发明名称 Recognition apparatus and method thereof, and computer program
摘要 A recognition apparatus for recognizing a position and an orientation of a target object, inputs a captured image of the target object captured by an image capturing apparatus; detects a plurality of feature portions from the captured image, and to extract a plurality of feature amounts indicating image characteristics in each of the plurality of feature portions; inputs property information indicating respective physical properties in the plurality of feature portions on the target object; inputs illumination information indicating an illumination condition at the time of capturing the captured image; determines respective degrees of importance of the plurality of extracted feature amounts based on the respective physical properties indicated by the property information and the illumination condition indicated by the illumination information; and recognizes the position and the orientation of the target object based on the plurality of feature amounts and the respective degrees of importance thereof.
申请公布号 US9087265(B2) 申请公布日期 2015.07.21
申请号 US201113030956 申请日期 2011.02.18
申请人 CANON KABUSHIKI KAISHA 发明人 Saruta Takayuki;Matsugu Masakazu;Aoba Masato
分类号 G06K9/00;G06K9/46;G01B11/00 主分类号 G06K9/00
代理机构 Fitzpatrick, Cella, Harper & Scinto 代理人 Fitzpatrick, Cella, Harper & Scinto
主权项 1. A recognition apparatus for recognizing a position and an orientation of a target object, comprising: a processor and a memory which together comprise: an extraction unit configured to detect a plurality of feature portions from a captured image, and to extract a plurality of feature amounts indicating image characteristics in each of the plurality of feature portions; a first input unit configured to input normal vectors in the plurality of feature portions on the target object; a second input unit configured to input at least one of direction of illumination and direction of image capture apparatus at the time of capturing the captured image; a holding unit configured to hold information with respect to angles between normal vectors in a plurality of feature portions on the target object in a learning image and at least one of direction of illumination and direction of image capture apparatus at the time of capturing the learning image in a learning process; a determination unit configured to determine respective degrees of importance of the plurality of extracted feature portions based on the input normal vectors, the input at least one of direction of illumination and direction of image capture apparatus, and the held information with respect to angles; a weighting unit configured to weight each of the plurality of extracted feature amounts based on the determined corresponding degree of importance; and a recognition unit configured to recognize the position and the orientation of the target object based on the plurality of feature amounts weighted by the weighting unit.
地址 Tokyo JP