pattern Analysis，and Cybernetics，2017：219-223.
[7] LIU C Y，LIAO W H，RUAN S J.Crowd gathering detection based on the foreground stillness model[J].IEICE Transactions on Information and Systems，2018，101（7）：1968-1971.
[8] YANG D S，LIU C Y，LIAO W H，et al.Crowd gathering and commotion detection based on the stillness and motion model[J].Multimedia Tools and Applications，2020，79（27）：19435-19449.
[9] 黄贺贺，曾园园，张毅，等.基于群体行为分析的人群异常聚集预测方法[J].计算机工程，2020，46（3）：292-298.
HUANG H H，ZENG Y Y，ZHANG Y，et al.Prediction method of abnormal crowd aggregation based on group behavior analysis[J].Computer Engineering，2020，46（3）：292-298.
[10] 罗凡波，王平，徐桂菲，等.基于多尺度卷积神经网络的人群聚集异常预测[J].计算机工程与科学，2020，42（12）：2223-2232.
LUO F B，WANG P，XU G F，et al.Prediction of crowd massing abnormity based on multi-scale convolutional neural network[J].Computer Engineering & Science，2020，42（12）：2223-2232.
[11] BAI L，WU C，XIE F，et al.Crowd density detection method based on crowd gathering mode and multi-column convolutional neural network[J].Image and Vision Computing，2021，105：104084.
[12] XU J，ZHAO H，MIN W，et al.DGG：a novel framework for crowd gathering detection[J].Electronics，2022，11（1）：31.
[13] ZHU Y，DEWELL R B，WANG H，et al.Pre-synaptic muscarinic excitation enhances the discrimination of looming stimuli in a collision-detection neuron[J].Cell Reports，2018，23（8）：2365-2378.
[14] WERNITZNIG S，RIND F C，ZANKEL A，et al.The complex synaptic pathways onto a looming-detector neuron revealed using serial block-face scanning electron micro-
scopy[J].Journal of Comparative Neurology，2022，530（2）：518-536.
[15] RIND F C，BRAMWELL D I.Neural network based on the input organization of an identified neuron signaling impending collision[J].Journal of Neurophysiology，1996，75（3）：967-985.
[16] YUE S，RIND F C.Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement[J].IEEE Transactions on Neural Networks，2006，17（3）：705-716.
[17] 张国鹏，张春.基于生物视觉的碰撞预警传感器[J].传感器与微系统，2016，35（3）：70-73.
ZHANG G P，ZHANG C.Collision warning sensor based on biological vision[J].Transducer and Microsystem Technologies，2016，35（3）：70-73.
[18] HU B，YUE S，ZHANG Z.A rotational motion perception neural network based on asymmetric spatiotemporal visual information processing[J].IEEE Transactions on Neural Networks and Learning Systems，2017，28（11）：2803-2821.
[19] HU B，ZHANG Z.Bio-plausible visual neural network for spatio-temporally spiral motion perception[J].Neurocomputing，2018，310：96-114.
[20] HU B，ZHANG Z，LI L.LGMD-based visual neural network for detection crowd escape behavior[C]//2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems，2018：772-778.
[21] JAYACHANDRAN D，OBEROI A，SEBASTIAN A，et al.A low-power biomimetic collision detector based on an in-memory molybdenum disulfide photodetector[J].Nature Electronics，2020，3（10）：646-655.
[22] HU B，ZHANG Z.Bio-inspired visual neural network on spatio-temporal depth rotation perception[J].Neural Computing and Applications，2021，33（16）：10351-10370.
[23] ZHAO J，WANG H，BELLOTTO N，et al.Enhancing LGMD’s looming selectivity for UAV with spatial-temporal distributed presynaptic connections[J].IEEE Transactions on Neural Networks and Learning Systems，2021.DOI：10.
1109/TNNLS.2021.3106946.
[24] 胡滨.基于蝗虫视觉神经的运动模式识别研究及应用[D].贵州：贵州大学，2019.
HU B.Research and application on motion pattern recognition based on locust vision neural systems[D].Guizhou：Guizhou University，2019.
[25] YUE S，RIND F C.A synthetic vision system using directionally selective motion detectors to recognize collision[J].Artificial Life，2007，13（2）：93-122.
[26] JOHANSSON A，HELBING D，AL-ABIDEEN H Z，et al.From crowd dynamics to crowd safety：a video-based analysis[J].Advances in Complex Systems，2008，11（4）：497-527.
[27] FELICIANI C，ZURIGUEL I，GARCIMARTíN A，et al.Systematic experimental investigation of the obstacle effect during non-competitive and extremely competitive evacuations[J].Scientific Reports，2020，10（1）：1-20.
[28] KHANI M H，GOLLISCH T.Linear and nonlinear chromatic integration in the mouse retina[J].Nature Communications，2021，12：1900.
[29] HéNAFF O J，BAI Y，CHARLTON J A，et al.Primary visual cortex straightens natural video trajectories[J].Nature Communications，2021，12：5982.
[30] ZHANG A J，WU S M.Antagonistic surround responses in different cones are mediated by feedback synapses from different horizontal cells[J].Vision Research，2021，186：13-22.
[31] WANG H，PENG J，YUE S.A directionally selective small target motion detecting visual neural network in cluttered backgrounds[J].IEEE Transactions on Cybernetics，2018，50（4）：1541-1555.
[32] ROSE O，JOHNSON J，WANG B，et al.Visual prototypes in the ventral stream are attuned to complexity and gaze behavior[J].Nature Communications，2021，12（1）：1-16.
[33] TAHERKHANI A，BELATRECHE A，LI Y，et al.A review of learning in biologically plausible spiking neural networks[J].Neural Networks，2020，122：253-272.
[34] ALLAIN P，COURTY N，CORPETTI T.AGORASET：a dataset for crowd video analysis[C]//1st ICPR International Workshop on Pattern Recognition and Crowd Analysis，2012：1-6.
[35] FERRYMAN J，SHAHROKNI A.Pets2009：dataset and challenge[C]//2009 12th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance，2009：1-6.
[36] CHAN A B，VASCONCELOS N.Modeling，clustering，and segmenting video with mixtures of dynamic textures[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2008，30（5）：909-926.
[37] HASSNER T，ITCHER Y，KLIPER-GROSS O.Violent flows：real-time detection of violent crowd behavior[C]//2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops，2012：1-6.
[38] IZHIKEVICH E M.Which model to use for cortical spiking neurons?[J].IEEE Transactions on Neural Networks，2004，15（5）：1063-1070.