US 11,735,316 B2
Method and apparatus of labeling target in image, and computer recording medium
Yongming Shi, Beijing (CN); Ge Ou, Beijing (CN); Qiong Wu, Beijing (CN); and Chun Wang, Beijing (CN)
Assigned to BEIJING BOE TECHNOLOGY DEVELOPMENT CO., LTD., Beijing (CN); and BOE TECHNOLOGY GROUP CO., LTD., Beijing (CN)
Appl. No. 17/253,216
Filed by Beijing BOE Technology Development Co., Ltd., Beijing (CN); and BOE TECHNOLOGY GROUP CO., LTD., Beijing (CN)
PCT Filed Apr. 20, 2020, PCT No. PCT/CN2020/085613
§ 371(c)(1), (2) Date Dec. 17, 2020,
PCT Pub. No. WO2020/228490, PCT Pub. Date Nov. 19, 2020.
Claims priority of application No. 201910406757.3 (CN), filed on May 16, 2019.
Prior Publication US 2021/0118137 A1, Apr. 22, 2021
Int. Cl. G06T 7/00 (2017.01); G16H 30/40 (2018.01); G06T 7/70 (2017.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); G06F 18/214 (2023.01); G06F 18/2431 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/44 (2022.01)
CPC G16H 30/40 (2018.01) [G06F 18/214 (2023.01); G06F 18/2431 (2023.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06T 7/0012 (2013.01); G06T 7/70 (2017.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30096 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A method of labeling a target in an image, comprising:
acquiring an image;
acquiring a first neural network, the first neural network comprises a multi-layer convolutional neural network and a fully connected layer, wherein each layer of the multi-layer convolutional neural network comprises a convolutional layer, an activation function layer and a down-sampling layer arranged successively;
processing the image by using the multi-layer convolutional neural network of the first neural network acquired so as to obtain a target position mask for the image; and
labeling the target in the image based on the target position mask,
wherein the processing the image by using the multi-layer convolutional neural network of the first neural network acquired so as to obtain a target position mask for the image comprises:
performing a large-value spatial position sampling on an output of the activation function layer in at least one layer of the first neural network;
mapping an output of a down-sampling layer associated with the activation function layer to a coordinate space for the image based on a result of the large-value spatial position sampling, so as to obtain a mapping matrix; and
obtaining the target position mask based on the mapping matrix.