Abstract

In recent years, with the increase in urbanization, it has become important to keep track of infrastructure in a geographical area. Urban planners rely on accurate building area calculations to assess the spatial characteristics and dynamics of built environments, informing critical decision-making processes. Satellite technologies have been developing rapidly and applied to many remote sensing applications due to which high-resolution images of a geographical area are obtained with much ease. To estimate the area of buildings we use deep neural networks to analyze images from high-resolution satellite data by extracting useful semantic features and segmenting all buildings. We then evaluate and compare four of these models to find how well each of these models segmented out the buildings from the image. After we train and evaluate, we compare the models based on the mIoU score with the Unet model (with ResNet18 encoder) obtaining the highest mIoU score (0.83).

Keywords: Satellite imagery, area estimation, Neural Networks, segmentation.

Keywords

  • Data Modeling
  • Artificial Intelligence
  • Data Architecture
  • ETL
  • SaaS ETL
  • Datawarehousing

References

  1. LeCun, Y. et al. (1998) Convolutional networks for images, speech, and Time Series: The handbook of brain theory and neural networks, Guide books. Available at: https://dl.acm.org/doi/10.5555/303568.303704 (Accessed: 27 June 2023).
  2. Minaee, S. et al. (2020) Image segmentation using Deep Learning: A Survey, arXiv.org. Available at: https://arxiv.org/abs/2001.05566 (Accessed: 27 June 2023).
  3. H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid Scene Parsing Network.” Available: https://arxiv.org/pdf/1612.01105.pdf
  4. T. Xiao, Y. Liu, B. Zhou, Y. Jiang, and J. Sun, “Unified Perceptual Parsing for Scene Understanding.” Accessed: June 27, 2023. [Online]. Available: https://arxiv.org/pdf/1807.10221.pdf
  5. K. Sun et al., “High-Resolution Representations for Labeling Pixels and Regions.” Available: https://arxiv.org/pdf/1904.04514.pdf
  6. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” 2015. Available: https://arxiv.org/pdf/1505.04597.pdf
  7. Liu, X., Deng, Z. and Yang, Y. (2018) Recent progress in Semantic Image Segmentation - Artificial Intelligence Review, SpringerLink. Available at: https://link.springer.com/article/10.1007/s10462-018-9641-3 (Accessed: 27 June 2023).
  8. J. Long, E. Shelhamer, and T. Darrell, “Fully Convolutional Networks for Semantic Segmentation,” arXiv.org, 2014. https://arxiv.org/abs/1411.4038
  9. Everingham, M. et al. (2009) The Pascal Visual Object Classes (VOC) Challenge - International Journal of Computer Vision, SpringerLink. Available at: https://link.springer.com/article/10.1007/s11263-009-0275-4 (Accessed: 27 June 2023).
  10. M. Cordts et al., “The Cityscapes Dataset for Semantic Urban Scene Understanding,” arXiv:1604.01685 [cs], Apr. 2016, Available: https://arxiv.org/abs/1604.01685
  11. K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” arXiv.org, Dec. 10, 2015. https://arxiv.org/abs/1512.03385
  12. Lin, T.-Y. et al. (2017) Feature Pyramid Networks for Object Detection, arXiv.org. Available at: https://arxiv.org/abs/1612.03144 (Accessed: 27 June 2023).
  13. D. Zhu, H. Yao, B. Jiang, and P. Yu, “Negative Log Likelihood Ratio Loss for Deep Neural Network Classification,” arXiv.org, Apr. 27, 2018. https://arxiv.org/abs/1804.10690 (accessed Jun. 27, 2023).
  14. C. H. Sudre, W. Li, T. Vercauteren, S. Ourselin, and M. Jorge Cardoso, “Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations,” Springer Link, 2017. https://link.springer.com/chapter/10.1007%2F978-3-319-67558-9_28
  15. Mohanty, S.P. et al. (2020) Deep learning for understanding satellite imagery: An experimental survey, Frontiers. Available at: https://www.frontiersin.org/articles/10.3389/frai.2020.534696/full (Accessed: 27 June 2023).
  16. A. Van Etten, D. Lindenbaum, and T. M. Bacastow, “SpaceNet: A Remote Sensing Dataset and Challenge Series,” arXiv.org, Jul. 14, 2019. https://arxiv.org/abs/1807.01232 (accessed Jun. 27, 2023).