[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to main content
Springer Nature Link
Log in

BiReNet: Bilateral Network with Feature Aggregation and Edge Detection for Remote Sensing Images Road Extraction

  • Conference paper
  • First Online:
Pattern Recognition and Computer Vision (PRCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15043))

Included in the following conference series:

  • 75 Accesses

Abstract

Extracting roads from remote sensing images is a significant and challenging topic. Most existing advanced methods perform well in general scenarios but cannot cope with complex scenarios, such as obscured and covered roads. This paper proposes a Bilateral Road Extraction Network (BiReNet) consisting of an edge detection branch and a road extraction branch. Firstly, we adopt an effective and efficient LinkNet architecture in the road extraction branch and add an extra Feature Fusion Module (FFM) behind the skip connection part. The FFM is capable of efficiently aggregating the features at the same level from the decoder and the corresponding encoder, thus preserving abundant spatial information and amplifying comprehension of road structures. Secondly, we design a novel Edge Detection Module (EDM) in the edge detection branch to enhance the road edge features by capturing the gradient information using Pixel Difference Convolution (PDC), which enables fine-grained constraints on the road extraction and improves the accuracy and connectivity of the road. Extensive experiments on two publicly available road datasets show that BiReNet performs favorably against other state-of-the-art remote sensing road extraction methods and demonstrates stronger robustness in complex scenarios. Specifically, for a 1024\(\,\times \,\)1024 input, BiReNet achieved 0.6769 IoU on the DeepGlobe road dataset and 0.6072 IoU on the Massachusetts road dataset with a speed of 24 FPS on one GeForce GTX3090. The code is available at https://github.com/LPeng625/BiReNet.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
GBP 19.95
Price includes VAT (United Kingdom)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
GBP 54.99
Price includes VAT (United Kingdom)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
GBP 69.99
Price includes VAT (United Kingdom)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Youn, J., Bethel, J.S.: Adaptive snakes for urban road extraction. Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci. 35(3), 465–470 (2004)

    Google Scholar 

  2. Dal Poz, A. P., Do Vale, G. M.: Dynamic programming approach for semi-automated road extraction from medium-and high-resolution images. ISPrS Arch. 34(Part 3), W8 (2003)

    Google Scholar 

  3. Lin, X., Zhang, R., Shen, J.: A template-matching based approach for extraction of roads from very high-resolution remotely sensed imagery. Int. J. Image Data Fusion 3(2), 149–168 (2012)

    Article  MATH  Google Scholar 

  4. Youquan, H., Hanxing, Q., Jian, W., Wei, Z., Jianfang, X.: Studying of road crack image detection method based on the mathematical morphology. In: 2011 4th International Congress on Image and Signal Processing, vol. 2, pp. 967–969. IEEE (2011)

    Google Scholar 

  5. Gavankar, N.L., Ghosh, S.K.: Automatic building footprint extraction from high-resolution satellite image using mathematical morphology. Eur. J. Remote. Sens. 51(1), 182–193 (2018)

    Article  Google Scholar 

  6. Guiming, S., Jidong, S.: Remote sensing image edge-detection based on improved Canny operator. In: 2016 8th IEEE International Conference on Communication Software and Networks (ICCSN), pp. 652–656. IEEE (2016)

    Google Scholar 

  7. Chauhan, V.K., Dahiya, K., Sharma, A.: Problem formulations and solvers in linear SVM: a review. Artif. Intell. Rev. 52(2), 803–855 (2019)

    Article  MATH  Google Scholar 

  8. Zhang, Q., Couloigner, I.: Benefit of the angular texture signature for the separation of parking lots and roads on high resolution multi-spectral imagery. Pattern Recogn. Lett. 27(9), 937–946 (2006)

    Article  MATH  Google Scholar 

  9. Yuan, J., Wang, D., Wu, B., Yan, L., Li, R.: LEGION-based automatic road extraction from satellite imagery. IEEE Trans. Geosci. Remote Sens. 49(11), 4528–4538 (2011)

    Article  MATH  Google Scholar 

  10. Chaurasia, A., Culurciello, E.: Linknet: exploiting encoder representations for efficient semantic segmentation. In: 2017 IEEE Visual Communications and Image Processing (VCIP), pp. 1–4. IEEE (2017)

    Google Scholar 

  11. Xu, Y., Chen, H., Du, C., Li, J.: MSACon: mining spatial attention-based contextual information for road extraction. IEEE Trans. Geosci. Remote Sens. 60, 1–17 (2021)

    MATH  Google Scholar 

  12. Wu, Z., Zhang, J., Zhang, L., Liu, X., Qiao, H.: Bi-HRNet: a road extraction framework from satellite imagery based on node heatmap and bidirectional connectivity. Remote Sens. 14(7), 1732 (2022)

