Remote sensing image dense target deep learning detection method
A technology of dense targets and remote sensing images, applied in the field of high-resolution remote sensing image recognition, can solve the problem that extremely dense targets are difficult to be effectively extracted, and achieve the effect of ground object positioning and high-precision ground object positioning.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0026] Below by embodiment, further illustrate outstanding feature and remarkable progress of the present invention, only in order to illustrate the present invention and in no way limit the present invention.
[0027] The embodiment of the present invention provides a remote sensing image dense target deep learning detection method, which specifically includes the following steps:
[0028] (1) Using self-labeled high-spatial-resolution remote sensing image dense greenhouse object detection data set (GHDOERS), the GH DOERS training data set contains 1290 Google Earth images, and the test set and verification set are 430 and 862 images respectively. is 512x512 pixels. The dataset contains data from 6 provinces and regions across the country, including: Hubei Province, Liaoning Province, Shandong Province, Xinjiang Uygur Autonomous Region, Shaanxi Province, and Jiangsu Province.
[0029] 1.1. Select the training set and test set TrainA and TestB in the data set for the sample d...
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