Calculation of the Dimensions and Speed of the Car from the Video Received from the Uncalibrated Camera
Subject Areas : electrical and computer engineeringR. Asgarian Dehkordi 1 , H. Khosravi 2
1 -
2 -
Keywords: Car dimensionsspeed detectioncamera calibrationbackground modeling,
Abstract :
In this paper, a fully automated method for calibrating the camera and obtaining dimensions and speed of vehicles is presented. In this method, at first, vanishing points and the focal length of the camera are obtained, according to the directions of the cars in the initial frames. After detecting moving vehicles, their 3D bounding box are created using the vanishing points. In order to deal with the perspective, the bounding box of each vehicle is projected on a hypothetical road and then to have their real dimensions in meter, the metric coefficient (pixel-to-meter conversion) is obtained. This calculates the coefficient; a dominant car is detected and according to its metric dimensions, the pixel to meter coefficient is computed. Projecting the vehicle on the road surface and the use of the metric coefficient provides the possibility of expressing the actual speeds and dimensions of the vehicles in each frame. However, it may have some errors. To increase the accuracy of the results, these parameters are aggregated along the vehicle's path, and some histograms are made up for the speed and dimensions of each vehicle. Then the maximum of these histograms is reported as new values of speed and dimensions for each vehicle. This will improve the accuracy. Creating histograms for each vehicle requires tracking of the car in multiple frames. For this purpose, a fast algorithm is presented. Comparing the results of the proposed method with previous methods indicates higher processing speed and better response. The average error of dimension estimation is 1.4%, and the error of speed estimation is 1.1 km/h. The average processing speed for testing videos in MATLAB is about 3.5 frames per second.
[1] M. Dubska, A. Herout, R. Juranek, and J. Sochor, "Fully automatic roadside camera calibration for traffic surveillance," IEEE Trans. on Intelligent Transportation Systems, vol. 16, no. 3, pp. 1162-1171, Jun. 2015.
[2] D. N. Dawson and S. T. Birchfield, "An energy minimization approach to automatic traffic camera calibration," IEEE Trans. on Intelligent Transportation Systems, vol. 14, no. 3, pp. 1095-1108, Sep. 2013.
[3] T. N. Schoepflin and D. J. Dailey, "Dynamic camera calibration of roadside traffic management cameras for vehicle speed estimation," IEEE Trans. on Intelligent Transportation Systems, vol. 4, no. 2, pp. 90-98, Jun. 2003.
[4] K. Wang, H. Huang, Y. Li, and F. Y. Wang, "Research on lane-marking line based camera calibration," in Proc. of IEEE Int. Conf. on Vehicular Electronics and Safety, 6 pp. 1-6, Beijing, China, 13-15 Dec. 2007.
[5] T. W. Pai, W. J. Juang, and L. J. Wang, "An adaptive windowing prediction algorithm for vehicle speed estimation," in Proc. of IEEE Intelligent Transportation Systems, ITSC'01, pp. 901-906, Oakland, CA, USA, 25-29 Aug. 2001.
[6] X. C. He and N. H. C. Yung, "A novel algorithm for estimating vehicle speed from two consecutive images," in Proc. of IEEE Workshop on Applications of Computer Vision, pp. 12-12, Austin, TX, USA, 21-22 Feb. 2007.
[7] F. Cathey and D. Dailey, "A novel technique to dynamically measure vehicle speed using uncalibrated roadway cameras," in Proc. Intelligent Vehicles Symp., pp. 777-782, Las Vegas, NV, USA, 6-8 Jun. 2005.
[8] X. You and Y. Zheng, "An accurate and practical calibration method for roadside camera using two vanishing points," Neurocomputing, vol. 204, pp. 222-230, Sept. 2016.
[9] P. Filipiak, B. Golenko, and C. Dolega, "NSGA-II based auto-calibration of automatic number plate recognition camera for vehicle speed measurement," in Proc. 19th European Conf. on Applications of Evolutionary Computation, pp. 803-818, Apr. 2016.
