QQ客服 官方微博 反馈留言

	Viewpoint space partitioning based on affine invariant features
	Sun Jie ; Ma Huimin ; Li Fengting
	2010-10-12 ; 2010-10-12
关键词	Practical Theoretical or Mathematical/ affine transforms feature extraction object recognition pose estimation support vector machines Zernike polynomials/ 3D object viewpoint space partitioning affine invariant feature extraction strategy multiscale autoconvolution trace transform Zernike moment two-dimensional projective image 3D object posture recognition Princeton shape benchmark pattern recognition SVM support vector machine/ B6135E Image recognition B0230 Integral transforms B0210 Algebra C5260B Computer vision and image processing techniques C1130 Integral transforms C6170K Knowledge engineering techniques C1110 Algebra
中文摘要	The viewpoint space of 3D objects, such as aircraft, automobiles, and humans is partitioned using three affine invariant features based on a multi-scale auto convolution, a trace transform, and the Zernike moment to express the 3D objects within minimum two-dimensional projective images. The images are then nonuniformly projected for object recognition to simplify the 3D recognition process and increase the recognition rate of 3D objects. The paper presents an affine invariant feature extraction strategy for different 3D objects that can recognize arbitrary postures of the 3D object. Tests with models from the Princeton shape benchmark show that the good recognition effect can be achieved by the proposed method and the recognition rate is great than 90%.
语种	中文
出版者	Tsinghua University Press ; China
内容类型	期刊论文
源URL	[http://hdl.handle.net/123456789/82557]
专题	清华大学
推荐引用方式 GB/T 7714	Sun Jie,Ma Huimin,Li Fengting. Viewpoint space partitioning based on affine invariant features[J],2010, 2010.
APA	Sun Jie,Ma Huimin,&Li Fengting.(2010).Viewpoint space partitioning based on affine invariant features..
MLA	Sun Jie,et al."Viewpoint space partitioning based on affine invariant features".(2010).

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。