Open Access

ARTICLE

FIBTNet: Building Change Detection for Remote Sensing Images Using Feature Interactive Bi-Temporal Network

Jing Wang^1,2,*, Tianwen Lin¹, Chen Zhang¹, Jun Peng^1,*

1 School of Geographic Information and Tourism, Chuzhou University, Chuzhou, 239000, China
2 Anhui Province Key Laboratory of Physical Geographic Environment, Chuzhou University, Chuzhou, 239000, China

* Corresponding Authors: Jing Wang. Email: ; Jun Peng. Email:

Computers, Materials & Continua 2024, 80(3), 4621-4641. https://doi.org/10.32604/cmc.2024.053206

Received 27 April 2024; Accepted 14 August 2024; Issue published 12 September 2024

Abstract

In this paper, a feature interactive bi-temporal change detection network (FIBTNet) is designed to solve the problem of pseudo change in remote sensing image building change detection. The network improves the accuracy of change detection through bi-temporal feature interaction. FIBTNet designs a bi-temporal feature exchange architecture (EXA) and a bi-temporal difference extraction architecture (DFA). EXA improves the feature exchange ability of the model encoding process through multiple space, channel or hybrid feature exchange methods, while DFA uses the change residual (CR) module to improve the ability of the model decoding process to extract different features at multiple scales. Additionally, at the junction of encoder and decoder, channel exchange is combined with the CR module to achieve an adaptive channel exchange, which further improves the decision-making performance of model feature fusion. Experimental results on the LEVIR-CD and S2Looking datasets demonstrate that iCDNet achieves superior F1 scores, Intersection over Union (IoU), and Recall compared to mainstream building change detection models, confirming its effectiveness and superiority in the field of remote sensing image change detection.

---

Keywords

---