A similar landslide recommendation method based on landslide profile image classification model
A technology of profile images and classification models, applied in character and pattern recognition, instruments, calculations, etc., to achieve the effect of high classification accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0034] Such as figure 1 As shown, a similar landslide recommendation method based on the landslide profile image classification model includes the following steps:
[0035] S1. Use ArcGIS to preprocess the landslide profile images in the collected field investigation form or landslide engineering layout documents to obtain ASCII text type data, read the image array in the text data and store it in a two-dimensional array as training data set;
[0036] S2. On the basis of step S1, the data group is multi-classified according to 7 different landslide geological features, and labeled, and used as a supervised learning sample;
[0037] S3, adopt row-column scanning method to image two-dimensional array, obtain the characteristic array that length is , as sample data;
[0038] S4. Use the random forest algorithm to construct a random forest classification model, import 80% of the sample data for learning, 20% of which are used as a verification set, and 80% are used as a training...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


