Adaptive Radar Clutter Removal via Trajectory Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional map-based clutter removal mechanisms in vehicle radar systems are unreliable, as they often erroneously identify moving objects as static clutter, leading to failure in detecting critical events like pedestrians entering the street, and waste resources by focusing on static objects.
Innovation Solution
Adaptive clutter removal methods that analyze radar scans in real-time using characteristics such as Doppler velocity, track uniformity, displacement vector, and point density to dynamically identify and flag static objects without relying on geometric map data, allowing the system to focus on moving objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If map-based clutter removal is used to remove echoes from static objects, then processing efficiency is improved by filtering out static clutter, but reliability deteriorates because moving objects near static objects are erroneously removed
Solution Approach 1:
The patent transitions from static map-based clutter removal to dynamic trajectory-based clutter removal. By analyzing the motion trajectories of radar targets over multiple frames and comparing them with expected vehicle motion patterns, the system dynamically determines whether targets are clutter or valid moving objects. This resolves the contradiction by maintaining high processing efficiency while improving reliability through adaptive, real-time motion analysis.
Solution Approach 2:
The patent changes the basis for clutter identification from spatial parameters (map coordinates) to temporal parameters (trajectory characteristics, Doppler velocity, displacement vectors). By monitoring how target positions, velocities, and accelerations change over time, the system can distinguish between stationary clutter and moving objects even when they are spatially close, thereby maintaining processing efficiency while eliminating false removals.
2Reliability
If all static objects are monitored and processed, then clutter removal coverage is improved, but processing complexity increases and system performance deteriorates
Solution Approach 1:
The patent extracts only the essential characteristics needed for clutter identification (trajectory patterns, Doppler velocity, displacement vectors) from the full radar data set. By focusing computation on these key parameters rather than processing all raw radar returns for all potential clutter objects, the system achieves comprehensive clutter removal coverage while maintaining acceptable processing complexity and system performance.
Solution Approach 2:
The patent applies partial action by selectively processing only those radar targets that exhibit characteristics consistent with clutter (e.g., stationary or slowly moving targets with trajectories matching vehicle motion). Rather than uniformly processing all detected objects, the system applies simplified clutter removal logic to relevant targets, reducing overall processing complexity while maintaining reliable clutter removal coverage.
3Ease of operation
If map data is used to identify clutter locations, then clutter identification is simplified, but accuracy deteriorates because map data may not reflect real-time object positions
Solution Approach 1:
The patent implements feedback by continuously comparing radar-detected target trajectories with expected vehicle motion patterns and updating clutter identification decisions in real-time. This closed-loop approach maintains the simplicity of automated clutter identification while dramatically improving accuracy, as the system adapts to actual environmental conditions rather than relying on potentially outdated or inaccurate map data.
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 improves the accuracy and reliability of clutter removal, enhancing the vehicle's ability to detect moving objects and reduce processing complexity, thereby supporting safer navigation decisions.
Implementation Method 1
A characteristic indicative of a trajectory pattern relating to one or more respective sets of target points is obtained... the characteristic is determined by computing an average Doppler velocity between locations of the one or more respective sets of target points
Data Source
AI summary
Various embodiments of the present technology can include systems, methods, and non-transitory computer readable media configured to adaptively identify clutter points representing static objects from a sensor data scan. A plurality of sensor data scans are captured, by a sensor unit placed on a vehicle, at a plurality of consecutive time instants while the vehicle is traveling along a route. A set of target points from each of the plurality of sensor data scans is identified. A characteristic indicative of a trajectory pattern relating to one or more respective sets of target points is obtained from one or more sensor data scans taken at consecutive time instants. In response to determining that the characteristic satisfies a pre-defined condition, an indicator with the respective sets of target points is adopted as relating to one or more static objects in an environment at which the vehicle is situated.