US 12,008,797 B2
Image segmentation method and image processing apparatus
Zhi Tian, Adelaide (AU); Tong He, Adelaide (AU); Chunhua Shen, Adelaide (AU); Youliang Yan, Shenzhen (CN); Songcen Xu, Shenzhen (CN); Yiren Zhou, London (GB); Xiaofei Wu, Shenzhen (CN); and Jianzhuang Liu, Shenzhen (CN)
Assigned to Huawei Technologies Co., Ltd., Shenzhen (CN)
Filed by Huawei Technologies Co., Ltd., Shenzhen (CN)
Filed on Jul. 22, 2021, as Appl. No. 17/383,181.
Application 17/383,181 is a continuation of application No. PCT/CN2020/077366, filed on Mar. 1, 2020.
Claims priority of application No. 201910157603.5 (CN), filed on Mar. 1, 2019.
Prior Publication US 2021/0350168 A1, Nov. 11, 2021
Int. Cl. G06V 10/44 (2022.01); G06F 18/2135 (2023.01); G06F 18/2137 (2023.01); G06F 18/214 (2023.01); G06F 18/25 (2023.01); G06N 3/08 (2023.01); G06T 3/40 (2006.01); G06V 10/77 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/457 (2022.01) [G06F 18/2135 (2023.01); G06F 18/2137 (2023.01); G06F 18/214 (2023.01); G06F 18/253 (2023.01); G06N 3/08 (2013.01); G06T 3/40 (2013.01); G06V 10/454 (2022.01); G06V 10/7715 (2022.01); G06V 10/82 (2022.01)] 15 Claims
OG exemplary drawing
 
1. An image segmentation method, comprising:
obtaining an input image and a processing requirement, wherein the processing requirement is used to indicate to perform target processing on a target feature map group obtained by performing image segmentation on the input image;
performing multi-layer feature extraction on the input image to obtain a plurality of feature maps;
downsampling the plurality of feature maps to obtain a plurality of feature maps with a reference resolution, wherein the reference resolution is less than a resolution of the input image;
fusing the plurality of feature maps with the reference resolution to obtain at least one feature map group;
upsampling the at least one feature map group by using a transformation matrix W, to obtain the target feature map group, wherein the target feature map group has a same resolution as that of the input image, the transformation matrix W is obtained by modeling training data of an image segmentation task, and one dimension of the transformation matrix W is the same as a quantity of channels of the feature group; and
performing the target processing on the target feature map group based on the processing requirement to obtain a target image.