Airport runway foreign matter detection method and device based on characteristics of characteristic spectrum
A foreign object detection and airport runway technology, applied in the field of radar, can solve the problems of waste of time and resources, complex scattering characteristics of airport runways, etc., and achieve the effect of small error
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment 1
[0090] According to the parameters of the classifier, the optimal classification surface is obtained, and the feature vector of the test sample (FOD echo) is judged according to the optimal classification surface. Among them, all false alarm signals fall within the optimal classification surface. If there is no signal, it means that there is no FOD on the runway before the plane takes off, otherwise, it means that there is FOD on the runway before the plane takes off. Specific embodiment 1, two kinds of features feature1 and feature2 are extracted from the test sample (FOD echo), and the trained classifier is used to classify the two kinds of features used for testing.
[0091] For the test sample, use the trained minimum and maximum probability machine to classify it according to the following steps:
[0092] 6a) performing feature extraction on the test sample to obtain a feature vector f={feature1, feature2} formed of the two features for testing;
[0093] 6b) Input the fe...
specific Embodiment 2
[0098] Specific embodiment two: (can replace the implementation process of step 61); extract two kinds of features from the test sample set, and use the trained classifier to classify the two kinds of features used for testing.
[0099] For the test sample, utilize the trained minimum maximum probability machine to classify it according to the following steps: 6a) carry out feature extraction for the test sample, obtain the feature vector f={feature1, feature2};
[0100] 6b) Use the two features corresponding to the background clutter data feature vector and the background clutter data label to train the minimum and maximum probability machine classifier, and obtain the minimum and maximum probability machine classifier parameter a opt and b opt ; where a opt is the optimal solution of the minimum maximum probability machine; b opt = 1;
[0101] 6c) According to parameter a opt and b opt Obtain the optimal classification surface, and judge the FOD echo feature vector acc...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap