Radar Doppler Spectrum Encoding for Low-Compute Object Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automotive radar systems face challenges in efficiently processing large volumes of radar data for object detection, which can overwhelm the processing capabilities of onboard controllers, hindering real-time object detection and autonomous driving applications.
Innovation Solution
A method involving doppler spectrum encoding is employed to reduce the size of radar tensors by identifying a predetermined number of reflection intensity peaks, generating encoded vectors, and using neural networks for feature extraction and object detection, allowing for real-time processing on less powerful controllers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If radar data is processed with high detail and completeness, then object detection accuracy is improved, but processing complexity and computational load increase
Solution Approach 1:
The patent extracts only the most relevant features from radar data by identifying and encoding peak reflection intensities. Instead of processing the entire radar tensor, the system extracts key peaks (typically 3-5 per range-angle combination) that contain the most important object information, thereby reducing processing complexity while maintaining detection accuracy.
Solution Approach 2:
The patent transforms the radar data representation by changing parameters from raw reflectivity values to encoded vectors containing peak intensity, frequency, and width. This parameter transformation reduces data dimensionality and complexity while preserving the essential characteristics needed for accurate object detection.
2Reliability
If complete radar tensor data is processed, then detection reliability is improved, but processing time increases
Solution Approach 1:
The system extracts only the essential peak information from the complete radar tensor, processing only the most significant reflection intensities rather than all data points. This extraction approach maintains detection reliability by focusing on the most informative features while dramatically reducing processing time.
Solution Approach 2:
The patent applies partial action by processing only a subset of the most important peaks (3-5 peaks per range-angle combination) rather than the complete radar dataset. This partial processing approach provides sufficient information for reliable detection within real-time constraints.
3Measurement precision
If detailed feature extraction is performed, then object detection accuracy is improved, but computational power requirements increase
Solution Approach 1:
The patent extracts only the essential features needed for accurate detection: peak intensity, frequency, and width. By extracting only these critical features rather than performing comprehensive analysis of all radar data, the system achieves high detection accuracy with reduced computational power requirements suitable for onboard controllers.
Data Source
AI summary
A method of performing doppler spectrum encoding for radar object detection. The method includes receiving a radar tensor including a doppler for range and angle combinations. An encoded vector is generated for each of the range and angle combinations. The encoded vector includes a reflection intensity, a frequency of the reflection intensity, and a width of a reflection intensity peak for a predetermined number of greatest reflection intensity peaks for each of the range and angle combinations. An encoded vector dataset is generated from the encoded vectors. Feature extraction is performed on the encoded vector dataset with a feature extraction neural network to generate an extracted feature dataset with extracted feature information for each of the range and angle combinations. Object detection is performed on the extracted feature dataset with an object detection neural network to generate an object detection output for identifying objects.