    Google Scholar 

  13. Hu, Z., Shi, W., Liu, H., Chen, X.: Road detection via a dual-task network based on cross-layer graph fusion modules. IEEE Geosci. Remote Sens. Lett. 19, 3198077 (2022)

    Google Scholar 

  14. Hu, J., Gao, J., Yuan, Y., Chanussot, J., Wang, Q.: LGNet: location-guided network for road extraction from satellite images. IEEE Trans. Geosci. Remote. Sens. (2023)

    Google Scholar 

  15. Guo, H., Su, X., Wu, C., Du, B., Zhang, L.: Building-road collaborative extraction from remote sensing images via cross-task and cross-scale interaction. IEEE Trans. Geosci. Remote. Sens. (2024)

    Google Scholar 

  16. Demir, I., Koperski, K., Lindenbaum, D., Pang, G., Huang, J., Basu, S., Hughes, F., Tuia, D., Raskar, R.: Deepglobe 2018: a challenge to parse the earth through satellite images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 172–181 (2018)

    Google Scholar 

  17. Mnih, V.: Machine Learning for Aerial Image Labeling. University of Toronto (Canada) (2013)

    Google Scholar 

  18. Yang, Z., Zhou, D., Yang, Y., Zhang, J., Chen, Z.: Road extraction from satellite imagery by road context and full-stage feature. IEEE Geosci. Remote Sens. Lett. 20, 3228967 (2023)

    Google Scholar 

  19. Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5–9, 2015, Proceedings, Part III 18 (pp. 234–241). Springer International Publishing (2015)

    Google Scholar 

  20. Deng, F., Luo, W., Ni, Y., Wang, X., Wang, Y., Zhang, G.: UMiT-Net: a U-shaped mix-transformer network for extracting precise roads using remote sensing images. IEEE Trans. Geosci. Remote. Sens. (2023)

    Google Scholar 

  21. Ye, Z., Guo, Q., Wei, J., Zhang, H., Bian, L., Cao, S.: Recognition of terminal buds of densely-planted Chinese fir seedlings using improved YOLOv5 by integrating attention mechanism. Front. Plant Sci. 13, 991929 (2022)

    Google Scholar 

  22. Zhou, L., Zhang, C., Wu, M.: D-LinkNet: LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 182–186 (2018)

    Google Scholar 

  23. Wang, Y., Peng, Y., Li, W., Alexandropoulos, G.C., Yu, J., Ge, D., Xiang, W.: DDU-Net: dual-decoder-U-Net for road extraction using high-resolution remote sensing images. IEEE Trans. Geosci. Remote Sens. 60, 1–12 (2022)

    Google Scholar 

  24. Wu, Q., Luo, F., Wu, P., Wang, B., Yang, H., Wu, Y.: Automatic road extraction from high-resolution remote sensing images using a method based on densely connected spatial feature-enhanced pyramid. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. 14, 3–17 (2020)

    Article  MATH  Google Scholar 

  25. Lan, M., Zhang, Y., Zhang, L., Du, B.: Global context based automatic road segmentation via dilated convolutional neural network. Inf. Sci. 535, 156–171 (2020)

    Article  MathSciNet  MATH  Google Scholar 

  26. Xie, Y., Miao, F., Zhou, K., Peng, J.: HsgNet: a road extraction network based on global perception of high-order spatial information. ISPRS Int. J. Geo Inf. 8(12), 571 (2019)

    Google Scholar 

  27. Tang, Y., Wang, T., Liu, D.: MFFAGAN: generative adversarial network with multi-level feature fusion attention mechanism for remote sensing image super-resolution. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. (2024)

    Google Scholar 

  28. Liu, Y., Yao, J., Lu, X., Xia, M., Wang, X., Liu, Y.: RoadNet: learning to comprehensively analyze road networks in complex urban scenes from high-resolution remotely sensed images. IEEE Trans. Geosci. Remote Sens. 57(4), 2043–2056 (2018)

    Article  MATH  Google Scholar 

  29. Lu, X., Zhong, Y., Zheng, Z., Liu, Y., Zhao, J., Ma, A., Yang, J.: Multi-scale and multi-task deep learning framework for automatic road extraction. IEEE Trans. Geosci. Remote Sens. 57(11), 9362–9377 (2019)

    Article  MATH  Google Scholar 

  30. Wei, Y., Zhang, K., Ji, S.: Simultaneous road surface and centerline extraction from large-scale remote sensing images using CNN-based segmentation and tracing. IEEE Trans. Geosci. Remote Sens. 58(12), 8919–8931 (2020)

