|
Article information
2019 , Volume 24, ¹ 6, p.117-124
Smagin A.S., Dubrovin K.N.
On computer vision algorithms for searching breaks in meshed fencing constructions
Purpose. The paper addresses image processing algorithms for the computer vision system of an autonomous uninhabited underwater vehicle, which automatically monitors the state of the mesh fence and thereby exclude the presence of a person in an aggressive underwater environment. Methodology. The MultiScale Retinex with Color Restoration algorithm and the Otsu method were implemented using the Python programming language to pre-process and filter the image. Methods from OpenCV computer vision library were used to detect damage to the mesh fence. Results. An algorithm is proposed for highlighting the impulses of mesh fencing in underwater conditions using computer vision methods implemented by the Python software. The software implementation results are provided. It is shown that computer vision methods effectively cope with determining the integrity of network cells in weakly and medium-noisy images. To work in more complex optical conditions, it is proposed to include a neural network module in the software package. Findings. The analysis of the results of the software package showed that it successfully copes with the classification of network cells in clean images. However, the transformations carried out at the pre-processing stage are not enough to complete noise elimination. In this regard, this study will continue to improve and expand the functionality of the software package. The result of the study will be a software package with a neural network module for full filtering of the external background and efficient detection of the mesh fence problem areas.
[full text] [link to elibrary.ru]
Keywords: algorithm, computer vision, edges detection, machine learning, software
doi: 10.25743/ICT.2019.24.6.014.
Author(s):
Smagin Alexey Sergeevich
Position: Junior Research Scientist
Office: Mining Institute of Far-Eastern branch of Russian Academy of Science
Address: 680000, Russia, Khabarovsk, Ussury Boulevard,5
E-mail: smaginkhv@gmail.com
Dubrovin Konstantin Nikolaevich
Position: engineer
Office: Computing Center of Far-Eastern branch of Russian Academy of Science
Address: 680000, Russia, Khabarovsk, Ussury Boulevard,5
E-mail: nob_keeper_93@mail.ru
References:
[1] Gonzalez, R.C., Woods, R.E. Digital image processing. Prentice Hall; 2007: 976.
[2] Pratt, W.K. Digital image processing. CRC Press; 1978: 756.
[3] Zhang, S., Wang, T., Dong, J., Yu, H.: Underwater image enhancement via extended multi-scale retinex. Neurocomputing. 2017; (245):1–9.
[4] Yuen Peng Loh, Chee Seng Chan. Getting to know low-light images with the Exclusively Dark dataset. Computer Vision and Image Understanding. 2019; (178):30–42.
[5] Doo Hyun Choi, Ick Hoon Jang, Mi Hye Kim. Color image enhancement using single-scale retinex based on an improved image formation model. 16th European Signal Processing Conference (EUSIPCO 2008), Lausanne, Switzerland, August 25-29, 2008, copyright by EURASIP. Available at: https://www.eurasip.org/Proceedings/Eusipco/Eusipco2008/papers/1569104826.pdf
[6] Science support is now a storytelling issue. Available at: http://www.theunderwaterwoman.com/science-storytelling
[7] Otsu, N.A. Threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics. 1979; 9(1):62–66.
[8] Radke, R.J., Andra, S., Al-Kofahi, O., Roysam, B. Image change detection algorithms: a systematic survey. IEEE Trans. Imag Process. 2005; 14(3): 294–307.
[9] Sorokin, A.A., Makogonov, S.V., Korolev, S.P. The information infrastructure for collective scientific work in the Far East of Russia. Scientific and Technical Inform. Proc. 2017; 44(4):302–304.
Bibliography link:
Smagin A.S., Dubrovin K.N. On computer vision algorithms for searching breaks in meshed fencing constructions // Computational technologies. 2019. V. 24. ¹ 6. P. 117-124
|
