A Scientometric and Literature Analysis of Deep Learning-Based Semantic Segmentation in Remote Sensing (2015–2025)

Roshni Rajendran, Nagaraj P

Abstract


Semantic segmentation of remote sensing images has advanced rapidly, enabling applications in land cover mapping, disaster response, and urban monitoring. This study presents a hybrid scientometric and literature-based analysis of 733 Scopus-indexed publications (2015–2025). Results show a 29.24% annual growth rate, with China, the United States, and Germany as leading contributors and Wuhan University as the most prolific institution. Research output peaked in 2023, driven by transformers and hybrid architectures such as SegFormer, Mask2Former, and Swin Transformer, which outperform CNN baselines. Citation and keyword analyses reveal two core directions: applied geospatial tasks (land cover, urban analysis, disaster management) and computational advances (CNNs, transformers, domain adaptation). While foundational works remain highly cited, emerging models emphasize efficiency, multimodal fusion, and generalization. Persistent challenges include dataset imbalance, cross-domain adaptation, and lack of standardized benchmarks. By combining bibliometric mapping with methodological synthesis, this study consolidates research trends and highlights future directions in multimodal learning, explainable AI, and robust, scalable segmentation frameworks.


Full Text:

PDF

References


J. Lv, Q. Shen, and M. Lv, “Deep learning-based semantic segmentation of remote sensing images: a review,” Frontiers in Ecology and Evolution, vol. 11, 2023.

X. Li and J. Li, “MFCA-Net: A deep learning method for semantic segmentation of remote sensing images,” Scientific Reports, vol. 14, no. 5745, 2024.

X. Wang, H. Zhang, Y. Chen, and Y. Liu, “A deep learning method for optimizing semantic segmentation accuracy of remote sensing images based on improved UNet,” Scientific Reports, vol. 13, no. 7600, 2023.

J. Song, A.-X. Zhu, and Y. Zhu, “Transformer-Based Semantic Segmentation for Extraction of Building Footprints from Very-High-Resolution Images,” Sensors, vol. 23, no. 11, p. 5166, 2023.

Y. Liu, “Remote sensing image scene classification based on convolutional neural networks,” Informatica, vol. 49, no. 9, 2025.

J. Feng, Z. Wang, Y. Zhang, and H. Li, “SMBCNet: A Transformer-Based Approach for Change Detection in Remote Sensing Images through Semantic Segmentation,” Remote Sensing, vol. 15, no. 14, p. 3566, 2023.

X. Yuan, J. Shi, and L. Gu, “A review of deep learning methods for semantic segmentation of remote sensing imagery,” Expert Systems with Applications, vol. 169, p. 114417, 2021. doi: 10.1016/j.eswa.2020.114417.

K. R. Hasan, A. B. Tuli, M. A.-M. Khan, S.-H. Kee, M. A. Samad, and A.-A. Nahid, “Deep-learning-based semantic segmentation for remote sensing: A bibliometric literature review,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 1390–1418, 2023.

J. Li, Y. Cai, Q. Li, M. Kou, and T. Zhang, “A Review of Remote Sensing Image Segmentation by Deep Learning Methods,” International Journal of Digital Earth, vol. 17, no. 1, 2024. doi: 10.1080/17538947.2024.2328827.

A. A. Aleissaee, H. El-Askary, A. A. Nasr, and W. Abd-Elrahman, “Transformers in Remote Sensing: A Survey,” Remote Sensing, vol. 15, no. 7, p. 1860, 2023.

Y. Ma, “Transformer-Based Method for Semantic Segmentation and Reconstruction of the Martian Surface,” ISPRS Archives, vol. XLVIII-1/W2, pp. 1643–1649, 2023.

C. Zhang, Y. Sun, and F. Li, “Lightweight semantic segmentation network with configurable context and small object attention,” Frontiers in Computational Neuroscience, vol. 17, p. 1280640, 2023.

S. Verma, F. Lindseth, and G. Kiss, “SegDesicNet: Lightweight Semantic Segmentation in Remote Sensing with Geo-Coordinate Embeddings for Domain Adaptation,” in Proc. IEEE/CVF Winter Conf. on Applications of Computer Vision (WACV), 2025.

L. Wang, X. Hu, D. Li, and Y. Zhou, “A Transformer-based multi-modal fusion network for semantic segmentation of remote sensing images,” Information Fusion, vol. 94, pp. 1–12, 2024.

H. Tang, Y. Han, J. Zheng, Z. Wang, and L. Wang, “An Optimized YOLOv5s-rd Framework for Efficient Target Detection in Remote Sensing Images,” Informatica, vol. 49, no. 18, 2025.

