CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Convolutional Neural Networks with Neural Cascade Classifier for Pedestrian Detection
Tong Bei(童贝); Fan Bin; Wu Fuchao; Tong B(童贝)
2016-10
会议名称全国模式识别学术会议(CCPR)
会议日期2016年11月
会议地点四川省成都市电子科技大学图书馆求实厅
摘要The combination of traditional methods (e.g., ACF) and Convolutional Neural Networks (CNNs) has achieved great success in pedestrian detection. Despite effectiveness, design of this method is intricate. In this paper, we present an end-to-end network based on Faster R-CNN and neural cascade classifier for pedestrian detection. Different from Faster R-CNN that only makes use of the last convolutional layer, we utilize features from multiple layers and feed them to a neural cascade classifier. Such an architecture favors more low-level features and implements a hard negative mining process in the network. Both of these two factors are important in pedestrian detection. The neural cascade classifier is jointly trained with the Faster R-CNN in our unifying network. The proposed network achieves comparable performance to the state-of-the-art on Caltech pedestrian dataset with a more concise framework and faster processing speed. Meanwhile, the detection result obtained by our method is tighter and more accurate.
关键词Convolutional Neural Network Cascade Classifier Faster R-cnn Pedestrian Detection
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14472
专题模式识别国家重点实验室_机器人视觉
通讯作者Tong B(童贝)
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Tong Bei,Fan Bin,Wu Fuchao,et al. Convolutional Neural Networks with Neural Cascade Classifier for Pedestrian Detection[C],2016.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
paper_45.pdf(1574KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Tong Bei(童贝)]的文章
[Fan Bin]的文章
[Wu Fuchao]的文章
百度学术
百度学术中相似的文章
[Tong Bei(童贝)]的文章
[Fan Bin]的文章
[Wu Fuchao]的文章
必应学术
必应学术中相似的文章
[Tong Bei(童贝)]的文章
[Fan Bin]的文章
[Wu Fuchao]的文章
相关权益政策
暂无数据
收藏/分享
文件名: paper_45.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。