Vehicle Target Detection with Longitudinal Risk Recalculation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle target detection systems generate erroneous warnings due to errors in speed estimation in the transverse direction, particularly when a target moves in the longitudinal direction, leading to inaccurate distance and speed measurements caused by micro-Doppler effects and a small Radar Cross Section (RCS) of pedestrians.
Innovation Solution
A target detection system for vehicles that computes a final risk level by reevaluating time-to-collision and impact point, considering changes in transverse speed, using both detection sensors for reflected waves and camera sensors for image data to accurately assess the presence and movement of targets, thereby reducing erroneous warnings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If radar detection is used to detect targets in the blind spot area, then target detection capability is improved, but erroneous warnings occur due to speed estimation errors in the transverse direction
Solution Approach 1:
The system changes the parameter being monitored from transverse speed to longitudinal speed. When a target is detected in the blind spot area, the system determines whether the target is moving in the longitudinal direction (toward or away from the host vehicle) rather than relying on transverse speed measurements. This parameter change eliminates the speed estimation errors caused by micro-Doppler effects and short transverse distances.
Solution Approach 2:
Instead of using the conventional approach of estimating transverse speed to assess collision risk, the system inverts the approach by using longitudinal speed estimation. The control unit determines collision risk based on whether the target is approaching or receding in the longitudinal direction, which is the opposite of the traditional transverse speed-based method and avoids the associated measurement errors.
2Difficulty of detecting and measuring
If micro-Doppler effects are used for target classification, then target type identification is improved, but speed estimation accuracy deteriorates due to additional Doppler shifts
Solution Approach 1:
The system segments the speed measurement function from the target classification function. While micro-Doppler effects are utilized for target classification (identifying whether the target is a pedestrian, vehicle, or other object), the collision risk assessment uses a separate longitudinal speed estimation that is not contaminated by the micro-Doppler effects used for classification.
Solution Approach 2:
The system introduces an intermediary approach where the longitudinal speed component is extracted and used as the primary metric for collision risk assessment, while micro-Doppler analysis is used separately for target classification. This intermediary longitudinal speed measurement acts as a mediator that is not affected by the micro-Doppler effects that complicate transverse speed measurements.
3Reliability
If transverse speed is used for collision risk assessment, then risk evaluation is improved, but false alarms increase due to speed errors when targets move in longitudinal direction
Solution Approach 1:
The system changes the parameter for collision risk assessment from transverse speed to longitudinal speed. By determining whether a target is moving toward or away from the host vehicle in the longitudinal direction, the system eliminates the speed estimation errors that occur when targets move primarily in the longitudinal direction, thereby reducing false alarms while maintaining reliable risk assessment.
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
The system provides a more precise final risk level assessment, reducing false alarms by accounting for transverse speed changes and improving the accuracy of target detection, especially for pedestrians, thereby enhancing safety and reducing unnecessary warnings.
Implementation Method 1
estimate a distance or a relative speed between the radar and the different vehicle or the obstacle using a time difference between these two signals and an amount of change in Doppler frequency
Implementation Method 2
receive an electromagnetic wave signal reflected from a different vehicle or an obstacle
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In a case where a person moves away in a longitudinal direction from the vicinity of a vehicle, a condition for generating a warning is satisfied due to a change in a speed in a transverse direction. Thus, a warning system generates an erroneous warning. In order to solve this problem, there are proposed a target detection system for a vehicle and a target detection method for a vehicle, both of which are capable of computing a final risk level, taking into consideration not only results of recomputing a time-to-collision and an impact point, but also the presence or absence of a target that is detected by a camera sensor. The time-to-collision and the impact point are recomputed, taking into consideration a change in a speed in a transverse direction that occurs when the target moves in the longitudinal direction.