Y. Li, Y. Zhao, Y. Zhang, and W. Gong, “A2-FPN: An attention augmented feature pyramid network for building segmentation from very high resolution images,” Remote Sensing, vol. 13, no. 6, pp. 1123–1137, 2021.

J. Li, J. Yang, L. He, and S. Gong, “ABCNet: Adaptive bilateral context network for semantic segmentation of remote sensing images,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 179, pp. 108–122, 2021.

Y. Bo, C. Zhang, and L. Fan, “BASNet: Burned area segmentation network for real-time damage mapping in remote sensing images,” Remote Sensing Letters, vol. 12, no. 4, pp. 349–358, 2021.

J. Song, Y. Zhu, and A.-X. Zhu, “Transformer-based semantic segmentation for building footprint extraction,” Sensors, vol. 23, no. 11, pp. 1–17, 2023.

M. Gibril, R. Smits, and A. Samadzadegan, “Large-scale building extraction using Swin Transformer and Mask2Former,” Advances in Space Research, vol. 73, no. 1, pp. 25–37, 2024.

H. Cui, X. Li, and Q. Yang, “Improved Swin Transformer-based semantic segmentation of post-earthquake dense buildings in urban areas,” Remote Sensing, vol. 15, no. 8, pp. 2302–2315, 2023.

S. Khallaghi, J. R. Eastman, and L. D. Estes, “A review of technical factors to consider when designing neural networks for semantic segmentation of Earth Observation imagery,” arXiv preprint arXiv:2308.09221, 2023.

C. Broni-Bediako, J. Xia, and N. Yokoya, “Real-time semantic segmentation: A brief survey and comparative study in remote sensing,” Remote Sensing, vol. 15, no. 19, pp. 4855–4872, 2023.

W. Zhao, H. Tang, and Y. Liu, “SEG-Road: A CNN-transformer hybrid network for road segmentation from VHR images,” Computer Vision and Image Understanding, vol. 221, p. 103470, 2022.

L. Wang, X. Hu, and D. Li, “MetaSegNet: Metadata-collaborative vision-language representation learning for semantic segmentation of remote sensing images,” arXiv preprint arXiv:2312.12735, 2023.

O. Ajibola and J. Cabral, “A review and meta-analysis of semantic segmentation models in land use/land cover mapping,” ISPRS International Journal of Geo-Information, vol. 12, no. 4, p. 216, 2024.

Y. Zhang, X. Meng, and L. Zhou, “A semi-supervised learning method for remote sensing semantic segmentation based on consistency regularization,” Information Fusion, vol. 80, pp. 93–104, 2023.

Y. Chen, S. Lu, and T. Zhang, “Few-shot semantic segmentation of remote sensing imagery using prototype learning,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 201, pp. 45–59, 2024.

F. Liu, H. Jin, and Y. Sun, “Domain adaptation for semantic segmentation of remote sensing images with distribution alignment,” Computer Vision and Image Understanding, vol. 239, p. 103828, 2024.

J. Wang, L. Zhang, and K. Lin, “Cross-domain semantic segmentation for remote sensing imagery using adversarial learning,” ISPRS International Journal of Geo-Information, vol. 13, no. 1, p. 25, 2024.

Y. Tao, M. Shi, and J. Cheng, “Attention-guided deep neural network for road extraction from high-resolution remote sensing images,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 182, pp. 200–214, 2021.

H. Zhu, W. Zhang, and C. Yang, “Urban green space segmentation using spectral-spatial fusion of high-resolution satellite images,” Remote Sensing Letters, vol. 14, no. 1, pp. 43–55, 2023.

Q. Zhang, B. Liu, and Y. Wang, “Semantic segmentation for agricultural field mapping using remote sensing images and encoder-decoder networks,” Agricultural Systems, vol. 207, p. 103633, 2023.

L. Wang, S. Dong, Y. Chen, X. Meng, S. Fang and S. Fei, "MetaSegNet: Metadata-Collaborative Vision-Language Representation Learning for Semantic Segmentation of Remote Sensing Images," in IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-11, 2024, Art no. 5644211, doi: 10.1109/TGRS.2024.3477548.

D. Hong et al., "SpectralGPT: Spectral Remote Sensing Foundation Model," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 8, pp. 5227-5244, Aug. 2024, doi: 10.1109/TPAMI.2024.3362475.




DOI: https://doi.org/10.31449/inf.v49i4.9049

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.