基于多尺度卷积神经网络的人群聚集异常预测

计算机工程与科学 ›› 2020, Vol. 42 ›› Issue (12): 2223-2232.

基于多尺度卷积神经网络的人群聚集异常预测

罗凡波1,2，王平1，徐桂菲1，雷勇军3，范烊1

(1.西华大学电气与电子信息学院，四川成都 610039；2.国网四川省电力公司达州供电公司，四川达州 635000；

3.国网四川省电力公司资阳供电公司，四川资阳 641300)

收稿日期:2019-09-23 修回日期:2020-03-05 接受日期:2020-12-25 出版日期:2020-12-25 发布日期:2021-01-05
基金资助:
教育部“春晖计划”（Z2012029）;四川省人工智能重点实验室基金（2016RYJ07）;西华大学研究生创新基金（ycjj2018025）

Prediction of crowd massing abnormity based on multi-scale convolutional neural network

LUO Fan-bo1,2,WANG Ping1,XU Gui-fei1,LEI Yong-jun3,FAN Yang1

(1.College of Electrical & Electronic Information，Xihua University，Chengdu 610039;

2.State Grid Sichuan Electric Power Company Dazhou Power Supply Company,Dazhou 635000;

3.State Grid Sichuan Electric Power Company Ziyang Power Supply Company，Ziyang 641300,China)

Received:2019-09-23 Revised:2020-03-05 Accepted:2020-12-25 Online:2020-12-25 Published:2021-01-05

摘要/Abstract

摘要： 已有的公共场所人群聚集异常行为检测方法较少，且大多检测方法都是在人群已经异常聚集后再进行检测，检测准确率不高，时效性不够好。提出一种基于多尺度卷积神经网络（MCNN）的人群聚集异常预测模型。首先，通过多尺度卷积神经网络训练一个人群计数模型，用训练好的模型对人群聚集异常视频进行测试；然后在测试中完成人群人数统计与人群头部坐标点获取，进而计算人群密度、人群距离势能与人群分布熵；最后将得到的3种人群运动状态特征值利用PSO-ELM进行训练，得到预测模型，通过特征数据的变化，完成人群聚集行为的预测。实验结果表明，与现有算法相比，该模型能有效实现人群聚集异常行为的预警与检测，时效性强，为采取相应应急措施提供了更多时间，预测准确率达到了9717%。

关键词: 聚集异常预测, MCNN, 人群运动状态, 人群密度, 人群距离势能, 人群分布熵

Abstract: There are few methods for detecting abnormal behaviors of crowd massing in public places, and they have the following problem: most of the detection methods are performed after the crowd has gathered abnormally, and the detection accuracy is not high, and the timeliness is not good enough. Therefore, a crowd massing anomaly prediction model based on
multi-scale convolutional neural network (MCNN) is proposed. Firstly, a crowd counting model is built through MCNN for testing the video of crowd massing anomaly. In the test, the number of crowd and the coordinate points of their heads are acquired. Secondly, the crowd density, crowd distance potential energy and crowd distribution entropy are calculated. Finally, the predictive model is built through the eigenvalues of three crowd motion state by PSO-ELM. Through the change of characteristic data, the prediction is completed. The experimental results show that, compared with the existing algorithms, the proposed algorithm can effectively achieve the early warning and detection of abnormal behaviors in crowd massing. With a prediction accuracy rate of 97.17%, it’s more time-sensitive and provides more time for taking corresponding emergency measures.

Key words: prediction of crowd massing abnormity, multi-scale convolutional neural network, crowd motion state, crowd density, crowd distance potential energy, crowd distribution entropy

罗凡波, 王平, 徐桂菲, 雷勇军, 范烊. 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 Fan-bo, WANG Ping, XU Gui-fei, LEI Yong-jun, FAN Yang. Prediction of crowd massing abnormity based on multi-scale convolutional neural network[J]. Computer Engineering & Science, 2020, 42(12): 2223-2232.