US 12,008,793 B2
Object behavior analysis method, information display method, and electronic device
Fengshuo Hu, Beijing (CN); Bingchuan Shi, Beijing (CN); and Rui Zheng, Beijing (CN)
Assigned to BOE Technology Group Co., Ltd., Beijing (CN)
Appl. No. 17/426,110
Filed by BOE Technology Group Co., Ltd., Beijing (CN)
PCT Filed Jan. 12, 2021, PCT No. PCT/CN2021/071204
§ 371(c)(1), (2) Date Jul. 28, 2021,
PCT Pub. No. WO2021/164464, PCT Pub. Date Aug. 26, 2021.
Claims priority of application No. 202010096745.8 (CN), filed on Feb. 17, 2020.
Prior Publication US 2022/0319234 A1, Oct. 6, 2022
Int. Cl. G06T 7/70 (2017.01); G06V 10/25 (2022.01); G06V 20/40 (2022.01); G06V 20/52 (2022.01); G06V 40/20 (2022.01)
CPC G06V 10/25 (2022.01) [G06T 7/70 (2017.01); G06V 20/40 (2022.01); G06V 20/52 (2022.01); G06V 40/20 (2022.01)] 17 Claims
OG exemplary drawing
 
1. An object behavior analysis method, comprising:
acquiring multiple frames of images to be processed from a video of a target scene;
detecting at least one first-type object in any frame of image to be processed, and determining key point information of any first-type object;
determining key point merging information of any first-type object in a present image according to key point information of first-type objects in the present image and a reference image group, wherein the present image is any frame of image to be processed during present processing, and the reference image group comprises at least one frame of image to be processed before the present image; and
determining a behavior analysis result of any first-type object in the present image according to the key point merging information of the first-type object in the present image,
wherein determining the key point merging information of any first-type object in the present image according to the key point information of the first-type objects in the present image and the reference image group comprises:
for the present image and any two adjacent frames of images to be processed in the reference image group, determining a matching relationship of multiple first-type objects in the two adjacent frames of images to be processed according to key point information of each first-type object in the two adjacent frames of images to be processed;
determining a matching relationship between any first-type object in the present image and at least one first-type object in the reference image group according to the present image and the matching relationship of the multiple first-type objects in any two adjacent frames of images to be processed in the reference image group; and
determining the key point merging information of any first-type object in the present image according to the matching relationship between the first-type object in the present image and the at least one first-type object in the reference image group and the key point information,
wherein the key point merging information of the first-type object comprises coordinate information with a highest confidence corresponding to the key point of each category of the first-type object and the highest confidence corresponding to the coordinate information.