Related Experiment Video
Updated: Aug 24, 2025
08:47
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
1.6K
A Method for Extracting Building Information from Remote Sensing Images Based on Deep Learning
Lianying Li1, Xi Chen2, Lianchao Li3
1School of Art and Design, Harbin University, Harbin, Heilongjiang 150086, China.
Computational Intelligence and Neuroscience
|October 24, 2022
Summary
This study introduces a new deep learning method for remote sensing image analysis, improving building information extraction and object contour accuracy. The approach enhances segmentation performance and efficiency for diverse remote sensing applications.
Area of Science:
- Remote Sensing
- Computer Vision
- Artificial Intelligence
Background:
- Semantic segmentation of remote sensing images is crucial for information extraction.
- Current algorithms struggle with precise object contour capture and inter-object interaction analysis.
Purpose of the Study:
- To propose a deep learning-based method for enhanced building information extraction from remote sensing images.
- To improve the accuracy and efficiency of object contour capture and dataset fitting.
Main Methods:
- Integration of the DeepLabv3+ semantic segmentation model with Mixconv2d for multi-scale feature recognition.
- Application of Rdrop Loss regularization to enhance contour accuracy and dataset consistency across different resolutions.
Main Results:
- The proposed method demonstrates improved algorithm efficiency and result accuracy in remote sensing image segmentation.
- Effective capture of object contours and improved segmentation performance were observed.
Conclusions:
- The developed deep learning approach offers a robust solution for semantic segmentation in remote sensing.
- The method effectively addresses limitations in contour detection and information extraction from remote sensing data.
