Intelligent Binocular Compound Eye Vision System for Detecting Azimuth and Distance to Object on Plane

Authors

  • Kirill N. Belov South Ural State University (Chelyabinsk, Russia)
  • Evelina A. Bibikova South Ural State University (Chelyabinsk, Russia)
  • Ivan V. Buldashev South Ural State University (Chelyabinsk, Russia)
  • Nataliya D. Kundikova South Ural State University (Chelyabinsk, Russia)
  • Yurii V. Mukhin South Ural State University (Chelyabinsk, Russia)
  • Andrey N. Nikolaev South Ural State University (Chelyabinsk, Russia)
  • Andrey V. Portnov South Ural State University (Chelyabinsk, Russia)
  • Yaroslav M. Ridnyi South Ural State University (Chelyabinsk, Russia)
  • Leonid B. Sokolinsky South Ural State University (Chelyabinsk, Russia)
  • Artem E. Starkov South Ural State University (Chelyabinsk, Russia)
  • Alexander A. Shulginov South Ural State University (Chelyabinsk, Russia)

DOI:

https://doi.org/10.14529/cmse250101

Keywords:

compound eye vision, optical model, distance and azimuth detection, CCD image sensor, neural network model, prototype

Abstract

The article is devoted to the prototype of an artificial binocular compound eye vision system for detecting the azimuth and distance to an object on a plane using an artificial neural network. A analytical review of modern distance and azimuth detection systems based on active and passive sensors is given. An intelligent binocular vision system is proposed, which is a passive optical sensor that allows you to determine the azimuth and distance to a round object of arbitrary size, emitting in the visible or infrared ranges of the electromagnetic spectrum. The general architecture of the compound eye vision system is considered. The main structural elements of the system are: an optical module, a hardware and software controller and a neural network module. The optical module uses a pair of lenses to convert the light signal from the object into two pixel Fourier images, which are fed to the input of the hardware and software controller. The controller performs primary processing of pixel Fourier images and converts them into two bit masks, the elements of which correspond to separate facets (each facet integrates four adjacent columns of the pixel image). The resulting bit masks are fed into a neural network module, which, based on their analysis, determines the coordinates of the object in the form of distance and azimuth.

Author Biographies

Kirill N. Belov, South Ural State University (Chelyabinsk, Russia)

ассистент кафедры оптоинформатики

Evelina A. Bibikova, South Ural State University (Chelyabinsk, Russia)

к.ф.-м.н., доцент кафедры оптоинформатики

Ivan V. Buldashev, South Ural State University (Chelyabinsk, Russia)

старший преподаватель кафедры оптоинформатики

Nataliya D. Kundikova, South Ural State University (Chelyabinsk, Russia)

д.ф.-м.н., профессор, заведующий кафедрой оптоинформатики

Yurii V. Mukhin, South Ural State University (Chelyabinsk, Russia)

к.ф.-м.н., доцент кафедры оптоинформатики

Andrey N. Nikolaev, South Ural State University (Chelyabinsk, Russia)

доцент кафедры радиоэлектроники и систем связи

Andrey V. Portnov, South Ural State University (Chelyabinsk, Russia)

аспирант кафедры системного программирования

Yaroslav M. Ridnyi, South Ural State University (Chelyabinsk, Russia)

к.ф.-м.н., доцент кафедры оптоинформатики

Leonid B. Sokolinsky, South Ural State University (Chelyabinsk, Russia)

д.ф.-м.н., профессор, заведующий кафедрой системного программирования

Artem E. Starkov, South Ural State University (Chelyabinsk, Russia)

аспирант кафедры системного программирования

Alexander A. Shulginov, South Ural State University (Chelyabinsk, Russia)

к.ф.-м.н., доцент кафедры оптоинформатики

References

Ben-Ari M., Mondada F. Elements of robotics. Springer Nature, 2017. 308 p. DOI: 10.1007/978-3-319-62533-1.

Mahajan A., Walworth M. 3D position sensing using the differences in the time-of-flights from a wave source to various receivers. IEEE Transactions on Robotics and Automation. 2001. Vol. 17, no. 1. P. 91–94. DOI: 10.1109/70.917087.

Journet B.A., Poujouly S. High-resolution laser rangefinder based on a phase-shift measurement method. Three-Dimensional Imaging, Optical Metrology, and Inspection IV. Vol. 3520 / ed. by K.G. Harding, D.J. Svetkoff, K. Creath, J.S. Harris. International Society for Optics, Photonics. SPIE, 1998. P. 123–132. DOI: 10.1117/12.334326.

Zhang C., Lindner S., Antolovic I.M., et al. A 30-frames/s, 252 x 144 SPAD Flash LiDAR With 1728 Dual-Clock 48.8-ps TDCs, and Pixel-Wise Integrated Histogramming. IEEE Journal of Solid-State Circuits. 2018. Vol. 54, no. 4. P. 1137–1151. DOI: 10.1109/JSSC.2018.2883720.

