US 12,333,742 B2
Object tracking integration method and integrating apparatus
Jiun-In Guo, Hsinchu (TW); and Jhih-Sheng Lai, Hsinchu (TW)
Assigned to Wistron Corporation, New Taipei (TW)
Filed by Wistron Corporation, New Taipei (TW)
Filed on Jun. 29, 2022, as Appl. No. 17/852,378.
Claims priority of application No. 111114105 (TW), filed on Apr. 13, 2022.
Prior Publication US 2023/0334675 A1, Oct. 19, 2023
Int. Cl. G06T 7/292 (2017.01); G06T 7/70 (2017.01); G06V 10/25 (2022.01); G06V 10/75 (2022.01)
CPC G06T 7/292 (2017.01) [G06T 7/70 (2017.01); G06V 10/25 (2022.01); G06V 10/751 (2022.01); G06V 10/753 (2022.01); G06T 2207/20132 (2013.01); G06T 2207/20212 (2013.01); G06T 2207/30241 (2013.01); G06V 2201/07 (2022.01)] 18 Claims
OG exemplary drawing
 
1. An object tracking integration method, comprising:
obtaining at least one first image and at least one second image, wherein the at least one first image is from a first image capturing apparatus, and the at least one second image is from a second image capturing apparatus;
detecting at least one target object in the at least one first image and in the at least one second image, comprising:
cropping a region of interest from the first image to generate a cropped image with only the region of interest;
respectively detecting the at least one target objects in the first image and the cropped image, to obtain a detection result of the at least one target objects in the first image and a detection result of the at least one target objects in the cropped image, wherein the detection result of the at least one target object comprises representative information of the at least one target object; and
combining the detection result of the at least one target object in the first image and the detection result of the at least one target object in the cropped image, wherein a union of the detection results of two images, which comprises a same target object detected in the first image and the cropped image, is taken as a combination of the detection result in the first image and the detection result in the cropped image;
matching a detection result of the at least one target object in the at least one first image and a detection result of the at least one target object in the at least one second image; and
updating the detection result of the at least one target object according to a matching result between the detection result of the at least one first image and the detection result of the at least one second image.