1887

Abstract

Summary

Industry-scale land seismic data acquisition in the arid area requires an accurate land cover map to arrive at a safe, reliable, and successful project execution. Unmanned Aerial Vehicle (UAV) surveys offer a cheap, fast, and sustainable method with a low CO2 footprint to obtain an accurate orthomosaic image of the area. Cloth simulation filter, random forest algorithm, and conditional generative adversarial network (CGAN) represent a spectrum of method complexity commonly utilized to classify land cover from UAV-based ortho imageries. This study investigates the applicability of the three abovementioned methods for land cover classification using UAV-based imageries tailored for seismic data acquisition in the arid area. With minor imprecision, CGAN outperforms the random forest algorithm and the cloth simulation filter in terms of accuracy. CGAN is exceptionally accel in classifying small features in densely-populated areas. However, if one only needs to separate the orthomosaic image into the ground and non-ground features, the cloth simulation filter coupled with edge detection gives the fastest result with acceptable accuracy.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202310164
2023-06-05
2026-01-20

  • From This Site

    /content/papers/10.3997/2214-4609.202310164
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Al-Najjar, Husam A. H., BaharehKalantar, BiswajeetPradhan, VahidehSaeidi, Alfian AbdulHalin, NaonoriUeda, and ShattriMansor. 2019. “Land Cover Classification from fused DSM and UAV Images Using Convolutional Neural Networks.” Remote Sensing11 (12): 1461. https://www.mdpi.com/2072-4292/11/12/1461.
     [Google Scholar]
  2. Canny, John. 1986. “A Computational Approach To Edge Detection.” IEEE Transactions on Pattern Analysis and Machine IntelligencePAMI-8: 679–698. https://doi.org/10.1109/TPAMI.1986.4767851.
     [Google Scholar]
  3. Christovam, L. E., M. H.Shimabukuro, M.Galo, and E.Honkavaara. 2022. “Pix2pix Conditional Generative Adversarial Network with MLP Loss Function for Cloud Removal in a Cropland Time Series.” Remote Sensing14 (1): 144. https://www.mdpi.com/2072-4292/14/1/144.
     [Google Scholar]
  4. Isola, P., J.Zhu, T.Zhou, and A. A.Efros. 2017. “Image-to-Image Translation with Conditional Adversarial Networks.” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR): 5967–5976.
     [Google Scholar]
  5. Khanna, P., A.Ramdani, G. S.Gairola, and V.Vahrenkamp. 2022. 3D Digital Outcrop Models Late Jurassic (Oxfordian) Hanifa Fm - Wadi Birk, Central Saudi Arabia: Shallow marine carbonate platform sediments equivalent to Arabian subsurface reservoirs. edited by Mendeley: Mendeley.
     [Google Scholar]
  6. Porter, T. R., and M.Martin. 1998. “Exploration GIS: Optimising 3D seismic operations.” In SEG Technical Program Expanded Abstracts 1998, 115–116.
     [Google Scholar]
  7. Ramdani, A., P.Khanna, G. S.Gairola, H.Sherif, and V.Vahrenkamp. 2022. “Assessing and processing three-dimensional photogrammetry, sedimentology, and geophysical data to build high-fidelity reservoir models based on carbonate outcrop analogues.” AAPG Bulletin106 (10): 1975–2011. https://doi.org/10.1306/05152221092.
     [Google Scholar]
  8. Wang, X., H.Yan, C.Huo, J.Yu, and C.Pant. 2018. “Enhancing Pix2Pix for Remote Sensing Image Classification.” 24th International Conference on Pattern Recognition (ICPR), Beijing, China, 20–24 Aug. 2018.
     [Google Scholar]
  9. Wang, Z., A. C.Bovik, H. R.Sheikh, and E. P.Simoncelli. 2004. “Image quality assessment: from error visibility to structural similarity.” IEEE Transactions on Image Processing13 (4): 600–612. https://doi.org/10.1109/TIP.2003.819861.
     [Google Scholar]
  10. Zhang, Wuming, JianboQi, PengWan, HongtaoWang, DonghuiXie, XiaoyanWang, and GuangjianYan. 2016. “An Easy-to-Use Airborne LiDAR Data Filtering Method Based on Cloth Simulation.” Remote Sensing8 (6): 501. https://www.mdpi.com/2072-4292/8/6/501.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202310164
Loading
Machine-Learning Based Land-Cover Classification Using UAV Imageries Intended for Seismic Survey Scouting in Arid Area
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.202310164
/content/papers/10.3997/2214-4609.202310164
/content/papers/10.3997/2214-4609.202310164
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error