Determining Moving Object Properties using "Controlled" Image Blurring

Authors: Loktev D.A. Published: 06.06.2020
Published in issue: #2(131)/2020  
DOI: 10.18698/0236-3933-2020-2-98-116

Category: Instrument Engineering, Metrology, Information-Measuring Instruments and Systems | Chapter: Information-Measuring and Control Systems  
Keywords: parameter assessment, object detection, mass estimation, image analysis, object blurring, dynamics

The paper proposes an approach to detecting, capturing and identifying vehicles in an image in order to determine their geometrical, kinematic and dynamic properties. Monitoring the properties determined in real time will assist in detecting violations of vehicle regulations, in analysing and preventing potential accidents by means of using the parameters obtained to control vehicle motion, as well as in implementing a digital model of the environment, including its possible virtual reality representation. To detect the object, we employ the YOLOv3 algorithm using convolutional neural network training. Canny and Hough detectors are used to determine the object boundaries and its axle positions. We propose a method for determining the object boundary blurring based on numerically finding the first, second and third derivatives with respect to each coordinate axis and subsequently refining the result at different resolutions. After detecting the axles in a vehicle and determining their number via passive image analysis, a model of vertical oscillations is selected for the vehicle; the geometrical and kinematic parameters obtained are then used to assess the automotive vehicle dynamics. We describe in detail brour vehicle model featuring two axles. We assume the parameters of an artificial obstacle such as a speed breaker to be the initial conditions of the oscillating system

This work was supported by the Ministry of Education and Science of the Russian Federation (project no. 2.5048.2017/8.9)


[1] Boykov V.N., Skvortsov A.V., Sarychev D.S. Digital motorway as an industry segment of digital economy. Transport Rossiyskoy Federatsii, 2018, no. 2, pp. 56--60 (in Russ.).

[2] Onyesolu M., Udoka Eze F. Understanding virtual reality technology: advances and applications. IntechOpen, 2011, pp. 53--70. DOI: https://doi.org/10.5772/15529

[3] Usanov D.A., Skripal’ A.V., Avdeev K.S. Determining distances to objects using a frequency-switched semiconductor laser autodyne. Tech. Phys. Lett., 2007, vol. 33, no. 11, pp. 930--932. DOI: https://doi.org/10.1134/S1063785007110119

[4] Mansour M., Ismail Y., Swillam M. Subwavelength focusing in the infrared range using a meta surface. ACES, 2017. DOI: https://doi.org/10.23919/ROPACES.2017.7916019

[5] Beder Chr., Bartczak B., Koch R. A comparison of PMD-cameras and stereo-vision for the task of surface reconstruction using patchlets. IEEE Conf. Comput. Vision Pattern Recogn., 2007. DOI: https://doi.org/10.1109/CVPR.2007.383348

[6] Wiedemann M., Sauer M., Driewer F., et al. Analysis and characterization of the PMD camera for application in mobile robotics. Proc. 17th World Cong. Int. Federation of Automatic Control. Seoul, 2008, pp. 46--51.

[7] Devyaterikov E.A., Mikhaylov B.B. Computer vision system for mobile robot path measuring. Mekhanika, upravlenie i informatika, 2012, no. 2, pp. 219–224 (in Russ.).

[8] Loktev D.A., Loktev A.A. Determination of object location by analyzing the image blur. Contemp. Eng. Sci., 2015, vol. 8, no. 11, pp. 467--475. DOI: http://dx.doi.org/10.12988/ces.2015.52198

[9] Loktev A.A., Sychev V.P., Loktev D.A. Contribution to the problem of designing a vision module for track superstructure elements on high-speed mainlines. Transport Rossiyskoy Federatsii, 2017, no. 1, pp. 22--26 (in Russ.).

[10] Loktev A.A., Alfimtsev A.N., Loktev D.A. Algorithm of placement of video surveillance cameras and its software implementation. Vestnik MGSU, 2012, no. 5, pp. 167--175 (in Russ.).

[11] Redmon J., Farhadi A. YOLOv3: an incremental improvement. arxiv.org: веб-сайт. URL: https://arxiv.org/abs/1804.02767v1 (дата обращения: 15.12.2019).

[12] Ross G. Fast R-CNN. arxiv.org: website. Available at: https://arxiv.org/abs/1504.08083 (accessed: 15.12.2019).

[13] Canny J.F. Finding edges and lines in images. Masterʼs thesis. MIT, 1983.

[14] Zhou Q., Aggarwal J. Tracking and classifying moving objects from video. Performance Evaluation of Tracking Systems Workshop, 2001.

[15] Ramer U. An iterative procedure for the polygonal approximation of plane curves. Comput. Graph. Image Process., 1972, vol. 1, no. 3, pp. 244--256.

[16] Douglas D., Peucker T. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. The Canadian Cartographer, 1973, vol. 19, no. 2, pp. 112--122.

[17] Goldenshluger A., Zeevi A. The Hough transform estimator. Ann. Stat., 2004, vol. 32, no. 5, pp. 1908--1932.

[18] Kudrina M.A. Using Hough transformation for detecting lines and circles in pictures. Izvestiya Samarskogo nauchnogo tsentra Rossiyskoy akademii nauk [Izvestia RAS SamSC], 2014, vol. 16, no. 4-2, pp. 476--478 (in Russ.).

[19] Sychev V.P., Loktev A.A., Loktev D.A., et al. Increase in informative value of railway track maintenance assessment. Mir transporta [World of Transport and Transportation], 2017, vol. 15, no. 2, pp. 20--31 (in Russ.).

[20] Loktev D.A., Loktev A.A. Diagnostics of external defects of railway infrastructure by analysis of its images. Proc. GloSIC, 2018. DOI: https://doi.org/10.1109/GloSIC.2018.8570083

[21] Bouguet J.-Y. Pyramidal implementation of the Lucas --- Kanade feature tracker: description of the algorithm. Intel Corporation Microprocessor Research Labs, 2000.

[22] Loktev A.A., Bakhtin V.F., Chernikov I.Yu., et al. Method of determining external defects of a structure by analyzing a series of its images in the monitoring system. Vestnik MGSU, 2015, no. 3, pp. 7--16 (in Russ.).

[23] Eliseev V.V., Oborin E.A., Mitkin V.G. Vehicle vibrations on uneven road: influence of dynamic properties of suspension. Teoriya mekhanizmov i mashin [Theory of Mechanisms and Machines], 2017, vol. 15, no. 1, pp. 6--16 (in Russ.).

[24] Lopanitsyn E.A. Modelirovanie vertikal’nykh kolebaniy avtomobilya [Modeling of vehicle vertical vibrations]. V: Izbrannye problemy prikladnoy mekhaniki i matematiki [In: Selected problems of applied mechanics and mathematics]. Moscow, MSTU MAMI Publ., 2003, pp. 208--234 (in Russ.).

[25] Loktev D.A., Kochnev V.A., Loktev A.A. Prediction of occurrence of deviations from railway track maintenance standards before the fault affecting the transportation process. Nauka i tekhnika transporta [Science and Technology in Transport], 2018, no. 4, pp. 62--69 (in Russ.).

[26] Loktev A.A., Loktev D.A. Transverse impact of a ball on a sphere with allowance for waves in the target. Tech. Phys. Lett., 2008, vol. 34, no. 11, pp. 960--963. DOI: https://doi.org/10.1134/S1063785008110187