中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 脑图谱与类脑智能实验室
  5. 类脑认知计算
Cognitive Template-Clustering Improved LineMod for Efficient Multi-object Pose Estimation

文献类型：期刊论文

作者Zhang, Tielin1; Yang, Yang5; Zeng, Yi1,2,3,4; Zhao, Yuxuan1
刊名COGNITIVE COMPUTATION
出版日期2020-03-17
页码10
关键词Muller-Lyer illusion Cognitive template-clustering Brain-inspired computation LineMod 6D pose estimation
ISSN号1866-9956
DOI10.1007/s12559-020-09717-5
通讯作者Zhang, Tielin(tielin.zhang@ia.ac.cn)
英文摘要Various types of theoretical algorithms have been proposed for 6D pose estimation, e.g., the point pair method, template matching method, Hough forest method, and deep learning method. However, they are still far from the performance of our natural biological systems, which can undertake 6D pose estimation of multi-objects efficiently, especially with severe occlusion. With the inspiration of the Muller-Lyer illusion in the biological visual system, in this paper, we propose a cognitive template-clustering improved LineMod (CT-LineMod) model. The model uses a 7D cognitive feature vector to replace standard 3D spatial points in the clustering procedure of Patch-LineMod, in which the cognitive distance of different 3D spatial points will be further influenced by the additional 4D information related with direction and magnitude of features in the Muller-Lyer illusion. The 7D vector will be dimensionally reduced into the 3D vector by the gradient-descent method, and then further clustered by K-means to aggregately match templates and automatically eliminate superfluous clusters, which makes the template matching possible on both holistic and part-based scales. The model has been verified on the standard Doumanoglou dataset and demonstrates a state-of-the-art performance, which shows the accuracy and efficiency of the proposed model on cognitive feature distance measurement and template selection on multiple pose estimation under severe occlusion. The powerful feature representation in the biological visual system also includes characteristics of the Muller-Lyer illusion, which, to some extent, will provide guidance towards a biologically plausible algorithm for efficient 6D pose estimation under severe occlusion.
资助项目Beijing Natural Science Foundation[4184103] ; National Natural Science Foundation of China[61806195] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDB32070100] ; Beijing Municipality of Science and Technology[Z181100001518006] ; CETC Joint Fund[6141B08010103] ; Beijing Academy of Artificial Intelligence (BAAI)
WOS研究方向Computer Science ; Neurosciences & Neurology
语种英语
WOS记录号WOS:000520697600002
出版者SPRINGER
资助机构Beijing Natural Science Foundation ; National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Sciences ; Beijing Municipality of Science and Technology ; CETC Joint Fund ; Beijing Academy of Artificial Intelligence (BAAI)
源URL[http://ir.ia.ac.cn/handle/173211/38692]  
专题类脑智能研究中心_类脑认知计算
通讯作者Zhang, Tielin
作者单位1.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China
4.Univ Chinese Acad Sci, Beijing, Peoples R China
5.Peking Univ, Sch Software & Microelect, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Tielin,Yang, Yang,Zeng, Yi,et al. Cognitive Template-Clustering Improved LineMod for Efficient Multi-object Pose Estimation[J]. COGNITIVE COMPUTATION,2020:10.
APA Zhang, Tielin,Yang, Yang,Zeng, Yi,&Zhao, Yuxuan.(2020).Cognitive Template-Clustering Improved LineMod for Efficient Multi-object Pose Estimation.COGNITIVE COMPUTATION,10.
MLA Zhang, Tielin,et al."Cognitive Template-Clustering Improved LineMod for Efficient Multi-object Pose Estimation".COGNITIVE COMPUTATION (2020):10.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。