Segmentation of Small Objects in Satellite Imagery Using Dense U-Net in Massachusetts Buildings Dataset

  • Muhammad Iqbal Izzul Haq Universitas Indonesia
  • Aniati Murni Arymurthy Universitas Indonesia
  • Irham Muhammad Fadhil Universitas Indonesia
Keywords: class imbalance, dataset, end-to-end, convolution, denseU-net

Abstract

Class imbalance is a serious problem that disrupts the process of semantic segmentation of satellite imagery in urban areas in Earth remote sensing. Due to the large objects dominating the segmentation process, small object are consequently limited, so solutions based on optimizing overall accuracy are often unsatisfactory. Due to the class imbalance of semantic segmentation in Earth remote sensing images in urban areas, we developed the concept of Down-Sampling Block (DownBlock) to obtain contextual information and Up-Sampling Block (UpBlock) to restore the original resolution. We proposed an end-to-end deep convolutional neural network (DenseU-Net) architecture for pixel-wise urban remote sensing image segmentation. this method to segmentation the small object in satellite imagery.The accuracy of the small object class in this study was further improved using our proposed method. This study used data from the Massachusetts Buildings dataset using Dense U-Net method and obtained an overall accuracy of 84.34%.

 

Downloads

Download data is not yet available.

References

S. Liu, Y. Li, and X. Tong, “Superpixel-based multiple change detection in very-high-resolution remote sensing images,” RSIP 2017 - Int. Work. Remote Sens. with Intell. Process. Proc., no. 3, pp. 25–27, 2017, doi: 10.1109/RSIP.2017.7958817.

O. Regniers, L. Bombrun, V. Lafon, and C. Germain, “Supervised Classification of Very High Resolution Optical Images Using Wavelet-Based Textural Features,” IEEE Trans. Geosci. Remote Sens., vol. 54, no. 6, pp. 3722–3735, 2016, doi: 10.1109/TGRS.2016.2526078.

X. Cao, R. Li, L. Wen, J. Feng, and L. Jiao, “Deep Multiple Feature Fusion for Hyperspectral Image Classification,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 11, no. 10, pp. 3880–3891, 2018, doi: 10.1109/JSTARS.2018.2866595.

Y. Seo and K. S. Shin, “Image classification of fine-grained fashion image based on style using pre-trained convolutional neural network,” 2018 IEEE 3rd Int. Conf. Big Data Anal. ICBDA 2018, pp. 387–390, 2018, doi: 10.1109/ICBDA.2018.8367713.

Z. Wang, X. Xiang, Z. Zhao, and F. Su, “Deep Image Retrieval: Indicator and Gram Matrix Weighting for Aggregated Convolutional Features,” Proc. - IEEE Int. Conf. Multimed. Expo, vol. 2018-July, pp. 1–6, 2018, doi: 10.1109/ICME.2018.8486547.

V. Iglovikov, S. Mushinskiy, and V. Osin, “Satellite Imagery Feature Detection using Deep Convolutional Neural Network: A Kaggle Competition,” 2017, [Online]. Available: http://arxiv.org/abs/1706.06169

Y. Liu, D. M. Nguyen, N. Deligiannis, W. Ding, and A. Munteanu, “Hourglass-shape network based semantic segmentation for high resolution aerial imagery,” Remote Sens., vol. 9, no. 6, pp. 1–24, 2017, doi: 10.3390/rs9060522.

M. Volpi and D. Tuia, “Dense semantic labeling of subdecimeter resolution images with convolutional neural networks,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 2, pp. 881–893, 2017, doi: 10.1109/TGRS.2016.2616585.

X. Gao et al., “An End-to-End Neural Network for Road Extraction from Remote Sensing Imagery by Multiple Feature Pyramid Network,” IEEE Access, vol. 6, pp. 39401–39414, 2018, doi: 10.1109/ACCESS.2018.2856088.

T. Wang, Y. Zhao, L. Zhu, G. Liu, Z. Ma, and J. Zheng, “Lung CT image aided detection COVID-19 based on Alexnet network,” Proc. - 2020 5th Int. Conf. Commun. Image Signal Process. CCISP 2020, pp. 199–203, 2020, doi: 10.1109/CCISP51026.2020.9273512.

S. S. Kaddoun, Y. Aberni, L. Boubchir, M. Raddadi, and B. Daachi, “Convolutional Neural Algorithm for Palm Vein Recognition using ZFNet Architecture,” BioSMART 2021 - Proc. 4th Int. Conf. Bio-Engineering Smart Technol., no. iv, 2021, doi: 10.1109/BioSMART54244.2021.9677799.

X. Liu, M. Chi, Y. Zhang, and Y. Qin, “Classifying High Resolution Remote Sensing Images by Fine-Tuned VGG Deep Networks,” in IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, Jul. 2018, pp. 7137–7140. doi: 10.1109/IGARSS.2018.8518078.

Y. Yang, P. Bi, and Y. Liu, “License Plate Image Super-Resolution Based on Convolutional Neural Network,” 2018 3rd IEEE Int. Conf. Image, Vis. Comput. ICIVC 2018, pp. 723–727, 2018, doi: 10.1109/ICIVC.2018.8492768.

D. Gritzner and J. Ostermann, “Minimizing Manual Labeling Effort for The Semantic Segmentation of Aerial Images,” in 2021 IEEE Statistical Signal Processing Workshop (SSP), Jul. 2021, pp. 81–85. doi: 10.1109/SSP49050.2021.9513774.

Z. Cheng and D. Fu, “Remote Sensing Image Segmentation Method based on HRNET,” in IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, Sep. 2020, vol. 2507, no. February, pp. 6750–6753. doi: 10.1109/IGARSS39084.2020.9324289.

R. Dong, X. Pan, and F. Li, “DenseU-Net-Based Semantic Segmentation of Small Objects in Urban Remote Sensing Images,” IEEE Access, vol. 7, pp. 65347–65356, 2019, doi: 10.1109/ACCESS.2019.2917952.

Published
2022-06-30
How to Cite
Muhammad Iqbal Izzul Haq, Aniati Murni Arymurthy, & Irham Muhammad Fadhil. (2022). Segmentation of Small Objects in Satellite Imagery Using Dense U-Net in Massachusetts Buildings Dataset . Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 6(3), 376 - 379. https://doi.org/10.29207/resti.v6i3.3993
Section
Artikel Teknologi Informasi