EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Scale and Multi-Network Deep Feature Fusion for Discriminative Scene Classification of High-Resolution Remote Sensing Images

Baohua Yuan, Sukhjit Singh Sehra, Bernard Chiu

Remote Sensing · 24.10.2024 · 16 (21) · 3961

DOI: 10.3390/rs16213961 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 24.10.2024. Verfasst von Baohua Yuan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Grant Council of the HKSAR, China, Jiangsu Engineering Research Center of Digital Twinning Technology for Key Equipment in Petrochemical Process.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The advancement in satellite image sensors has enabled the acquisition of high-resolution remote sensing (HRRS) images. However, interpreting these images accurately and obtaining the computational power needed to do so is challenging due to the complexity involved. This manuscript proposed a multi-stream convolutional neural network (CNN) fusion framework that involves multi-scale and multi-CNN integration for HRRS image recognition. The pre-trained CNNs were used to learn and extract semantic features from multi-scale HRRS images. Feature extraction using pre-trained CNNs is more efficient than training a CNN from scratch or fine-tuning a CNN. Discriminative canonical correlation analysis (DCCA) was used to fuse deep features extracted across CNNs and image scales. DCCA reduced the dimension of the features extracted from CNNs while providing a discriminative representation by maximizing the within-class correlation and minimizing the between-class correlation. The proposed model has been evaluated on NWPU-RESISC45 and UC Merced datasets. The accuracy associated with DCCA was 10% and 6% higher than discriminant correlation analysis (DCA) in the NWPU-RESISC45 and UC Merced datasets. The advantage of DCCA was better demonstrated in the NWPU-RESISC45 dataset due to the incorporation of richer within-class variability in this dataset. While both DCA and DCCA minimize between-class correlation, only DCCA maximizes the within-class correlation and, therefore, attains better accuracy. The proposed framework achieved higher accuracy than all state-of-the-art frameworks involving unsupervised learning and pre-trained CNNs and 2–3% higher than the majority of fine-tuned CNNs. The proposed framework offers computational time advantages, requiring only 13 s for training in NWPU-RESISC45, compared to a day for fine-tuning the existing CNNs. Thus, the proposed framework achieves a favourable balance between efficiency and accuracy in HRRS image recognition.

Förderung

  • Research Grant Council of the HKSAR, China
  • Jiangsu Engineering Research Center of Digital Twinning Technology for Key Equipment in Petrochemical Process

Zitieren

APA

Yuan, B., Sehra, S. S., & Chiu, B. (2024). Multi-Scale and Multi-Network Deep Feature Fusion for Discriminative Scene Classification of High-Resolution Remote Sensing Images. Remote Sensing, 16(21), 3961. https://doi.org/10.3390/rs16213961

Vancouver

Yuan B, Sehra SS, Chiu B. Multi-Scale and Multi-Network Deep Feature Fusion for Discriminative Scene Classification of High-Resolution Remote Sensing Images. Remote Sensing. 2024;16(21):3961. doi:10.3390/rs16213961

BibTeX
@article{Yuan2024,
  author = {Yuan, Baohua and Sehra, Sukhjit Singh and Chiu, Bernard},
  title = {Multi-Scale and Multi-Network Deep Feature Fusion for Discriminative Scene Classification of High-Resolution Remote Sensing Images},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {21},
  pages = {3961},
  doi = {10.3390/rs16213961}
}
Kostenlos starten →