Image semantic segmentation method, electronic equipment and readable storage medium

Abstract

The invention discloses an image semantic segmentation method, electronic equipment and a readable storage medium. Based on an FCN model based on depth feature fusion, the image semantic segmentationmethod replaces the traditional convolution operation by cavity convolution, constructs original images with different resolutions to form image pyramids, hierarchically inputs the FCN model, fuses the output characteristics of the upper layer with the output characteristics of the lower layer, and fuses output features to a bottom layer from top to bottom layer by layer for transposed convolution, and the output features of the bottom layer perform transposition convolution so as to enable the output resolution to be consistent with a bottom-layer input image, thus improving the sensitivity to target positioning, and the segmentation precision is ensured through optimization processing of a full-connection conditional random field subsequently, thereby obtaining a better segmentation effect.

Description

technical field [0001] The invention relates to the technical field of image semantic segmentation, in particular to an image semantic segmentation method, electronic equipment and a readable storage medium. Background technique [0002] Semantic segmentation is one of the important cornerstones in the field of computer vision. It not only classifies each pixel in the image, but also marks the object category to which the pixel belongs in the image, that is, it can not only segment the area, but also perform content analysis on the area. label. [0003] Semantic segmentation can generally be divided into several different tasks such as figure 1 As shown, among them, figure 1 (a): pixel-level segmentation; figure 1 (b): scene analysis; figure 1 (c): Combination of localization and classification. exist figure 1 In (a), given an image, it may be necessary to distinguish all pixels in the image belonging to people and all pixels belonging to horses, and each category of p...

AI Technical Summary

Problems solved by technology

[0022] Aiming at the defect that FCN cannot well balance the high-level abstract classification problem and the low-level precise positioning problem, the present invention provides an image semantic segmentation method, electronic equipment and readable storage medium, taking into account the sensitivity of target positioning and segmentation accuracy

Images