针对传统高斯肤色模型在肤色和光照变化较大情况下不能有效提取肤色区域的问题,提出一种改进的高斯肤色模型,并将其应用于人脸检测中。模型参数采用一种自适应更新的参数选择方法,通过对相似度人脸和灰度人脸在对应像素点加权相乘的方式...针对传统高斯肤色模型在肤色和光照变化较大情况下不能有效提取肤色区域的问题,提出一种改进的高斯肤色模型,并将其应用于人脸检测中。模型参数采用一种自适应更新的参数选择方法,通过对相似度人脸和灰度人脸在对应像素点加权相乘的方式,得到将肤色相似度信息和灰度分布信息有效结合的人脸肤色模型,并结合Adaboost算法设计了人脸检测方法。在FERET(facial recognition technology database)、LFW(labeled faces in the wild)、GTFD(Georgia Tech face database)和多人脸图库上的实验结果表明,该模型的肤色提取正确率比传统高斯肤色模型提高了27.1%,提出的人脸检测方法的检测率比Adaboost算法提高了5.5%。展开更多
We applied the model of American Meteorological Society-Environmental Protection Agency Regulatory Model（AERMOD） as a tool for the analysis of nitrogen dioxide（NO2） emissions from a cement complex as a part of the...We applied the model of American Meteorological Society-Environmental Protection Agency Regulatory Model（AERMOD） as a tool for the analysis of nitrogen dioxide（NO2） emissions from a cement complex as a part of the environmental impact assessment.The dispersion of NO2 from four cement plants within the selected cement complex were investigated both by measurement and AERMOD simulation in dry and wet seasons.Simulated values of NO2 emissions were compared with those obtained during a 7-day continuous measurement campaign at 12 receptors.It was predicted that NO2 concentration peaks were found more within 1 to 5 km,where the measurement and simulation were in good agreement,than at the receptors 5 km further away from the reference point.The QuantileQuantile plots of NO2 concentrations in dry season were mostly fitted to the middle line compared to those in wet season.This can be attributed to high NO2 wet deposition.The results show that for both the measurement and the simulation using the AERMOD,NO2 concentrations do not exceed the NO2 concentration limit set by the National Ambient Air Quality Standards（NAAQS） of Thailand.This indicates that NO2 emissions from the cement complex have no significant impact on nearby communities.It can be concluded that the AERMOD can provide useful information to identify high pollution impact areas for the EIA guidelines.展开更多
文摘针对传统高斯肤色模型在肤色和光照变化较大情况下不能有效提取肤色区域的问题,提出一种改进的高斯肤色模型,并将其应用于人脸检测中。模型参数采用一种自适应更新的参数选择方法,通过对相似度人脸和灰度人脸在对应像素点加权相乘的方式,得到将肤色相似度信息和灰度分布信息有效结合的人脸肤色模型,并结合Adaboost算法设计了人脸检测方法。在FERET(facial recognition technology database)、LFW(labeled faces in the wild)、GTFD(Georgia Tech face database)和多人脸图库上的实验结果表明,该模型的肤色提取正确率比传统高斯肤色模型提高了27.1%,提出的人脸检测方法的检测率比Adaboost算法提高了5.5%。
基金the Royal Golden Jubilee Ph.D program (IUG50K0021)Thailand Research Fund (TRF) for the financial support
文摘We applied the model of American Meteorological Society-Environmental Protection Agency Regulatory Model（AERMOD） as a tool for the analysis of nitrogen dioxide（NO2） emissions from a cement complex as a part of the environmental impact assessment.The dispersion of NO2 from four cement plants within the selected cement complex were investigated both by measurement and AERMOD simulation in dry and wet seasons.Simulated values of NO2 emissions were compared with those obtained during a 7-day continuous measurement campaign at 12 receptors.It was predicted that NO2 concentration peaks were found more within 1 to 5 km,where the measurement and simulation were in good agreement,than at the receptors 5 km further away from the reference point.The QuantileQuantile plots of NO2 concentrations in dry season were mostly fitted to the middle line compared to those in wet season.This can be attributed to high NO2 wet deposition.The results show that for both the measurement and the simulation using the AERMOD,NO2 concentrations do not exceed the NO2 concentration limit set by the National Ambient Air Quality Standards（NAAQS） of Thailand.This indicates that NO2 emissions from the cement complex have no significant impact on nearby communities.It can be concluded that the AERMOD can provide useful information to identify high pollution impact areas for the EIA guidelines.
