Utilizing the Principal Component Analysis on Multispectral Aerial Imagery for Identification of Underlying Structures

Authors: M. Bosques-Perez, W. Izquierdo, H. Martin, L. Deng, J. Rodriguez, T. Yan, M. Cabrerizo, A. Barreto, N. Rishe, M. Adjouadi

Abstract:

Aerial imagery is a powerful tool when it comes to analyzing temporal changes in ecosystems and extracting valuable information from the observed scene. It allows us to identify and assess various elements such as objects, structures, textures, waterways, and shadows. To extract meaningful information, multispectral cameras capture data across different wavelength bands of the electromagnetic spectrum. In this study, the collected multispectral aerial images were subjected to principal component analysis (PCA) to identify independent and uncorrelated components or features that extend beyond the visible spectrum captured in standard RGB images. The results demonstrate that these principal components contain unique characteristics specific to certain wavebands, enabling effective object identification and image segmentation.

Keywords: Big data, image processing, multispectral, principal component analysis.

References:

[1] S. Kovbasiuk, L. Kanevskyy and M. Romanchuk, ”Object Detection Method Based on Aerial Image Instance Segmentation by Unmanned Aerial System in the Framework of Decision Making System,” 2019 3rd International Conference on Advanced Information and Communications Technologies (AICT), Lviv, Ukraine, 2019, pp. 332-335, doi: 10.1109/AIACT.2019.8847875.
[2] Z. Song, H. Zhang, F. Liu, S. Chen and F. Zhang, ”Unmanned Aerial Vehicle Coverage Path Planning Algorithm Based on Cellular Automata,” 2018 International Conference on Information Systems and Computer Aided Education (ICISCAE), Changchun, China, 2018, pp. 371-374, doi: 10.1109/ICISCAE.2018.8666895.
[3] I. Yoon, M. H. Hayes and J. Paik, ”Wavelength-adaptive image formation model and geometric classification for defogging unmanned aerial vehicle images,” 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, 2013, pp. 2454-2458, doi: 10.1109/ICASSP.2013.6638096.
[4] P. Duan, S. Hu, X. Kang and S. Li, ”Shadow Removal of Hyperspectral Remote Sensing Images With Multiexposure Fusion,” in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-11, 2022, Art no. 5537211, doi: 10.1109/TGRS.2022.3203808.
[5] Y. Chen, Q. Weng, L. Tang, X. Zhang, M. Bilal and Q. Li, ”Thick Clouds Removing From Multitemporal Landsat Images Using Spatiotemporal Neural Networks,” in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-14, 2022, Art no. 4400214, doi: 10.1109/TGRS.2020.3043980.
[6] J. Brauers and T. Aach, ”Longitudinal aberrations caused by optical filters and their compensation in multispectral imaging,” 2008 15th IEEE International Conference on Image Processing, San Diego, CA, USA, 2008, pp. 525-528, doi: 10.1109/ICIP.2008.4711807.
[7] C. Iturrino, F. X. Arias, H. Sierra and E. Arzuaga, ”Single-Shot Multispectral Image Acquisition for Low-Altitude Remote Sensing using Light Diffraction Techniques,” 2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), Amsterdam, Netherlands, 2019, pp. 1-5, doi: 10.1109/WHISPERS.2019.8920879.
[8] Z. -W. Pan and H. -L. Shen, ”Multispectral Image Super-Resolution via RGB Image Fusion and Radiometric Calibration,” in IEEE Transactions on Image Processing, vol. 28, no. 4, pp. 1783-1797, April 2019, doi: 10.1109/TIP.2018.2881911.
[9] W. J. Cukierski, Xin Qi and D. J. Foran, ”Moving beyond color: The case for multispectral imaging in brightfield pathology,” 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Boston, MA, USA, 2009, pp. 1111-1114, doi: 10.1109/ISBI.2009.5193251.
[10] S. Xiaorui and W. Lingda, ”Denoising of Hyperspectral Images Based on Principal Component Analysis and Adaptive Sparse Coding,” 2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS), Beijing, China, 2018, pp. 1-6, doi: 10.1109/PRRS.2018.8486272.
[11] M. Kusban, A. Susanto and O. Wahyunggoro, ”Feature extraction for palmprint recognition using kernel-PCA with modification in Gabor parameters,” 2016 1st International Conference on Biomedical Engineering (IBIOMED), Yogyakarta, Indonesia, 2016, pp. 1-6, doi: 10.1109/IBIOMED.2016.7869820.
[12] G. Zhou, W. Chen, J. A. Kelmelis and D. Zhang, ”A comprehensive study on urban true orthorectification,” in IEEE Transactions on Geoscience and Remote Sensing, vol. 43, no. 9, pp. 2138-2147, Sept. 2005, doi: 10.1109/TGRS.2005.848417.
[13] “About worldview-3 I A satellite with unsurpassed accuracy & agility,” Geoimage, https://www.geoimage.com.au/satellites-sensors/worldview-3/ (accessed May 22, 2023).