Joerg Deigmoeller
ABSTRACT
Within the scope of the EU-funded project porTiVity (portable interactivity), an application has been developed, that automatically modifies SDTV (Standard Definition Television) sports productions for viewing on mobile TV displays by means of intelligent cropping and scaling. It crops regions of interest of sports productions based on a smart combination of production metadata and systematic video analysis methods. This approach allows a context-based composition for cropped images. It provides a differentiation between the original SD-version of the production and the processed one adapted to the requirements for mobile TV. Envisaged is the integration of the tool in post-production and live workflows.
- C. Arthur. (2009, September 5). Television is a turnoff for mobile users, http://www.guardian.co.uk/technology/2007/aug/02/guardianweeklytechnologysection.mobilephonesGoogle Scholar
- A. Treisman. Features and Objects in Visual Processing. Scientific American, vol. 255, pp. 106--115, 1986. Google ScholarDigital Library
- L. Itti, C. Koch, E. Niebur. A Model of Saliency-based Visual Attention for Rapid Scene Analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 20, pp. 1254--1259, 1998 Google ScholarDigital Library
- W.-H. Cheng, W.-T. Chu, and J.-L. Wu. A Visual Attention Based Region-of-interest Determination Framework for Video Sequences. IEICE Transactions on Information and Systems Journal, vol. E-88D, no. 7, pp. 1578--1586, 2005 Google ScholarDigital Library
- T. Deselaers, P. Dreuw, H. Ney. Pan, Zoom, Scan -- Time-coherent, Trained Automatic Video Cropping. IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, 2008Google Scholar
- X. Hou. L. Zhang. Saliency Detection: A Spectral Residual Approach. Conference on Computer Vision and Pattern Recognition, Minneapolis, 2007Google Scholar
- J. Zaller. (2009, September 5). Snell & Wilcox's Helios: Optimizes Video for Distribution to Mobile TV Devices. http://www.snellwilcox.com/news_events/press_coverage/Google Scholar
- M. Knee, R. Piroddi. (2009, September 5). Aspect Processing: The Shape of Things to Come, http://www.snellwilcox.com/community/documents/support_documentation/white_papers/Google Scholar
- O. Le Meur, P. Le Callet, D. Barba. Predicting visual fixations on video based on low-level visual features. Vision Research, vol. 47, pp. 2483--2498, 2007Google ScholarCross Ref
- A. Dearden, Y. Demiris, O. Grau, Tracking football player movement from a single moving camera using particle filters. Proceedings of the 3rd European Conference on Visual Media Production (CVMP), pp. 29--37, 2006Google Scholar
- S. Frintrop, VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search. Lecture Notes in Artificial Intelligence, vol. 3899, 2006 Google ScholarDigital Library
- S. Mason, (2009, September 5). Mobile TV -- results from the DVB-H trial in Oxford. http://www.ebu.ch/en/technical/trev/trev_306-mason.pdfGoogle Scholar
- BMF Documentation. "BMF -- Broadcast Metadata exchange Format", Institut fuer Rundfunktechnik, Version 01.00.00, Munich, 2007Google Scholar
- (2009, September 5). Opencv library Documentation. http://opencv.willowgarage.com/wiki/Google Scholar
- J. Y. Bouguet, Pyramidal Implementation of the Lucas Kanade Feature Tracker Description of the algorithm. Intel Corporation Microprocessor Research Labs, 1999Google Scholar
- P. Rousseeuw. Least Median of Squares Regression. Journal of the American Statistics Association, vol. 79, pp. 871--880, 1984Google ScholarCross Ref
- R. Hartley, A. Zisserman. Multiple View Geometry in Computer Vision -- Second Edition. Cambridge University Press, 2003 Google ScholarDigital Library
- Z. Zhang, R. Deriche, O. Faugeras, Q. T. Luong. A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry. Artificial Intelligence, vol. 78, pp. 87--119, 1995. Google ScholarDigital Library
- (2009, September 5). homest: A C/C++ Library for Robust, Non-linear Homography Estimation, http://www.ics.forth.gr/~lourakis/homest/Google Scholar
- (2009, September 5). Saliency Tollbox, http://www.saliencytoolbox.net/index.htmlGoogle Scholar
- (2009, September 5). Spectral Residual, http://www.its.caltech.edu/~xhou/Google Scholar
- D. L. Ruderman, The statistics of natural images. Computation in Neural Systems, vol. 5, pp. 517--548, 1994.Google ScholarCross Ref
- D. A. Forsyth, J. Ponce. Computer Vision - A Modern Approach. Prentice Hall. New Jersey, 2003 Google ScholarDigital Library
- B. Schölkpf, C. Burges, A. Smola. Advances in Kernel Methods: Support Vector Learning. Cambridge, 1999Google Scholar
- (2009, October 20). ITU Gaze Tracker, http://www.gazegroup.org/downloads/23-gazetrackerGoogle Scholar
Index Terms
- An approach to intelligently crop and scale video for broadcast applications
Recommendations
Contextual cropping and scaling of TV productions
In this paper, an application is presented which automatically adapts SDTV (Standard Definition Television) sports productions to smaller displays through intelligent cropping and scaling. It crops regions of interest of sports productions based on a ...
Monitoring crop phenology with street-level imagery using computer vision
Highlights- Method to automatically collect side looking imagery for agriculture parcels.
- Crop types and phenology obtained from computer vision.
- Demonstration over monthly surveyed totalling 400,000 pictures for 17 crop types.
- Deep ...
AbstractStreet-level imagery holds a significant potential to scale-up in-situ data collection. This is enabled by combining the use of cheap high-quality cameras with recent advances in deep learning compute solutions to derive relevant thematic ...
Extracting Regions of Interest in Biomedical Images
FBIE '08: Proceedings of the 2008 International Seminar on Future BioMedical Information EngineeringRegions of interest (ROI) usually means the meaningful and important regions in the images. The use of ROI can avoid the processing of irrevelent image points and accelerate the processing. Extraction of regions of interest from images is an important ...
Comments