Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Fine-Grained Extraction of Road Networks via Joint Learning of Connectivity and Segmentation (2312.04744v1)

Published 7 Dec 2023 in cs.CV and cs.LG

Abstract: Road network extraction from satellite images is widely applicated in intelligent traffic management and autonomous driving fields. The high-resolution remote sensing images contain complex road areas and distracted background, which make it a challenge for road extraction. In this study, we present a stacked multitask network for end-to-end segmenting roads while preserving connectivity correctness. In the network, a global-aware module is introduced to enhance pixel-level road feature representation and eliminate background distraction from overhead images; a road-direction-related connectivity task is added to ensure that the network preserves the graph-level relationships of the road segments. We also develop a stacked multihead structure to jointly learn and effectively utilize the mutual information between connectivity learning and segmentation learning. We evaluate the performance of the proposed network on three public remote sensing datasets. The experimental results demonstrate that the network outperforms the state-of-the-art methods in terms of road segmentation accuracy and connectivity maintenance.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. T. Géraud and J.-B. Mouret, “Fast Road Network Extraction in Satellite Images Using Mathematical Morphology and Markov Random Fields,” EURASIP Journal on Advances in Signal Processing, vol. 2004, no. 16, p. 473593, Dec. 2004. [Online]. Available: https://doi.org/10.1155/S1110865704409093
  2. G. Cheng, Y. Wang, Y. Gong, F. Zhu, and C. Pan, “Urban road extraction via graph cuts based probability propagation,” in 2014 IEEE International Conference on Image Processing (ICIP), Oct. 2014, pp. 5072–5076, iSSN: 2381-8549.
  3. P. Doucette, P. Agouris, A. Stefanidis, and M. Musavi, “Self-organised clustering for road extraction in classified imagery,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 55, no. 5, pp. 347–358, Mar. 2001. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0924271601000272
  4. L. Cohen and R. Kimmel, “Global minimum for active contour models: a minimal path approach,” in Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.   San Francisco, CA, USA: IEEE, 1996, pp. 666–673. [Online]. Available: http://ieeexplore.ieee.org/document/517144/
  5. M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active contour models,” International Journal of Computer Vision, vol. 1, no. 4, pp. 321–331, Jan. 1988. [Online]. Available: https://doi.org/10.1007/BF00133570
  6. G. Máttyus, W. Luo, and R. Urtasun, “DeepRoadMapper: Extracting Road Topology from Aerial Images,” in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 3458–3466.
  7. F. Bastani, S. He, S. Abbar, M. Alizadeh, H. Balakrishnan, S. Chawla, S. Madden, and D. DeWitt, “RoadTracer: Automatic Extraction of Road Networks from Aerial Images,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.   Salt Lake City, UT: IEEE, Jun. 2018, pp. 4720–4728, cVPR. [Online]. Available: https://ieeexplore.ieee.org/document/8578594/
  8. C. Ventura, J. Pont-Tuset, S. Caelles, K.-K. Maninis, and L. Van Gool, “Iterative Deep Learning for Road Topology Extraction,” arXiv:1808.09814 [cs], Aug. 2018. [Online]. Available: http://arxiv.org/abs/1808.09814
  9. Z. Li, J. D. Wegner, and A. Lucchi, “Topological Map Extraction from Overhead Images,” arXiv:1812.01497 [cs], Apr. 2019, arXiv: 1812.01497. [Online]. Available: http://arxiv.org/abs/1812.01497
  10. Y.-Q. Tan, S.-H. Gao, X.-Y. Li, M.-M. Cheng, and B. Ren, “VecRoad: Point-Based Iterative Graph Exploration for Road Graphs Extraction,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).   Seattle, WA, USA: IEEE, Jun. 2020, pp. 8907–8915, cVPR. [Online]. Available: https://ieeexplore.ieee.org/document/9157398/
  11. X. Li, Y. Wang, L. Zhang, S. Liu, J. Mei, and Y. Li, “Topology-Enhanced Urban Road Extraction via a Geographic Feature-Enhanced Network,” IEEE Transactions on Geoscience and Remote Sensing, pp. 1–12, 2020, liXG.
  12. A. Newell, K. Yang, and J. Deng, “Stacked hourglass networks for human pose estimation,” in European conference on computer vision.   Springer, 2016, pp. 483–499.
  13. C. Steger, C. Glock, W. Eckstein, H. Mayer, and B. Radig, “Model-Based Road Extraction from Images,” in In: Automatic Extraction of Man-Made Objects from Aerial and Space Images, Birkh auser Verlag Basel.   Birkhauser Verlag, 1995, pp. 275–284.
  14. K. Treash, “Automatic Road Detection In Grayscale Aerial Images,” Journal of Computing in Civil Engineering, vol. 14, Jul. 2001.
  15. H. Ma, Q. Qin, S. Du, L. Wang, and C. Jin, “Road extraction from ETM panchromatic image based on Dual-Edge Following,” Aug. 2007, pp. 460–463.
  16. N. Yager and A. Sowmya, “Support Vector Machines for Road Extraction from Remotely Sensed Images,” Aug. 2003, pp. 285–292.
  17. S.-R. Park and T. Kim, “Semi-automatic road extraction algorithm from IKONOS images using template matching,” in Proc. 22nd Asian Conference on Remote Sensing, 2001, pp. 1209–1213.
  18. D. Chaudhuri, N. K. Kushwaha, and A. Samal, “Semi-Automated Road Detection From High Resolution Satellite Images by Directional Morphological Enhancement and Segmentation Techniques,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 5, no. 5, pp. 1538–1544, Oct. 2012, conference Name: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.
