Acta Informatica Pragensia X:X | DOI: 10.18267/j.aip.32343

RoadNeXt-CSS: ConvNeXt-Adapted Encoder-Decoder Road Extraction for Robust Spatial Information Systems

Rachmawan Atmaji Perdana ORCID...1, Aniati Murni Arymurthy ORCID...2, Risnandar Risnandar ORCID...1
1 Research Center for Artificial Intelligence and Cybersecurity, Institute of Electronics and Informatics, National Research and Innovation Agency, Bandung, Indonesia
2 Department of Computer Science, Faculty of Computer Science, University of Indonesia, Depok, Indonesia

Background: Road extraction from remote sensing imagery is essential for geospatial information systems but faces challenges of thin structures, severe class imbalance and similarity between roads and non-roads.

Objective: We propose RoadNeXt-CSS, integrating a ConvNeXt encoder, inverse frequency weighting (IFW) loss and a scale sensitive decoder to address these challenges.

Methods: RoadNeXt-CSS was trained and evaluated on the Massachusetts Roads and DeepGlobe benchmarks using intersection over union (IoU) as the primary metric. ConvNeXt extracts rich spatial semantic features, IFW mitigates foreground background imbalance and the scale sensitive decoder adaptively weights multi level features. Component-wise ablation experiments were conducted to isolate the contribution of each proposed component and paired t-tests were applied to assess statistical significance against baseline models.

Results: RoadNeXt-CSS achieves IoU of 0.6779 (Massachusetts Roads) and 0.6984 (DeepGlobe), outperforming RCFSNet and other baselines (p < 0.001). Ablation analysis confirms that the ConvNeXt encoder, IFW loss and scale-sensitive decoder contribute independently to performance gains.

Conclusion: The three components together provide robust and statistically significant road extraction improvements, supporting transportation planning, disaster response and navigation systems.

Keywords: Road extraction; Remote sensing imagery; ConvNeXt; Semantic segmentation; Class imbalance.

Received: April 21, 2026; Revised: June 17, 2026; Accepted: July 8, 2026; Prepublished online: November 6, 2026 

Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. Ahmed, Md. I., Foysal, Md., Chaity, M. D., & Hossain, A. B. M. A. (2024). DeepRoadNet: A deep residual based segmentation network for road map detection from remote aerial image. IET Image Processing, 18(1), 265-279. https://doi.org/10.1049/ipr2.12948 Go to original source...
    2. Akhtarmanesh, A., Abbasi-Moghadam, D., Sharifi, A., Yadkouri, M. H., Tariq, A., & Lu, L. (2024). Road Extraction from Satellite Images Using Attention-Assisted UNet. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 1126-1136. https://doi.org/10.1109/JSTARS.2023.3336924 Go to original source...
    3. Anil, P., & Natarajan, S. (2010). A novel approach using active contour model for semi-automatic road extraction from high resolution satellite imagery. In 2010 Second International Conference on Machine Learning and Computing, (pp. 263-266). IEEE. https://doi.org/10.1109/ICMLC.2010.36 Go to original source...
    4. Chaurasia, A., & Culurciello, E. (2017). LinkNet: Exploiting encoder representations for efficient semantic segmentation. In 2017 IEEE Visual Communications and Image Processing (VCIP), (pp. 1-4). IEEE. https://doi.org/10.1109/VCIP.2017.8305148 Go to original source...
    5. Dai, L., Zhang, G., & Zhang, R. (2023). RADANet: Road Augmented Deformable Attention Network for Road Extraction From Complex High-Resolution Remote-Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-13. https://doi.org/10.1109/TGRS.2023.3237561 Go to original source...
    6. Du, Y., Sheng, Q., Zhang, W., Zhu, C., Li, J., & Wang, B. (2023). From local context-aware to non-local: A road extraction network via guidance of multi-spectral image. ISPRS Journal of Photogrammetry and Remote Sensing, 203, 230-245. https://doi.org/https://doi.org/10.1016/j.isprsjprs.2023.07.026 Go to original source...
    7. Huan, H., Sheng, Y., Zhang, Y., & Liu, Y. (2022). Strip Attention Networks for Road Extraction. Remote Sensing, 14(18). https://doi.org/10.3390/rs14184516 Go to original source...
    8. Jie, Y., He, H., Xing, K., Yue, A., Tan, W., Yue, C., Jiang, C., & Chen, X. (2022). MECA-Net: A MultiScale Feature Encoding and Long-Range Context-Aware Network for Road Extraction from Remote Sensing Images. Remote Sensing, 14, 5342. https://doi.org/10.3390/rs14215342 Go to original source...
    9. Li, R., Duan, C., Zheng, S., Zhang, C., & Atkinson, P. M. (2022). MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images. IEEE Geoscience and Remote Sensing Letters, 19, 1-5. https://doi.org/10.1109/LGRS.2021.3052886 Go to original source...
    10. Li, Y., Zhang, R., & Wu, Y. (2017). Road network extraction in high-resolution SAR images based CNN features. In 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), (pp. 1664-1667). IEEE. https://doi.org/10.1109/IGARSS.2017.8127293 Go to original source...
    11. Liu, R., Wu, J., Lu, W., Miao, Q., Zhang, H., Liu, X., Lu, Z., & Li, L. (2024). A Review of Deep Learning-Based Methods for Road Extraction from High-Resolution Remote Sensing Images. Remote Sensing, 16(12), 2056. https://doi.org/10.3390/rs16122056 Go to original source...
    12. Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022). A ConvNet for the 2020s. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (pp. 11966-11976). IEEE. https://doi.org/10.1109/CVPR52688.2022.01167 Go to original source...
    13. Mei, J., Li, R.-J., Gao, W., & Cheng, M.-M. (2021). CoANet: Connectivity Attention Network for Road Extraction From Satellite Imagery. IEEE Transactions on Image Processing, 30, 8540-8552. https://doi.org/10.1109/TIP.2021.3117076 Go to original source...
    14. Mo, S., Shi, Y., Yuan, Q., & Li, M. (2024). A Survey of Deep Learning Road Extraction Algorithms Using High-Resolution Remote Sensing Images. Sensors, 24(5), 1708. https://doi.org/10.3390/s24051708 Go to original source...
    15. Perdana, R. A., Arimurthy, A. M., & Risnandar. (2024). Remote Sensing Scene Classification using ConvNeXt-Tiny Model with Attention Mechanism and Label Smoothing. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 8(3), 389-400. https://doi.org/10.29207/resti.v8i3.5731 Go to original source...
    16. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. In N. Navab, J. Hornegger, W. M. Wells, & A. F. Frangi (Eds.), Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015 (pp. 234-241). Springer. https://doi.org/10.1007/978-3-319-24574-4_28 Go to original source...
    17. Simler, C. (2011). An improved road and building detector on VHR images. In 2011 IEEE International Geoscience and Remote Sensing Symposium, (pp. 507-510). IEEE. https://doi.org/10.1109/IGARSS.2011.6049176 Go to original source...
    18. Soni, Y., Meena, U., Mishra, V. K., & Soni, P. K. (2025). AM-UNet: Road Network Extraction from high-resolution Aerial Imagery Using Attention-Based Convolutional Neural Network. Journal of the Indian Society of Remote Sensing, 53(1), 135-147. https://doi.org/10.1007/s12524-024-01974-3 Go to original source...