Bamji C., Godbaz J., Oh M., et al. A Review of Indirect Time-of-Flight Technologies. IEEE Transactions on Electron Devices. 2022. Vol. 69, no. 6. P. 2779–2793. DOI: 10.1109/TED.2022.3145762.

Dorsch R.G., Häusler G., Herrmann J.M. Laser triangulation: fundamental uncertainty in distance measurement. Appl. Opt. 1994. Mar. Vol. 33, no. 7. P. 1306–1314. DOI: 10.1364/AO.33.001306.

Liebe C.C., Coste K. Distance Measurement Utilizing Image-Based Triangulation. IEEE Sensors Journal. 2013. Vol. 13, no. 1. P. 234–244. DOI: 10.1109/JSEN.2012.2212428.

Bondžulic B.P., Mitrovic S.T., Barbaric Ž.P., Andric M.S. A comparative analysis of three monocular passive ranging methods on real infrared sequences. Journal of Electrical Engineering. 2013. Vol. 64, no. 5. P. 305–310. DOI: 10.2478/jee-2013-0044.

Li L. Building an accurate 3D model of a circular feature for robot vision. Opto-Electronics Review. 2012. Vol. 20. P. 120–125. DOI: 10.2478/s11772-012-0017-y.

Jüngel M., Mellmann H., Spranger M. Improving vision-based distance measurements using reference objects. RoboCup 2007: Robot SoccerWorld Cup XI 11. Vol. 5001. Springer, 2008. P. 89–100. DOI: 10.1007/978-3-540-68847-1_8.

Geidarov P. Algorithm for determining the position and size of objects based on image analysis. Computer Optics. 2011. Vol. 35, no. 2. P. 275–280. (in Russian).

Witus G., Hunt S. Monocular visual ranging. Unmanned Systems Technology X. Vol. 6962. SPIE, 2008. P. 38–44. DOI: 10.1117/12.778686.

Zuev S.V. Monostatic method for measuring the distance to object, its direction and movement speed. 2008. (in Russian).

Lumsdaine A., Georgiev T. The focused plenoptic camera. 2009 IEEE International Conference on Computational Photography (ICCP). IEEE, 2009. P. 1–8. DOI: 10.1109/ICCPHOT.2009.5559008.

Chen Y., Jin X., Dai Q. Distance measurement based on light field geometry and ray tracing. Optics Express. 2017. Vol. 25, no. 1. P. 59–76. DOI: 10.1364/OE.25.000059.

Heinze C., Spyropoulos S., Hussmann S., Perwass C. Automated robust metric calibration algorithm for multifocus plenoptic cameras. IEEE Transactions on Instrumentation and Measurement. 2016. Vol. 65, no. 5. P. 1197–1205. DOI: 10.1109/TIM.2015.2507412.

Sardemann H., Maas H.-G. On the accuracy potential of focused plenoptic camera range determination in long distance operation. ISPRS Journal of Photogrammetry and Remote Sensing. 2016. Vol. 114. P. 1–9. DOI: 10.1016/j.isprsjprs.2016.01.012.

Mahammed M.A., Melhum A.I., Kochery F.A. Object distance measurement by stereo vision. International Journal of Science and Applied Information Technology (IJSAIT). 2013. Vol. 2, no. 2. P. 05–08.

Jeong C.-J., Park G.-M. Real-time Auto Tracking System using PTZ Camera with DSP. International Journal of Advanced Smart Convergence. 2013. Vol. 2, no. 1. P. 32–35. DOI: 10.7236/IJASC.2013.2.1.032.

Starkov A.E., Sokolinsky L.B. Building 2D Model of Compound Eye Vision for Machine Learning. Mathematics. 2022. Vol. 10, no. 2. DOI: 10.3390/math10020181.

Biewald L. Experiment Tracking with Weights and Biases. 2020. URL: https://docs.wandb.ai/.

Goodfellow I., Bengio Y., Courville A. Deep Learning (Adaptive Computation and Machine Learning). MIT Press, 2016. 800 p. URL: http://www.deeplearningbook.org.

Willmott C.J., Matsuura K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research. 2005. Vol. 30, no. 1. P. 79–82. DOI: 10.3354/CR030079.

Bisong E. Building Machine Learning and Deep Learning Models on Google Cloud Platform. Apress, 2019. 709, XXIX p. DOI: 10.1007/978-1-4842-4470-8.

Myttenaere A., Golden B., Rossi F. Mean Absolute Percentage Error for regression models. Neurocomputing. 2016. Vol. 192. P. 38–48. DOI: 10.1016/J.NEUCOM.2015.12.114.

Barten A.P. The coefficient of determination for regression without a constant term. The Practice of Econometrics. International Studies in Economics and Econometrics. Vol. 15 / ed. by R. Heijmans, H. Neudecker. Springer, 1987. P. 181–189. DOI: 10.1007/978-94-009-3591-4_12.

Downloads

Published

2025-04-01

Issue

Vol. 14 No. 1 (2025)

Section

Numerical Mathematics

License

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.