US 12,254,663 B2
Method and system of recognizing and processing object edges and computer-readable storage medium
Qingsong Xu, Hangzhou (CN); and Qing Li, Hangzhou (CN)
Assigned to Hangzhou Glority Software Limited, Hangzhou (CN)
Appl. No. 17/641,436
Filed by Hangzhou Glority Software Limited, Hangzhou (CN)
PCT Filed Jul. 21, 2021, PCT No. PCT/CN2021/107516
§ 371(c)(1), (2) Date Mar. 9, 2022,
PCT Pub. No. WO2022/028247, PCT Pub. Date Feb. 10, 2022.
Claims priority of application No. CN202010784883.5 (CN), filed on Aug. 6, 2020.
Prior Publication US 2022/0335704 A1, Oct. 20, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 10/44 (2022.01); G06T 3/04 (2024.01); G06T 7/13 (2017.01); G06T 7/73 (2017.01); G06V 10/82 (2022.01)
CPC G06V 10/44 (2022.01) [G06T 3/04 (2024.01); G06T 7/13 (2017.01); G06T 7/73 (2017.01); G06V 10/82 (2022.01); G06T 2207/20084 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A method of recognizing and processing object edges, comprising:
obtaining an input image, wherein the input image comprises an object with edges, and the edges of the object comprise a plurality of object vertices, wherein each of the plurality of object vertices corresponds an image vertex;
recognizing, through an object vertex recognition model, the input image;
obtaining a relative position between each of the plurality of object vertices and the image vertex;
determining an actual position of each of the object vertices in the input image according to the relative position of each of the object vertices and the corresponding image vertex thereof; and
sequentially connecting adjacent object vertices to form edge lines to obtain the edges of the object with edges in the input image according to the actual position of each of the object vertices in the input image,
wherein the step of obtaining the relative position of each of the object vertices and the corresponding image vertex thereof further comprises:
extending adjacent edge lines to obtain the object vertices outside the input image,
wherein the object vertex recognition model is trained by using a training sample set, sample images in the training sample set is labeled by extending adjacent edge lines to obtain object vertices outside one of the sample images.