Image semantic segmentation method and device, electronic equipment and readable storage medium

Abstract

The invention discloses an image semantic segmentation method and device and electronic equipment. The method is implemented through a semantic segmentation model comprising a feature extraction module, a feature aggregation module and a feature fusion module, and comprises the following steps: extracting shallow features and deep features of a target image through the feature extraction module, and constructing a feature pyramid of the target image according to the deep features; wherein the feature pyramid comprises deep features of the corresponding image on different scales; aggregating the deep features of different scales in the feature pyramid of the target image through a feature aggregation module to obtain an aggregated feature map; and fusing the shallow features of the target image and the aggregation feature map through a feature fusion module to obtain a fusion feature map, and obtaining a corresponding semantic segmentation result according to the fusion feature map.

Description

technical field [0001] The present invention relates to the technical field of image processing, and more specifically, relates to a semantic segmentation method, device, electronic device and readable storage medium of an image. Background technique [0002] Image semantic segmentation, also known as image semantic annotation, refers to classifying a category label for each pixel unit in the image (a pixel unit can be one or a preset number of pixels) according to the semantic information of the image. The category label corresponding to the semantic information divides the image into image regions corresponding to different semantic information. Semantic segmentation of images has broad application prospects in areas such as autonomous driving, scene understanding, robot vision, and medical image analysis. [0003] Although, with the emergence of deep convolutional neural networks, computer vision processing tasks such as semantic segmentation of images have achieved brea...

AI Technical Summary

Problems solved by technology

[0003] Although, with the emergence of deep convolutional neural networks, computer vision processing tasks such as semantic segmentation of images have achieved breakthrough development, but due to the complexity of implementing semantic segmentation of images, there are still many problems. For example, for image Including objects of different scales (such as buildings, scenery, people, etc.), through the current mainstream image semantic segmentation method (for example, the method of strong supervision), it cannot be accurately segmented, and the accuracy of image semantic segmentation is low

Images