A semantic segmentation optimization method and device for an edge image

Abstract

The invention relates to a semantic segmentation optimization method for an edge image. The method comprises the steps of selecting image data; Using the image data to train and verify an image semantic segmentation model and a full connection condition random field model; Obtaining a semantic segmentation result of the image by using the trained image semantic segmentation model; Obtaining a superpixel segmentation result of the image edge information by using a superpixel segmentation algorithm; Optimizing the semantic segmentation result by using the superpixel segmentation result to form afirst optimization result; And optimizing the first optimization result by using the trained full connection condition random field model. According to the method provided by the invention, the advanced semantic information in the image can be effectively extracted, the image edge information is reserved through the super-pixel segmentation algorithm, the semantic segmentation accuracy of an existing segmentation model on the image edge is improved through the local edge optimization algorithm, and the method is flexible to implement, high in compatibility and relatively high in robustness.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a semantic segmentation optimization method and device for edge images. Background technique [0002] With the continuous improvement of the computer science system and the continuous development of multimedia and Internet technology, as an important branch of computer science, computer vision represented by digital image processing is gradually integrated into every corner of modern society. Image semantic segmentation is one of the important basic problems in computer vision. Its goal is to classify each pixel of the image, divide the image into several regions, and the regions are independent without overlapping and have their own visual meanings. , and give them different visual labels to facilitate subsequent image analysis and visual understanding. From a macro point of view, the semantic segmentation of images can be regarded as the pre-processing pro...

AI Technical Summary

Problems solved by technology

Although the existing image semantic segmentation technology has reached a fairly good level of overall segmentation accuracy, the existing methods usually cannot accurately locate a single target.

If there is overlap between objects or other complex occlusions, the existing semantic segmentation algorithm cannot handle them well. Generally, the result is that multiple objects are glued together, and the edges cannot be clearly identified. Objects will be mislabeled as other classes

Images