Image semantic segmentation model generation method and device, equipment and storage medium

Abstract

The invention discloses an image semantic segmentation model generation method and device, equipment and a storage medium. The method comprises the steps of obtaining an image sample set; using the image sample set to train an image semantic segmentation model; wherein the image semantic segmentation model comprises a feature map extraction part and a feature map analysis part, the feature map extraction part comprises a plurality of cascaded hole convolution processing residual error modules, and the feature map analysis part is constructed based on an attention mechanism, a pixel correlationmechanism and multi-scale information. According to the technical scheme provided by the embodiment of the invention, the attention mechanism is effectively utilized to learn the dependency relationship in spatial position and channel dimension, the feature expression capability is enhanced, the pixel correlation mechanism is utilized to make the segmentation result more accurate, and meanwhile,the multi-scale feature information is also utilized to learn a global scene to improve the accuracy of pixel point classification.

Description

technical field [0001] The present application generally relates to the technical field of data processing, and in particular relates to a method, device, equipment and storage medium for generating an image semantic segmentation model. Background technique [0002] Image semantic segmentation is the basic technology of image understanding, and its application in automatic driving systems, drones and wearable devices is very important. Usually an image is composed of many pixels (Pixel), and "semantic segmentation" is to group pixels according to the different semantic meanings expressed in the image (Grouping) / Segmentation (Segmentation). [0003] The application of deep learning in the fields of computer vision, image and video analysis has achieved great success. Image segmentation using deep learning can be understood as classifying each pixel in the image, that is, classifying the objects appearing in the input image and locating the positions of objects of different c...

AI Technical Summary

Problems solved by technology

However, image segmentation based on deep learning still has shortcomings such as matching relationship errors, fuzzy classification, and ignoring small target objects.

Images