Road surface meteorological state image segmentation method based on YOLOv8-BRFA model

By using the YOLOv8-BRFA model, combined with a dynamic sparse attention mechanism and a hardware-sensing neural network, the problem of high-precision real-time segmentation of road weather detection under complex lighting conditions was solved. It achieved efficient identification and segmentation of conditions such as water accumulation, icing, and dampness, adapts to low light and non-uniform lighting environments, reduces computational complexity, and improves detection accuracy.

CN121837635APending Publication Date: 2026-04-10CHONGQING UNIV OF TECH
0 Cites 2 Cited by

Patent Information

Application Number
CN202511993135.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-26
Publication Date
2026-04-10

AI Technical Summary

Technical Problem

Existing road weather detection technologies suffer from large parameter quantities and high computational complexity under multi-wavelength near-infrared imaging conditions, making it difficult to achieve high-precision real-time segmentation of multiple roadbeds and multiple weather conditions. In particular, the feature extraction capability is insufficient under complex lighting conditions, and traditional models cannot meet the deployment and real-time processing requirements of edge devices.

Method used

A road surface meteorological state image segmentation method based on the YOLOv8-BRFA model is adopted. By introducing a dynamic sparse attention mechanism, hardware-sensing neural network and adaptive decoupled detection head, combined with mathematical morphology algorithm and Retinex theory for illumination homogenization preprocessing, a road surface meteorological state segmentation model is constructed to achieve real-time and accurate segmentation and detection under complex illumination conditions.

Benefits of technology

While reducing computational complexity, the robustness and accuracy of the model are improved. It can effectively segment and identify various road weather conditions such as water accumulation, icing, and dampness, adapt to low light and non-uniform lighting environments, and meet the deployment requirements of real-time edge devices.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a road surface meteorological state image segmentation method based on a YOLOv8-BRFA model. The method comprises the following steps: acquiring a near-infrared road surface meteorological image data set; designing a dynamic sparse attention mechanism and a hardware perception neural network based on a YOLOv8 network architecture, and constructing a road surface meteorological state segmentation model in combination with an adaptive decoupling detection head; training the road surface meteorological state segmentation model by using a near-infrared road surface meteorological image data set to obtain a trained road surface meteorological state segmentation model; and obtaining a to-be-detected road surface meteorological image, inputting the to-be-detected road surface meteorological image into the trained road surface meteorological state segmentation model, and carrying out road surface meteorological state identification and segmentation to obtain a positioning and segmentation result of the to-be-detected road surface meteorological image. According to the invention, through structure improvement, the calculation complexity is reduced while the precision of the image segmentation model is improved, and real-time and accurate segmentation and detection of the road surface meteorological state under the complex illumination condition are realized.
Need to check novelty before this filing date? Find Prior Art