[10] D. C. Luvizon, B. T. Nassu, and R. Minetto, "Vehicle speed estimation by license plate detection and tracking," in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP'14, pp. 6563-6567, Florence, Italy, 4-9 May 2014.
[11] I. Sina, et al., "Vehicle counting and speed measurement using headlight detection," in Proc. Int. Conf. on Advanced Computer Science and Information Systems, ICACSIS'13, pp. 149-154, Bali, Indonesia, 28-29 Sept. 2013.
[12] H. Eslami, A. Raie, and K. Faez, "Precise vehicle speed measurement for law enforcement applications based on calibrated camera with parallel standard patterns,"IET Computer Vision, vol. 10, no. 5, pp. 398-406, Aug. 2016.
[13] M. Famouri, Z. Azimifar, and A. Wong, "A novel motion plane-based approach to vehicle speed estimation," IEEE Trans. on Intelligent Transportation Systems, vol. 20, no. 4, pp. 1237-1246, Apr. 2019.
[14] س. ا. آقایان و ح. خسروی، "تخمین بلادرنگ سرعت خودرو از طریق دوربین به کمک ردیابی مرکز ثقل و پیادهسازی آن روی برد توسعه 4XU،" مجموعه مقالات دهمین کنفرانس بینایی ماشین و پردازش تصویر ایران، اصفهان، انجمن ماشین بینایی و پردازش تصویر ایران، 6 صص.، اصفهان، آذر 1396.
[15] M. Dubsk'a, J. Sochor, and A. Herout, "Automatic camera calibration for traffic understanding," in Proc. of the British Machine Vision Conf., 12 pp., Nottingham, UK, 2014.
[16] J. Sochor and A. Herout, "Unsupervised processing of vehicle appearance for automatic understanding in traffic surveillance," in Proc. Int. Conf. on Digital Image Computing: Techniques and Applications, DICTA'15, 8 pp., Adelaide, Australia, 23-25 Nov. 2015.
[17] S. Kamijo, Y. Matsushita, K. Ikeuchi, and M. Sakauchi, "Traffic monitoring and accident detection at intersections," in Proc. IEEE/IEEJ/JSAI Int. Conf. on Intelligent Transportation Systems, pp. 703-708, Tokyo, Japan, 5-8 Oct. 1999.
[18] Z. Zivkovic, "Improved adaptive Gaussian mixture model for background subtraction," in Proc. of the 17th Int. Conf. on Pattern Recognition, ICPR'04, vol. 2, pp. 28-31, 26-26 Aug. 2004.
[19] P. D. Patil and A. D. Kumbhar, "Bilateral filter for image denoising," in Proc. Int. Conf. on Green Computing and Internet of Things, ICGCIoT'15, pp. 299-302, Noida, India, 8-10 Oct. 2015.
[20] N. Otsu, "A threshold selection method from gray-level histograms," IEEE Trans. on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, Jan. 1979.
[21] J. Sochor, Traffic Analysis from Video, Thesis Ph.D., Brno University of Technology, 2014.
[22] پ. معلم و ر. عسگریان دهکردی، "ردیابی تصویری سریع، مطمئن و مقاوم نسبت به انسداد با کمک یک مدل تقسیمشده مبتنی بر لبه،" نشريه مهندسی برق و مهندسی کامپيوتر ايران، ب- مهندسي كامپيوتر ، سال 15، شماره 1، صص. 45-37، بهار 1396.
[23] https://medusa.fit.vutbr.cz/traffic/research-topics/traffic-camera-calibration/automatic-camera-calibration-for-traffic-understanding-bmvc-2014/
[24] J. Sochor, R. Juranek, J. Spanhel, L. Marsik, and A. Siroky, "BrnoCompSpeed: review of traffic camera calibration and comprehensive dataset for monocular speed measurement," CoRR, 10 pp., 2017.