Image segmentation method and device, equipment, and storage medium

Abstract

The invention discloses an image segmentation method and device, equipment and a storage medium, and the method comprises the steps that an encoder codes an obtained to-be-processed image, and obtainsa multi-layer first feature map which comprises first features of different scales; the encoder comprises at least two encoding layers which are connected in sequence, each encoding layer outputs a first feature map, and the input of each encoding layer comprises an output result of a front layer or the to-be-processed image; a decoder decodes the multi-layer first feature map to obtain a fused feature map; the decoder comprises at least two decoding layers which are connected in sequence, each decoding layer is realized by adopting a content attention operator and a space attention operator,and the input of each decoding layer comprises a first feature map of which the output result and the scale of a front layer are consistent; and a classifier performs pixel-by-pixel classification onthe fusion feature map to obtain an image segmentation result of the to-be-processed image.

Description

technical field [0001] This application relates to computer vision technology, involving but not limited to an image segmentation method, device, equipment, and storage medium. Background technique [0002] Image segmentation mainly uses the color, intensity, texture and other information of image pixels to perform pixel-level semantic classification of images. In related technologies, image semantic segmentation is generally performed through the encoding and decoding framework in the deep convolutional network, and the image is input to the encoder Downsampling is performed to obtain a high-level feature map containing high-level features with low resolution but rich semantic information. Afterwards, the high-level feature map is input into the decoder and gradually restored to the resolution of the original image through multiple upsampling. Fusion results in image segmentation. [0003] However, since the fusion of the high-level feature map and the low-level feature m...

AI Technical Summary

Problems solved by technology

[0003] However, since the fusion of the high-level feature map and the low-level feature map by the deep convolutional network is only the sum of the transformed features in the receptive field, there may be a feature misalignment problem between the high-level features and the low-level features.

Images