Automated, quick, and precise building extraction from aerial images using ll-unet model

Hasmukh P Koringa, Miral J Patel

Abstract


The subject matter of this article is the detection and semantic segmentation of buildings from high-resolution aerial images. It extracts building images from similar characteristics of roads and soil objects. It is used for various applications such as urban planning, infrastructure development, and disaster management. The goal of this study is to develop a fast, accurate, and automatic building detection model based on the semantic segmentation LL-UNET architecture that is optimized and tuned with proper hyper parameter settings. The tasks to be solved are as follows: collect remote sensing building dataset that is divided into three parts of training, validation, and testing; apply data augmentation on the training dataset by vertical flip, horizontal flip, and rotation methods; further pass into the bilateral filter to remove noises from the images; optimize LL-UNET model by various optimizer methods and tuned hyper parameter by proper selection value, the method is compared by the performance metrics recall, precision, and accuracy. The following results were obtained: the model is evaluated under the training loss curve and accuracy curve of different optimizers SGD, ASGD, ADAM, ADAMW, and RMSProp; it measures the training time, mean accuracy, and mean IOU parameters during the training phase; the testing phase is evaluated by precision and recall; the method is compared by visualizing the result of LL-UNET + different optimizers; and the proposed method is compared with the existing method by common evolution parameters metric. Conclusions. The scientific novelty of the results obtained is as follows: 1) the LL-UNET effectively segmented the building remotely sensed images in the limited number of training samples available; 2) the loss function of the model observed under hyper parameter selection of the optimizer, learning rate, batch size, and epochs; which makes an optimal model to extract the building in an accurate and fast manner from the complex background; 3) the proposed model results compared with a well-known model of the building extraction under the common evaluation metrics of F1 score.

Keywords


Deep Learning; Semantic Segmentation; LL-UNET; Buildings

Full Text:

PDF

References


Chen, Q. Y., & Feng, D. Z. Feature matching of remote‐sensing images based on bilateral local–global structure consistency. IET Image Processing, 2023, vol. 17, iss. 14, pp. 3909-3926. DOI: 10.1049/ipr2.12907.

Ma, X, Xu, J., Chong, Q., Ou, S., Xing, H., & Ni, M. FCUnet: Refined remote sensing image segmentation method based on a fuzzy deep learning conditional random field network. IET Image Processing, 2023, vol. 17, iss. 12, pp. 3616-3629. DOI: 10.1049/ipr2.12870.

Norman, M., Shahar, H. M., Mohamad, Z., Rahim, A., Mohd, F. A., & Shafri, H. Z. M. Urban building detection using object-based image analysis (OBIA) and machine learning (ML) algorithms. IOP Conference Series: Earth and Environmental Science, 2021, vol. 620, article no. 012010. 12 p. DOI: 10.1088/1755-1315/620/1/012010.

Alsabhan, W., Alotaiby, T., & Dudin, B. Detecting Buildings and Nonbuildings from Satellite Images Using U-Net. Hindawi Computational Intelligence and Neuroscience, vol. 2022, article no. 4831223. DOI: 10.1155/2022/4831223.

Kothari, A. M., & Patel, M. Road network extraction methods from remote sensing images: a review paperx. International Journal of Next-Generation Computing, 2022, vol. 13, no. 2, DOI: 10.47164/ijngc.v13i2.376.

Hermosilla, T., Ruiz, L. A., Recio, J. A., & Estornell, J. Evaluation of Automatic Building Detection Approaches Combining High Resolution Images and LiDAR Data. Remote Sens., 2011, vol. 3, iss. 6, pp. 1188-1210. DOI: 10.3390/rs3061188.

You, Y., Wang, S., Ma, Y., Chen, G., Wang, B., Shen, M., & Liu, W. Building Detection from VHR Remote Sensing Imagery Based on the Morphological Building Index. Remote Sens., 2018, vol. 10, iss. 8, article no. 1287. DOI: 10.3390/rs10081287.

Patel, M. J., & Kothari, A. M. Deep Learning-Enabled Road Segmentation and Edge-Centerline Extraction from High-Resolution Remote Sensing Images. International Journal of Image and Graphics, 2023, vol. 23, no. 06, article no. 2350058. DOI: 10.1142/S0219467823500584.

