High-resolution remote sensing image saliency target detection method combining frequency and edge learning
A remote sensing image and target detection technology, applied in neural learning methods, instruments, scene recognition, etc., can solve the problem of insufficient detection ability of remote sensing images, and achieve the effect of strengthening frequency information
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0029] refer to figure 1 As shown, it is a high-scoring remote sensing image saliency target detection method combining edge learning and frequency channel attention of the present invention, and the specific steps are as follows:
[0030] (1) Making high-scoring remote sensing image samples, including the following steps:
[0031] (1-1) Prepare high-scoring remote sensing images: Manually select salient areas, use ArcGIS software to manually mark the edges of the object targets, draw strictly following the boundaries of the real objects, and assign attribute values of semantic types to the objects, among which salient areas are drawn. The label is 1, and other areas are marked as 0, and the corresponding vector file and original image are obtained, and the vector file is rasterized into surface labels and line labels.
[0032] (1-2) Expand the data: perform data enhancement operations such as mirroring, rotating, and cropping operations on the image obtained in step (1-1)...
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