Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

CCT-DOSA: a hybrid architecture for road network extraction from satellite images in the era of IoT

  • Original Paper
  • Published:
Evolving Systems Aims and scope Submit manuscript

Abstract

This research addresses the critical task of road network extraction from satellite images within the context of satellite IoT environments in urban planning and disaster management. We introduce the Convolution Coupled Transformer with Deformable Orientational Self-Attention (CCT-DOSA) architecture, a hybrid model that integrates convolutional layers, transformer blocks, and a novel DOSA mechanism. Our approach leverages both local and global features to carry out precise and accurate road segmentation. Furthermore, the DOSA mechanism has the dynamic ability to design the improved road extraction model from the satellite images. This improved model smoothen the road extraction process through heterogeneous features. Through comprehensive experimentation on these datasets, we present numerical results that highlight the efficacy of CCT-DOSA. The impact of various hyperparameters and architectural choices are analyzed for emphasizing the importance of fine-tuning and the adaptability of attention mechanisms. Our model achieves superior performance with an IoU of 0.958, precision of 0.985, recall of 0.973, and an F1-Score of 0.973 and surpasses five existing state-of-the-art approaches, emphasizing its robustness and efficiency in road network extraction. These results indicate a robust ability to accurately segment road networks from satellite images. Overall, the CCT-DOSA architecture offers promising potential for real-world applications in satellite IoT environments.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

The data that support the findings of this study are available from the corresponding author upon reasonable request.

References

  • Ahmed MW, Saadi S, Ahmed M (2022) Automated road extraction using reinforced road indices for Sentinel-2 data. Array 16:100257

    Article  Google Scholar 

  • Behera TK, Sa PK, Nappi M, Bakshi S (2022) Satellite IoT based road extraction from VHR images through superpixel-CNN architecture. Big Data Research 30:100334

    Article  Google Scholar 

  • Chen Z, Wang C, Li J, Fan W, Du J, Zhong B (2021) Adaboost-like End-to-End multiple lightweight U-nets for road extraction from optical remote sensing images. Int J Appl Earth Obs Geoinf 100:102341

    Google Scholar 

  • Chen X, Sun Q, Guo W, Qiu C, Yu A (2022) GA-Net: A geometry prior assisted neural network for road extraction. Int J Appl Earth Obs Geoinf 114:103004

    Google Scholar 

  • Chen H, Li Z, Wu J, Xiong W, Du C (2023a) SemiRoadExNet: A semi-supervised network for road extraction from remote sensing imagery via adversarial learning. ISPRS J Photogramm Remote Sens 198:169–183

    Article  Google Scholar 

  • Chen Z, Luo Y, Wang J, Li J, Wang C, Li D (2023b) DPENet: Dual-path extraction network based on CNN and transformer for accurate building and road extraction. Int J Appl Earth Obs Geoinf 124:103510

    Google Scholar 

  • Dai L, Zhang G, Zhang R (2023) RADANet: road augmented deformable attention network for road extraction from complex high-resolution remote-sensing images. IEEE Trans Geosci Remote Sens 61:1–13

    Google Scholar 

  • Ghandorh H, Boulila W, Masood S, Koubaa A, Ahmed F, Ahmad J (2022) Semantic segmentation and edge detection—Approach to road detection in very high resolution satellite images. Remote Sensing 14(3):613

    Article  Google Scholar 

  • Guan H, Lei X, Yu Y, Zhao H, Peng D, Junior JM, Li J (2022) Road marking extraction in UAV imagery using attentive capsule feature pyramid network. Int J Appl Earth Obs Geoinf 107:102677

    Google Scholar 

  • Khan MJ, Singh PP (2023) Advanced road extraction using CNN-based U-Net model and satellite imagery. Prime-Adv Electr Eng Electr Energy 5:100244

    Article  Google Scholar 

  • Khan SD, Alarabi L, Basalamah S (2023) DSMSA-Net: Deep spatial and multi-scale attention network for road extraction in high spatial resolution satellite images. Arab J Sci Eng 48(2):1907–1920

    Article  Google Scholar 

  • Kherdekar VA, Naik SA (2021) Convolution neural network model for recognition of speech for words used in mathematical expression. Turkish J Comput Math Educ 12(6):4034–4042

    Google Scholar 

  • Kumar KM (2024) RoadTransNet: advancing remote sensing road extraction through multi-scale features and contextual information. SIViP 18:2403–2412. https://doi.org/10.1007/s11760-023-02916-1

    Article  Google Scholar 

  • Kumar KM, Velayudham A (2024) Towards perfecting road extraction: the fusion of dilated convolution-based layers and vision transformer. J Spat Sci. https://doi.org/10.1080/14498596.2024.2309605

    Article  Google Scholar 

  • Li J, Liu Y, Zhang Y, Zhang Y (2021a) Cascaded attention DenseUNet (CADUNet) for road extraction from very-high-resolution images. ISPRS Int J Geo Inf 10(5):329

    Article  Google Scholar 

  • Li P, He X, Qiao M, Miao D, Cheng X, Song D, Chen M, Li J, Zhou T, Guo X, Yan X (2021b) Exploring multiple crowdsourced data to learn deep convolutional neural networks for road extraction. Int J Appl Earth Obs Geoinf 104:102544

    Google Scholar 

  • Lian R, Huang L (2020) DeepWindow: Sliding window based on deep learning for road extraction from remote sensing images. IEEE J Selected Topics Appl Earth Observ Remote Sens 13:1905–1916

    Article  Google Scholar 

  • Liang Y, Qin G, Sun M, Yan J, Jiang H (2021) MAFNet: Multi-style attention fusion network for salient object detection. Neurocomputing 422:22–33

    Article  Google Scholar 

  • Lin Y, Jin F, Wang D, Wang S, Liu X (2023) Dual-Task Network for Road Extraction from High-Resolution Remote Sensing Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

  • Liu X, Wang Z, Wan J, Zhang J, Xi Y, Liu R, Miao Q (2023) RoadFormer: Road extraction using a swin transformer combined with a spatial and channel separable convolution. Remote Sensing 15(4):1049

    Article  Google Scholar 

  • Luo Z, Zhou K, Tan Y, Wang X, Zhu R, Zhang L (2023) AD-RoadNet: An auxiliary-decoding road extraction network improving connectivity while preserving multiscale road details. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

  • Lv K, Wang W, Zhou Z, Wang X (2022) An improved watershed algorithm on multi-directional edge detection for road extraction in remote images. Int J Innov Comput Inf Control 18:851–866

    Google Scholar 

  • Soni PK, Rajpal N, Mehta R (2021) Road network extraction using multi-layered filtering and tensor voting from aerial images. Egyptian J Remote Sens Space Sci 24(2):211–219

    Google Scholar 

  • Subhashini D, Dutt VSI (2022) An innovative hybrid technique for road extraction from noisy satellite images. Materials Today: Proceedings 60:1229–1233

    Google Scholar 

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

    Google Scholar 

  • Xu Q, Long C, Yu L, Zhang C (2023) Road extraction with satellite images and partial road maps. IEEE Trans Geosci Remote Sens 61:1–14

    Google Scholar 

  • Yang S, Deng Z, Li X, Zheng C, Xi L, Zhuang J, Zhang Z, Zhang Z (2021) A novel hybrid model based on STL decomposition and one-dimensional convolutional neural networks with positional encoding for significant wave height forecast. Renewable Energy 173:531–543

    Article  Google Scholar 

  • Yin W, Qian M, Wang L, Qi J, Lu H (2022) Road extraction from satellite images with iterative cross-task feature enhancement. Neurocomputing 506:300–310

    Article  Google Scholar 

  • Yin A, Ren C, Yan Z, Xue X, Zhou Y, Liu Y, Lu J, Ding C (2023) C2S-RoadNet: Road extraction model with depth-wise separable convolution and self-attention. Remote Sensing 15(18):4531

    Article  Google Scholar 

  • Yuan G, Li J, Liu X, Yang Z (2022) Weakly supervised road network extraction for remote sensing image based scribble annotation and adversarial learning. Journal of King Saud University-Computer and Information Sciences 34(9):7184–7199

    Article  Google Scholar 

  • Zhang Y, Gao X, Duan Q, Yuan L, Gao X (2022) DHT: Deformable hybrid transformer for aerial image segmentation. IEEE Geosci Remote Sens Lett 19:1–5

    Google Scholar 

  • Zhou M, Sui H, Chen S, Liu J, Shi W, Chen X (2022) Large-scale road extraction from high-resolution remote sensing images based on a weakly-supervised structural and orientational consistency constraint network. ISPRS J Photogramm Remote Sens 193:234–251

    Article  Google Scholar 

Download references

Funding

Not applicable.

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, PET Engineering College, Vallioor, Tamilnadu, India

    K. Madhan Kumar

  2. Department of Computer Science and Engineering, Jansons Institute of Technology, Coimbatore, Tamilnadu, India

    A. Velayudham

Authors
  1. K. Madhan Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. Velayudham
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to K. Madhan Kumar.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Human and animal rights

This article does not contain any studies with human or animal subjects performed by any of the authors.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Consent to participate

Not applicable.

Consent for publication

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kumar, K.M., Velayudham, A. CCT-DOSA: a hybrid architecture for road network extraction from satellite images in the era of IoT. Evolving Systems 15, 1939–1955 (2024). https://doi.org/10.1007/s12530-024-09599-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12530-024-09599-0

Keywords

Search

Navigation