Radar Target Detection Learning from Reception and Tracking Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Radar devices face challenges in detecting distant, small, or cluttered targets in low-SNR environments, and enlarging the antenna to improve detection performance increases hardware and cost.
Innovation Solution
A learning device and method that generates learning data from radar signals and tracking signals to train a target detection model, which is then applied to enhance detection accuracy without increasing hardware costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the antenna is enlarged to improve detection performance, then the detection accuracy is improved, but the hardware cost increases
Solution Approach 1:
The patent replaces the mechanical approach of enlarging the antenna with a signal processing approach using machine learning. The target detection model learns from reception signals and tracking signals to identify targets, substituting physical hardware expansion with intelligent algorithmic processing to achieve improved detection accuracy without increasing antenna size or hardware cost.
Solution Approach 2:
The patent changes the parameter of detection approach from physical antenna characteristics to signal processing parameters. By training a target detection model using learning data derived from reception signals and tracking signals, the system adjusts detection parameters algorithmically rather than physically, enabling improved detection performance through software-based parameter optimization.
2Reliability
If the antenna is enlarged to detect distant and small targets, then the detection capability is improved, but the cost increases
Solution Approach 1:
The patent substitutes mechanical antenna enlargement with an intelligent signal processing system. The target detection model, trained using learning data from reception signals and tracking signals, enhances detection capability for distant and small targets through algorithmic pattern recognition rather than physical hardware expansion, thereby improving reliability without increasing cost.
Solution Approach 2:
The patent creates a virtual model of target detection through machine learning. The target detection model learns from training data that includes reception signals and tracking signals, creating a computational copy of the detection process that can identify targets without requiring physical hardware modifications, thus enhancing detection capability cost-effectively.
3Measurement precision
If the antenna is enlarged to detect targets in clutter and jamming, then the detection performance is improved, but the hardware cost increases
Solution Approach 1:
The patent replaces mechanical antenna enlargement with intelligent signal processing to handle clutter and jamming. The target detection model, trained using learning data from reception signals and tracking signals, learns to distinguish targets from clutter and jamming through pattern recognition, achieving improved detection performance without increasing hardware cost or antenna size.
Data Source
AI summary
The learning device learns the target detection model used in the radar device. The learning device includes an acquisition unit, a learning data generation unit, and a learning processing unit. The acquisition unit acquires a reception signal generated based on the received wave and a tracking signal generated based on the reception signal from the radar device. The learning data generation unit generates learning data using the reception signal and the tracking signal. The learning processing unit learns a target detection model that detects a target from the reception signal, using the learning data.