Scene Understanding Device for Vehicle Risk Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing degree-of-risk calculation apparatuses face increased arithmetic load when detecting multiple obstacles, leading to longer calculation times.
Innovation Solution
A scene understanding device that sets pre-defined obstacle detection frames and close observation frames corresponding to road structures, determining obstacles and calculating risk only at specific spots, thereby reducing unnecessary calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If risk potentials are calculated for all gridded areas around the host vehicle, then comprehensive risk assessment is achieved, but arithmetic load increases excessively when many obstacles are detected
Solution Approach 1:
The patent divides the monitoring area into specific spot regions where vehicles are likely to bump into other vehicles or pedestrians, rather than calculating risk for all gridded areas. This segmentation focuses computational resources on high-risk zones only, reducing overall arithmetic load while maintaining comprehensive risk assessment where needed.
Solution Approach 2:
The patent applies different processing quality levels to different spatial regions. High-risk specific spots receive detailed risk calculation with multiple obstacle detection frames, while other areas use simpler assessment methods. This local quality approach optimizes the balance between assessment comprehensiveness and computational efficiency.
2Reliability
If risk potentials are calculated for all gridded areas, then complete coverage is achieved, but calculation time increases
Solution Approach 1:
The patent segments the calculation process into two stages: first identifying specific spots with high collision risk based on road structure, then performing detailed risk potential calculation only in those segmented regions. This reduces calculation time while maintaining complete coverage of areas that matter most for safety.
Solution Approach 2:
The patent performs preliminary identification of specific spots using obstacle detection frames shaped according to road structure before conducting full risk calculations. This preliminary action filters out areas where detailed calculation is unnecessary, reducing overall calculation time while ensuring complete coverage of high-risk zones.
Data Source
AI summary
A scene understanding device obtains map data where one, two or more obstacle detection frames, shaped corresponding to a road structure, for detecting an obstacle are set in advance for a specific spot on a road where a vehicle would otherwise bump into a vehicle or a pedestrian. The scene understanding device determines whether there exists an obstacle in the obstacle detection frames set for the specific spot on a scheduled traveling route of a host vehicle, and calculates the degree of risk at the specific spot based on a result of determining whether there exists an obstacle therein.