    19. Sudre, C. H., Li, W., Vercauteren, T., Ourselin, S., & Jorge Cardoso, M. (2017). Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, (pp. 240-248). Springer. https://doi.org/10.1007/978-3-319-67558-9_28 Go to original source...
    20. Sugino, T., Kawase, T., Onogi, S., Kin, T., Saito, N., & Nakajima, Y. (2021). Loss Weightings for Improving Imbalanced Brain Structure Segmentation Using Fully Convolutional Networks. Healthcare, 9(8), 938. https://doi.org/10.3390/healthcare9080938 Go to original source...
    21. Tan, X., Xiao, Z., Wan, Q., & Shao, W. (2021). Scale Sensitive Neural Network for Road Segmentation in High-Resolution Remote Sensing Images. IEEE Geoscience and Remote Sensing Letters, 18(3), 533-537. https://doi.org/10.1109/LGRS.2020.2976551 Go to original source...
    22. Wang, H., Bai, L., Ji, B., Shen, J., Jin, Y., Ye, F., & Zhu, C. (2023). Gated Fusion and Dual Attention Network for Road Extraction from Satellite Imagery. In 2023 8th International Conference on Image, Vision and Computing (ICIVC), (pp. 495-500). IEEE. https://doi.org/10.1109/ICIVC58118.2023.10270019 Go to original source...
    23. Wang, Q., Bai, H., He, C., & Cheng, J. (2022). Fe-LinkNet: Enhanced D-LinkNet with Attention and Dense Connection for Road Extraction in High-Resolution Remote Sensing Images. In IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, (pp. 3043-3046). IEEE. https://doi.org/10.1109/IGARSS46834.2022.9883026 Go to original source...
    24. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., & Hu, Q. (2020). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (pp. 11531-11539). IEEE. https://doi.org/10.1109/CVPR42600.2020.01155 Go to original source...
    25. Wang, W., Yang, N., Zhang, Y., Wang, F., Cao, T., & Eklund, P. (2016). A Review of Road Extraction from Remote Sensing Images. Journal of Traffic and Transportation Engineering, 3(3), 271-282. https://doi.org/10.1016/j.jtte.2016.05.005 Go to original source...
    26. Wang, X., Hu, Z., Shi, S., Hou, M., Xu, L., & Zhang, X. (2023). A deep learning method for optimizing semantic segmentation accuracy of remote sensing images based on improved UNet. Scientific Reports, 13(1), 7600. https://doi.org/10.1038/s41598-023-34379-2 Go to original source...
    27. Wang, X., Qin, C., Bai, M., Ma, Q., & Li, G. (2025). CAFormer: A connectivity-aware vision transformer for road extraction from remote sensing images. The Visual Computer, 41(10), 7965-7981. https://doi.org/10.1007/s00371-025-03849-1 Go to original source...
    28. Wei, D., Li, P., Xie, H., & Xu, Y. (2023). DRCNet: Road Extraction From Remote Sensing Images Using DenseNet With Recurrent Criss-Cross Attention and Convolutional Block Attention Module. IEEE Access, 11, 126879-126891. https://doi.org/10.1109/ACCESS.2023.3332121 Go to original source...
    29. Wei, Z., & Zhang, Z. (2023). Remote Sensing Image Road Extraction Network Based on MSPFE-Net. Electronics, 12(7), 1713. https://doi.org/10.3390/electronics12071713 Go to original source...
    30. Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018). CBAM: Convolutional Block Attention Module. In V. Ferrari, M. Hebert, C. Sminchisescu, & Y. Weiss (Eds.), Computer Vision - ECCV 2018 (pp. 3-19). Springer. https://doi.org/10.1007/978-3-030-01234-2_1 Go to original source...
    31. Yang, Z., Zhou, D., Yang, Y., Zhang, J., & Chen, Z. (2023). Road Extraction From Satellite Imagery by Road Context and Full-Stage Feature. IEEE Geoscience and Remote Sensing Letters, 20, 1-5. https://doi.org/10.1109/LGRS.2022.3228967 Go to original source...
    32. Zhang, C., Murai, S., & Baltsavias, E. P. (1999). Road network detection by mathematical morphology. In ISPRS Workshop" 3D Geospatial Data Production: Meeting Application Requirements, (pp. 1-18). ISPRS.
    33. Zhang, P., Niu, L., Cai, M., Chen, H., & Sun, X. (2024). AAUConvNeXt: Enhancing Crop Lodging Segmentation with Optimized Deep Learning Architectures. Plant Phenomics, 6, 0182. https://doi.org/10.34133/plantphenomics.0182 Go to original source...
    34. Zhang, Y., Zhang, L., Niu, P., & Xu, W. (2023). AGF-Net: Adaptive Road Extraction Network with Global Feature Fusion. In 2023 5th International Conference on Data-Driven Optimization of Complex Systems, (pp. 1-7). IEEE. https://doi.org/10.1109/DOCS60977.2023.10294802 Go to original source...
    35. Zhang, Z., Sun, X., & Liu, Y. (2022). GMR-Net: Road-Extraction Network Based on Fusion of Local and Global Information. Remote Sensing, 14(21), 5476. https://doi.org/10.3390/rs14215476 Go to original source...
    36. Zhou, J., Bischof, W. F., & Caelli, T. (2006). Road tracking in aerial images based on human-computer interaction and Bayesian filtering. ISPRS Journal of Photogrammetry and Remote Sensing, 61(2), 108-124. https://doi.org/https://doi.org/10.1016/j.isprsjprs.2006.09.002 Go to original source...
    37. Zhou, L., Zhang, C., & Wu, M. (2018). D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), (pp. 182-186). IEEE. https://doi.org/10.1109/CVPRW.2018.00034 Go to original source...

    This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return