Parikh, Y., & Dr. Koringa, H. A Systematic Analysis of CMR Segmentation Using Deep Learning. International Journal of Next-Generation Computing, 2022, vol. 13 special iss. 3. DOI: 10.47164/ijngc.v13i3.825, 2022.

Guo, H., Liu, Z., Jiang, H., Wang, C., Liu, J., & Liang, D. Big Earth Data: a new challenge and opportunity for Digital Earth’s development. Int J Digit Earth, 2017, vol. 10, iss. 1, pp. 1-12. DOI: 10.1080/17538947.2016.1264490.

Zhang, Y. Optimisation of building detection in satellite images by combining multispectral classification and texture filtering. ISPRS Journal of Photogrammetry & Remote Sensing, 1999, vol. 54, iss. 1, pp. 50-60. DOI: 10.1016/S0924-2716(98)00027-6.

Femin, A., & Biju, K. S. Accurate Detection of Buildings from Satellite Images using CNN. 2nd International Conference on Electrical, Communication and Computer Engineering (ICECCE), Istanbul, Turkey, 12-13 June 2020, pp. 1-5. DOI: 10.1109/ICECCE49384.2020.9179232.

Kala, S., & Jeyakumar, M. K. A Proficient Satellite Image Building Detection Using Fuzzy and Neural Network Techniques. International Journal of Engineering Research and Technology, 2019, vol. 12, no. 1, pp. 89-96. Available at: https://www.ripublication.com/irph/ijert19/ijertv12n1_13.pdf (accessed 12.12.2023).

Hamaguchi, R., & Hikosaka, S. Building detection from satellite imagery using ensemble of size-specific detectors. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA, 2018, pp. 187-191. DOI: 10.1109/CVPRW.2018.00041.

Afanasyev, I., & Prathap, G. Deep Learning Approach for Building Detection in Satellite Multispectral Imagery. International Conference on Intelligent Systems (IS), Funchal, Portugal, 2018, pp. 461-465. DOI: 10.1109/IS.2018.8710471.

Wang, H., & Miao, F. Building extraction from remote sensing images using deep residual U-Net. European Journal of Remote Sensing, 2022, vol. 55, no. 1, pp. 71-85. DOI: 10.1080/22797254.2021.2018944.

Sirko, W., Kashubin, S., Ritter, M., Annkah, A., Bouchareb, Y. S. E., Dauphin, Y., Keysers, D., Neumann, M., Cisse, M., & Quinn, J. Continental-Scale Building Detection From High Resolution Satellite Imagery. arXiv preprint arXiv:2107.12283, 2021. DOI: 10.48550/arXiv.2107.12283.

Moghalles, K., Li, H.-C., Al‐Huda, Z., Raza, A., & Malik, A. Weakly supervised building semantic segmentation via superpixel‐CRF with initial deep seeds guiding. IET Image Processing, 2022, vol. 16, no. 12, pp. 3258-3267. DOI: 10.1049/ipr2.12558.

Chen, S., Ogawa, Y., Zhao, C., & Sekimoto, Y. Large-scale individual building extraction from open-source satellite imagery via super-resolution-based instance segmentation approach. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, vol. 195, pp. 129-152. DOI: 10.1016/j.isprsjprs.2022.11.006.

Nguyen, V., Ho, T. A., Vu, D. A., Anh, N. T. N., & Thang, T. N. Building footprint extraction in dense areas using super resolution and frame field learning. 12 th International Conference on Awareness Science and Technology (iCAST), November 2023, pp. 112-117. DOI: 10.1109/iCAST57874.2023.10359290.

He, W., Li, J., Cao, W., Zhang, L., & Zhang, H. Building extraction from remote sensing images via an uncertainty-aware network. arXiv preprint arXiv:2307.12309, 2023. DOI: 10.48550/arXiv.2307.12309.

Wang, M., Chen, K., Su, L., Yan, C., Xu, S., Zhang, H., Yuan, P., Jiang, X., & Zhang, B. RSBuilding: Towards General Remote Sensing Image Building Extraction and Change Detection with Foundation Model. arXiv preprint arXiv:2403.07564, 2024. DOI: 10.48550/arXiv.2403.07564.

