Semi-supervised learning and feature evaluation for RGB-D object recognition

doi:10.1016/j.cviu.2015.05.007

CASIA OpenIR > 模式识别实验室

	Semi-supervised learning and feature evaluation for RGB-D object recognition
	Cheng, Yanhua; Zhao, Xin; Huang, Kaiqi; Tan, Tieniu
发表期刊	COMPUTER VISION AND IMAGE UNDERSTANDING
	2015-10-01
卷号	139 期号:5 页码:149-160
文章类型	Article
摘要	With new depth sensing technology such as Kinect providing high quality synchronized RGB and depth images (RGB-D data), combining the two distinct views for object recognition has attracted great interest in computer vision and robotics community. Recent methods mostly employ supervised learning methods for this new RGB-D modality based on the two feature sets. However, supervised learning methods always depend on large amount of manually labeled data for training models. To address the problem, this paper proposes a semi-supervised learning method to reduce the dependence on large annotated training sets. The method can effectively learn from relatively plentiful unlabeled data, if powerful feature representations for both the RGB and depth view can be extracted. Thus, a novel and effective feature termed CNN-SPM-RNN is proposed in this paper, and four representative features (KDES [1], CKM [2], HMP [3] and CNN-RNN [4]) are evaluated and compared with ours under the unified semi-supervised learning framework. Finally, we verify our method on three popular and publicly available RGB-D object databases. The experimental results demonstrate that, with only 20% labeled training set, the proposed method can achieve competitive performance compared with the state of the arts on most of the databases. (C) 2015 Elsevier Inc. All rights reserved.
关键词	Rgb-d Object Recognition Feature Representation Feature Evaluation Semi-supervised Learning
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.cviu.2015.05.007
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000361081600012
引用统计	被引频次：29[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/173211/8980
专题	模式识别实验室
作者单位	Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Cheng, Yanhua,Zhao, Xin,Huang, Kaiqi,et al. Semi-supervised learning and feature evaluation for RGB-D object recognition[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2015,139(5):149-160.
APA	Cheng, Yanhua,Zhao, Xin,Huang, Kaiqi,&Tan, Tieniu.(2015).Semi-supervised learning and feature evaluation for RGB-D object recognition.COMPUTER VISION AND IMAGE UNDERSTANDING,139(5),149-160.
MLA	Cheng, Yanhua,et al."Semi-supervised learning and feature evaluation for RGB-D object recognition".COMPUTER VISION AND IMAGE UNDERSTANDING 139.5(2015):149-160.

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
Semi-supervised lear（3157KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载