500 rub
Journal Information-measuring and Control Systems №2 for 2026 г.
Article in number:
Intelligent system for recognizing 3D objects based on lidar data and neural network architectures
Type of article: scientific article
DOI: https://doi.org/10.18127/j20700814-202602-08
UDC: 004.032.26
Keywords: Lidar neural networks pattern recognition point cloud CNN visualization classification
Authors:

I.K. Belova1, E.O. Deryugina3, E.V. Simakova3

1-3 Kaluga Branch of Bauman Moscow State Technical University (Kaluga, Russia)

1 belova.ik@bmstu.ru, 2 deryugina_eo@bmstu.ru, 3 simakovaev@student.bmstu.ru

Abstract:

The article is dedicated to the development of an intelligent system for recognizing 3D objects based on data obtained from an optical laser rangefinder. The main focus is on investigating the architecture of neural networks applicable to the recognition task, as well as analyzing methods for collecting and processing point clouds. Special attention is given to constructing a functional model and implementing a software package that realizes visualization and classification algorithms. Experimental results of system testing and directions for its further development are presented.

Pages: 60-67
For citation

Belova I.K., Deryugina E.O., Simakova E.V. Intelligent system for recognizing 3D objects based on lidar data and neural network architectures. Information-measuring and Control Systems. 2026. V. 24. № 2. P. 60−67. DOI: https://doi.org/10.18127/j20700814-202602-08 (in Russian)

References
  1. Davydenko Egor Viktorovich. Razrabotka i analiz algoritmov tsifrovoi obrabotki signalov v zadache opticheskoi lazernoi triangulyatsii: avtoreferat dis. … kandidata tekhnicheskikh nauk: 05.12.04. Vladimir: Vladimirskii gos. un-t. 2009. 23 s.  https://search.rsl.ru/ru/record/01003466752 (10.06.2023). (in Russian)
  2. Electronic resource. Arduino Official Site. https://www.arduino.cc (02.04.2025).
  3. Electronic resource. National Instruments. LabVIEW Documentation. https://www.ni.com/ru-ru/shop/labview.html (02.04.2025).
  4. Electronic resource. RPLIDAR A1 Datasheet. https://www.slamtec.com/en/Lidar/A1 (02.04.2025).
  5. Qi C.R. et al. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Proceedings of the IEEE CVPR. 2017. P. 652−660.
  6. Wu Z. et al. 3D ShapeNets: A Deep Representation for Volumetric Shapes. Proceedings of the IEEE CVPR. 2015. P. 1912−1920.
  7. Electronic resource. Open3D Library. http://www.open3d.org (02.04.2025).
  8. Kuznetsov N.N. Tekhnologii mashinnogo zreniya i tsifrovykh dvoinikov. M.: Tekhnosfera. 2023. 280 s. (in Russian)
Date of receipt: 04.03.2026
Approved after review: 18.03.2026
Accepted for publication: 31.03.2026