August 16, 2025WaterOpen Access

Automatic Detection System for Rainfall-Induced Shallow Landslides in Southeastern China Using Deep Learning and Unmanned Aerial Vehicle Imagery

View Full Paper

Ask AI

Bookmark

The system achieves a pixel accuracy of 92.3%, significantly improving landslide detection effectiveness compared to traditional methods.
Mean Intersection over Union stands at 90.7%, indicating high precision in identifying landslide boundaries in real time.
An automatic detection system employs deep learning and UAV images for timely hazard assessment in southeastern China.
This novel approach supports emergency response efforts, emphasizing the importance of automation and accuracy in landslide identification.

Discussion

No takes yet. Share an insight, caveat, or question.

Automated system improves landslide detection accuracy in southeastern China, highlighting UAV and deep learning integration.

Zhu et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark