Driving Assistance Detection Region Adjustment for Turn Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driving assistance systems face accuracy deterioration when detecting solid objects during vehicle turns, as the difference between chronologically different bird's-eye view images can incorrectly identify the road surface as a solid object due to changes in vehicle behavior.
Innovation Solution
A driving assistance device with a turning state detection means that modifies the detection region's position, shape, or area based on the vehicle's turning state to prevent false recognition of solid objects, thereby maintaining detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If difference image method is used for solid object detection, then detection capability is provided, but detection accuracy deteriorates during vehicle turning due to false recognition of road surface
Solution Approach 1:
The detection region is divided into multiple sub-regions (first detection region and second detection region) with different detection standards. The first detection region uses a first detection standard while the second detection region uses a second detection standard, allowing selective application of detection stringency based on spatial location relative to the vehicle turning path.
Solution Approach 2:
Different detection standards are applied to different spatial regions. The first detection standard is applied in regions where false recognition is less likely, while the second detection standard is applied in regions prone to false recognition during turning. This local differentiation maintains overall detection accuracy while reducing false positives.
2Area of stationary object
If detection region is expanded to cover more area, then detection coverage is improved, but false recognition increases during turning
Solution Approach 1:
The detection region is segmented into multiple sub-regions with different detection standards applied to each. This allows the overall detection region to be expanded for better coverage while applying stricter detection only where necessary to prevent false recognition during turning.
Solution Approach 2:
The detection standard parameter is changed based on spatial location and vehicle state. By adjusting the detection standard (first vs. second standard) according to the region and turning state, the system maintains high detection coverage while adapting the detection stringency to minimize false recognition in problematic areas.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
When a turning state detection unit 12 detects that a host vehicle Ca is in a turning state, a detection region modification unit 13 alters a position of a detection region with respect to the host vehicle, or a form or an area of the detection region (detection regions Raa, Rab) based on the turning state of the host vehicle Ca. For example, the smaller the turning radius of the host vehicle Ca, the shorter the detection region modification unit 13 sets the region length of the detection region. Hereby, the region closest to the host vehicle Ca is set, to a limited extent, as the detection regions Raa, Rba.