|
|||||
|
|
| 基于并行通道级联网络的鲁棒行人检测 | |
| 引用本文： | 何姣姣,张永平,姚拓中,刘肯,肖江剑.基于并行通道级联网络的鲁棒行人检测[J].模式识别与人工智能,2018,31(12):1134-1142. |
| 作者姓名： | 何姣姣 张永平 姚拓中 刘肯 肖江剑 |
| 作者单位： | 1.长安大学 电子与控制工程学院 西安 710064 2.宁波工程学院 电子与信息工程学院 宁波 315016 3.长安大学 信息工程学院 西安 710064 4.中国科学院宁波材料技术与工程研究所 先进制造所计算机视觉 宁波 315201 |
| 基金项目： | 国家自然科学基金项目(No.61771270)、浙江省自然科学基金项目(No.2017A610109,LQ15F020004)、浙江省重点研发计划项目(2018C01086)、国家关键技术研发计划项目(No. 2015BAF14B01)、宁波市自然科学基金项目(2018A610160)资助 |
| 摘 要： | 针对广角视场下远处行人分辨率较低、存在不同程度的畸变的问题,文中提出基于并行通道级联网络的鲁棒行人检测算法.以更快的区域卷积神经网络(Faster RCNN)为基础,引入差分图作为弱监督信息,再引入基于通道级联网络(CCN).然后设计并行CCN,将差分图和原图同时作为并行网络输入,融合更丰富的图像特征.最后在候选区域建议网络中,结合行人尺度在图像中分布的特点,聚类确定符合行人特点的搜索框.实验表明,文中算法在广角视场存在畸变情况下更有利于小尺寸行人检测. |
| 关 键 词： | 并行级联通道网络 小尺寸行人检测 广角监控 区域候选聚类 |
| 收稿时间： | 2018-08-13 |
Robust Pedestrian Detection Based on Parallel Channel Cascade Network |
|
| HE Jiaojiao,ZHANG Yongping,YAO Tuozhong,LIU Ken,XIAO Jiangjian.Robust Pedestrian Detection Based on Parallel Channel Cascade Network[J].Pattern Recognition and Artificial Intelligence,2018,31(12):1134-1142. | |
| Authors: | HE Jiaojiao ZHANG Yongping YAO Tuozhong LIU Ken XIAO Jiangjian |
| Affiliation: | 1.School of Electronic Control, Chang'an University, Xi'an 710064 2.School of Electronic and Information Engineering, Ningbo University of Techology, Ningbo 315016 3.School of Information Engineering, Chang'an University, Xi'an 710064 4.Advanced Manufacturing Institute Computer Vision Team, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo 315201 |
| Abstract: | In the wide-angle field with perspective distortion, the resolution of distant pedestrian is low and there is distortion in a broad range of scales. Aiming at these problems, a robust pedestrian detection algorithm based on parallel channel cascade network is proposed. Firstly, differential information is introduced as weak supervisory information. Secondly, a new feature extraction network, channel cascade network(CCN), is proposed. On this basis, a parallel CCN is designed, and the difference map and the original map are utilized as its input. More abundant image features are fused. Finally, in the region proposal network, the distribution of pedestrians in the picture is characterized by clustering, and anchors meeting the pedestrian's characteristics are clustered. Experimental results show that the proposed algorithm is better than the standard Faster-RCNN algorithm and FPN algorithm for small-scale pedestrian detection in the presence of wide-angle field of view distortion. |
| Keywords: | Parallel Cascade Channel Network Small Size Pedestrian Detection Wide-Angle Monitoring Regional Candidate Clustering |
| 点击此处可从《模式识别与人工智能》浏览原始摘要信息 | |
| 点击此处可从《模式识别与人工智能》下载全文 | |
