Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

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

A semantic segmentation and generalization technology, applied in the semantic segmentation method and system field of cross-domain road scenes, can solve the problems of high data dependence in the target domain and poor generalization performance, so as to save manpower and material resources, reduce labor force, and facilitate data acquisition Effect

Active Publication Date: 2022-06-24
SICHUAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • High generalization method and system for semantic segmentation of cross-domain road scenes
  • High generalization method and system for semantic segmentation of cross-domain road scenes
  • High generalization method and system for semantic segmentation of cross-domain road scenes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] In order to facilitate the understanding of those skilled in the art, the present invention will be further described below with reference to the embodiments and the accompanying drawings, and the contents mentioned in the embodiments are not intended to limit the present invention.

[0057] In the current semantic segmentation methods, it is difficult to obtain the image data of the target domain in advance. Taking autonomous driving as an example, it is impossible for the operator to obtain the road images of all target areas in advance, and the existing segmentation methods can only be performed for the known target domain. segmentation, so the trained model can only be applied to this specific domain and cannot generalize to other target domains.

[0058] figure 1A flow chart of a highly generalized cross-domain road scene semantic segmentation method is shown, including:

[0059] S10: Generate a virtual image and a corresponding label through a game engine.

[00...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

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 ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/41G06T7/194G06N3/04G06N3/08G06Q10/06
CPCG06T7/41G06T7/194G06N3/04G06N3/08G06Q10/06393G06T2207/20132
Inventor 雷印杰彭铎
Owner SICHUAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products