Method of comparing and transforming images obtained using UAV

Bohdan Karapet, Roman Savitskyi, Tetiana Vakaliuk

Abstract


The subject matter of this article involves reviewing and developing methods for the comparison and transformation of images obtained using UAV via Computer Vision tools. The goal is to improve methods for image comparison and transformation. Various image-processing methods were employed to achieve the goal of this study,thereby contributing to the development of practical algorithms and approaches for image analysis and comparison. The tasks can be described as follows: 1) development of image comparison methods: design tools for the comparison of images from UAV that efficiently detect differences using algorithms such as cv2.absdiff and the PIL module; 2) Image transformation: implement transformation methods for images from UAV, including perspective transformation and thresholding, to enhance the quality and accuracy of image analysis. The methods used were algorithm development, image transformation methods, statistical analysis, experimental testing, and performance evaluation. The metrics used in this article are response time and accuracy. Algorithms for image comparison have also been refined, particularly those transformed through Global Threshold Value, Adaptive Mean Thresholding, and Adaptive Gaussian Thresholding. A novel change filtering method was introduced to enhance the precision of image comparison by filtering out insignificant alterations following image transformation. Comprehensive investigation of image comparison involving edge detection methods has been systematically presented. The results contain the development of practical algorithms and approaches for image analysis and comparison applicable in diverse areas such as military, security, and agriculture. Possibilities of applying our methods and algorithms in the context of drones were also considered, which is particularly relevant in tasks related to computer vision in unmanned aerial vehicles, where limited resources and the need for real-time processing of a large volume of data create unique challenges. Conclusions. The results contain OpenCV and PIL image comparison methods. OpenCV pixel-by-pixel comparison algorithm showed a better response time with the same accuracy. OpenCV method has 92,46% response time improvement compared with PIL and is 276ms. As for image thresholding with comparison, a method based on Global Threshold Value showed the shortest response time (266ms) and the lowest accuracy. The highest accuracy and response time (366ms) were obtained using the Adaptive Gaussian Thresholding method.

Keywords


UAV; computer vision; image comparison; image transformation; image processing

Full Text:

PDF

References


Bhatt, D., Patel, C., Talsania, H., Patel, J., Vaghela, R., Pandya, S., & Ghayvat, H. CNN variants for computer vision: History, architecture, application, challenges and future scope. Electronics, 2021, vol. 10, iss. 20, article no. 2470. DOI: 10.3390/electronics10202470.

Davies, E. R. Computer vision: principles, algorithms, applications, learning. Academic Press Publ., 2018. DOI: 10.1016/C2015-0-05563-0.

Janai, J., Güney, F., Behl, A., & Geiger, A., 2020. Computer vision for autonomous vehicles: Problems, datasets and state of the art. Foundations and Trends® in Computer Graphics and Vision, 2020, vol. 12, iss. 1-3, pp. 1-308. DOI: 10.1561/0600000079.

Rebrov, V., & Lukin, V. Post-processing of compressed noisy images using BM3D filter. Radioelectronic and Computer Systems, 2023, no. 4, pp. 100-111. DOI: 10.32620/reks.2023.4.09.

Bilozerskyi, V., Dergachov, K., Krasnov, L., Zymovin, A., & Popov, A. New method for video stream brightness stabilization: algorithms and performance evaluation. Radioelectronic and Computer Systems, 2023, no. 3, pp. 125-135. DOI: 10.32620/reks.2023.3.10.

Barkovska, O., Filippenko, I., Semenenko, I., Korniienko, V., & Sedlaček, P. Adaptation of FPGA architecture for accelerated image preprocessing. Radioelectronic and Computer Systems, 2023, no. 2, pp. 94-106. DOI: 10.32620/reks.2023.2.08.

Ning, Z., Hu, H., Wang, X., Guo, L., Guo, S., Wang, G., & Gao, X. Mobile edge computing and machine learning in the internet of unmanned aerial vehicles: A survey. ACM Computing Surveys, 2023, vol. 56, iss. 1, article no. 13, pp. 1-31. DOI: 10.1145/3604933.

Petrosian, A. R., Petrosyan, R. V., Pilkevych, I. A., & Graf, M. S. Efficient model of PID controller of unmanned aerial vehicle. Journal of Edge Computing, 2023, vol. 2, iss. 2, pp. 104–124. DOI: 10.55056/jec.593.

