Radar Double-Bounce Detection for False-Positive Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Radar systems in autonomous vehicles face inaccuracies due to double bounce radar returns, leading to false-positive object detections and misclassifications, which can compromise safety and efficiency in navigating environments.
Innovation Solution
A radar management system that employs a multistage filtering technique to detect and mitigate double bounce radar signals by evaluating azimuth, range, and velocity criteria, clustering radar points, and modifying data to remove or label erroneous detections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If radar systems transmit radio waves to detect objects, then object detection capability is improved, but false-positive detections occur due to double bounce reflections
Solution Approach 1:
The patent converts the harmful double bounce reflection into a useful detection target by analyzing its characteristic signature (azimuth, range, velocity relationships) and identifying it as a specific object type rather than treating it as noise to be eliminated. This allows the system to utilize the reflected signal while distinguishing it from genuine objects through pattern recognition.
Solution Approach 2:
The patent changes the approach from detecting physical parameters (azimuth, range, velocity) of objects to detecting mathematical relationships between these parameters. By establishing that double bounce returns exhibit specific parameter relationships (e.g., velocity ratio of 2:1, specific azimuth-range correlations), the system can reliably distinguish false positives from genuine detections.
2Measurement precision
If multistage filtering techniques are applied to detect double bounce signals, then detection accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent segments the object detection process into distinct stages: initial object detection, candidate identification based on parameter relationships, verification against geometric constraints, and final classification. This segmentation allows each stage to focus on specific aspects of the problem, reducing overall complexity while maintaining high accuracy.
Solution Approach 2:
The patent performs preliminary filtering by identifying candidate double bounce detections based on characteristic parameter relationships before applying more complex verification. This preliminary action eliminates obvious false positives early in the process, reducing the computational burden of subsequent analysis stages.
3Reliability
If radar data is processed to identify and remove false positives, then safety is improved, but processing time increases
Solution Approach 1:
The patent applies different processing depths to different detected objects based on their risk characteristics. High-priority candidates exhibiting strong double bounce signatures undergo comprehensive multi-stage verification, while low-priority detections receive minimal processing. This localized quality approach ensures safety-critical detections are thoroughly validated without unnecessarily processing all detections at maximum detail.
Solution Approach 2:
The patent implements a tiered verification process where only candidate detections meeting specific criteria undergo full multi-stage analysis, while others receive partial processing or are accepted with standard validation. This partial action approach maintains safety for critical cases while reducing overall processing time by avoiding exhaustive analysis of all detections.
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
Improves the accuracy of radar data processing, reducing processing time and latency, thereby enhancing the safety and efficiency of autonomous vehicle operations by filtering out false-positive detections.
Implementation Method 1
measuring a distance from the radar device to the object by transmitting a radio wave and receiving a reflection of the radio wave from the object
Implementation Method 2
evaluating azimuth, range, and velocity criteria
Data Source
AI summary
Techniques for detecting radar data inaccuracies using a multistage filtering technique are discussed herein. A vehicle may capture radar data including a set of radar points. The vehicle can input the radar data into a machine-learning model configured to detect objects and/or generate bounding boxes associated with such detected objects. In some instances, the vehicle may cluster the radar points such that a cluster includes the radar points located proximate to and/or within a bounding box. To identify double bounce object detections, the vehicle may determine whether a detected object is a false-positive double bounce object detection based on evaluating the azimuth, range, and relative velocity double bounce criteria. Based on the detected object satisfying the double bounce criteria for azimuth, range, and relative velocity, the vehicle may modify the radar data.