基于卷积神经网络人体行为识别的院前急救措施研究  

Research on first aid measures based on convolutional neural network recognition human actions

作　　者：于清[1] 姜佩京 王耀国 王智悦 Yu Qing;Jiang Peijing;Wang Yaoguo;Wang Zhiyue(School of Information Science and Engineering,Xinjiang University,Urumqi 830046,Xinjiang Uygur Autonomous Region,China;School of Software,Xinjiang University,Urumqi 830091,Xinjiang Uygur Autonomous Region,China;Information Center,People's Hospital of Xinjiang Uygur Autonomous Region,Urumqi 830001,Xinjiang Uygur Autonomous Region,China)

机构地区：[1]新疆大学信息科学与工程学院,乌鲁木齐830046 [2]新疆大学软件学院,乌鲁木齐830091 [3]新疆自治区人民医院信息中心,乌鲁木齐830001

出　　处：《中华危重病急救医学》2020年第11期1385-1387,共3页Chinese Critical Care Medicine

基　　金：国家自然科学基金(61562082,U1603262)。

摘　　要：目的探讨基于卷积神经网络(CNN)的人体行为识别在新一代院前急救中的应用。方法从蒙特利尔跌倒视频数据集获取60份视频,按5∶1比例分为模型训练数据和评价测试数据。①数据模型训练:利用奇异值分解对图片进行清晰化处理,通过目标检测与傅里叶变换识别图片中人体的目标边界,将人体曲线描绘出来;利用OpenCv计算机视觉和机器学习软件库人体姿态估计将人体的重要部位(如臀部、膝盖)标出,计算重要部位连线与水平方向的夹角及检测框架的长宽比例,识别人体是否具有异常行为。②评价测试:从模型训练数据集中随机提取6个视频,每个视频抽取10个1帧,将每帧看成一张图片,对每帧进行CNN行为识别,计算正常行为和异常行为的识别率。结果数据模型训练过程中,对每帧进行人为的标签化,训练CNN人体行为识别模型。评测结果显示,正常行为识别率为(90.33±3.03)%,异常行为识别率为(87.74±2.88)%。结论在路人发生危险行为时,通过CNN识别人体行为可判断其是否处于危急状态,并及时发出预警,对院前急救起到至关重要的作用。Objective To explore the application of human behavior recognition based on convolutional neural network(CNN)in the new generation of pre-hospital first aid.Methods Sixty videos were obtained from the Montreal Falling Video Data base,and divided into model training data and evaluation test data at a ratio of 5∶1.①Data model training:singular value decomposition was used to clarify the picture,the target boundary of the human body in the picture was identified through target detection and Fourier transform,then the human body curve was described;OpenCv computer vision and machine learning software library to estimate the body pose were used to mark the important parts of the human body(such as hips,knees),the angle between the line of important parts and the horizontal direction and the length and width ratio of the detection frame were calculated,and whether the human body had abnormal behavior was identified.②Evaluation test:6 videos were randomly extracted from the model training data set,10 frame were extracted from each video,each frame was treated as one picture,CNN behavior recognition was used on each frame,and calculated the recognition rate between normal behavior and abnormal behavior.Results In the process of data model training,each frame was artificially labeled to train the CNN human behavior recognition model.The evaluation results showed that the recognition rate of normal behavior was(90.33±3.03)%,and the recognition rate of abnormal behavior was(87.74±2.88)%.Conclusion When passers-by have dangerous behaviors,the identification of human behaviors through CNN can determine whether they are in a critical state,and issue early warning in time,which plays a vital role in pre-hospital first aid.

关 键 词：院前急救 人体行为识别 图像处理 

分 类 号：R459.7[医药卫生—急诊医学] TP391.41[医药卫生—治疗学] TP183[医药卫生—临床医学]