Technological advances in computer science and their application in our daily life allow us to improve our understanding of problems and solve them effectively.A system design to detect people with fever and determine...Technological advances in computer science and their application in our daily life allow us to improve our understanding of problems and solve them effectively.A system design to detect people with fever and determine highrisk areas using infrared thermography and big data is presented.In order to detect people with fever,face detection algorithms of Viola-Jones and Kanade-Lucas are investigated,and comparison between them is presented using a training set of 406 thermal images and a test set of 2072 thermal images.Thermography analysis is performed on detected faces to obtain the temperature level on Celsius scale.With this information a sample database is created.To perform big data experimental analysis,Power Bi tool is used to determine the high-risk area.The experimental results show that Viola-Jones algorithm has a higher performance recognizing faces of thermal images than KanadeLucas,having a high detection rate,less false-positives rate and false-negatives rate.展开更多
针对传统遥感图像数据分析算法存在鲁棒性较差、适应度与计算效率均偏低的问题,文中基于YOLOv3提出了一种轻量化的遥感图像数据分析算法。该算法使用YOLOv3作为神经网络模型的框架,并将内部的Darknet-53多尺度卷积作为主网络。为了减小...针对传统遥感图像数据分析算法存在鲁棒性较差、适应度与计算效率均偏低的问题,文中基于YOLOv3提出了一种轻量化的遥感图像数据分析算法。该算法使用YOLOv3作为神经网络模型的框架,并将内部的Darknet-53多尺度卷积作为主网络。为了减小主网的冗余度,通过SE-Net模型连接网络的深层与浅层卷积,在轻量化的同时也增强了模型的深度特征提取能力。同时,根据改进后网络的权重输出结果,采用剪枝算法对卷积核进行简化,进而完成了模型的轻量化。在实验测试中,轻量化后的模型可显著提升FPS(Frames Per Second)值,且算法的mAP指标为93.25%,在对比算法中为最优,表明了算法模型的有效性及其性能的优越性。展开更多
文摘Technological advances in computer science and their application in our daily life allow us to improve our understanding of problems and solve them effectively.A system design to detect people with fever and determine highrisk areas using infrared thermography and big data is presented.In order to detect people with fever,face detection algorithms of Viola-Jones and Kanade-Lucas are investigated,and comparison between them is presented using a training set of 406 thermal images and a test set of 2072 thermal images.Thermography analysis is performed on detected faces to obtain the temperature level on Celsius scale.With this information a sample database is created.To perform big data experimental analysis,Power Bi tool is used to determine the high-risk area.The experimental results show that Viola-Jones algorithm has a higher performance recognizing faces of thermal images than KanadeLucas,having a high detection rate,less false-positives rate and false-negatives rate.
文摘针对传统遥感图像数据分析算法存在鲁棒性较差、适应度与计算效率均偏低的问题,文中基于YOLOv3提出了一种轻量化的遥感图像数据分析算法。该算法使用YOLOv3作为神经网络模型的框架,并将内部的Darknet-53多尺度卷积作为主网络。为了减小主网的冗余度,通过SE-Net模型连接网络的深层与浅层卷积,在轻量化的同时也增强了模型的深度特征提取能力。同时,根据改进后网络的权重输出结果,采用剪枝算法对卷积核进行简化,进而完成了模型的轻量化。在实验测试中,轻量化后的模型可显著提升FPS(Frames Per Second)值,且算法的mAP指标为93.25%,在对比算法中为最优,表明了算法模型的有效性及其性能的优越性。