  19. W. Shi, Z. Miao, and J. Debayle, “An Integrated Method for Urban Main-Road Centerline Extraction From Optical Remotely Sensed Imagery,” IEEE Transactions on Geoscience and Remote Sensing, vol. 52, no. 6, pp. 3359–3372, Jun. 2014, conference Name: IEEE Transactions on Geoscience and Remote Sensing.
  20. L. Zhou, C. Zhang, and M. Wu, “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).   Salt Lake City, UT, USA: IEEE, Jun. 2018, pp. 192–1924. [Online]. Available: https://ieeexplore.ieee.org/document/8575492/
  21. C. Tao, J. Qi, Y. Li, H. Wang, and H. Li, “Spatial information inference net: Road extraction using road-specific contextual information,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 158, pp. 155–166, Dec. 2019. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0924271619302382
  22. Z. Liu, R. Feng, L. Wang, Y. Zhong, and L. Cao, “D-Resunet: Resunet and Dilated Convolution for High Resolution Satellite Imagery Road Extraction,” in IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, Jul. 2019, pp. 3927–3930, iSSN: 2153-7003.
  23. T. Sun, Z. Chen, W. Yang, and Y. Wang, “Stacked U-Nets With Multi-Output for Road Extraction,” in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun. 2018, cVPR.
  24. V. Mnih and G. E. Hinton, “Learning to Detect Roads in High-Resolution Aerial Images,” in Computer Vision – ECCV 2010, ser. Lecture Notes in Computer Science, K. Daniilidis, P. Maragos, and N. Paragios, Eds.   Berlin, Heidelberg: Springer, 2010, pp. 210–223.
  25. P. Li, Y. Zang, C. Wang, J. Li, M. Cheng, L. Luo, and Y. Yu, “Road network extraction via deep learning and line integral convolution,” in 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Jul. 2016, pp. 1599–1602, iSSN: 2153-7003.
  26. A. Mosinska, P. Marquez-Neila, M. Koziński, and P. Fua, “Beyond the pixel-wise loss for topology-aware delineation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3136–3145.
  27. A. Batra, S. Singh, G. Pang, S. Basu, C. Jawahar, and M. Paluri, “Improved Road Connectivity by Joint Learning of Orientation and Segmentation,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).   Long Beach, CA, USA: IEEE, Jun. 2019, pp. 10 377–10 385, orientation and segmentation, spacent. [Online]. Available: https://ieeexplore.ieee.org/document/8953380/
  28. Z. Yu, C. Feng, M.-Y. Liu, and S. Ramalingam, “Casenet: Deep category-aware semantic edge detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 5964–5973, caseNet(CVPR).
  29. Y. Liu, J. Yao, X. Lu, M. Xia, X. Wang, and Y. Liu, “RoadNet: Learning to Comprehensively Analyze Road Networks in Complex Urban Scenes From High-Resolution Remotely Sensed Images,” IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, vol. 57, no. 4, p. 14, 2019.
  30. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention.   Springer, 2015, pp. 234–241.
  31. T. Li, M. Comer, and J. Zerubia, “Feature Extraction and Tracking of CNN Segmentations for Improved Road Detection from Satellite Imagery,” in 2019 IEEE International Conference on Image Processing (ICIP), Sep. 2019, pp. 2641–2645, iSSN: 2381-8549.
  32. A. Buslaev, S. S. Seferbekov, V. Iglovikov, and A. Shvets, “Fully Convolutional Network for Automatic Road Extraction From Satellite Imagery.” in CVPR Workshops, 2018, pp. 207–210.
  33. O. Filin, A. Zapara, and S. Panchenko, “Road Detection With EOSResUNet and Post Vectorizing Algorithm,” in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun. 2018, cVPR.
  34. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
  35. D. Costea, A. Marcu, E. Slusanschi, and M. Leordeanu, “Roadmap Generation Using a Multi-Stage Ensemble of Deep Neural Networks With Smoothing-Based Optimization,” in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun. 2018, cVPR.
  36. A. Chaurasia and E. Culurciello, “Linknet: Exploiting encoder representations for efficient semantic segmentation,” in 2017 IEEE Visual Communications and Image Processing (VCIP).   IEEE, 2017, pp. 1–4.
  37. S. Sun, W. Xia, B. Zhang, and Y. Zhang, “Road Centerlines Extraction from High Resolution Remote Sensing Image,” in IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, Jul. 2019, pp. 3931–3934, iSSN: 2153-7003.
  38. W. Yujun, H. Xiangyun, and G. Jinqi, “End-to-End Road Centerline Extraction via Learning a Confidence Map,” in 2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS), Aug. 2018, pp. 1–5.
  39. J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132–7141.
  40. V. Mnih, “Machine learning for aerial image labeling,” PhD Thesis, University of Toronto, 2013, university of Toronto.
  41. M. Kampffmeyer, N. Dong, X. Liang, Y. Zhang, and E. P. Xing, “Connnet: A long-range relation-aware pixel-connectivity network for salient segmentation,” IEEE Transactions on Image Processing, vol. 28, no. 5, pp. 2518–2529, 2018.
  42. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 2117–2125.
  43. A. Paszke, A. Chaurasia, S. Kim, and E. Culurciello, “Enet: A deep neural network architecture for real-time semantic segmentation,” arXiv preprint arXiv:1606.02147, 2016.
  44. A. Van Etten, D. Lindenbaum, and T. M. Bacastow, “SpaceNet: A Remote Sensing Dataset and Challenge Series,” arXiv:1807.01232 [cs], Jul. 2019, arXiv: 1807.01232. [Online]. Available: http://arxiv.org/abs/1807.01232
  45. “OpenStreetMap.” [Online]. Available: https://www.openstreetmap.org/
  46. F. Yu, D. Wang, E. Shelhamer, and T. Darrell, “Deep layer aggregation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 2403–2412.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets