-
Notifications
You must be signed in to change notification settings - Fork 21
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Data preprocessing #8
Comments
我们这个工作都是基于每个数据每个波段进行的0-1的归一化
G-z-w ***@***.***> 于2023年6月3日周六 15:15写道:
…
您好,请问您是怎么将原SAR和MSI数据进行归一化操作的呢?原图数据范围层次不起,分布不均,但是我看您处理后的数据都在[0,1]范围内,可以告知具体的操作方式吗?谢谢
以下是某些SAR数据某些通道的数据分布:
[image: image]
<https://user-images.githubusercontent.com/95175307/243064856-95ed2f1a-e7d3-4a15-af50-02d7cbcaaef9.png>
[image: image]
<https://user-images.githubusercontent.com/95175307/243064868-74d0709b-7bb8-4951-b6b8-5b91f1ee0874.png>
以下是某些MSI数据某些通道的数据分布:
[image: image]
<https://user-images.githubusercontent.com/95175307/243064907-ef76226d-f455-4c36-9bd8-dc040a8b0944.png>
[image: image]
<https://user-images.githubusercontent.com/95175307/243064916-f9b3bc4d-f10a-44a2-9084-9fbaa01c4bf0.png>
非常期待您的回复。感谢!
—
Reply to this email directly, view it on GitHub
<#8>, or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFL2GZRCG5E2IKLS4OZ35FTXJLQBLANCNFSM6AAAAAAYZD3MR4>
.
You are receiving this because you are subscribed to this thread.Message
ID: ***@***.***>
|
这样会不会损失掉每个通道的偏置信息,只留下每个通道的相对值。 |
任何归一化都会损失一定的偏置信息,这是个trade-off的问题。看你主要是什么应用或是目的了,或是数据的质量如何,遥感图像质量良莠不齐,不像自然图像。
G-z-w ***@***.***> 于2023年6月4日周日 00:32写道:
… 这样会不会损失掉每个通道的偏置信息,只留下每个通道的相对值。
—
Reply to this email directly, view it on GitHub
<#8 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFL2GZRYD763DMOBG5TJVZTXJNRKLANCNFSM6AAAAAAYZD3MR4>
.
You are receiving this because you commented.Message ID:
***@***.***>
|
感谢感谢!! |
您好,请问您是怎么将原SAR和MSI数据进行归一化操作的呢?原图数据范围层次不起,分布不均,但是我看您处理后的数据都在[0,1]范围内,可以告知具体的操作方式吗?谢谢
以下是某些SAR数据某些通道的数据分布:
以下是某些MSI数据某些通道的数据分布:
非常期待您的回复。感谢!
The text was updated successfully, but these errors were encountered: