- Research Article
- Open Access
A Content-Adaptive Analysis and Representation Framework for Audio Event Discovery from "Unscripted" Multimedia
EURASIP Journal on Advances in Signal Processingvolume 2006, Article number: 089013 (2006)
We propose a content-adaptive analysis and representation framework to discover events using audio features from "unscripted" multimedia such as sports and surveillance for summarization. The proposed analysis framework performs an inlier/outlier-based temporal segmentation of the content. It is motivated by the observation that "interesting" events in unscripted multimedia occur sparsely in a background of usual or "uninteresting" events. We treat the sequence of low/mid-level features extracted from the audio as a time series and identify subsequences that are outliers. The outlier detection is based on eigenvector analysis of the affinity matrix constructed from statistical models estimated from the subsequences of the time series. We define the confidence measure on each of the detected outliers as the probability that it is an outlier. Then, we establish a relationship between the parameters of the proposed framework and the confidence measure. Furthermore, we use the confidence measure to rank the detected outliers in terms of their departures from the background process. Our experimental results with sequences of low- and mid-level audio features extracted from sports video show that "highlight" events can be extracted effectively as outliers from a background process using the proposed framework. We proceed to show the effectiveness of the proposed framework in bringing out suspicious events from surveillance videos without any a priori knowledge. We show that such temporal segmentation into background and outliers, along with the ranking based on the departure from the background, can be used to generate content summaries of any desired length. Finally, we also show that the proposed framework can be used to systematically select "key audio classes" that are indicative of events of interest in the chosen domain.
Jasinschi RS, Dimitrova N, McGee T, Agnihotri L, Zimmerman J, Li D: Integrated multimedia processing for topic segmentation and classification. Proceeding of International Conference on Image Processing (ICIP '01), October 2001, Thessaloniki, Greece 3: 366–369.
Lienhart R: Automatic text recognition for video indexing. Proceeding of 4th ACM International Conference on Multimedia (ACM Multimedia '96), November 1996, Boston, Mass, USA 11–20.
Hanjalic A, Kakes G, Lagendijk RL, Biemond J: DANCERS: Delft advanced news retrieval system. IS&T/SPIE Electronic Imaging 2001: Storage and Retrieval for Media Databases 2001, January 2001, San Jose, Calif, USA, Proceedings of SPIE 4315: 301–310.
Wang Y, Liu Z, Huang J-C: Multimedia content analysis-using both audio and visual clues. IEEE Signal Processing Magazine 2000, 17(6):12–36. 10.1109/79.888862
Winston H, Hsu H-M, Chang S-F: A statistical framework for fusing mid-level perceptual features in news story segmentation. Proceeding of IEEE International Conference on Multimedia and Expo (ICME '03), July 2003, Baltimore, Md, USA 2: 413–416.
Aner A, Kender JR: Video summaries through mosaic-based shot and scene clustering. Proceeding of 7th European Conference on Computer Vision (ECCV '02), May–June 2002, Copenhagen, Denmark 4: 388–402.
Li Y, Kuo CC: Content-based video analysis, indexing and representation using multimodal information, M.S. thesis. University of Southern California, Los Angeles, Calif, USA; 2003.
Sundaram H, Chang S-F: Determining computable scenes in films and their structures using audio-visual memory models. Proceeding of 8th ACM International Conference on Multimedia (ACM Multimedia '00), October–November 2000, Los Angeles, Calif, USA 95–104.
Nitta N, Babaguchi N, Kitahashi T: Extracting actors, actions and events from sports video—a fundamental approach to story tracking. Proceeding of 15th International Conference on Pattern Recognition (ICPR '00), September 2000, Barcelona, Spain 4: 718–721.
Ekin A, Tekalp AM: Automatic soccer video analysis and summarization. IS&T/SPIE 15th Annual Symposium on Electronic Imaging Science and Technology: Storage and Retrieval for Media Databases 2003, January 2003, Santa Clara, Calif, USA, Proceedings of SPIE 5021: 339–350.
Pan H, van Beek P, Sezan MI: Detection of slow-motion replay segments in sports video for highlights generation. Proceeding of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '01), May 2001, Salt Lake City, Utah, USA 3: 1649–1652.
Xu M, Maddage NC, Xu C, Kankanhalli M, Tian Q: Creating audio keywords for event detection in soccer video. Proceeding of IEEE International Conference on Multimedia and Expo (ICME '03), July 2003, Baltimore, Md, USA 2: 281–284.
Xie L, Chang S-F, Divakaran A, Sun H: Unsupervised mining of statistical temporal structures in video. In Video Mining. Edited by: Rosenfeld A, Doermann D, DeMenthon D. Kluwer Academic, Boston, Mass, USA; 2003:279–309.
Wu G, Wu Y, Jiao L, Wang Y-F, Chang EY: Multi-camera spatio-temporal fusion and biased sequence-data learning for security surveillance. Proceeding of 11th ACM International Conference on Multimedia (ACM Multimedia '03), November 2003, Berkeley, Calif, USA 528–538.
Xiong Z, Rui Y, Radhakrishnan R, Divakaran A, Huang TS: A unified framework for video summarization, browsing and retrieval. In Handbook of Image & Video Processing. 2nd edition. Edited by: Bovik Al. Academic Press, San Diego, Calif, USA; 1013–1030.
Xiong Z, Radhakrishnan R, Divakaran A, Huang TS: Effective and efficient sports highlights extraction using the minimum description length criterion in selecting GMM structures [audio classification]. Proceeding of IEEE International Conference on Multimedia and Expo (ICME '04), June 2004, Taipei, Taiwan 3: 1947–1950.
Xiong Z, Radhakrishnan R, Divakaran A, Huang TS: Audio events detection based highlights extraction from baseball, golf and soccer games in a unified framework. Proceeding of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '03), April 2003, Hong Kong, China 5: 632–635.
Shi J, Malik J: Normalized cuts and image segmentation. Proceeding of Computer Vision and Pattern Recognition (CVPR '97), June 1997, San Juan, Puerto Rico, USA 731–737.
Rao RP, Pearlman WA: Multirate vector quantization of image pyramids. Proceeding of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '91), April 1991, Toronto, Ontario, Canada 4: 2657–2660.
Duda RO, Hart PE: Pattern Classification and Scene Analysis. John Wiley & Sons, New York, NY, USA; 1973.
Perona P, Freeman WT: A factorization approach to grouping. Proceeding of 5th European Conference on Computer Vision (ECCV '98), June 1998, Freiburg, Germany 1: 655–670.
Wand MP, Jones MC: Kernel Smoothing. Chapman & Hall, London, UK; 1995.
Sheather SJ, Jones MC: A reliable data-based bandwidth selection method for kernel density estimation. Journal of the Royal Statistical Society. Series B 1991, 53(3):683–690.
Comaniciu D, Ramesh V, Meer P: The variable bandwidth mean shift and data-driven scale selection. Proceeding of 8th IEEE International Conference on Computer Vision (ICCV '01), July 2001, Vancouver, British Columbia, Canada 1: 438–445.
Papoulis A: Probability, Random Variables and Stochastic Processes. McGraw-Hill, New York, NY, USA;
Rabiner L, Juang B-H: Fundamentals of Speech Recognition, Prentice Hall Signal Processing Series. Prentice-Hall, Englewood Cliffs, NJ, USA; 1993.
Radhakrishnan R, Otsuka I, Xiong Z, Divakaran A: Modeling sports highlights using a time-series clustering framework and model interpretation. Storage and Retrieval Methods and Applications for Multimedia 2005, January 2005, San Jose, Calif, USA, Proceedings of SPIE 5682: 269–276.
Upcroft B, Ong LL, Kumar S, Ridley M, Bailey T, et al.: Rich probabilistic representations for bearing only decentralised data fusion. Proceeding of The Eighth International Conference on Information Fusion, July 2005, Philadelphia, Pa, USA