18179501. Spectral Image Relationship Extraction simplified abstract (The Boeing Company)
Contents
Spectral Image Relationship Extraction
Organization Name
Inventor(s)
Leo Ho Chi Hui of Alhambra CA (US)
Haig Francis Krikorian of Fullerton CA (US)
Spectral Image Relationship Extraction - A simplified explanation of the abstract
This abstract first appeared for US patent application 18179501 titled 'Spectral Image Relationship Extraction
The patent application describes a method for real-time subpixel detection and classification using spectral demixing.
- The method involves inputting a spectral library of targets, a multi-spectral image cube, and a list of background image samples.
- A candidate ground spatial distance (GSD) cell within the multi-spectral image cube is selected for spectral demixing.
- The demixed candidate GSD cell is compared against the spectral library and background image samples to determine if it contains an identifiable target.
- If the candidate GSD cell does not resemble a target or a background sample, it is labeled as unknown.
- Local global reconciliation is applied to confirm true detections of targets and reject false detections of non-targets.
- Detected targets or unknowns are output in real-time.
Potential Applications: - Remote sensing applications - Surveillance and security systems - Environmental monitoring
Problems Solved: - Real-time detection and classification of targets in multi-spectral images - Reduction of false detections and confirmation of true targets
Benefits: - Improved accuracy in target detection - Real-time processing capabilities - Enhanced efficiency in analyzing multi-spectral data
Commercial Applications: Title: Real-time Subpixel Detection System for Remote Sensing Applications This technology can be utilized in industries such as defense, agriculture, and disaster management for efficient target detection and classification in real-time.
Questions about Real-time Subpixel Detection and Classification: 1. How does the method of spectral demixing contribute to accurate target detection?
- The spectral demixing process separates the spectral signatures of different materials, allowing for precise identification of targets in multi-spectral images.
2. What are the advantages of using real-time processing for subpixel detection in remote sensing applications?
- Real-time processing enables immediate decision-making based on detected targets, enhancing the efficiency of monitoring and analysis.
Original Abstract Submitted
Real-time subpixel detection and classification is provided. The method comprises receiving input of a spectral library of targets, a multi-spectral image cube, and a list of background image samples. A candidate ground spatial distance (GSD) cell within the multi-spectral image cube is selected for spectral demixing. The spectrally demixed candidate GSD cell is compared against the spectral library and the list of background image samples. A determination is made whether the candidate GSD cell contains an identifiable target. The candidate GSD cell is labeled unknown if it does not resemble a target in the spectral library nor a sample in the list of potential background image sample. Local global reconciliation is applied to the candidate GSD cell to reject false detections of non-targets and confirm true detection of targets. Detected targets from the candidate GSD cell or an unknown are output in real-time.
