US 11,694,425 B2
Multi-spectrum visual object recognition
Yue Lin, Beijing (CN); Li Cao, Beijing (CN); Jing Bai, Beijing (CN); Mu Wei, Beijing (CN); and Bing Qian, Beijing (CN)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on May 10, 2021, as Appl. No. 17/315,428.
Prior Publication US 2022/0358320 A1, Nov. 10, 2022
Int. Cl. G06V 10/44 (2022.01); G06V 10/30 (2022.01); G06V 10/56 (2022.01); G06V 10/50 (2022.01); G06V 10/75 (2022.01)
CPC G06V 10/44 (2022.01) [G06V 10/30 (2022.01); G06V 10/507 (2022.01); G06V 10/56 (2022.01); G06V 10/751 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining, by one or more processors, a first image corresponding to visible light and a second image corresponding to invisible light with respect to an object;
identifying, by the one or more processors, a first contour of the object based on the first image;
identifying, by the one or more processors, a second contour of the object based on the second image, wherein the first contour is covered at least in part by an invisible light-transmissive obstacle and the second contour is not blocked by the invisible light-transmissive obstacle;
integrating, by the one or more processors, the first contour of the object and the second contour of the object to generate a multi-spectrum contour of the object; and
recognizing, by the one or more processors, the object using the multi-spectrum contour of the object.