Automatic Extraction of Urban Features from Very High-Resolution Digital Data Using Deep Neural Networks: A Case Study of Ahvaz City

Authors

1 Shahid Chamran University of Ahvaz

2 Department of RS and GIS, Faculty of Earth Sciences, Shahid Chamran University of Ahvaz, Ahvaz, Iran

Abstract

Continuous growth and development in urban planning, along with rapid changes on the ground, have increased the need for continuous examination of these changes. Remote sensing could be considered as one of the most suitable methods to achieve this goal. Utilizing deep learning methods to extract features from images is a common method in producing land cover maps because it enables the analysis of high-level abstract concepts. This not only minimizes human involvement in information production but also reduces time and costs. In this research, suitable training samples were prepared for automatically extracting urban features such as buildings, green spaces, bare land, and roads. Among various architectures of deep learning, the UNet model was chosen as the main model of the study due to its higher accuracy in results. Additionally, the VGG-16 model was used as the backbone for transfer learning technique. Training this network was performed once with three-band aerial images (RGB) and in another state by combining image bands with digital surface models (RGB+nDSM) to compare the results and introduce the best method for extracting urban features. The results showed that the VGG-16+UNet model performed class extraction with higher overall accuracy (88.14%) in the presence of a digital surface model compared to running the model with aerial image bands (76.34%). Furthermore, based on these results, it was evident that the algorithm used in this research and its architecture can be effective in preparing urban maps and detecting significant changes.

