The Research on Land Cover Change Detection Employing 
the Deep Learning Model Transformer

Biao Yang

doi:10.70711/aitr.v2i11.7411

The Research on Land Cover Change Detection Employing the Deep Learning Model Transformer

Biao Yang

Abstract

The goal of land cover change detection is to use remote - sensing photos taken at different intervals to identify land surface
changes. This study thoroughly examines the benefits of the Transformer deep learning model in land cover change detection. It explores
Transformer - based models for change detection, identifies major advancements of the Transformer architecture, and methodically examines
CNNs shortcomings in this field. Moreover, representative application instances are used to assess these models limitations and performance.

Keywords

Transformer Model; Remotely Sensed Images; Deep Learning; Feature Change

Full Text:

PDF

Included Database

References

[1] Pan Mengyang, Yang Hang, Fan Xianghui Remote Sensing Image ChangeDetection Based on CNN-Transformer Structure [J]. Liquid

Crystals and Displays, 2024, 39(10):1361-1379.

[2] Saber Mehdipour, Seyed Abolghasem Mirroshandel et al. "Vision Transformers in Precision Agriculture: A Comprehensive

Survey."[2025-04-30].

[3] Song R, Ni W, Cheng W, et al. CSANet: Cross-temporal interaction symmetric attention network for hyperspectral image change detection. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 1-5.

[4] Degao Wang, Zhangyu Sun et al. "Pine wood nematode disease area identification based on multi-temporal multi-source remote sensing

images and BIT model." Geocarto International[2024-01-01].

[5] Biyuan Liu, Huaixin Chen et al. "Transformer-based Multimodal Change Detection with Multitask Consistency Constraints."

ArXiv[2023-10-13].

[6] Significant advantages in three major benchmarks: Improving change detection performance with generative-adversarial augmentation

of dataset. V.A. Knyaz et al.[2024-11-03].

DOI: http://dx.doi.org/10.70711/aitr.v2i11.7411

Refbacks

There are currently no refbacks.