Comparative Analysis of Deep Learning Models for Building Extraction from High-resolution Satellite Imagery
Main Article Content
Abstract
In this research, an approach to extract buildings from Google's satellite imagery was proposed. The performances of various deep learning models (U-Net, RIU-Net, U-Net++, Res-U-Net, and DeepLabV3+) on pre-processed datasets were compared. The models were trained using the similarity metrics of Intersection over Union (IoU) and Dice Similarity Coefficient (DSC). The best-performing models among the segmentation techniques were Res-U-Net and DeepLabV3+. Res-U-Net, an enhanced version of the traditional U-Net model that incorporates residual connections for improved feature propagation, achieved an F1 score of 85.43% when using the RGB dataset. Similarly, DeepLabV3+ also achieved high performance on the Enhanced RGB dataset, obtaining an F1 score of 85.18% after applying pre-processing techniques. This research highlights the significance of color as a dominant feature for accurate building extraction from satellite images. The findings contribute to improved methodologies for building identification, benefiting urban planning, and disaster management applications.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright Transfer Statement
The copyright of this article is transferred to Current Applied Science and Technology journal with effect if and when the article is accepted for publication. The copyright transfer covers the exclusive right to reproduce and distribute the article, including reprints, translations, photographic reproductions, electronic form (offline, online) or any other reproductions of similar nature.
The author warrants that this contribution is original and that he/she has full power to make this grant. The author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors.
Here is the link for download: Copyright transfer form.pdf
References
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D.G., Steiner, B., Tucker, P.A., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., & Zhang, X. (2016). TensorFlow: A system for large-scale machine learning. In Proceedings of the 12th USENIX symposium on operating systems design and implementation (pp. 265-283). USENIX Association. https://doi.org/10.48550/arXiv.1605.08695
Alom, M. Z., Yakopcic, C., Hasan, M., Taha, T. M., & Asari, V. K. (2019). Recurrent residual U-Net for medical image segmentation. Journal of Medical Imaging, 6(1). Article 014006. https://doi.org/10.1117/1.JMI.6.1.014006
Alsabhan, W., & Alotaiby, T. (2022). Automatic building extraction on satellite images using Unet and ResNet50. Computational Intelligence and Neuroscience, 2022(1), Article 5008854. https://doi.org/10.1155/2022/5008854
Alsabhan, W., Alotaiby, T., & Dudin, B. (2022). Detecting buildings and nonbuildings from satellite images using U-Net. Computational Intelligence and Neuroscience, 2022(1), Article 4831223. https://doi.org/10.1155/2022/4831223
Aslantaş, N., Bayram, B., Bakirman, T. (2021). Building segmentation from VHR aerial imagery using DeepLabv3+ architecture. In Proceedings of the 42nd Asian conference on remote sensing (pp. 135-143). Asian Association on Remote Sensing.
Bakirman, T., Komurcu, I., & Sertel, E. (2022). Comparative analysis of deep learning based building extraction methods with the new VHR Istanbul dataset. Expert Systems with Applications, 202, Article 117346. https://doi.org/10.1016/j.eswa.2022.117346
Boyle, S. A., Kennedy, C. M., Torres, J. Colman, K., Pérez-Estigarribia, P. E., & de la Sancha, N. U. (2014). High-resolution satellite imagery is an important yet underutilized resource in conservation biology. PLoS One, 9(1), Article e86908. https://doi.org/10.1371/journal.pone.0086908
Chen, LC., Zhu, Y., Papandreou, G., Schroff, F., Adam, H. (2018). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In Proceedings editors Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.). In Proceeding of the 15th European conference on computer vision (pp. 833-851). Springer. https://doi.org/10.1007/978-3-030-01234-2_49
Chen, S., Ogawa, Y., Zhao, C., & Sekimoto, Y. (2023). Large-scale individual building extraction from open-source satellite imagery via super-resolution-based instance segmentation approach. ISPRS Journal of Photogrammetry and Remote Sensing. 195, 129-152. https://doi.org/10.1016/j.isprsjprs.2022.11.006
Chhor, G., Aramburu, C. B., & Bougdal-Lambert, I. (2017). Satellite image segmentation for building detection using U-Net. http://cs229.stanford.edu/proj2017/final-reports/5243715.pdf
Daranagama, S., & Witayangkurn, A. (2021). Automatic building detection with polygonizing and attribute extraction from high-resolution images. ISPRS International Journal of Geo-Information, 10(9), Article 606. https://doi.org/10.3390/ijgi10090606
Diakogiannis, F. I., Waldner, F., Caccetta, P., & Wu, C. (2020). ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data. ISPRS Journal of Photogrammetry and Remote Sensing, 162, 94-114. https://doi.org/10.1016/j.isprsjprs.2020.01.013
Dice, L. R. (1945). Measures of the amount of ecologic association between species. Ecology, 26(3), 297-302. https://doi.org/10.2307/1932409
Gavankar, N. L., & Ghosh, S. K. (2018). Automatic building footprint extraction from high-resolution satellite image using mathematical morphology. European Journal of Remote Sensing, 51(1), 182-193. https://doi.org/10.1080/22797254.2017.1416676
Gedraite, E. S., & Hadad, M. (2011). Investigation on the effect of a Gaussian Blur in image filtering and segmentation. In Proceedings of the 53rd international symposium on electronics in marine (pp. 393-396). IEEE.
