摘要
针对乘客在搭乘扶梯时的危险行为难以被实时准确检测的问题,提出了一种基于视频监控的手扶电梯乘客异常行为识别算法。首先,使用YOLOv3对图像中乘客的位置进行检测;接着,使用MobileNetv2作为基网络,结合反卷积层对检测出来的乘客进行人体骨架提取;然后,使用骨架距离作为跟踪依据,采用匈牙利匹配算法对相邻帧间的人体骨架进行匹配,实现视频中乘客的ID号分配;最后,通过图卷积神经网络对乘客关键点信息进行异常行为识别。在GTX1080GPU上的实验结果表明,文中提出的识别算法的处理速度能达到15 f/s,异常行为识别准确率达94.3%,能够实时准确地识别手扶电梯上乘客的异常行为。
Aiming at the problem that dangerous behavior of passengers on the escalator is difficult to be accurately detected in real time,an algorithm for identifying abnormal behavior of escalator passengers based on video surveillance was proposed.Firstly,YOLOv3 was used to detect the position of the passenger in the image.Secondly,MobileNetv2 was used as the base network,which was combined with the deconvolution layer to extract the human skeleton of the detected passenger.Thirdly,the Hungarian assignment algorithm based on skeleton distance was used to realize the allocation of passenger ID numbers in the video.Finally,with keypoints as the input,the graph convolutional neural network was used to recognize the abnormal behavior of passenger.The experimental results on the GTX1080GPU show that the proposed recognition algorithm can achieve a processing speed of 15 f/s and an abnormal behavior recognition accuracy rate of 94.3%,which can accurately recognize the abnormal behavior of passengers on the escalator in real time.
作者
杜启亮
黄理广
田联房
黄迪臻
靳守杰
李淼
DU Qiliang;HUANG Liguang;TIAN Lianfang;HUANG Dizhen;JIN Shoujie;LI Miao(School of Automation Science and Engineering,South China University of Technology,Guangzhou 510640,Guangdong,China;Key Laboratory of Autonomous Systems and Network Control of the Ministry of Education,Guangzhou 510640,Guangdong,China;Guangzhou Metro Group Co.,Ltd.,Guangzhou 510335,Guangdong,China;Hitachi Elevator(Guangzhou)
出处
《华南理工大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2020年第8期10-21,共12页
Journal of South China University of Technology(Natural Science Edition)
基金
国家科技部海防公益类项目(201505002)
广东省科技计划项目(2016B090912001)
广东省重点领域研发计划“新一代人工智能”重大科技专项(2018B010109001)
广东省重点领域研发计划“精准农业”重点专项(2019B020214001)
广州市产业技术重大攻关计划(2019-01-01-12-1006-0001)
华南理工大学中央高校基本科研业务费专项资金资助项目(2018KZ05)
华南理工大学研究生教育改革项目(zysk2018005)。
关键词
手扶电梯
深度学习
卷积神经网络
行人检测
人体关键点提取
匈牙利匹配算法
escalator
deep learning
convolutional neural networks
pedestrian detection
pose estimation
Hungarian assignment algorithm