Domain Adaptation for Pedestrian Detection Based on Prediction Consistency

Pedestrian detection is an active area of research in computer vision. It remains a quite challenging problem in many applications where many factors cause a mismatch between source dataset used to train the pedestrian detector and samples in the target scene. In this paper, we propose a novel domai...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Li-ping, Tang Huan-ling, An Zhi-yong
Format: Article
Language:English
Published: Wiley 2014-01-01
Series:The Scientific World Journal
Online Access:http://dx.doi.org/10.1155/2014/280382
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850176798170546176
author Yu Li-ping
Tang Huan-ling
An Zhi-yong
author_facet Yu Li-ping
Tang Huan-ling
An Zhi-yong
author_sort Yu Li-ping
collection DOAJ
description Pedestrian detection is an active area of research in computer vision. It remains a quite challenging problem in many applications where many factors cause a mismatch between source dataset used to train the pedestrian detector and samples in the target scene. In this paper, we propose a novel domain adaptation model for merging plentiful source domain samples with scared target domain samples to create a scene-specific pedestrian detector that performs as well as rich target domain simples are present. Our approach combines the boosting-based learning algorithm with an entropy-based transferability, which is derived from the prediction consistency with the source classifications, to selectively choose the samples showing positive transferability in source domains to the target domain. Experimental results show that our approach can improve the detection rate, especially with the insufficient labeled data in target scene.
format Article
id doaj-art-bd8cfa1cfcc14b93b38230778cfbd614
institution OA Journals
issn 2356-6140
1537-744X
language English
publishDate 2014-01-01
publisher Wiley
record_format Article
series The Scientific World Journal
spelling doaj-art-bd8cfa1cfcc14b93b38230778cfbd6142025-08-20T02:19:11ZengWileyThe Scientific World Journal2356-61401537-744X2014-01-01201410.1155/2014/280382280382Domain Adaptation for Pedestrian Detection Based on Prediction ConsistencyYu Li-ping0Tang Huan-ling1An Zhi-yong2Key Laboratory of Intelligent Information Processing, Universities of Shandong (Shandong Institute of Business and Technology), Yantai 264005, ChinaSchool of Computer Science and Technology, Shandong Institute of Business and Technology, Yantai 264005, ChinaKey Laboratory of Intelligent Information Processing, Universities of Shandong (Shandong Institute of Business and Technology), Yantai 264005, ChinaPedestrian detection is an active area of research in computer vision. It remains a quite challenging problem in many applications where many factors cause a mismatch between source dataset used to train the pedestrian detector and samples in the target scene. In this paper, we propose a novel domain adaptation model for merging plentiful source domain samples with scared target domain samples to create a scene-specific pedestrian detector that performs as well as rich target domain simples are present. Our approach combines the boosting-based learning algorithm with an entropy-based transferability, which is derived from the prediction consistency with the source classifications, to selectively choose the samples showing positive transferability in source domains to the target domain. Experimental results show that our approach can improve the detection rate, especially with the insufficient labeled data in target scene.http://dx.doi.org/10.1155/2014/280382
spellingShingle Yu Li-ping
Tang Huan-ling
An Zhi-yong
Domain Adaptation for Pedestrian Detection Based on Prediction Consistency
The Scientific World Journal
title Domain Adaptation for Pedestrian Detection Based on Prediction Consistency
title_full Domain Adaptation for Pedestrian Detection Based on Prediction Consistency
title_fullStr Domain Adaptation for Pedestrian Detection Based on Prediction Consistency
title_full_unstemmed Domain Adaptation for Pedestrian Detection Based on Prediction Consistency
title_short Domain Adaptation for Pedestrian Detection Based on Prediction Consistency
title_sort domain adaptation for pedestrian detection based on prediction consistency
url http://dx.doi.org/10.1155/2014/280382
work_keys_str_mv AT yuliping domainadaptationforpedestriandetectionbasedonpredictionconsistency
AT tanghuanling domainadaptationforpedestriandetectionbasedonpredictionconsistency
AT anzhiyong domainadaptationforpedestriandetectionbasedonpredictionconsistency