GIS English. (2023). SAS Planet. https://gisenglish.geojamal.com/2018/06/download-sas-planet-nightly-all.html
Google. (2022). Google maps/google earth additional terms of service. https://www.google.com/help/terms_maps/?hl=en-US
Google. (n.d.). Google colaboratory. https://colab.google/
Han, J., Wang, Z., Wang, Y., & Hou, W. (2022). Building extraction algorithm from remote sensing images based on improved DeepLabv3+ network. Journal of Physics: Conference Series, 2303(1), Article 012010. https://doi.org/10.1088/1742-6596/2303/1/012010
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of 2016 IEEE conference on computer vision and pattern recognition (pp. 770-778). IEEE. https://doi.ieeecomputersociety.org/10.1109/CVPR.2016.90
International Commission on Illumination. (2012). CIE 15: Technical report: Colorimetry (3rd edition). https://archive.org/details/gov.law.cie.15.2004/page/n1/mode/2up
Ivanovsky, L., Khryashchev, V., Pavlov, V., & Ostrovskaya, A. (2019). Building detection on aerial images using U-NET neural networks. In Proceedings of the 24th Conference of Open Innovations Association (pp. 116-122). IEEE. https://doi.org/10.23919/FRUCT.2019.8711930
Jaccard, P. (1912). The distribution of the flora in the Alpine zone.1. New Phytologist, 11(2), 37-50. https://doi.org/10.1111/j.1469-8137.1912.tb05611.x
Kohavi, R. & Provost, F. (1998). Glossary of terms. Machine learning—special issue on applications of machine learning and the knowledge discovery process. Machine Learning, 30, 271-274. https://doi.org/10.1023/A:1017181826899
Rosentrater, K. A., & Evers, A. D. (2018). Flour treatments, applications, quality, storage and transport. In K. A. Rosentrater, & A. D. Evers (eds.). Kent's technology of cereals (5th ed., pp. 515-564). Woodhead Publishing. https://doi.org/10.1016/B978-0-08-100529-3.00007-4
Li, Z., Zheng, J., Zhu, Z., Yao, W., & Wu, S. (2014). Weighted guided image filtering. IEEE Transactions on Image processing, 24(1), 120-129. https://doi.org/10.1109/TIP.2014.2371234
Lin, B. S., Michael, K., Kalra, S., & Tizhoosh, H. R. (2017). Skin lesion segmentation: U-nets versus clustering. In Proceeding of the 2017 IEEE symposium series on computational intelligence (pp. 1-7). IEEE. https://doi.org/10.1109/SSCI.2017.8280804
Liu, M., Fu, B., Xie, S., He, H., Lan, F., Li, Y., Lou, P. & Fan, D. (2021). Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm. Ecological Indicators, 125, Article 107562. https://doi.org/10.1016/j.ecolind.2021.107562
McCarthy, M. J., & Halls, J. N. (2014). Habitat mapping and change assessment of coastal environments: an examination of WorldView-2, QuickBird, and IKONOS satellite imagery and airborne LiDAR for mapping barrier island habitats. ISPRS International Journal of Geo-Information, 3(1), 297-325. https://doi.org/10.3390/ijgi3010297
Namdeo, A., & Bhadoriya, S. S. (2016). A review on image enhancement techniques with its advantages and disadvantages. International Journal for Science and Advance Research in Technology, 2(5), 171-182.
Ronneberger, O., Fischer, P., Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. In N. Navab, J. Hornegger, W. Wells, & A. Frangi (eds.). In Proceeding of 18th medical image computing and computer-assisted intervention (pp. 234-241). Springer. https://doi.org/10.1007/978-3-319-24574-4_28
Sariturk, B., & Seker, D. Z. (2022). A residual-inception U-Net (RIU-Net) approach and comparisons with U-Shaped CNN and transformer models for building segmentation from high-resolution satellite images. Sensors, 22(19), Article 7624. https://doi.org/10.3390/s22197624
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 1-48. https://doi.org/10.1186/s40537-019-0197-0
Sørensen, T. (1948). A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on Danish commons. Biologiske Skrifter, 5, 1-34.
Vidhya, G. R., & Ramesh, H. (2017). Effectiveness of contrast limited adaptive histogram equalization technique on multispectral satellite imagery. In Proceedings of the 17th international conference on video and image processing (pp. 234-239). Association for Computing Machinery. https://doi.org/10.1145/3177404.3177409
Wen, Q., Jiang, K., Wang, W., Liu, Q., Guo, Q., Li, L., & Wang, P. (2019). Automatic building extraction from Google Earth images under complex backgrounds based on deep instance segmentation network. Sensors, 19(2), Article 333. https://doi.org/10.3390/s19020333
Wu, Y., Wang, G., Wang, Z., Wang, H., & Li, Y. (2022). DI-Unet: Dimensional interaction self-attention for medical image segmentation. Biomedical Signal Processing and Control, 78, Article 103896. https://doi.org/10.1016/j.bspc.2022.103896
Xu, Y., Wu, L., Xie, Z., & Chen, Z. (2018). Building extraction in very high resolution remote sensing imagery using deep learning and guided filters. Remote Sensing, 10(1), Article 144. https://doi.org/10.3390/rs10010144
Zhang, L., Dong, R., Yuan, S., Li, W., Zheng, J., & Fu, H. (2021). Making low-resolution satellite images reborn: a deep learning approach for super-resolution building extraction. Remote Sensing, 13(15), Article 2872. https://doi.org/10.3390/rs13152872
Zhang, Y., Chen, W., Chen, Y., & Tang, X. (2018). A post-processing method to improve the white matter hyperintensity segmentation accuracy for randomly-initialized U-net. In Proceeding of the 23rd international conference on digital signal processing (pp. 1-5). IEEE. https://doi.org/10.1109/ICDSP.2018.8631858
Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., & Liang, J. (2018). UNet++: A Nested U-net architecture for medical image segmentation. In Proceedings of deep learning in medical image analysis and multimodal learning for clinical decision support (pp. 3-11). Springer. https://doi.org/10.1007/978-3-030-00889-5_1