Summary
Multimedia transmissions, especially sports transmissions, are an important share of the services offered by mobile network operators. Due to limited capacity, lossy compression codecs have to be used, inducing a significant quality degradation. The quality impairments can particularly be observed in soccer games, when the ball is blurred or even totally disappears at the low-resolution user terminal. We present a complete system for a suitable preprocessing of the original video by means of ball sharpening or enlarging in the original video sequence to avoid problems caused by resolution down-sampling and compression. The proposed system includes a novel initial ball-recognition algorithm and an improved ball-trajectory tracking. Output videos show a considerable improvement in visual quality. Our algorithm runs robustly and is real-time capable, which allows for preprocessing employment in live broadcasting.
Zusammenfassung
Multimedia-Übertragungen, insbesondere Sportübertragungen, stellen einen wichtigen Teil der Dienste heutiger Mobilfunkanbieter dar. Mobilfunknetze haben jedoch immer eine begrenzte Kapazität, was den Einsatz von verlustbehafteten Komprimierungsverfahren notwendig macht, welche wiederum einen erheblichen Qualitätsverlust mit sich bringen. Vor allem bei Fußballvideos macht sich eine Qualitätsverminderung besonders stark bemerkbar, da der Ball bei Betrachtung am Endgerät entweder stark verschmiert oder gar nicht mehr zu sehen ist. In der vorliegenden Arbeit schlagen die Autoren ein System zur Verbesserung der Videoqualität vor, in welchem durch eine passende Vorverarbeitung der Ball geschärft und leicht vergrößert wird, um Probleme der Unterabtastung und der Kompression zu vermeiden. Das entwickelte System beinhaltet eine neuartige "Erst-Ball-Erkennung" und eine verbesserte Ball-Verfolgung. Die mit dieser Methode bearbeiteten Videos zeigen eine erhebliche Verbesserung in der visuellen Qualität, das System ist weiters robust und echtzeitfähig, was einen Einsatz in Live-Sendungen ermöglicht.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
3GPP Std. TS 26.234 (2002): Transparent end-to-end Packet Switched Streaming Service (PSS); Protocols and Codecs. Rev. 4, Dec. 2002.
Dimou, A., Nemethova, O., Rupp, M. (2005): Scene change detection for h.264 using dynamic threshold techniques. In: Proc. of 5th EURASIP Conf. on Speech and Image Processing, Multimedia Communications and Service, Smolenice, Slovak Republic. June 2005.
Ekin, A., Tekalp, A. M., Mehrotra, R. (2003): Automatic soccer video analysis and summarization. IEEE Transactions on Image Processing, 12 (7): 796–807.
Hanjalic, A. (2004): Content-based analysis of digital video. Kluwer Academic Publishers.
ITU-T Recommendation P.910 (1999) Subjective video quality assessment methods for multimedia applications.
Jähne, B. (1997): Practical handbook on image processing for scientific applications (Hardcover) 1st edn. CRC-Press.
Leo, M., D'orazio, T., Distante, A. (2003): Independent component analysis for ball recognition in soccer images. In: Proc. of Int. Conf. on Intelligent Systems and Control, Salzburg. June 2003: 351–355.
Liang, D., Liu, Y., Huang, Q., Gao, W. (2005): A scheme for ball detection and tracking in broadcast soccer video. In: Advances in Multimedia Information Processing – PCM 2005: 6th Pacific-Rim Conf. an Multimedia, Jeju Island, Korea. Nov. 2005: 864–875.
Nemethova, O., Zahumensky, M., Rupp, M. (2004): Preprocessing of ball game video-sequences for robust transmission over mobile networks. In: Proc. of the 9th CDMA Int. Conf. (CIC 2004), Seoul, Korea. October 2004.
Ohm, J.-R. (2004): Multimedia Communication Technology. Springer, 2004.
Ren, J., Orwell, J., Jones, G. A. (2004): Estimating the position of a football from multiple image sequences. BMVA One Day Symp. on Spatiotemporal Image Processing, London, UK. Mar. 2004.
Shah, M., Rangarajan, K., Tsai, P.-S. (1993): Motion trajectories. IEEE Transactions on Systems. Man and Cybernetics, 23 (4): 1138–1150.
Yu, X., Tian, Q., Wan, K. W. (2003): A novel ball detection framework for real soccer video. In: Proc. of Int. Conf. on Multimedia and Expo (ICME), Baltimore, USA. July 2003.
Yu, X., Xu, C., Leong, H. W., Tian, Q., Tang, Q., Wan, K. (2003): Trajectory-based ball detection and tracking with applications to semantic analysis of broadcast soccer video. In: Proc. of the Eleventh ACM Int. Conf. on Multimedia, Berkeley, USA, Nov. 2003, pp 11–20.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wrulich, M., Nemethova, O., Superiori, L. et al. Ball appearance improvement in low-resolution soccer videos. Elektrotech. Inftech. 124, 337–345 (2007). https://doi.org/10.1007/s00502-007-0476-x
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s00502-007-0476-x