Keywords

Main Subjects

References

Abdollahi, A., Pradhan, B., Shukla, N., Chakraborty, S., Alamri, A., 2021. Multi-Object Segmentation in Complex Urban Scenes from High-Resolution Remote Sensing Data. Journal of Remote Sensing 13(18) 1-22. https://doi.org/10.3390/rs13183710
Ahmadian, N., Sedaghat, A., Mohammadi, N., 2023. Performance evaluation of three deep learning models in building footprint extraction from aerial and satellite images. Engineering Journal of Geospatial Information Technology 11(1), 105-123. http://jgit.kntu.ac.ir/article-1-912-en.html
Badrinarayanan, V., Kendall, A., Cipolla, R., 2017. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence 39(12), 2481-2495. https://doi.org/10.1109/TPAMI.2016.2644615
Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H., 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV) 801-818. https://link.springer.com/conference/eccv
Chen, Y., Jiang, H., Li, C., Jia, X., Ghamisi, P., 2016. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE transactions on geoscience and remote sensing 54 6232-6251. https://doi.org/10.1109/TGRS.2016.2584107
Chen, Z., Zhang, T., Ouyang, C., 2018. End-to-end airplane detection using transfer learning in remote sensing images. Remote Sensing, 10(1) 139-151. https://doi.org/10.3390/rs10010139
Dong, R., Bai, L., Li, F., 2020. SiameseDenseU‐Net‐based Semantic Segmentation of Urban Remote Sensing Images. Mathematical Problems in Engineering(1) 1515630.https://doi.org/10.1155/2020/1515630
Du, S., Du, S., Liu, B.,  Zhang, X., 2021. Incorporating DeepLabv3+ and object-based image analysis for semantic segmentation of very high resolution remote sensing images. International Journal of Digital Earth 14(3), 357-378. https://doi.org/10.1080/17538947.2020.1831087
Farhadi, N., Kiani, A., Ebadi, H., 2019. Target detection from high-resolution remote sensing images using deep learning methods. Iranian Journal of Remote Sensing & GIS, 11(1) pp.48 64. https://doi.org/10.52547/gisj.11.1.48
He, K., Zhang, X., Ren, S., Sun, J., 2015. Deep Residual Learning for Image Recognition.
arXiv:1512.03385. https://doi.org/10.48550/arXiv.1512.03385
He, K., Zhang, X., Ren, S., Sun, J., 2015. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. vol. 37, no. 9, pp. 1904-1916. https://doi.org/10.1109/TPAMI.2015.2389824
Iglovikov, V., Shvets, A., 2018. Ternausnet: U-net with vgg11 encoder pre-trained on imagenet for image segmentation. arXiv vol. 18, no. 1, pp. 37-42. https://doi.org/10.48550/arXiv.1801.05746
KaboliZadeh, M., Rangzan, K., Saberi, A., 2023. Automatic extraction of urban objects from highresolution aerial images using convolutional neural networks (Study area: Ahvaz city). Advanced Applied Geology 13(2), 408-422. https://doi.org/10.22055/aag.2023.42422.2330
Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. https://doi.org/10.48550/arXiv.1412.6980
Liu, X., Chi, M., Zhang, Y., Qin, Y., 2018. Classifying high resolution remote sensing images by fine-tuned VGG deep networks. In IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium (pp. 7137-7140). IEEE. https://doi.org/10.1109/IGARSS.2018.8518078
Long, J., Shelhamer, E., Darrell, T., 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (3431-3440 PP.). https://doi.org/10.48550/arXiv.1411.4038
McGlinchy, J., Muller, B., Johnson, B., Joseph, M., Diaz, J., 2021. Fully convolutional neural network for impervious surface segmentation in mixed urban environment. Photogrammetric Engineering & Remote Sensing 87(2), 117-123. https://doi.org/10.14358/PERS.87.2.117
Mulyanto, M., Faisal, M., Prakosa, S.W.,  Leu, J.S., 2020. Effectiveness of focal loss for minority classification in network intrusion detection systems. Symmetry, 13(1), 4-12 https://doi.org/10.3390/sym13010004
Pan, Z., Xu, J., Guo, Y., Hu, Y., Wang, G., 2020. Deep learning segmentation and classification for urban village using a worldview satellite image based on U-Net. Remote Sensing, 12(10), 1574-1582. https://doi.org/10.3390/rs12101574
Ronneberger, O., Fischer, P., Brox, T., 2015. 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 (234-241 PP.). Springer International Publishing. http://dx.doi.org/10.1007/978-3-319-24574-4_28
Sang, D.V., Minh, N.D., 2018. Fully residual convolutional neural networks for aerial image segmentation. In Proceedings of the 9th International Symposium on Information and Communication Technology, 289-296. https://doi.org/10.1145/3287921.3287970
Sariturk, B., Bayram, B., Duran, Z., Seker, D.Z., 2020. Feature extraction from satellite images using segnet and fully convolutional networks (FCN). International Journal of Engineering and Geosciences 5(3), 138-143. https://doi.org/10.26833/ijeg.645426
Shinohara, T., Xiu, H., Matsuoka, M., 2020. FWNet: semantic segmentation for full-waveform LiDAR data using deep learning. Sensors 20 3568. http://dx.doi.org/10.3390/s20123568
Simonyan, K., Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. https://doi.org/10.48550/arXiv.1409.1556
Singh Punn, N.,  Agarwal, S., 2021. Modality specific U-Net variants for biomedical image segmentation: A survey. arXiv e-prints, pp.arXiv. ???. https://ui.adsabs.harvard.edu/link_gateway/2021arXiv210704537S/doi:10.48550/arXiv.2107.04537
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: Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 14, Proceedings 3, pp. 240-248. https://doi.org/10.48550/arXiv.1707.03237
Sun, K., Zhao, Y., Jiang, B., Cheng, T., Xiao, B., Liu, D., Mu, Y., Wang, X., Liu, W., Wang, J., 2019. High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514. https://doi.org/10.48550/arXiv.1904.04514
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V.,  Rabinovich, A., 2015. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition pp. 1-9. https://doi.org/10.48550/arXiv.1409.4842
United Nations Department of Economic and Social Affairs., 2014. World Urbanization Prospects The 2014 Revision. Demographic Research. 517. https://doi:(ST/ESA/SER.A/366).
Vetrivel, A., Gerke, M., Kerle, N., Nex, F., Vosselman, G., 2018. Disaster damage detection through
synergistic use of deep learning and 3D point cloud features derived from very high-resolution oblique aerial images, and multiple-kernel-learning. ISPRS journal of photogrammetry and remote sensing 140, 45-59. https://doi.org/10.1016/j.isprsjprs.2017.03.001
Volpi, M., Tuia, D., 2016. Dense semantic labeling of subdecimeter resolution images with convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing 55(2), 881-893. https://doi.org/10.1109/TGRS.2016.2616585
Wen, D., Huang, X., Zhang, L., Benediktsson, J.A., 2015. A novel automatic change detection method for urban high-resolution remotely sensed imagery based on multiindex scene representation. IEEE Transactions on Geoscience and Remote Sensing 54(1), 609-625. https://doi.org/10.1109/TGRS.2015.2463075
Yang, H., Yu, B., Luo, J., Chen, F., 2019. Semantic segmentation of high spatial resolution images with deep neural networks. GIScience & remote sensing 56(5), 749-768. https://doi.org/10.1080/15481603.2018.1564499
Yang, R., Dai, Q., Cheng, H., Zhang, Y., Chen, N., Wang, L., 2022. Improving Semantic Segmentation Performance by Jointly Using High Resolution Remote Sensing Image and Ndsm. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 3 77-83. https://doi.org/10.5194/isprs-annals-V-3-2022-77-2022
Yu, B., Yang, L., Chen, F., 2018. Semantic segmentation for high spatial resolution remote sensing images based on convolution neural network and pyramid pooling module. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 11(9) 3252-3261. https://doi.org /10.1109/JSTARS.2018.2860989
Zhang, J., Lin, S., Ding, L., Bruzzone, L., 2020. Multi-scale context aggregation for semantic segmentation of remote sensing images. Remote Sensing, 12(4) 701. https://doi.org/10.3390/rs12040701
Zhang, L., Shao, Z., Liu, J., Cheng, Q., 2019. Deep learning based retrieval of forest aboveground biomass from combined LiDAR and landsat 8 data. Remote Sensing 11 14591471 https://doi.org/10.3390/rs11121459
Advanced Applied Geology
Volume 14, Issue 4
January 2025
Pages 1058-1071

Files

Share

How to cite

Statistics