Model-based work-piece localization with salient feature selection

	Model-based work-piece localization with salient feature selection
	Zhu, Wenjun; Qin, Zhengke; Wang, Peng; Qiao, Hong
	2013-12
会议名称	Robotics and Biomimetics (ROBIO), 2013 IEEE International Conference on
会议日期	12-14 Dec. 2013
会议地点	Shenzhen, China
摘要	This paper presents a model-based work-piece localization method with salient feature selection. Model-based localization is suitable for work-piece which is one kind of the typical 3D rigid objects with less texture. However, localization based on 3D model will cause high failure rate in heavily cluttered scenes. We propose a new model-based localization method, which is integrated with salient feature selection. Two different models: 3D model and training images are used, and the salient feature selection procedure extracts the regions which may contain the objects potentially. Experiments demonstrate the effectiveness of the proposed method.
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/14767
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
作者单位	Institute of Automaton, Chinese Academy of Science
推荐引用方式 GB/T 7714	Zhu, Wenjun,Qin, Zhengke,Wang, Peng,et al. Model-based work-piece localization with salient feature selection[C],2013.