基于改进深度学习模型C-GRBM的人体行为识别OA北大核心CSCDCSTPCD
Human action recognition based on improved depth learning model C-GRBM
为了提高复杂视频中人体行为识别的性能,在Gate限制玻尔兹曼机(gate restricted boltzmann machine,GRBM)模型基础上提出一种结合卷积神经网络的Convolutional-GRBM(C-GRBM)模型.利用视频图像平稳性的特点,通过不同的卷积核提取可见层不同的特征,提高模型局部特征提取能力,进而得到更好的人体行为识别率;加入池化操作,对卷积层输出的不同位置上的特征进行聚合统计,降低卷积层输出特征量的维度,从而解决…查看全部>>
A model of convolutional-gate restricted Boltzmann machine ( C-GRBM) combined with a convolutional neural network, which was based on the GRBM model, is proposed herein to improve the performance of human ac-tion recognition in complicated videos.First, by taking advantage of the smoothness of video frames, and extracting different visible layer characteristics using different convolution kernels, the ability of extracting local model features and the succes…查看全部>>
毕晓君;冯雪赟
哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001
信息技术与安全科学
深度学习人体行为识别Gate限制玻尔兹曼机卷积神经网络支持向量机
deep learninghuman behavior recognitiongate restricted Boltzmann machine( GRBM)convolutional neural networksupport vector machine
《哈尔滨工程大学学报》 2018 (1)
156-162,7
评论