Driving Assistance Detection Region Adjustment for Turn Accuracy

Resolve Bottlenecks,
Find Innovative Solutions
Generate 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

VSEngineering 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

Engineering Contradiction:
Improvesolid object detection accuracyVSAvoidfalse recognition of road surface as solid object
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

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.

Inventive Principle:
Principle #1Segmentation

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.

Inventive Principle:
Principle #3Local quality

2Area of stationary object

If detection region is expanded to cover more area, then detection coverage is improved, but false recognition increases during turning

Engineering Contradiction:
Improvedetection region areaVSAvoidfalse recognition of road surface
Core Design Contradiction:
Area of stationary objectVSObject-affected harmful factors

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.

Inventive Principle:
Principle #1Segmentation

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.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP2741270B1Driving assistance apparatus and driving assistance method
Publication Date: 2020.11.25 NISSAN MOTOR CO LTD
  • EP2741270B1 patent drawingFigure 1
  • EP2741270B1 patent drawingFigure 2
  • EP2741270B1 patent drawingFigure 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.