Vehicle Pre-Crash Control for Radar Ghost Object Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional driving supporting apparatuses struggle to accurately determine the presence of 'ghost' objects, which are erroneously detected due to sub-reflections from boundary structural objects, leading to potential unnecessary pre-crash controls.
Innovation Solution
The apparatus employs a dual-sensor system, where a first sensor (millimeter wave radar) detects objects and a second sensor (camera) specifically detects boundary structural objects, allowing for accurate differentiation and reduction of ghost object detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single millimeter wave radar is used to detect both objects and boundary structural objects, then the device complexity is reduced, but the measurement precision of boundary structural object detection deteriorates, leading to ghost object detection errors
Solution Approach 1:
The detection function is segmented into two independent parts: a first sensor (millimeter wave radar) dedicated to detecting moving objects, and a second sensor (camera) dedicated to detecting boundary structural objects. This segmentation allows each sensor to optimize its detection algorithm for its specific target type, eliminating the interference that causes ghost detection when using a single sensor for both purposes.
Solution Approach 2:
The second sensor (camera) acts as an intermediary to detect boundary structural objects, providing independent verification data that mediates the ghost detection problem. By introducing this intermediate detection layer, the system can distinguish between real objects and ghost reflections without compromising the primary radar's object detection function.
2Loss of information
If the millimeter wave radar detects sub-reflection points from boundary structural objects, then information about boundary structural objects is obtained, but the reliability of object detection deteriorates due to ghost detection
Solution Approach 1:
The detection system is segmented into two independent detection streams: one for objects (first sensor) and one for boundary structural objects (second sensor). This prevents the contamination of object detection information with ghost detection errors, as each sensor type processes its designated target independently without cross-interference.
Solution Approach 2:
The system uses feedback from the second sensor's boundary structural object detection to improve the reliability of the first sensor's object detection. By comparing radar-detected objects with camera-detected boundary structures, the system can identify and filter out ghost detections, creating a feedback loop that enhances overall detection reliability.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the accuracy of boundary structural object detection, thereby reducing the likelihood of unnecessary pre-crash controls and improving the reliability of collision avoidance systems.
Implementation Method 1
a first sensor that detects an object present outside of a vehicle based on a reflection of a radio wave that the first sensor radiates
Implementation Method 2
a second sensor that detects a boundary structural object positioned at a boundary between a road area on which the vehicle can travel and an area other than the road area
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A driving supporting apparatus comprising a first sensor that detects an object present outside of a vehicle based on a reflection of a radio wave that the first sensor radiates, a second sensor that detects a boundary structural object positioned at a boundary between a road area on which the vehicle can travel and an area other than the road area, and a control unit configured to perform a pre-crash control to avoid a collision between the vehicle and a recognized object that is the object detected by the first sensor. The control unit is configured to make a possibility that the pre-crash control is performed when a far-side position condition to be satisfied when the recognized object is located at a far side of the boundary structural object with respect to the vehicle is satisfied lower than when the far-side position condition is not satisfied.