EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TChange: A Hybrid Transformer-CNN Change Detection Network

Yupeng Deng, Yu Meng, Jingbo Chen, Anzhi Yue, Diyou Liu, Jing Chen

Remote Sensing · 22.02.2023 · 15 (5) · 1219

DOI: 10.3390/rs15051219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 22.02.2023. Verfasst von Yupeng Deng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Change detection is employed to identify regions of change between two different time phases. Presently, the CNN-based change detection algorithm is the mainstream direction of change detection. However, there are two challenges in current change detection methods: (1) the intrascale problem: CNN-based change detection algorithms, due to the local receptive field limitation, can only fuse pairwise characteristics in a local range within a single scale, causing incomplete detection of large-scale targets. (2) The interscale problem: Current algorithms generally fuse layer by layer for interscale communication, with one-way flow of information and long propagation links, which are prone to information loss, making it difficult to take into account both large targets and small targets. To address the above issues, a hybrid transformer–CNN change detection network (TChange) for very-high-spatial-resolution (VHR) remote sensing images is proposed. (1) Change multihead self-attention (Change MSA) is built for global intrascale information exchange of spatial features and channel characteristics. (2) An interscale transformer module (ISTM) is proposed to perform direct interscale information exchange. To address the problem that the transformer tends to lose high-frequency features, the use of deep edge supervision is proposed to replace the commonly utilized depth supervision. TChange achieves state-of-the-art scores on the WUH-CD and LEVIR-CD open-source datasets. Furthermore, to validate the effectiveness of Change MSA and the ISTM proposed by TChange, we construct a change detection dataset, TZ-CD, that covers an area of 900 km2 and contains numerous large targets and weak change targets.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Deng, Y., Meng, Y., Chen, J., Yue, A., Liu, D., & Chen, J. (2023). TChange: A Hybrid Transformer-CNN Change Detection Network. Remote Sensing, 15(5), 1219. https://doi.org/10.3390/rs15051219

Vancouver

Deng Y, Meng Y, Chen J, Yue A, Liu D, Chen J. TChange: A Hybrid Transformer-CNN Change Detection Network. Remote Sensing. 2023;15(5):1219. doi:10.3390/rs15051219

BibTeX
@article{Deng2023,
  author = {Deng, Yupeng and Meng, Yu and Chen, Jingbo and Yue, Anzhi and Liu, Diyou and Chen, Jing},
  title = {TChange: A Hybrid Transformer-CNN Change Detection Network},
  journal = {Remote Sensing},
  year = {2023},
  volume = {15},
  number = {5},
  pages = {1219},
  doi = {10.3390/rs15051219}
}
Kostenlos starten →