A deep convolution neural network for object detection based | |
Yue Qi1,2,3; Ma Caiwen1; Ma Caiwen(马彩文) | |
刊名 | journal of harbin institute of technology |
2017 | |
卷号 | 49期号:5页码:159-164 |
关键词 | deep neural network elastic momentum target detection model optimization |
ISSN号 | 0367-6234 |
其他题名 | 指数弹性动量卷积神经网络及其在行人检测中的应用 |
通讯作者 | yue qi,yueqi6@163.com |
产权排序 | 1 |
英文摘要 | deep convolutional neural network(cnn) has too many parameters to initialize, and the usual random initialization method is easy to disappear of modified gradient and the problem of premature. the unsupervised pca learning method is used to obtain oriented initialization parameters. and the gradient descendent method with exponential flexible momentum for updating free parameters of the network is proposed on the basis of analyzing the error propagation of the network. image detection experiments are respectively carried out on pedestrian detection, and the results show that, compared with other artificial feature detection algorithms, this method can effectively improve target detection accuracy and the detection speed of this method is 20% faster than that of classical cnn; compared with homologous updating mechanism of other momentum, our method has faster convergence and smaller oscillation, and can improve the detection accuracy by 1.6%, 1.8% and 6.19% respectively in different depth models. |
学科主题 | computer science (provided by clarivate analytics) |
收录类别 | EI ; CSCD |
语种 | 中文 |
内容类型 | 期刊论文 |
源URL | [http://ir.opt.ac.cn/handle/181661/29183] |
专题 | 西安光学精密机械研究所_光电测量技术实验室 |
作者单位 | 1.Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710119, China 2.University of Chinese Academy of Sciences, Beijing 100039, China 3.Xi' an University of Posts and Telecomunications, Xi' an 710121, China |
推荐引用方式 GB/T 7714 | Yue Qi,Ma Caiwen,Ma Caiwen. A deep convolution neural network for object detection based[J]. journal of harbin institute of technology,2017,49(5):159-164. |
APA | Yue Qi,Ma Caiwen,&Ma Caiwen.(2017).A deep convolution neural network for object detection based.journal of harbin institute of technology,49(5),159-164. |
MLA | Yue Qi,et al."A deep convolution neural network for object detection based".journal of harbin institute of technology 49.5(2017):159-164. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论