Automatic extraction of urban objects from high-resolution aerial images using convolutional neural networks (Study area: Ahvaz city)

Authors

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

2 Department of Engineering Science, Division of Mathematics, Computer and Surveying Engineering, University West, Sjöberg, Lars

Abstract

Automatic extraction and reconstruction of these objects from aerial and satellite data can diminish the role of humans in the production of large-scale urban spatial information and reduce the cost and time, reduce their production drastically. Identifying target objects from aerial and satellite images using computer image processing techniques and neural networks is one of the most widely used algorithms for identifying urban features. Among these types of networks are Convolution Neural Networks, which have a high power to extract high-level features in all kinds of images. In this research, more than 850 educational examples of important urban structural features including buildings, roads and single trees have been prepared. In this research, among the different types of existing networks, due to the higher speed of processing, Convolution Neural Network based on one-shot multi-box detector with ResNet network base has been used in order to automatically discover and extract the range of these complications. The proposed model is trained by training samples based on 85% training data and 15% validation data, with 120 iterations and 93% accuracy. The trained model has been implemented on different images of the study area to discover the target complications. The evaluation results of the model are based on the accuracy criterion equal to 0.86, the recovery criterion equal to 0.82, and the F1Score criterion equal to 0.83. The results show that the proposed algorithm can be recruited in fields such as producing and updating large-scale urban maps and change detection in urban areas.

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
Alsabhan, W., Alotaiby, T., 2022. Automatic Building Extraction on Satellite Images Using Unet and ResNet50. Hindawi, Computational Intelligence and Neuroscience 2022, 1-12. https://doi.org/10.1155/2022/5008854
Baghani, A., Valadanzoej, M.J., Mokhtarzadeh, M., 2016. Large-scale cadastral map production from urban areas using UAV photogrammetry. The 1st National Conference on Geospatial Information Technology. 1-17. https://civilica.com/doc/461639
Daneshtalab, S., Rastiveis, H., Hosseiny, B., 2019. CNN-Based Feature-Level Fusion of Very High Resolution Aerial Imagery and LIDAR Data. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 279-284.
Granados-Bolanos, S., Quesada-Roman, A., Alvarado, G.E., 2020. Low-cost UAV applications in dynamic tropical volcanic landforms. Journal of Volcanology and Geothermal Research 410. https://doi.org/10.1016/j.jvolgeores.2020.107143
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. Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770-778. https://doi.org/10.1109/CVPR.2016.90
Onishi, M., Ise, T., 2018. Automatic classification of trees using UAV onboard camera and deep learning. ArXiv abs/1804.10390. https://doi.org/10.48550/arXiv.1804.10390
Rakianipour, S., 2019. Automatic building extraction from digital imagsusing artificial intelligence method. MSc thesis. Shahid Chamran University of Ahvaz.
Wang, X., Xu, N., Wang, B., Liu, Y., Zhang, Sh., 2022. Urban building extraction from high-resolution remote sensing imagery based on multi-scale recurrent conditional generative adversarial network. GIScience and Remote Sensing 59, 861-884. https://doi.org/10.1080/15481603.2022.2076382
Wang, Y., Li, Sh., Teng, F., Lin, Y., Wang, M., Cai, H., 2022. Improved Mask R-CNN for Rural Building Roof Type Recognition from UAV High-Resolution Images: A Case Study in Hunan Province, China. Journal of Remote Sensing 14(2), 1-25. https://doi.org/10.3390/rs14020265
Wang, K., Meng, Z., Wu, Z., 2021. Deep Learning-Based Ground Target Detection and Tracking for Aerial Photography from UAVs. Applied Sciences 11(18), 1-11. https://doi.org/10.3390/app11188434
Watanabe, S., Sumi, K., Ise, T., 2020. Identifying the vegetation type in Google Earth images using a convolutional neural network: a case study for Japanese bamboo forests. BMC Ecology 20(65), 1-14. https://doi.org/10.1186/s12898-020-00331-5
Xu, B., Wang, N., Chen, T., Li, M., 2015. Empirical evaluation of rectified activations in convolutional network. ArXiv Prepr. arXiv:1505.00853. https://doi.org/10.48550/arXiv.1505.00853
Xu, Z., 2022. UAV surveying and mapping information collection method based on Internet of Things. Internet of Things and Cyber–Physical Systems, 18, 138-144. https://doi.org/10.1016/j.iotcps.2022.07.002
Advanced Applied Geology
Volume 13, Issue 2
June 2023
Pages 408-422

Files

Share

How to cite

Statistics