Grasp type understanding - classification, localization and clustering

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 机器人应用与理论组

	Grasp type understanding - classification, localization and clustering
	Li, Yinlin; Zhang, Yuren; Qiao, Hong; Chen, Ken; Xi, Xuanyang
	2016
会议名称	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
关键词	OBJECTS HANDS
通讯作者	Li, YL
英文摘要	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.
会议录	PROCEEDINGS OF THE 2016 12TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA)
学科主题	Automation & Control Systems ; Engineering, Electrical & Electronic
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/12825]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组
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]. 见:12th World Congress on Intelligent Control and Automation (WCICA). Guilin, PEOPLES R CHINA. JUN 12-15, 2016.