Abstract
With low computation cost, motion vectors can be readily extracted from MPEG video streams and processed to estimate vehicle motion speed. A statistical model is proposed to model vehicle speed and noise. In order to achieve high estimation accuracy and also study the limitations of the proposed algorithm, we quantitatively evaluated four parameters used in our algorithm: temporal filter window size T, video resolution R v (CIF/QCIF), motion vector frame distance m, and video bit-rates. Our experiments showed that the mean vehicle speed can be estimated with high accuracy, up to 85 to 92% by proper spatial and temporal processing. The proposed algorithm is especially suitable for Skycam-based application, where the traditional tracking-based or virtual-loop-based approaches perform poorly because of their requirements of high-resolution images. Although extensive work has been done in extracting motion information directly from MPEG video data in compressed domain, to our best knowledge, this paper is the very first work in which stationary motion (speed) of moving objects can be estimated with high accuracy directly from MPEG motion vectors. Furthermore the proposed method is not limited to vehicle speed estimation by nature and it can be applied to other applications where the stationary motion assumption is satisfied.
Similar content being viewed by others
References
Bartolini F, Cappellini V, Colombo C, Mecocci A (1993) Enhancement of local optic flow techniques. In: Proceedings 4th international workshop on time varying image proceeding and moving object recognition, pp.359–366, June 10–11, Florence, Italy
Blake A, Curwen R, Zisserman A (1993) A framework for spatiotemporal control in the tracking of visual contours. Int J Comput Vis 11(2):127–146 (October)
Dimitrova N, Glshani F (1995) Motion recovery for video content classification. ACM Trans Inf Sys 13(4):408–439 (October)
Duda RO, Hart PE, Stock DG (2000) Pattern classification, 2nd edn. Wiley, New York, p 26
Eng H-L, Ma K-K (2001) Noise adaptive soft-switching median filter. IEEE Trans Image Process 10(2):242–251 (February)
Garcia C, Tziritas G (2002) Optimal projection of 2-D displacements for 3-D translational motion estimation. Image Vis Comput 20:793–804
Gonzales CA, Yeo H, Kuo CJ (1999) Requirements for motion estimation search range in MPEG-2 coded video. IBM J Res Develop 43(4):453-470 (July)
Harris C (1992) Tracking with rigid models. In: Blake A, Yuille A (eds) Active vision. MIT, Cambridge, MA
Information technology-coding of moving pictures and associated audio for digital storage media up to 1.5 Mbits/s: Video, ISO/IEC 11172-2, August 1993
Jin JS, Zhu Z, Xu G (2000) A stable vision system for moving vehicles. IEEE Trans Intell Transp Syst 1(1):32–39 (March)
Lai AHS, Yung NHC (2000) Vehicle-type identification through automated virtual loop assignment and block-based direction-biased motion estimation. IEEE Trans Intell Transp Syst 1(2):86–97 (June)
Li H, Shi H (1999) A fast algorithm for reconstructing motion-compensated blocks in compressed domain. J Vis Lang Comput 10(6):607–623
Malik J, Russell S, Beymer D, Coifman B, Huang T, Liddy D, McLauchlan P (1997) Traffic surveillance and detection technology development: new traffic sensor technology: final report. University of California—PATH
Marija J, Norusis/SPSS Inc (1992) SPSS for windows base system user’s guide release 5.0, p 183
Meng J, Chang S-F (1996) CVEPS: a compressed video editing and parsing system. In: Proceedings of ACM Multimedia 96:43–53, Boston, MA (November)
Michalopoulos PG (1991) Vehicle detection video through image processing: the autoscope system. IEEE Trans Veh Technol 40(1, Part 2):21–29 (February)
Milanese R, Deguillaume F, Jacot-Descombes A (1997) Video segmentation and camera motion characterization using compressed data. In: Proc. SPIE Conf. on Multimedia Storage and Archiving Systems II, Dallas, TX, Nov. 2–7
Patel NV, Sethi IK (1997) Video shot detection and characterization for video databases. Pattern Recogn 30(4):583–592 (April)
Pilu M (1998) On using raw MPEG motion vectors to determine global camera motion with applications to image mosaicing. SPIE visual communications and image processing ‘98, San Jose, CA, USA, Jan
Some Skycam websites: www.wthr.com/livecams/trafficcams.html; www.kgw.com/traffic/metrocams.html; www.eastciti.com/skycam.htm
Stiller C, Konrad J (1999) Estimating motion in image sequences: a tutorial on modeling and computation of 2D motion. IEEE Signal Process Mag 16:70–91 (July)
Wang H, Chang S-F (1997) A highly efficient system for automatic face region detection in MPEG video. IEEE Trans Circuits Syst Video Technol 7(4):615–628 (August)
Yeo B-L (1999) A fast microscopic browsing of MPEG-compressed video. Multimedia Syst 7:269–281
Yoon K, DeMenthon D, Doermann D (2000) Event detection from MPEG video in the compressed domain. International conference on pattern recognition (ICPR ’00) 1:1819–1825, Barcelona, Spain, September 03–08
Yu X, Duan L, Tian Q (2002) Highway traffic information extraction from Skycam MPEG video. In: Proceedings of IEEE 5th intelligent transportation systems conference (ITSC 2002), pp 37–42, Sep. 3–6
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yu, X., Xue, P., Duan, L. et al. An algorithm to estimate mean vehicle speed from MPEG Skycam video. Multimed Tools Appl 34, 85–105 (2007). https://doi.org/10.1007/s11042-006-0073-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-006-0073-8