Scene transformation for detector adaptation

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	Scene transformation for detector adaptation
	Liu, Liwei 1; Xing, Junliang2 ; Duan, Genquan 1; Ai, Haizhou 1; Junliang Xing
发表期刊	PATTERN RECOGNITION LETTERS
	2014-01-15
卷号	36 页码:154-160
文章类型	Article
摘要	This paper focuses on detecting vehicles in different target scenes with the same pre-trained detector which is very challenging due to view variations. To address this problem, we propose a novel approach for detection adaptation based on scene transformation, which contributes in both view transformation and automatic parameter estimation. Instead of modifying the pre-trained detectors, we transform scenes into frontal/rear view handling with pitch and yaw view variations. Without human interactions but only some general prior knowledge, the transformation parameters are automatically initialized, and then online optimized with spatial temporal voting, which guarantees that the transformation matches the pre-trained detector. Since there is no need of labeling new samples and manual camera calibration, our approach can considerably reduce manual interactions. Experiments on challenging real-world videos demonstrate that our approach achieves significant improvements over the pre-trained detector, and it is even comparable to the performance of the detector trained on fully labeled sequences. (C) 2013 Elsevier B.V. All rights reserved.
关键词	Vehicle Detection Detector Adaptation Scene Transformation Automatic Parameter Estimation
WOS标题词	Science & Technology ; Technology
关键词[WOS]	FACE DETECTION
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000329145400019
引用统计	被引频次：1[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/173211/3282
专题	多模态人工智能系统全国重点实验室_视频内容安全
通讯作者	Junliang Xing
作者单位	1.Tsinghua Univ, Comp Sci & Technol Dept, Beijing 100084, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Liu, Liwei,Xing, Junliang,Duan, Genquan,et al. Scene transformation for detector adaptation[J]. PATTERN RECOGNITION LETTERS,2014,36:154-160.
APA	Liu, Liwei,Xing, Junliang,Duan, Genquan,Ai, Haizhou,&Junliang Xing.(2014).Scene transformation for detector adaptation.PATTERN RECOGNITION LETTERS,36,154-160.
MLA	Liu, Liwei,et al."Scene transformation for detector adaptation".PATTERN RECOGNITION LETTERS 36(2014):154-160.

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
PRL14DetectorAdaptat（2323KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载