Map automatic updating method based on remote sensing image, storage medium and system
The invention provides an automatic map updating method based on a remote sensing image, a storage medium and a system. The method comprises the following steps: constructing a deep learning segmentation network; improving the deep learning segmentation network by using a residual network to obtain...
Saved in:
Main Authors | , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
03.08.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention provides an automatic map updating method based on a remote sensing image, a storage medium and a system. The method comprises the following steps: constructing a deep learning segmentation network; improving the deep learning segmentation network by using a residual network to obtain an improved deep learning segmentation network; acquiring a plurality of remote sensing images and corresponding surface feature labeling data; performing one-to-one corresponding random cutting on the plurality of remote sensing images and the corresponding surface feature labeling data to obtain a plurality of training samples; inputting the plurality of training samples into the improved deep learning segmentation network to carry out ground feature recognition training until the recognition precision of all ground features in the remote sensing image by the improved deep learning segmentation network reaches preset verification precision; extracting the remote sensing image of the current time phase of a target |
---|---|
Bibliography: | Application Number: CN202110587305 |