Laplace regularization least square synthetic aperture radar automatic target recognition method
An automatic target recognition, least squares technology, applied in the field of radar, can solve the problems of high recognition rate, low recognition rate, poor training performance, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0053] With reference to Fig. 1 and Fig. 2, Fig. 1 is the flowchart principle block diagram of the present invention's implementation step, Fig. 2 is the target image that the present invention is mainly aimed at, the training set is the image of 17 ° overlooking angle in the MSTAR data, and the test set is the image in the MSTAR data 15° top view image.
[0054] For the specific problem of SAR automatic target recognition, the KPCA feature extraction based on the present invention and Laplacian regularization least squares SAR automatic target recognition method are specifically described as follows:
[0055] Preprocessing is performed first, and a 60×60 area is cut from the center of the original 128×128 image, which contains the entire target, and the redundant background area is removed. On this basis, KPCA is used to extract the 35-dimensional features of the respective target images, and normalized to [-1, 1].
[0056] Divide each type of training samples in the range o...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com