基于可见光-热红外视觉监控的车间工人跌倒检测算法  

Fall detection for industrial workers using RGB and thermal infrared measurements

作　　者：王鑫[1] 刘晓楠 高焕兵[2,3] 曾子铭 张吟龙 WANG Xin;LIU Xiao-nan;GAO Huan-bing;ZENG Zi-ming;ZHANG Yin-long(College of Information and Control Engineering,Shenyang Jianzhu University,Shenyang 110168,China;School of Information and Electrical Engineering,Shandong Jianzhu University,Jinan 250101,China;Key Laboratory of Intelligent Buildings Technology,Shandong Jianzhu University,Jinan 250101,China;School of Automotive and Transportation Engineering,Shenzhen Polytechnic,Shenzhen 518055,China;Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110169,China)

机构地区：[1]沈阳建筑大学电气与控制工程学院,沈阳110168 [2]山东建筑大学电气工程学院,济南250101 [3]山东建筑大学山东省智能建筑技术重点实验室,济南250101 [4]深圳职业技术学院汽车与交通学院,广东深圳518055 [5]中国科学院沈阳自动化研究所,沈阳110169

出　　处：《控制与决策》2024年第4期1142-1150,共9页Control and Decision

基　　金：国家自然科学基金项目(62273332);中国科学院青年创新促进会会员项目(2022201);山东省智能建筑技术重点实验室开放课题项目(SDIBT202003);沈阳市科技计划项目(22-322-3-36)。

摘　　要：为了解决工厂车间视觉监控存在噪声干扰、光线变化、目标遮挡等问题,提出一种基于多模态视觉监控的工人跌倒检测算法.首先,采用热像仪和可见光相机获取车间内全天候监控图像,结合自适应滤波模型对图像进行降噪处理,以抑制环境噪声对监控图像的干扰;然后,构建一种改进的人体姿态特征提取网络,通过融合串联时间帧合并模块和位姿残差模块,以简化目标检测的特征图尺度,实现监控图像中工人区域被部分遮挡时姿态的实时、可靠预测;最后,设计人体轴线倾角、人体外接矩形框长宽比以及双膝盖点移动速度作为工人跌倒判别性特征,进而实现车间内工人的跌倒判别.在自建数据集和公开数据集上对所提出方法进行验证,实验结果表明,所提出算法的跌倒检测精度分别为95.6%和96.3%,与对比算法相比具有更好的准确性和实时性.Because of the problems of noise interference,illumination changes,and target occlusion of the visual monitoring in the factory,the existing fall detection algorithms have weak anti-noise ability,high lighting requirements,and poor target detection effect.It is intractable for the state-of-the-art visual surveillance methods to be reliably applied to all-weather factory workshop worker safety monitoring scenarios.Therefore,this paper presents a novel human fall detection method based on multimodal visual monitoring.Firstly,a thermal imager and a visible light camera are used to obtain the monitoring images in the workshop,and an adaptive median filter model is proposed to denoise the images and to suppress the interference of environmental noise on the monitoring images.Secondly,an improved lightweight convolutional neural network is used to extract the worker skeleton and joint sequence,and a time frame merging module and a pose residual fusion module are designed,so that the network can ensure that the worker pose occluded can be detected through the temporal correlation of adjacent frames.Finally,the inclination of the human body axis,the aspect ratio of the human body circumscribed rectangular frame and the moving speed of the double knee points are designed as the discriminative features of the worker fall.The proposed method has been verified on the collected dataset and public dataset.The experimental results show that the fall detection accuracy of the proposed method is 95.6% and 96.3%,respectively.Compared with the traditional methods,it has better accuracy and real-time performance and can be applied to worker fall detection in the factory workshop.

关 键 词：多模态 跌倒检测 轻量化卷积 时间帧合并 位姿残差融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]