    Article  MATH  Google Scholar 

  31. Li, X., Zhang, Z., Lv, S., Pan, M., Ma, Q., Yu, H.: Road extraction from high spatial resolution remote sensing image based on multi-task key point constraints. IEEE Access 9, 95896–95910 (2021)

    Article  Google Scholar 

  32. Lu, X., Zhong, Y., Zheng, Z., Chen, D., Su, Y., Ma, A., Zhang, L.: Cascaded multi-task road extraction network for road surface, centerline, and edge extraction. IEEE Trans. Geosci. Remote Sens. 60, 1–14 (2022)

    Google Scholar 

  33. Liu, D., Zhang, J., Liu, K., Zhang, Y.: Aerial remote sensing image cascaded road detection network based on edge sensing module and attention module. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2022)

    MATH  Google Scholar 

  34. Lin, Y., Jin, F., Wang, D., Wang, S., Liu, X.: Dual-task network for road extraction from high-resolution remote sensing images. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. (2023)

    Google Scholar 

  35. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  36. Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19 (2018)

    Google Scholar 

  37. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11534–11542 (2020)

    Google Scholar 

  38. Su, Z., Liu, W., Yu, Z., Hu, D., Liao, Q., Tian, Q., Pietikäinen, M., Liu, L.: Pixel difference networks for efficient edge detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5117–5127 (2021)

    Google Scholar 

  39. Chen, L. C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801–818 (2018)

    Google Scholar 

  40. Chen, S.B., Ji, Y.X., Tang, J., Luo, B., Wang, W.Q., Lv, K.: DBRANet: road extraction by dual-branch encoder and regional attention decoder. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2021)

    Google Scholar 

  41. Li, R., Duan, C., Zheng, S., Zhang, C., Atkinson, P.M.: MACU-Net for semantic segmentation of fine-resolution remotely sensed images. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2021)

    Google Scholar 

  42. Wang, Y., Seo, J., Jeon, T.: NL-LinkNet: toward lighter but more accurate road extraction with nonlocal operations. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2021)

    Google Scholar 

Download references

Acknowledgements

This work was supported by the Excellent Youth Foundation of Xinjiang Uygur Autonomous Region of China (2023D01E01), the National Natural Science Foundation of China (62266043), the Outstanding Young Talent Foundation of Xinjiang Uygur Autonomous Region of China (2023TSYCCX0043), the Tianshan Innovation Team Program of Xinjiang Uygur Autonomous Region of China (2023D14012), the Finance Science and Technology Project of Xinjiang Uyghur Autonomous Region (2023B01029-1, 2023B01029-2), the Natural Science Foundation of Xinjiang Uygur Autonomous Region of China (2022D01B123).

Author information

Authors and Affiliations

  1. School of Software, Xinjiang University, Urumqi, 830091, China

    Peng Liu & Yugang Qin

  2. School of Computer Science and Technology, Xinjiang University, Urumqi, 830046, China

    Yurong Qian & Yingying Fan

  3. Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region, Xinjiang University, Urumqi, 830046, China

    Peng Liu, Yurong Qian, Yugang Qin & Yingying Fan

  4. Key Laboratory of Software Engineering, Xinjiang University, Urumqi, 830091, China

    Peng Liu, Yurong Qian & Yugang Qin

  5. Beijing Anzhen Huanyu Aloe, No. 5 Anding Road, Chaoyang District, Beijing, 100029, China

    Hongyang Wei

Authors
  1. Peng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yurong Qian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hongyang Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yugang Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yingying Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yurong Qian .

Editor information

Editors and Affiliations

  1. Peking University, Beijing, China

    Zhouchen Lin

  2. Nankai University, Tianjin, China

    Ming-Ming Cheng

  3. Chinese Academy of Sciences, Beijing, China

    Ran He

  4. Xinjiang University, Urumqi, Xinjiang, China

    Kurban Ubul

  5. Xinjiang University, Urumqi, China

    Wushouer Silamu

  6. Peking University, Beijing, China

    Hongbin Zha

  7. Tsinghua University, Beijing, China

    Jie Zhou

  8. Chinese Academy of Sciences, Beijing, China

    Cheng-Lin Liu

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Liu, P., Qian, Y., Wei, H., Qin, Y., Fan, Y. (2025). BiReNet: Bilateral Network with Feature Aggregation and Edge Detection for Remote Sensing Images Road Extraction. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2024. Lecture Notes in Computer Science, vol 15043. Springer, Singapore. https://doi.org/10.1007/978-981-97-8493-6_28

Download citation

  • DOI: https://doi.org/10.1007/978-981-97-8493-6_28

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-97-8492-9

  • Online ISBN: 978-981-97-8493-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation