Method for motion detecting in the frame and large-sized object identification

Мұқаба

Дәйексөз келтіру

Толық мәтін

Ашық рұқсат Ашық рұқсат
Рұқсат жабық Рұқсат берілді
Рұқсат жабық Тек жазылушылар үшін

Аннотация

A method for motion detecting in a frame and large-sized object identification is described in the article. The use-case of the method is illustrated by the example from the maritime transport industry. The example shows the solution of the task of monitoring the position of an autonomous marine large-tonnage ship relative to the berth when performing loading and unloading operations and mooring operations. The paper incudes description of the structure of a measuring complex which includes optical meters. An operating principle of the complex is based on the method of motion detecting in a frame and large-sized object identification. A diagram of the algorithm for motion detecting in the frame and large-sized object identification is presented in the paper. The performance of the software implementation of the algorithm for motion detecting in the frame and large-sized object identification has been assessed in the article.

Толық мәтін

Рұқсат жабық

Авторлар туралы

V. Lopatina

Federal Research Center “Computer Science and Control,” Russian Academy of Sciences

Хат алмасуға жауапты Автор.
Email: int00h@mail.ru
Ресей, Moscow

Әдебиет тізімі

  1. Poujouly S., Journet B. A Twofold Modulation Frequency Laser Range Finder // J. Optics A: Pure and Applied Optics. 2002. № 4. P. 356–363.
  2. Zheng X.Y., Zhao C., Zhang H.Y., Zheng Z., Yang H.Z. Coherent Dual-frequency Lidar System Design for Distance and Speed Measurements // Intern. Conf. on Optical Instruments and Technology: Advanced Laser Technology and Applications. International Society for Optics and Photonics. Beijing, China, 2018. V. 10619.
  3. Jia F.X., Yu J.Y., Ding Z.L., Yuan F. Research on Real-time Laser Range Finding System // Applied Mechanics and Materials. 2013. V. 347.
  4. Beraldin J.A., Steenaart W. Overflow Analysis of a Fixed-Point Implementation of the Goertzel Algorithm // IEEE Transactions on Circuits and Systems. 1989. V. 36. № 2. P. 322–324.
  5. Finlayson D.M., Sinclair B. Advances in Lasers and Applications // Boca Raton, Florida, USA. CRC Press, 1998. P. 346.
  6. Lopatina V.V. Method of Fragment Based Tracking of Displacement of a Large Areal Object in Images // J. Phys.: Conf. Ser. 2021. V. 2061. P. 012113. https://doi.org/10.1088/1742-6596/2061/1/012113.
  7. Suzuki S., Keiichi A. Topological Structural Analysis of Digitized Binary Images by Border Following // Comput. Vis. Graph. Image Process. 1985. V. 30. P. 32–46.
  8. OpenCV 4.7.0. Open Source Computer Vision Library, 2022.
  9. ГОСТ Р 8.1030-2024.
  10. Lucas B.D., Kanade T. An Iterative Image Registration Technique with an Application to Stereo Vision // Intern. Joint Conf. on Artificial Intelligence. Vancouver, B.C., Canada, 1981.
  11. Farnebäck G. Two-Frame Motion Estimation Based on Polynomial Expansion // Image Analysis (SCIA). Lecture Notes in Computer Science, Eds J. Bigun, T. Gustavsson. Berlin, Heidelberg: Springer, 2003. V. 2749.
  12. Jain A., Murty M., Flynn P. Data Clustering: A Review // ACM Computing Surveys. 1999. V. 31. P. 264–323.
  13. Otsu N. A Threshold Selection Method from Gray-level Histograms // IEEE Trans. Sys., Man., Cyber. J. 1979. V. 9. P. 62–66.
  14. Гонсалес Р., Вудс Р. Цифровая обработка изображений. Изд. 3-е, исправ. и доп. М.: Техносфера, 2019. 1104 с. ISBN 978-5-94836-331-8.

Қосымша файлдар

Қосымша файлдар
Әрекет
1. JATS XML
Жүктеу
2. Fig. 1. Installation diagram of a complex of two optical measuring devices on a pier

Жүктеу (152KB)
Метадеректер
3. Fig. 2. Large-tonnage sea vessels at various distances from the berth

Жүктеу (269KB)
Метадеректер
4. Fig. 3. Visualization of the brightness of image pixels normalized in the range [0;1]; X, Y – longitudinal and vertical coordinates of pixels

Жүктеу (148KB)
Метадеректер
5. Fig. 4. Visualization in different projections of the brightness of image pixels after applying a rectangular low-pass filter; X, Y – longitudinal and vertical coordinates of pixels

Жүктеу (199KB)
Метадеректер
6. Fig. 5. Visualization in different projections of the brightness of image pixels after applying the threshold transformation; X, Y are the longitudinal and vertical coordinates of the pixels

Жүктеу (145KB)
Метадеректер
7. Fig. 6. Visualization of the difference between two adjacent frames; X, Y – longitudinal and vertical coordinates of pixels

Жүктеу (217KB)
Метадеректер
8. Fig. 7. Visualization of the difference between adjacent frames using the example of ships of different sizes, with different speeds of movement and at different distances from the berth

Жүктеу (388KB)
Метадеректер
9. Fig. 8. Visualization of contour analysis

Жүктеу (54KB)
Метадеректер
10. Fig. 9. Scheme of the algorithm for determining movement in the frame and identifying a large area object. LPF – low-pass filter

Жүктеу (339KB)
Метадеректер
11. Fig. 10. Examples of moving image areas (left) and moving areas potentially belonging to the vessel and its deck structures (right)

Жүктеу (327KB)
Метадеректер

© Russian Academy of Sciences, 2024