Online RGB-D tracking via detection-learning-segmentation
An, Ning; Zhao, Xiao-Guang; Hou, Zeng-Guang
2016-12
会议名称Pattern Recognition (ICPR), 2016 23rd International Conference on
会议日期4-8 Dec. 2016
会议地点Cancun, Mexico
摘要In this paper, we address the problem of online RGB-D tracking where the target object undergoes significant appearance changes. To sufficiently exploit the color and depth cues, we propose a novel RGB-D tracking framework (DLS) that simultaneously builds the target 2D appearance model and 3D distribution model. The framework decomposes the tracking task into detection, learning and segmentation. The detection and segmentation components locate the target collaboratively by using the two target models. An adaptive depth histogram is proposed in the segmentation component to efficiently locate the target in depth frames. The learning component estimates the detection and segmentation errors, updates the target models from the most confident frames by identifying two kinds of distractors: potential failure and occlusion. Extensive experimental results on a large-scale benchmark dataset show that the proposed method performs favourably against state-of-the-art RGB-D trackers in terms of efficiency, accuracy, and robustness. 
DOI10.1109/ICPR.2016.7899805
收录类别EI
引用统计
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14559
专题复杂系统管理与控制国家重点实验室_先进机器人
通讯作者An, Ning
作者单位Institute of Automation Chinese Academy of Sciences
推荐引用方式
GB/T 7714
An, Ning,Zhao, Xiao-Guang,Hou, Zeng-Guang. Online RGB-D tracking via detection-learning-segmentation[C],2016.
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
Online RGB-D trackin(1690KB)会议论文 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
[An, Ning]的文章
[Zhao, Xiao-Guang]的文章
[Hou, Zeng-Guang]的文章
百度学术
百度学术中相似的文章
[An, Ning]的文章
[Zhao, Xiao-Guang]的文章
[Hou, Zeng-Guang]的文章
必应学术
必应学术中相似的文章
[An, Ning]的文章
[Zhao, Xiao-Guang]的文章
[Hou, Zeng-Guang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Online RGB-D tracking via detection-learning-segmentation.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。