A parallel vision approach to scene-specific pedestrian detection
Zhang, Wenwen1,2; Wang, Kunfeng2; Liu, Yating2,3; Lu, Yue2,3; Wang, Fei-Yue2
发表期刊NEUROCOMPUTING
ISSN0925-2312
2020-06-21
卷号394页码:114-126
摘要

In recent years, with the development of computing power and deep learning algorithms, pedestrian detection has made great progress. Nevertheless, once a detection model trained on generic datasets (such as PASCAL VOC and MS COCO) is applied to a specific scene, its precision is limited by the distribution gap between the generic data and the specific scene data. It is difficult to train the model for a specific scene, due to the lack of labeled data from that scene. Even though we manage to get some labeled data from a specific scene, the changing environmental conditions make the pre-trained model perform bad. In light of these issues, we propose a parallel vision approach to scene-specific pedestrian detection. Given an object detection model, it is trained via two sequential stages: (1) the model is pre-trained on augmented-reality data, to address the lack of scene-specific training data; (2) the pre-trained model is incrementally optimized with newly synthesized data as the specific scene evolves over time. On publicly available datasets, our approach leads to higher precision than the models trained on generic data. To tackle the dynamically changing scene, we further evaluate our approach on the webcam data collected from Church Street Market Place, and the results are also encouraging. (C) 2019 Elsevier B.V. All rights reserved.

关键词Pedestrian detection Specific scene Synthetic data Video surveillance Parallel vision
DOI10.1016/j.neucom.2019.03.095
关键词[WOS]CAMERA NETWORKS
收录类别SCI
语种英语
资助项目National Natural Science Foundation of China[61533019] ; National Natural Science Foundation of China[U1811463]
项目资助者National Natural Science Foundation of China
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000531730600012
出版者ELSEVIER
七大方向——子方向分类人工智能+交通
引用统计
被引频次:15[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/39437
专题复杂系统管理与控制国家重点实验室_平行智能技术与系统团队
通讯作者Wang, Kunfeng
作者单位1.Xi An Jiao Tong Univ, Sch Software Engn, Xian 710049, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Zhang, Wenwen,Wang, Kunfeng,Liu, Yating,et al. A parallel vision approach to scene-specific pedestrian detection[J]. NEUROCOMPUTING,2020,394:114-126.
APA Zhang, Wenwen,Wang, Kunfeng,Liu, Yating,Lu, Yue,&Wang, Fei-Yue.(2020).A parallel vision approach to scene-specific pedestrian detection.NEUROCOMPUTING,394,114-126.
MLA Zhang, Wenwen,et al."A parallel vision approach to scene-specific pedestrian detection".NEUROCOMPUTING 394(2020):114-126.
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
1-s2.0-S092523121930(4090KB)期刊论文作者接受稿开放获取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
[Zhang, Wenwen]的文章
[Wang, Kunfeng]的文章
[Liu, Yating]的文章
百度学术
百度学术中相似的文章
[Zhang, Wenwen]的文章
[Wang, Kunfeng]的文章
[Liu, Yating]的文章
必应学术
必应学术中相似的文章
[Zhang, Wenwen]的文章
[Wang, Kunfeng]的文章
[Liu, Yating]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 1-s2.0-S0925231219308859-main.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。