SavedAdd your journal

Journals / Türkiye Uzaktan Algılama Dergisi / 2025 / Volume: 7 Issue: 2

Aerial imagery analysis using deep learning and adaptive histogram equalization

Gökhan Altan(ISKENDERUN TECHNICAL UNIVERSITY)0000-0001-7883-3131
Berkan Bozkurt(ISKENDERUN TECHNICAL UNIVERSITY)0000-0002-1661-5945
Pages
—
Publication Date
2025-12-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results show that the performance of the model gradually improves the capability with accuracy rates of 93.33% and 94.35% for training and validation using AHE, respectively.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The analysis of images obtained from aerial vehicles is used in various areas such as geographical mapping, border security, disaster management, urban planning, environmental monitoring, and agricultural land monitoring.
📊
Key Findings & Data:The performance of MobileNetV2, ResNet models, and CNN architectures with Inception blocks was examined with the Transfer Learning method.
💡
Conclusion & Impact:The results show that the performance of the model gradually improves the capability with accuracy rates of 93.33% and 94.35% for training and validation using AHE, respectively.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Aerial imagery · CNN · Deep learning

Abstract

The analysis of images obtained from aerial vehicles is used in various areas such as geographical mapping, border security, disaster management, urban planning, environmental monitoring, and agricultural land monitoring. In this context, high-resolution remote sensing images are used as a method in scene classification due to the intensive processing power required for segmentation. We aimed to assess the impact of pre-processing before feature learning using deep learning on various aerial scene images. The Adaptive Histogram Equalization (AHE) method was applied as a pre-processing stage in the analysis to provide clarity in the images and extract prominent dominant landmarks. The Convolutional Neural Network (CNN) was used for image classification. The performance of MobileNetV2, ResNet models, and CNN architectures with Inception blocks was examined with the Transfer Learning method. The results show that the performance of the model gradually improves the capability with accuracy rates of 93.33% and 94.35% for training and validation using AHE, respectively. The results prove that AHE on aerial images has the ability to extract significant characteristics for pre-trained architectures and transfer learning on scene classification.

🔖

Cite This Article

Altan, G., Bozkurt, B. (2025). Aerial imagery analysis using deep learning and adaptive histogram equalization. Türkiye Uzaktan Algılama Dergisi, Volume: 7 Issue: 2. https://doi.org/10.51489/tuzal.1678574

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (18)

  1. Altan, G. (2019). DeepGraphNet: Deep learning models in the classification of graphs. European Journal of Science and Technology, 319-327. https://doi.org/10.31590/ejosat.638256
  2. Altan, G. (2020). Deep learning-based mammogram classification for breast cancer, International Journal of Intelligent Systems and Applications in Engineering, 8 (4), 171– 176. https://doi.org/10.18201/ijisae.2020466308
  3. Altan, G. (2022). DeepOCT: An explainable deep learning architecture to analyze macular edema on OCT images, Engineering Science and Technology, an International Journal, 34, 101091, https://doi.org/10.1016/j.jestch.2021.101091
  4. Chen, R. C., Dewi, C., Zhuang, Y. C., & Chen, J. K. (2023). Contrast limited adaptive histogram equalization for recognizing road marking at night based on YOLO models. IEEE Access. 11, 92926 – 92942. https://doi.org/10.1109/ACCESS.2023.3309410
  5. Dyke, R. M., & Hormann, K. (2023). Histogram equalization using a selective filter. The visual computer, 39(12), 6221-6235. https://doi.org/10.1007/s00371-022-02723-8
  6. Francis, J., Bright, J., Esnaashari, S., Hashem, Y., Morgan, D., & Straub, V. J. (2023). Unsupervised feature extraction of aerial images for clustering and understanding hazardous road segments. Scientific Reports, 13(1), 10922. https://doi.org/10.1038/s41598-023-38100-1
  7. Hikuwai, M. V., Patorniti, N., Vieira, A. S., Frangioudakis Khatib, G., & Stewart, R. A. (2023). Artificial Intelligence for the Detection of Asbestos Cement Roofing: An investigation of multi-spectral satellite imagery and high-resolution aerial imagery. Sustainability, 15(5), 4276. https://doi.org/10.3390/su15054276
  8. Jahan, C. S., & Savakis, A. (2024). Continual domain adaptation on aerial images under gradually degrading weather. Journal of Applied Remote Sensing, 18(1), 016504. https://doi.org/10.1117/1.JRS.18.016504
  9. Jiang, C., Chen, Z., & Wolfe, J. M. (2024). Toward viewing behavior for aerial scene categorization. Cognitive Research: Principles and Implications, 9(1), 17. https://doi.org/10.1186/s41235-024-00541-1
  10. Saberi, Z., Hashim, N., Ali, A., Boursier, P., Abdullah, J., & Embi, Z. C. (2023). Adaptive contrast enhancement of satellite images based on histogram and non-linear transfer function methods. IAENG International Journal of Applied Mathematics, 53(1), 1-9.
  11. Saunders, J., Saeedi, S., & Li, W. (2024). Autonomous aerial robotics for package delivery: A technical review. Journal of Field Robotics, 41(1), 3-49. https://doi.org/10.1002/rob.22231
  12. Shen, X., Wang, H., Wei, B., & Cao, J. (2023). Real-time scene classification of unmanned aerial vehicles remote sensing image based on Modified GhostNet. Plos one, 18(6), e0286873. https://doi.org/10.1371/journal.pone.0286873
  13. Song, H., & Zhou, Y. (2023). Simple is best: A single-CNN method for classifying remote sensing images. Networks & Heterogeneous Media, 18(4), 1600-1629. https://doi.org/10.3934/nhm.2023070
  14. Xia, G. S., Hu, J., Hu, F., Shi, B., Bai, X., Zhong, Y., Zhang, L., & Lu, X. (2017). AID: A benchmark data set for performance evaluation of aerial scene classification. IEEE Transactions on Geoscience and Remote Sensing, 55(7), 3965-3981. https://doi.org/10.1109/TGRS.2017.2685945
  15. Xie, X., Cheng, G., Li, Q., Miao, S., Li, K., & Han, J. (2024). Fewer is more: Efficient object detection in large aerial images. Science China Information Sciences, 67(1), pp. 1-19. https://doi.org/10.1007/s11432-022-3718-5
  16. Yuan, X., Zhu, J., Lei, H., Peng, S., Wang, W., & Li, X. (2024). Duplex-hierarchy representation learning for remote sensing image classification. Sensors, 24(4), 1130. https://doi.org/10.3390/s24041130
  17. Zhang, Z., Mi, X., Yang, J., Wei, X., Liu, Y., Yan, J.,. & Yu, T. (2023). Remote sensing image scene classification in hybrid classical–quantum transferring CNN with small samples. Sensors, 23(18), 8010. https://doi.org/10.3390/s23188010
  18. Zhang, Z., Mi, X., Yang, J., Wei, X., Liu, Y., Yan, J.,. & Yu, T. (2023). Remote sensing image scene classification in hybrid classical–quantum transferring CNN with small samples. Sensors, 23(18), 8010. https://doi.org/10.3390/s23188010