Liu, Y., Pang, C., Zhan, Z., Zhang, X., & Yang, X. Building change detection for remote sensing images using a dual-task constrained deep siamese convolutional network model. IEEE Geoscience and Remote Sensing Letters, 2020, vol. 18, no. 5, pp. 811-815. DOI: 10.1109/LGRS.2020.2988032.

Mnih, V. Road and Building Detection Datasets. Massachusetts Buildings Dataset. Available at: https://www.cs.toronto.edu/~vmnih/data/. (accessed 12.12.2023).

Paris, S., Kornprobst, P., Tumblin, J., & Durand, F. Bilateral Filtering: Theory and Applications. Foundations and Trends in Computer Graphics and Vision, 2009, vol. 4, no. 1, pp. 1-73. DOI: 10.1561/0600000020.

Ronneberger, O., Fischer, P., & Brox, T. UNet: Convolutional networks for biomedical image segmentation. arXiv preprint arXiv:1505.04597, 2015, pp. 1-8. DOI: 10.48550/arXiv.1505.04597.

Patel, M. J., Kothari, A. M., & Koringa, H. P A novel approach for semantic segmentation of automatic road network extractions from remote sensing images by modified UNet. Radioelectronic and Computer Systems, 2022, no. 3, pp. 161-173. DOI: 10.32620/reks.2022.3.12.

Patel, M., & Koringa, H. P. Deep Learning Architecture U-Net Based Road Network Detection from Remote Sensing Images. International Journal of Next-Generation Computing, 2023, vol. 14, no. 3. DOI: 10.47164/ijngc.v14i3.1301.

Parikh, Y., & Koringa, H. Left Ventricle Segmentation using Bidirectional Convolution Dense Unet. Journal of Integrated Science & Technology, 2023, vol. 11, no. 1, article no. 417. Available at: https://pubs.thesciencein.org/journal/index.php/jist/article/view/417/297 (accessed 12.12.2023).

Gupta, A., Ramanath, R., Shi, J., & Keerthi, S. S. Adam vs. SGD: Closing the generalization gap on image classification. OPT2021: 13th Annual Workshop on Optimization for Machine Learning, 2021. Available at: https://opt-ml.org/papers/2021/paper53.pdf (accessed 12.12.2023).

Aatila, M., Lachgar, M., & Kartit, A. Comparative study of optimization techniques in deep learning: Application in the ophthalmology field. The International Conference on Mathematics & Data Science (ICMDS) 2020, Journal of Physics: Conference Series, 2021, vol. 1743. DOI 10.1088/1742-6596/1743/1/012002.

Yaloveha, V., Podorozhniak, A., & Kuchuk, H. Convolutional neural network hyperparameter optimization applied to land cover classification. Radioelectronic and computer systems, 2022, no. 1, pp. pp. 115-128. DOI: 10.32620/reks.2022.1.09.

Alshehhi, R. Marpu, P. R., Woon, W. L., & Mura, M. D. Simultaneous Extraction Of Roads And Buildings In Remote Sensing Imagery With Convolutional Neural Networks. ISPRS Journal of Photogrammetry And Remote Sensing, 2017, vol. 130, pp. 139-149. DOI: 10.1016/j.isprsjprs.2017.05.002.

He, K., & Sun, J. Convolutional neural networks at constrained time cost. IEEE Conference on Computer Vision and Pattern Recognition, arXiv preprint arXiv:1412.1710, 2015, pp. 1-8, DOI: 10.48550/arXiv.1412.1710.

Gamal, A., Wibisono, A., Wicaksono, S. B., Abyan, M. A., Hamid, N., Wisesa, H. A., Jatmiko, W., & Ardhianto, R. Automatic LIDAR building segmentation based on DGCNN and euclidean clustering. Journal of Big Data, 2020, no. 7, article no. 102. DOI: 10.1186/s40537-020-00374-x.




DOI: https://doi.org/10.32620/reks.2024.2.04

Refbacks

  • There are currently no refbacks.