3D descriptor and its application in contour analysis algorithm for automatic aircraft landing

A. E. Artemyev

Abstract


The article proposes a method for forming a three-dimensional object descriptor, which allows to reconstruct a one-dimensional contour descriptor and an object contour. Descriptor is designed to create algorithms for estimating the angular position of an aircraft from a monocular image to increase the integrity of navigation data at the landing phase, but it can also be used to estimate the orientation of spacecraft and other objects, as well as for recognition. The descriptor is a three-dimensional discrete Fourier transform of a set of contours. The process of forming a 3D descriptor includes creating a scene using a graphics library and rotating the camera around the object in orbits with a certain step, at each position a contour is extracted and saved to create a set of contours, from which a 3D descriptor is then formed. Two-dimensional trigonometric interpolation is used to reconstruct the one-dimensional contour descriptor of an object in an arbitrary spatial orientation, and three-dimensional interpolation is used for contour reconstruction. The advantage of the proposed descriptor is the ability to quickly calculate a one-dimensional contour descriptor invariant to rotation and scale to determine the angular position and recognize a texture-less object in the image. The ability to create a smooth objective function based on the proposed 3D descriptor greatly simplifies the optimization search.


Full Text:

PDF (Russian)

References


T.P. Wallace, P.A. Wintz, “An efficient three-dimensional aircraft recognition algorithm using normalized Fourier descriptors,” Computer Graphics and Image Processing, vol.13, no. 2, pp. 99-126, 1980. doi: 10.1016/S0146-664X(80)80035-9.

M.G. Breuers, N. de Reus, “Image-based aircraft pose estimation: A comparison of simulations and real-world data,” In Proc SPIE, vol. 4379. 472-479. doi: 10.1117/12.445395.; H. Poor, An Introduction to Signal Detection and Estimation, ch. 4.NY, Springer-Verlag, 1985.

O.V. Malyshev, Determination of spatial position and recognition of types of aircraft based on contour analysis: diss. ...cand. tech. sci. Rybinsk, 2011. [In Rus]

A.S. Mirzoyan, Development of recognition and positioning systems for aircraft and ground objects based on computational geometry methods: dis.. ...cand. tech. sci. Rybinsk, 2017. [In Rus]

T. Fu, X. Sun, “The relative pose estimation of aircraft based on contour model,” In International Conference on Optical and Photonics Engineering (icOPEN 2016), SPIE, vol. 10250, pp. 559-564, 2017. doi: 10.1117/12.2267118.

D. Fu, S. Han, W. Li, H. Lin, “The pose estimation of the aircraft on the airport surface based on the contour features,” IEEE Transactions on Aerospace and Electronic Systems, vol. 59, no. 2, pp. 817-826, 2022. doi: 10.1109/TAES.2022.3192220.

X. Zhang, Z. Jiang, H. Zhang, Q. Wei, “Vision-based pose estimation for textureless space objects by contour points matching,” IEEE Transactions on Aerospace and Electronic Systems, vol. 54, no. 5, pp. 2342-2355, 2018.

Leng D, Sun W. Contour-based iterative pose estimation of 3D rigid object. IET Computer Vision, 2011, 5, (5), pp. 291-300.

X. Zhang, H. Zhang, Q. Wei, et al., “Pose Estimation of Space Objects Based o n Hybrid Feature Matching of Contour Points,” In Advances in Image and Graphics Technologies, pp. 184-191, 2016.

R.L. Cosgriff, Identification of Shape, Technical Report 820-11, ASTIA AD-25-4792, Ohio State University Research Foundation. Columbus, Dec. 1960. pp. 826-840.

P.L.E. Ekombo, N. Ennahnahi, M. Oumsis, M. Meknassi, “Application of affine invariant Fourier descriptor to shape- based image retrieval,” International Journal of Computer Science and Network Security, vol.9, no. 7, pp. 240–247, 2009.

Ya.A. Furman, A.V. Krevetsky et al. Introduction to contour analysis; applications to signal image processing I.L. Egoshina, A.N. Leukhin; Ed. Y.A. Furman. 2nd ed., rev. Moscow, FIZMATLIT, 2003. [In Rus]

L. Bowen, S.S. Raja, … & K. Mawien, A Fourier descriptor and PSCS-RBF fusion method for pumping machine fault diagnosis. 10.21203/rs.3.rs-2878163/v1.

M. Andrews, R. Kakarala, “Shape simplification through polygonal approximation in the Fourier domain,”. In Proceedings of SPIE - The International Society for Optical Engineering. 2015, 9406. 10.1117/12.2078148.

N. Liao, B. Guo, Z. Li, Y. Zheng, “An Advanced Fourier Descriptor Based on Centroid Contour Distances,” Journal of Physics: Conference Series, vol. 1735, p. 012002, 2021. doi: 10.1088/1742-6596/1735/1/012002.

K.S. Park, N.S. Lee, “A three-dimensional Fourier descriptor for human body representation/reconstruction from serial cross sections,” Comput Biomed Res., vol. 20, no. 2, pp. 125-140, 1987. doi: 10.1016/0010-4809(87)90040-1.

A.E. Artemyev, High-speed and high-precision algorithm for determining the spatial position of a three-dimensional texturless object based on contour analysis. [Online]. URL: http://artemyev.tech/ (date: 25.12.2023), to be published.

A.E. Artemyev, Real-time and precision attitude and position estimation of a three-dimensional object on image. [Online]. URL: https://www.youtube.com/watch?v=LKqkDY9RVzs (date: 12.04.2023).


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162