High generalization method and system for semantic segmentation of cross-domain road scenes

Abstract

The invention discloses a highly generalizable cross-domain road scene semantic segmentation method, which includes: generating virtual images and corresponding labels through a game engine; using virtual images to generate global / local texture migration images; and performing virtual image and global / local texture migration. The image is sent to the neural network for training; the global / local texture transfer image trained by the neural network is subject to consistency constraints; the virtual image trained by the neural network and the local texture transfer image and local texture transfer image that have been constrained by the consistency are respectively associated with the label Calculate the loss value and train the semantic segmentation model based on the loss value; use the trained semantic segmentation model to perform semantic segmentation. This invention realizes data enhancement through global texture migration and local texture migration of virtual images, attacks the neural network, and forces the model to learn cross-domain invariant shape information; and this method only performs network training in the source domain, achieving reliable cross-domain Segmentation effect and strong generalization performance.

Description

Technical field [0001] The invention belongs to the field of computer vision technology, and specifically relates to a highly generalizable cross-domain road scene semantic segmentation method and system. Background technique [0002] Image semantic segmentation means that the computer understands the image based on its content and then performs visual segmentation. In recent years, with the continuous development of artificial intelligence, semantic segmentation technology based on deep learning has begun to be increasingly applied to various aspects such as industrial production, social security, and transportation. Among them, semantic segmentation to achieve driverless driving is a hot topic. direction is also the inevitable trend of development. Semantic segmentation is the core algorithm technology for autonomous vehicle driving. The on-board camera or lidar detects the image and inputs it into the neural network. The background computer can automatically segment the ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of high dependence on target domain data and poor generalization performance in the prior art, the present invention provides a cross-domain road scene semantic segmentation method that does not depend on target domain data and has considerable generalization performance. The game engine generates virtual data and performs image processing on the virtual data set, attacks the neural network, improves the robustness of the network to texture changes in cross-domain segmentation, and promotes the learning of the shape of objects in the image by the network, thereby enhancing the multi-domain generality of the model. optimized performance

Images