Grasp type understanding - classification, localization and clustering
Li, Yinlin; Zhang, Yuren; Qiao, Hong; Chen, Ken; Xi, Xuanyang; Li, YL
2016
会议名称12th World Congress on Intelligent Control and Automation (WCICA)
会议录名称PROCEEDINGS OF THE 2016 12TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA)
会议日期JUN 12-15, 2016
会议地点Guilin, PEOPLES R CHINA
摘要Prehensile analysis is a research field attracting multi-disciplinary interests, including computer science, mechanology and neuroscience. For robot, grasp type recognition provides critical information for human-robot interaction and robot self-learning. One of the research direction is to discover the common modes of human hand use with first-person point-of-view wearable cameras. In contrast to previous methods based on handcraft features and multi-stage pipeline, we use a convolutional neural network to learn discriminative features of grasp types automatically, which can also achieve grasptype localization and classification simultaneously in a single-stage pipeline. Furthermore, a clusteringmethod is also proposed to find the hierarchical relationships between different grasp types. Experiments are conducted on UT Grasp dataset and Yale human grasping dataset. The proposed method shows better accuracy and higher efficiency than traditional methods.
关键词Objects Hands
学科领域Automation & Control Systems ; Engineering, Electrical & Electronic
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12825
专题复杂系统管理与控制国家重点实验室_机器人理论与应用
通讯作者Li, YL
推荐引用方式
GB/T 7714
Li, Yinlin,Zhang, Yuren,Qiao, Hong,et al. Grasp type understanding - classification, localization and clustering[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
grasp.pdf(576KB)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
[Li, Yinlin]的文章
[Zhang, Yuren]的文章
[Qiao, Hong]的文章
百度学术
百度学术中相似的文章
[Li, Yinlin]的文章
[Zhang, Yuren]的文章
[Qiao, Hong]的文章
必应学术
必应学术中相似的文章
[Li, Yinlin]的文章
[Zhang, Yuren]的文章
[Qiao, Hong]的文章
相关权益政策
暂无数据
收藏/分享
文件名: grasp.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。