QQ客服 官方微博 反馈留言

	Multi-Stage Feature Learning Based Object Recognition and 3D Pose Estimation with Kinect
	Wei Zeng; Guoyuan Liang; Can Wang; Xinyu Wu
	2016
会议名称	IEEE International Conference on Information Science and Technology(ICIST)
会议地点	中国大连
英文摘要	Impressive achievements have been achieved over the years in object recognition and 3D pose estimation while detecting objects and estimating their 3D poses reliably is still a very challenging problem, especially for texture-less objects in heavily cluttered scenes. In this paper, we introduce an improved approach based on multi-stage feature learning to identify object as well as their 3D orientation efficiently. Our approach is motivated by visual neuroscience models. Currently similar architectures have been successfully applied to pedestrian detection, traffic recognition, face representation, etc. We compute the feature descriptors by multi-stage convolutional neural networks (CNNs) which could map the object identity and 3D poses to the Euclidean distance space by evaluating the similarity between descriptors. By contrast with classical approaches, our method relies on fast and approximate Nearest Neighbor (NN) matching to solve the large scale problems instead of one classifier per object or multi-class classifiers whose complexity grows rapidly with the number of objects. The experiments of detecting poorly-textured objects in cluttered scenarios have been carried out to verify the effectiveness and efficacy of the proposed approach.
收录类别	EI
语种	英语
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/10130]
专题	深圳先进技术研究院_集成所
作者单位	2016
推荐引用方式 GB/T 7714	Wei Zeng,Guoyuan Liang,Can Wang,et al. Multi-Stage Feature Learning Based Object Recognition and 3D Pose Estimation with Kinect[C]. 见:IEEE International Conference on Information Science and Technology(ICIST). 中国大连.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

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。