Image segmentation method, device and apparatus and storage medium

Abstract

The embodiment of the invention provides an image segmentation method, device and apparatus, and a storage medium. The method comprises: extracting an initial feature map of a to-be-processed image through a base network of an image segmentation model; pooling the initial feature map through an average pooling sub-model of the image segmentation model to obtain a first feature map carrying short-distance dependency relationship information; processing the initial feature map through at least one branch sub-model to obtain at least one target feature map, wherein the target feature map comprises a second feature map carrying global dependency relationship information and / or a third feature map carrying long-distance dependency relationship information; and cascading the first feature map with the target feature map, and then performing convolution to obtain an image segmentation result and outputting the image segmentation result. According to the method, the branch sub-models are arranged in parallel with the average pooling sub-model to obtain the feature map carrying global dependency relationship information and / or long-distance dependency relationship information, and the feature map carrying global dependency relationship information and / or long-distance dependency relationship information is cascaded with the feature map carrying short-distance dependency relationship information obtained by the average pooling sub-model, so that the feature representation capability is enhanced, and the image segmentation accuracy is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, to an image segmentation method, device, equipment, and storage medium. Background technique [0002] With the continuous development of AI technology and image processing technology, using AI image technology to improve our way of life and serve human beings has become a new trend in the research of AI technology. Image segmentation is an important and key image analysis technology. Its purpose is to divide the image into regions with different characteristics and extract the parts of interest. The result of image segmentation is the basis of image understanding such as image feature extraction and recognition. Therefore, It has an important position in the field of computer vision, and it also faces some new challenges. [0003] In the prior art, neural network models such as FCN, Segnet, and Pspnet are usually used for image segmentation. Alth...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, neural network models such as FCN, Segnet, and Pspnet are usually used for image segmentation. Although methods such as FCN, Segnet, and Pspnet help to capture objects of different proportions by fusing contextual information during image segmentation, they cannot take advantage of the overall The relationship between objects in the view, resulting in poor segmentation results; when the convolution operation is performed on the neural network, a local receptive field is generated, which may cause the corresponding features of pixels with the same label to be different, and this difference will further Lead to inconsistency within the class, thus affecting the accuracy of recognition

Images