Radar Wheel Detection for Lateral Velocity Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object detection systems in vehicles face challenges in accurately estimating the two-dimensional velocity of remote vehicles, especially when they are moving in a predominantly lateral or tangential direction relative to the host vehicle, and in correlating radar point data with camera image data.
Innovation Solution
A method and system that use target data from two radar sensors to identify the wheels of a remote vehicle as clusters of radar points with varying Doppler range rate values, performing fusion calculations to accurately estimate the position, orientation, and velocity of the remote vehicle, and simultaneously calibrate radar sensor alignment using wheel measurement data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional object detection systems use radar and camera sensors to detect remote vehicles, then object presence can be detected, but accurate estimation of two-dimensional velocity especially in lateral direction cannot be achieved
Solution Approach 1:
The patent segments the remote vehicle into multiple detectable components, specifically identifying wheels as distinct radar point clusters. By detecting individual wheels rather than treating the vehicle as a single object, the system can calculate more accurate two-dimensional velocity including lateral motion, resolving the contradiction between detection capability and measurement precision.
Solution Approach 2:
The patent transitions from conventional one-dimensional radar velocity measurement to two-dimensional velocity estimation by incorporating lateral velocity components. This is achieved through wheel detection and cluster analysis that captures motion in both longitudinal and lateral directions, enabling accurate velocity estimation for vehicles moving in predominantly lateral directions.
2Reliability
If radar point data is used to detect remote vehicles, then object detection is achieved, but accurate correlation with camera image data is difficult
Solution Approach 1:
The patent uses wheel detection as an intermediary element to correlate radar and camera data. Wheels serve as distinctive, easily identifiable features that appear in both radar point clouds and camera images, providing a common reference framework that simplifies sensor fusion and improves correlation accuracy between different sensor modalities.
3Measurement precision
If wheel detection is performed using radar point clusters with varying Doppler values, then accurate wheel location is achieved, but system complexity increases
Solution Approach 1:
The patent applies local quality analysis by examining specific regions of radar point data where wheels are expected to be located. Instead of processing the entire point cloud uniformly, the system focuses computational resources on identifying wheel-specific patterns (clusters with varying Doppler values) in relevant spatial zones, improving wheel location accuracy while managing algorithmic complexity.
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 provides accurate estimation of remote vehicle velocity and position, enabling effective warnings or evasive maneuvers in collision prevention systems and improving radar sensor alignment, leading to enhanced safety in lateral collision scenarios.
Implementation Method 1
Wheels on the remote vehicle are identified as clusters of radar points with essentially the same location but substantially varying Doppler range rate values
Data Source
AI summary
A method and system are disclosed for tracking a remote vehicle which is driving in a lateral position relative to a host vehicle. Target data from two radar sensors are provided to an object detection fusion system. Wheels on the remote vehicle are identified as clusters of radar points with essentially the same location but substantially varying Doppler range rate values. If both wheels on the near side of the remote vehicle can be identified, a fusion calculation is performed using the wheel locations measured by both radar sensors, yielding an accurate estimate of the position, orientation and velocity of the remote vehicle. The position, orientation and velocity of the remote vehicle are used to trigger warnings or evasive maneuvers in a Lateral Collision Prevention (LCP) system. Radar sensor alignment can also be calibrated with an additional fusion calculation based on the same wheel measurement data.