High-generalization cross-domain road scene semantic segmentation method and system

Abstract

The invention discloses a high-generalization cross-domain road scene semantic segmentation method. The method comprises the following steps: generating a virtual image and a corresponding label through a game engine; generating a global / local texture migration image by using the virtual image; sending the virtual image and the global / local texture migration image to a neural network for training; performing consistency constraint on the global / local texture migration image trained by the neural network; calculating loss values of the virtual image trained by the neural network and the local texture migration image and the local texture migration image subjected to consistency constraint with the labels respectively, and training a semantic segmentation model according to the loss values; and performing semantic segmentation by using the trained semantic segmentation model. According to the method, data enhancement is realized through global texture migration and local texture migration of a virtual image, a neural network is attacked, and a model is forced to learn cross-domain invariant shape information; moreover, the method only carries out network training in the source domain, achieves a reliable cross-domain segmentation effect, and has very high generalization performance.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a highly generalized cross-domain road scene semantic segmentation method and system. Background technique [0002] Image semantic segmentation means that the computer realizes the understanding of the image according to the content of the image, and then performs visual segmentation. In recent years, with the continuous development of artificial intelligence, semantic segmentation technology based on deep learning has been increasingly applied to various aspects of industrial production, social security and transportation. Among them, semantic segmentation to realize unmanned driving is a hot topic. The direction is also the inevitable trend of development. Semantic segmentation is the core algorithm technology of unmanned driving. Vehicle-mounted cameras or lidar detect images and input them into the neural network. The background computer can automatically...

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