DONATE

IAHR Document Library


« Back to Library Homepage « Book of Abstracts of the 9th IAHR Europe Congress (Lulea, 20...

Detection of Building Changes Using CNN with Transformers for Remote Sensing near Riverside Areas

Author(s): Jaehyun Shin; Seongwook Choi; Dong Sop Rhee

Linked Author(s):

Keywords: No Keywords

Abstract: This research utilizes a method for detecting building occupation changes near riverside areas using the Bitemporal Image Transformer as the change detection model, with LEVIR-CD database used for training and detection. The model combines CNN based feature extraction with context learning based on transformers, then generates a pixel level change mask by computing and segmenting the refined feature differences between the two times. This change detection method shows to be a usable tool for identifying building changes near riverside areas.

DOI:

Year: 2026

Copyright © 2026 International Association for Hydro-Environment Engineering and Research. All rights reserved. | Terms and Conditions