Road Condition Estimation Using Track and Image Feature Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for estimating road conditions are inaccurate in low-track scenarios, complex environments, and congested roads, leading to unreliable route planning and increased traffic congestion.
Innovation Solution
A method combining user tracks with road images using pre-trained models to extract track-related and image-related features, which are then input into a road condition estimation model to predict future road conditions, improving accuracy and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only user track data is used for road condition estimation, then the system complexity is low, but the measurement precision deteriorates in low-track scenarios and congested roads
Solution Approach 1:
The patent combines user track data with road image data into a unified feature extraction system. The track-related feature extractor processes GPS coordinates and movement patterns, while the image-related feature extractor analyzes road surface conditions from captured images. Both feature streams are merged and fed into a single road condition estimation model, enabling comprehensive assessment that overcomes the limitations of using either data source alone.
2Measurement precision
If multiple data sources (tracks and images) are integrated for road condition estimation, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The system segments the road condition estimation task into distinct modular components: a track-related feature extractor that processes GPS and movement data, an image-related feature extractor that analyzes road surface images, and a unified road condition estimation model. Each component handles specific data types independently, reducing overall system complexity while maintaining high measurement precision through integrated processing.
3Loss of time
If real-time road condition estimation is implemented, then the loss of time for route planning is reduced, but the use of energy increases due to continuous data processing
Solution Approach 1:
The system performs preliminary feature extraction on user tracks and road images before the actual road condition estimation is needed. Track-related features such as speed, acceleration, and route deviation are extracted in advance from GPS data. Image-related features including road surface texture and conditions are pre-processed from captured images. This preliminary processing reduces the computational burden during real-time estimation, decreasing energy consumption while maintaining fast response times for route planning.
Data Source
AI summary
The present disclosure provides a method and apparatus of estimating a road condition, and a method and apparatus of establishing a road condition estimation model, which relates to a field of big data and intelligent traffic. The method includes: acquiring, for a first preset duration before a first moment, a sequence of user tracks for a road and a sequence of road images for the road; extracting a track-related feature of the road from the sequence of the user tracks, and extracting an image-related feature of the road from the sequence of the road images; and inputting the track-related feature of the road and the image-related feature of the road into a pre-trained road condition estimation model, so as to determine, for a second preset duration after the first moment, a road condition information of the road by using an estimated result of the road condition estimation model.