Improvement of Machine Vision Video Signal Processing Algorithm for Higher Accuracy in Extended Object Speed Measurements
https://doi.org/10.31854/1813-324X-2024-10-1-41-48
EDN: JZHITL
Abstract
Machine vision systems are widely used for monitoring of the railway infrastructure condition. High reliability of machine vision systems allows using them not only for video recording but also for automation of technological processes. One of the important tasks in the process automation is measurement of an extended object speed (rail-road cars, electric locomotives and rolling stock). Some systems have a requirement to estimate speed in real time (braking of cars at a shunting yard). In this case the speed is calculated by two adjacent frames to ensure the minimum delay for measurement. However, the image of an extended object can be uninformative (image fragments are uniform in brightness), the weather can cause interference. It leads to high speed estimation error. This article describes the improvement for the existing real-time algorithm which allows for higher accuracy in speed measurements. The improvement implies selection of an informative image area corresponding to an extended object. A comparative analysis of the existing and improved algorithm showed a significant reduction in the estimation error in speed measurements.
About the Authors
R. Diyazitdinov
Povolzhskiy State University of Telecommunications and Informatics
Russian Federation
Russian Federation
N. Vasin
Povolzhskiy State University of Telecommunications and Informatics
Russian Federation
Russian Federation
References
1. Vasin N.N., Kurinsky V.Yu. Measuring of Lengthy Object Velocity with Closed Circuit Cameras. Journal of Instrument Engineering. 2013;56(10):77‒80. EDN:RGRLRB
2. Aliev E.V., Vesnin E.N., Malygin L.L., Mikhailov A.E., Tsarev V.A. Optical Identification of Rolling Stock Objects in the Tasks of Railway Transport Management. Automation in Industry. 2009;5:49‒54. EDN:KVUGWP
3. Obukhova N.A. Methods of Video Surveillance, Segmentation and Tracking of Moving Objects. D.Sc Thesis. St. Peters-burg: Saint Petersburg Electrotechnical University "LETI" Publ.; 2008. 32 p. EDN:NJEOFT
4. Pirim P. Method and Apparatus for Real-Time Identification and Localisation of a Zone with Attitudinal Displacement in a Scene and for Determining the Speed and Direction of Displacement. Patent RF, no. 2216780 C2, 20.11.2003. EDN:GQPAZF
5. Vesnin E., Tsarev V., Mikhailov A. Recognition of Wagon Numbers: Principles of Solution and Application in Industry. Control Engineering Russia. 2014;49(1):60‒66.
6. Vasin N.N., Kurinsky V.Yu. Method of Measuring the Speed of Motion of Extended Objects. Patent RF, no. 2398240 C1, 27.08.2010. EDN:GPIDIH
7. Diyazitdinov R.R., Vasin N.N. Method of Measuring the Speed of Motion of Extended Objects. Patent RF, no. 2747041 C1, 23.04.2021. EDN:DFPPTV
8. Diyazitdinov R., Vasin N. Using Television Image Fragments of a Machine Vision for Verifying Noise Immunity of an Extended Object Velocity Measurement. Proceedings of Telecommun. Univ. 2022;8(1):37‒40. DOI:10.31854/1813-324X-2022-8-1-37-40. EDN:QQWWLU
9. Vasin N.N., Diyazitdinov R.R. Method of Measuring the Speed of Motion of Extended Objects. Patent RF, no. 2803031 C1, 05.09.2023. EDN:CTIPSZ
Review
For citations:
Diyazitdinov R., Vasin N. Improvement of Machine Vision Video Signal Processing Algorithm for Higher Accuracy in Extended Object Speed Measurements. Proceedings of Telecommunication Universities. 2024;10(1):41-48. (In Russ.) https://doi.org/10.31854/1813-324X-2024-10-1-41-48. EDN: JZHITL
Views:
232
Email this article 