Abstract
In this paper, we present a novel approach for accurate vehicle speed estimation from video sequences. Common methods usually track sets of distinguishing features; however, feature extraction is a difficult task in dynamic environments. Herein, we propose a novel analysis method without feature extraction. Initially, a frame difference method is applied to a region of interest, from which projection histograms are obtained and a group of key bins are selected to represent the vehicle motion. Then, all the possible speeds are tested one by one, and the extreme value of the testing function is selected for the corresponding speed. The proposed system was tested on three data sets containing 2054 vehicles, where the ground truth of speed is obtained by a radar speed detector. The experiment results show that the proposed system has an average error of 0.3 km/h, with 99.4% of the estimation speed within the error of range (− 2 km/h, 2 km/h). The system turns out to be robust, accurate and real time for practical use.
Similar content being viewed by others
References
Banz C, Blume H, Pirsch P (2011) Real-time semi-global matching disparity estimation on the GPU. In: Proceeding of the IEEE ICCV workshops, November, pp 514–521
Cinzburg C, Raphael A, Weinshall D (2015) A cheapest system for vehicle speed detection. Preprint. arXiv:1501.06751
Dailey D, Cathey F, Pumrin S (2000) An algorithm to estimate mean traffic speed using uncalibrated cameras. IEEE Trans Intell Transp Syst 1(2):98–107
Dogan S, Temiz MS, Kulur S (2010) Real time speed estimation of moving vehicles from side view images from an uncalibrated video camera. Sensors 10(5):4805–4824
Grammatikopoulos L, Karras G, Petsa E (2005) Automatic estimation of vehicle speed from uncalibrated video sequences. In: Proceeding of the modern technologies, education and professional practice in geodesy and related fields, pp 332–338
Homm F, Kaempchen N, Ota J, Burschka D (2010) Efficient occupancy grid computation on the GPU with lidar and radar for road boundary detection. In: Proceeding of the IEEE IV symposium, June, pp 1006–1013
Jeyabharathi D, Dejey D (2016) Vehicle tracking and speed measurement system (VTSM) based on novel feature descriptor: diagonal hexadecimal pattern (DHP). J Vis Commun Image Represent 40:816–830
Lan J, Li J, Hu G et al (2014) Vehicle speed measurement based on gray constraint optical flow algorithm. Optik 125:289–295
Lin HY, Li KJ et al (2008) Vehicle speed detection from a single motion blurred image. Image Vis Comput 26(10):1327–1337
Llorca DF, Salinas C, Jimenez M et al (2016) Two-camera based accurate vehicle speed measurement using average speed at a fixed point. In: Proceeding of the IEEE ITSC, pp 2533–2538
Lu S, Song H, Xu X (2015) An enumeration method applied in intelligent transportation system. Int J Smart Home 9(2):143–150
Luvizon DC, Nassu BT, Minetto R (2016) A video-based system for vehicle speed measurement in urban roadways. IEEE Trans Intell Transp Syst 18:1393–1404
Madasu V, Hanmandlu M (2010) Estimation of vehicle speed by motion tracking on image sequences. In: Proceeding of the IEEE intelligent vehicles symposium, pp 185–190
Maduro C, Batista K, Peixoto P et al (2008) Estimation of vehicle velocity and traffic intensity using rectified images. In: Proceeding of the IEEE ICIP, pp 777–780
Palaio H, Maduro C, Batista K et al (2009) Ground plane velocity estimation embedding rectification on a particle filter multi-target tracking. In: Proceeding of the IEEE ICRA, pp 283–286
Song H, Lu S, Ma X et al (2014) Vehicle behavior analysis using target motion trajectories. IEEE Trans Veh Technol 63(8):3580–3591
Wu BF, Juang JH (2012) Adaptive vehicle detector approach for complex environments. IEEE Trans Intell Transp Syst 13(2):817–827
Zhiwei H, Yuanyuan L, Xueyi Y (2007) Models of vehicle speeds measurement with a single camera. In: Proceeding of the international conference on computational intelligence security workshops, pp 283–286
Zhiwen H, Yuanyuan L, Xueyi Y (2007) Models of vehicle speeds measurement with a single camera. In: Proceeding of the international conference on computational intelligence security workshops, pp 283–286
Funding
This study was funded by National Natural Science Foundation of China (Grant No. 61572083), funded by Scientific Research Program Funded by Shaanxi Provincial Education Department (Program No. 18JK0617). This study was also funded by the Doctoral Scientific Research Foundation of Xi’an Shiyou University (0106-134010003).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Communicated by V. Loia.
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lu, S., Wang, Y. & Song, H. A high accurate vehicle speed estimation method. Soft Comput 24, 1283–1291 (2020). https://doi.org/10.1007/s00500-019-03965-w
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-019-03965-w