针对经典卷积神经网络吸烟检测算法存在速度慢、误检率和硬件占有率高等问题,提出一种基于更快速区域卷积网络(faster region with convolution neural networks,Faster R-CNN)的吸烟快速检测算法。检测人脸并将检测到的人脸图像作为烟...针对经典卷积神经网络吸烟检测算法存在速度慢、误检率和硬件占有率高等问题,提出一种基于更快速区域卷积网络(faster region with convolution neural networks,Faster R-CNN)的吸烟快速检测算法。检测人脸并将检测到的人脸图像作为烟支检测区域,以缩小目标检测区域,并过滤掉与烟支相似的目标。使用图像分割方法对人脸区域进行烟支初检,初步判断有无烟支存在。利用Faster R-CNN算法对初步判断可能存在烟支的图像进行烟支目标检测并判断是否存在吸烟行为。实验结果表明,与经典的Faster R-CNN吸烟检测算法相比,提出算法的误检率、检测时间和CPU占用率有了明显降低。展开更多
In order to alleviate the shortcomings of most blind deconvolution algorithms,this paper proposes an improved fast algorithm for blind deconvolution based on decorrelation technique and broadband block matrix.Althougt...In order to alleviate the shortcomings of most blind deconvolution algorithms,this paper proposes an improved fast algorithm for blind deconvolution based on decorrelation technique and broadband block matrix.Althougth the original algorithm can overcome the shortcomings of current blind deconvolution algorithms,it has a constraint that the number of the source signals must be less than that of the channels.The improved algorithm deletes this constraint by using decorrelation technique.Besides,the improved algorithm raises the separation speed in terms of improving the computing methods of the output signal matrix.Simulation results demonstrate the validation and fast separation of the improved algorithm.展开更多
文摘针对经典卷积神经网络吸烟检测算法存在速度慢、误检率和硬件占有率高等问题,提出一种基于更快速区域卷积网络(faster region with convolution neural networks,Faster R-CNN)的吸烟快速检测算法。检测人脸并将检测到的人脸图像作为烟支检测区域,以缩小目标检测区域,并过滤掉与烟支相似的目标。使用图像分割方法对人脸区域进行烟支初检,初步判断有无烟支存在。利用Faster R-CNN算法对初步判断可能存在烟支的图像进行烟支目标检测并判断是否存在吸烟行为。实验结果表明,与经典的Faster R-CNN吸烟检测算法相比,提出算法的误检率、检测时间和CPU占用率有了明显降低。
基金Natural Science Fund of Anhui Province of China (050420101)
文摘In order to alleviate the shortcomings of most blind deconvolution algorithms,this paper proposes an improved fast algorithm for blind deconvolution based on decorrelation technique and broadband block matrix.Althougth the original algorithm can overcome the shortcomings of current blind deconvolution algorithms,it has a constraint that the number of the source signals must be less than that of the channels.The improved algorithm deletes this constraint by using decorrelation technique.Besides,the improved algorithm raises the separation speed in terms of improving the computing methods of the output signal matrix.Simulation results demonstrate the validation and fast separation of the improved algorithm.