Ma, M.-Y., Shen, S.-E., & Huang, Y.-C. Enhancing UAV Visual Landing Recognition with YOLO’s Object Detection by Onboard Edge Computing. Sensors, 2023, vol. 23, iss. 21, article no. 8999. DOI: 10.3390/s23218999.

Cao, L., Song, P., Wang, Y., Yang, Y., & Peng, B. An Improved Lightweight Real-Time Detection Algorithm Based on the Edge Computing Platform for UAV Images. Electronics, 2023, vol. 12, iss. 10, article no. 2274. DOI: 10.3390/electronics12102274.

Bemposta Rosende, S., Ghisler, S., Fernández-Andrés, J., & Sánchez-Soriano, J. Implementation of an Edge-Computing Vision System on Reduced-Board Computers Embedded in UAVs for Intelligent Traffic Management. Drones, 2023, vol. 7, iss. 11, article no. 682. DOI: 10.3390/drones7110682.

Gollapudi, S. OpenCV with Python. In: Learn Computer Vision Using OpenCV, Apress, Berkeley, CA, 2019, pp. 31-50. DOI: 10.1007/978-1-4842-4261-2_2.

Yulina, S. Implementation of Haar Cascade Classifier for Face Detection and Grayscale Image Transformation Using OpenCV. Jurnal Komputer Terapan, 2021, vol. 7, iss. 1, pp. 100-109. DOI: 10.35143/jkt.v7i1.3411.

Chadha, A., Kashyap, S., Gupta, M., & Kumar, V. License plate recognition system using OpenCV & PyTesseract. CSI Journal of Computing, 2020, vol. 3, iss. 3, pp. 31-35. Available at: https://www.researchgate.net/profile/Jyoti-Deone/publication/348232599_CSI_Journal_of_COMPUTING/links/5ff44163299bf14088707fa8/CSI-Journal-of-COMPUTING.pdf?_sg[0]=started_experiment_milestone&origin=journalDetail&_rtd=e30%3D (Accessed 17 Jan. 2024).

Lindblad, T., & Kinser, J. M. NumPy, SciPy and Python Image Library. Image Processing using Pulse-Coupled Neural Networks. Biological and Medical Physics, Biomedical Engineering. Springer, Berlin, Heidelberg, 2013, pp. 35-56. DOI: 10.1007/978-3-642-36877-6_3.

Zhang, Ju., Zhang, Ji., Chen, B., Gao, J., Ji, S., Zhang, X., & Wang, Z. A perspective transformation method based on computer vision. 2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA), Dalian, China, 2020, pp. 765-768. DOI: 10.1109/ICAICA50127.2020.9182641.

Batubara, M. A., Alam, S., Nisa, K., Utami, R. W., Fitriawan, H., & Ulvan, A. Estimating the number of trees in Margasari mangrove forests of Lampung through aerial images using adaptive thresholding and contour extraction methods. Proceedings of the International Conference on Sustainable Biomass (ICSB 2019), Atlantis Press Publ., 2021, vol. 202, pp. 131-136. DOI: 10.2991/aer.k.210603.022.

Rehman, N. A., & Haroon, F. Adaptive Gaussian and double thresholding for contour detection and character recognition of two-dimensional area using computer vision. Engineering Proceedings, 2023, vol. 32, iss. 1, article no. 23. DOI: 10.3390/engproc2023032023.

Sultana, H., Kamal, A. H. M., Apon, T. S., & Alam, M. G. R. Increasing embedding capacity of stego images by exploiting edge pixels in prediction error space. Cyber Security and Applications, 2024, vol. 2, article no. 100028. DOI: 10.1016/j.csa.2023.100028.

Grinberg, M. Flask web development: developing web applications with Python. 2nd edition. O’Reilly Media, Inc., 2018. 312 p. ISBN: 978-1491991732.

Orban, C. How to track objects with stationary background? Available at: https://www.authentise.com/post/how-to-track-objects-with-stationary-background (Accessed 17 Jan. 2024).

Devi, R. Geometric transformations and thresholding of images using Opencv-Python. GRD Journal for Engineering, 2017, vol. 2, iss. 11, pp. 49-52. Available at: https://www.grdjournals.com/uploads/article/GRDJE/V02/I11/0020/GRDJEV02I110020.pdf (Accessed 17 Jan. 2024).




DOI: https://doi.org/10.32620/reks.2024.1.09

Refbacks

  • There are currently no refbacks.