Pattern-Based Target Detection for Low-Velocity, Small Targets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately detect, track, and identify targets, particularly those with low velocity or small dimensions, and are prone to missing detections due to factors like clutter and low Radar Cross Section (RCS), which conventional methods like Kalman filters cannot effectively handle.
Innovation Solution
A system and method that processes data points from detection systems to identify subsets arranged in specific patterns indicative of target types, allowing for improved detection and tracking by analyzing data over extended periods and using multiple detection thresholds, machine learning algorithms, and adaptive detection system operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional detection systems use standard detection thresholds and processing methods, then system operation is simple and responsive, but detection accuracy for low velocity and small dimension targets deteriorates
Solution Approach 1:
The patent segments the detection process into multiple stages: initial detection with first threshold, pattern recognition analysis, and secondary detection with adjusted thresholds. This segmentation allows the system to handle different target types with specialized processing, improving detection accuracy for low velocity and small dimension targets while maintaining overall system manageability through modular architecture.
Solution Approach 2:
The system dynamically adjusts detection thresholds and processing parameters based on the detected pattern type and target characteristics. The processing circuitry adapts detection parameters in real-time based on analyzed patterns, enabling optimized detection accuracy for specific target categories without requiring complex fixed-configuration systems.
2Reliability
If the detection system processes data from extended periods to improve detection accuracy, then detection reliability improves, but system responsiveness deteriorates
Solution Approach 1:
The system performs preliminary pattern recognition analysis on detected data points to identify characteristic patterns before final target confirmation. This preliminary action filters and organizes data in advance, allowing the system to maintain extended processing windows for reliability while reducing actual response time by having data pre-processed and categorized.
Solution Approach 2:
The detection system continuously processes data points as they become available, maintaining an ongoing analysis of pattern compliance rather than batch processing. This continuous action ensures that detection reliability is maintained through sustained monitoring while responsiveness is preserved through real-time processing without idle periods.
3Adaptability or versatility
If the detection system uses multiple detection thresholds to handle different target types, then detection accuracy for various target categories improves, but device complexity increases
Solution Approach 1:
The processing circuitry is designed as a universal system that handles multiple target types through a single integrated architecture. The same circuitry analyzes different patterns and applies appropriate thresholds dynamically, eliminating the need for separate dedicated processing systems for each target type while maintaining high adaptability and detection accuracy across various categories.
Solution Approach 2:
The system changes detection parameters such as thresholds and analysis criteria based on the identified pattern type and target characteristics. By dynamically adjusting parameters rather than using fixed multiple threshold systems, the patent achieves versatile target type detection with reduced processing complexity through parameter adaptation rather than structural complexity.
4Measurement precision
If the detection system stores and processes historical data points to identify patterns, then target identification accuracy improves, but information processing load increases
Solution Approach 1:
The system extracts and stores only the essential pattern information from detected data points rather than retaining all raw data. By taking out and storing only the characteristic pattern features and compliance information, the system reduces the quantity of stored and processed historical data while maintaining high target identification accuracy through pattern recognition.
Solution Approach 2:
The system creates simplified representations or copies of historical data that capture essential pattern information without retaining full detail. These compressed pattern models allow the system to process historical information efficiently, reducing data processing volume while maintaining identification accuracy through the use of representative pattern copies rather than complete data records.
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
There are provided systems and methods comprising obtaining at least one set of data points informative of one or more targets detected by at least one detection system, wherein each given data point of the at least one set of data points is informative of a target of said one or more targets and is associated with data informative of at least one of a position or a velocity of the target, and processing the at least one set of data points to identify at least one subset of data points of the set of data points, arranged in compliance with a given pattern informative of a certain type of target.