Traffic Safety Support With Hierarchical Risk Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing traffic safety support systems struggle to accurately predict and provide real-time support for potential risks outside the detection range of on-board sensors, leading to increased processing load and reduced effectiveness in managing traffic safety for multiple participants.
Innovation Solution
A traffic safety support system that includes a recognizer to identify traffic participants and environments, a predictor to analyze risks using macro and micro risk estimation models, and a transmitter to provide targeted support information based on risk levels, reducing computational load and improving prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If information regarding an enormous number of traffic participants present in the target traffic area is aggregated to the server, then a stream of the traffic participants in the target traffic area can be grasped from a higher perspective, but processing load at the server increases
Solution Approach 1:
The target traffic area is divided into multiple local areas, and each local area is further divided into multiple blocks. This hierarchical segmentation allows the server to process risk information in smaller, manageable units rather than handling all traffic participants in the entire target area simultaneously, thus reducing processing load while maintaining comprehensive monitoring coverage.
Solution Approach 2:
Different processing approaches are applied to different regions based on their risk levels. High-risk blocks receive detailed individual traffic participant analysis, while low-risk blocks receive aggregated statistical processing. This local differentiation optimizes resource allocation and reduces overall processing load while maintaining prediction accuracy where it matters most.
2Measurement precision
If detailed processing is performed for all local areas, then prediction accuracy is improved, but processing load increases
Solution Approach 1:
The system applies different processing intensities to different blocks based on their risk levels. Blocks identified as high-risk undergo detailed individual traffic participant analysis with full processing, while low-risk blocks receive simplified aggregated statistical processing. This selective approach maintains high prediction accuracy for critical areas while reducing overall computational complexity.
Solution Approach 2:
Instead of performing detailed processing uniformly across all blocks, the system applies excessive (detailed) processing only to high-risk blocks where it is most needed, and partial (aggregated) processing to low-risk blocks. This partial action approach optimizes the balance between prediction accuracy and computational resources.
Data Source
AI summary
A traffic safety support system includes a target traffic area recognizer configured to acquire recognition information regarding traffic participants, and the like, in a target traffic area, a predictor 62 configured to predict a risk in the target traffic area on the basis of the recognition information, and a coordination support information notifier 65 configured to transmit coordination support information to support targets. The predictor 62 includes an area risk predictor 620 configured to extract a high risk area from a plurality of local areas obtained by subdividing the target traffic area on the basis of information obtained by performing statistical processing on the recognition information, and a traffic participant risk predictor 625 configured to predict a risk in future of traffic participants in the high risk area on the basis of information related to the high risk area among the recognition information.