Aircraft Accident and Crash Images Processing with Machine Learning

Yıl 2024, , 88 - 95, 27.06.2024

Halil İbrahim Gümüş , Ömer Osman Dursun

https://doi.org/10.30518/jav.1448219

Öz

The aviation industry is in constant need of innovations in terms of safety and operational efficiency. In this context, low-light image enhancement technologies play an important role in a numerous areas of disciplines, from night flights to accident and collision investigations. Machine learning, deep learning methods and traditional methods not only provide the aviation industry with an effective image processing and improvement capacity in low light conditions, but also reveal important information by analysing the data of low-light images of crashed and destroyed aircraft.
Within the scope of the study, traditional methods, deep learning method and machine learning are combined in order to enhance and process low-light ambient images of crashed and destroyed aircraft. By using Swish and Tanh activation functions together in the deep learning model, the performance of the neural networks used in the process of improving low-light environment images was improved and the image quality was increased. The enhanced images were evaluated and compared using PSNR and MSE as objective quality assessment measures. According to the PSNR and MSE criteria, the numerical results obtained from the image enhancement studies of the deep learning model were calculated as 29.85 and 100.44, respectively. The results introduce that the deep learning model provides better image enhancement than traditional methods. In conclusion, improvement of low-light image and processing is an important technological advancement in the aviation industry, enabling safer and more efficient operations. The successful of machine learning include deep learning and traditional methods shows that the aviation industry will achieve a safer and innovative structure in the future.

Anahtar Kelimeler

Aircraft accident, Machine learning, Image enhancement, Image processing, Low light

Kaynakça

• Ahmadian, A., Mishra, R. K., Reddy, G. Y. S., & Pathak, H. (2021). The Understanding of Deep Learning: A Comprehensive Review. Mathematical Problems in Engineering, 2021, 5548884.
• Chaney, M. (2013). Brightness, Contrast, Saturation and Sharpness. Steve’s Digicams.
• Chen, C.-H., et al. (2023). The Deep Learning-Based Image Enhancement Method for High-Contrast Low-Light Images. In 2023 9th International Conference on Applied System Innovation (ICASI) (pp. 89-91). Chiba, Japan: IEEE.
• Dhankar, A. A., & Gupta, N. (2021). A Systematic Review of Techniques, Tools and Applications of Machine Learning. In Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV) (pp. 764-768). Tirunelveli, India: IEEE.
• Gonzales, C., & Woods, R. E. (2002). Digital Image Processing. Prentice Hall, New Jersey.
• Haykin, S. (2009). Neural Networks and Learning Machines (3rd ed.). Pearson Education India.
• Karaburun, N. N., Arık Hatipoğlu, S., & Konar, M. (2024). SOC Estimation of Li-Po Battery Using Machine Learning and Deep Learning Methods. Journal of Aviation, 8(1), 26-31.
• Kayaalp, K., & Süzen, A. A. (2018). Deep Learning and Its Applications in Turkey. İksad Publishing House. ISBN: 978-605-7510-53-2.
• Kırac, E., & Özbek, S. (2024). Deep Learning Based Object Detection with Unmanned Aerial Vehicle Equipped with Embedded System. Journal of Aviation, 8(1), 15-25.
• Liu, H., Li, Y., & Zhu, H. (2022). A Fusion-based Enhancement Method for Low-light UAV Images. In 2022 34th Chinese Control and Decision Conference (CCDC) (pp. 5036-5041). Hefei, China.
• Öçer, N., Erdem, F., Küçük Matci, D., Comert, R., Kaplan, G., & Avdan, U. (2022). Comparison of Two Methods, Traditional and Deep Learning-Based, for the Enhancement of Satellite Images.
• Öztürk, S., & Öztürk, N. (2016). Development of an Image Enhancement Method Using Artificial Bee Colony Algorithm. Gazi University Journal of Science Part C: Design and Technology, 4(4), 173-183.
• Park, J., Vien, A. G., Kim, J.-H., & Lee, C. (2022). Histogram-Based Transformation Function Estimation for Low- Light Image Enhancement. In 2022 IEEE International Conference on Image Processing (ICIP) (pp. 1-5). Bordeaux, France: IEEE.
• Perla, S., & Dwaram, K. (2023). Low Light Image Illumination Adjustment Using Fusion of MIRNet and Deep Illumination Curves. In Multi-disciplinary Trends in Artificial Intelligence, R. Morusupalli et al. (Eds.), vol. 14078, Lecture Notes in Computer Science. Springer, Cham.
• Sharma, S., Sharma, S., & Athaiya, A. (2017). Activation Functions in Neural Networks. Towards Data Sci, 6(12), 310-316.
• Shen, L., Yue, Z., Feng, F., Chen, Q., Liu, S., & Ma, J. (2017). MSR-net: Low-light Image Enhancement Using Deep Convolutional Network. arXiv preprint arXiv:1711.02488.
• Singh, A., Chougule, P., Narang, V., Chamola, F., & Yu, F. R. (2022). Low-Light Image Enhancement for UAVs With Multi-Feature Fusion Deep Neural Networks. In IEEE Geoscience and Remote Sensing Letters, 19, 1-5.
• Tico, M., & Pulli, K. (2009). Image enhancement method via blur and noisy image fusion. In 2009 16th IEEE International Conference on Image Processing (ICIP) (pp. 1521-1524). Cairo, Egypt: IEEE.
• Yu, J., & Liao, Q. (2010). Color Constancy-Based Visibility Enhancement in Low-Light Conditions. In 2010 International Conference on Digital Image Computing: Techniques and Applications (pp. 441-446). Sydney, NSW, Australia: IEEE.
• Zhang, Y., Di, X., Zhang, B., & Wang, C. (2020). Self-supervised image enhancement network: Training with low light images only. arXiv preprint arXiv:2002.11300.
• Zhu, M., Pan, P., Chen, W., & Yang, Y. (2020). Eemefn: Low-light image enhancement via edge-enhanced multi-exposure fusion network. In Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 13106- 13113. April 2020.