News Program Detection in TV Broadcast Videos

ABSTRACT

Television news channels broadcast different kinds of content like debates, interviews, commercials along with news presentations. Real-time detection of these news programs or their retrieval from large volumes of stored broadcast videos is a challenging problem and is a necessary first step for broadcast analytics. News program detection is even harder in Indian context where closed caption text or program markers are not provided by TV news channels (not mandated by law). We propose a two-stage approach to classify news video segments. First, broadcast video shots are classified with multiple labels based on a set of audio-visual features. Second, sequences of these shot features are modeled to detect news programs. Another contribution of this work is the construction of a dataset of 120 hours of shot categories and news programs from Indian English news channels. We have experimented with SVM, HMM and CRF based classifiers and achieved a F1 score of 99% in detecting news programs while experimenting on our dataset.

References

1. P. K. Atrey, M. A. Hossain, S. A. El, and M. S. Kankanhalli. Multimodal fusion for multimedia analysis: a survey. Multimedia systems, 16(6):345--379, 2010.
2. S. P. Chatzis and Y. Demiris. The infinite-order conditional random field model for sequential data modeling. Pattern Analysis and Machine Intelligence, 35(6):1523--1534, 2013.
3. Y. Chen, Z. Li, M. Li, and W.-Y. Ma. Automatic classification of photographs and graphics. In ICME, pages 973--976. IEEE, 2006.
4. T. G. Dietterich. Machine learning for sequential data: A review. In Structural, syntactic, and statistical pattern recognition, pages 15--30. Springer, 2002.
5. N. Dimitrova, L. Agnihotri, and G. Wei. Video classification based on hmm using text and faces. In European Signal Processing Conference, 2000.
6. L. Elin and A. Lapides. Designing and Producing the Television Commercial. Pearson/A and B, 2004.
7. R. Kannao and P. Guha. Tv commercial detection using success based locally weighted kernel combination. In MultiMedia Modeling, pages 793--805. Springer, 2016.
8. W. Kim, J. Park, and C. Kim. A novel method for efficient indoor--outdoor image classification. Journal of Signal Processing Systems, 61(3):251--258, 2010.
9. J. Lafferty, A. McCallum, and F. C. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. 2001.
10. H. Li, B. Jou, J. G. Ellis, D. Morozoff, and S.-F. Chang. News rover: Exploring topical structures and serendipity in heterogeneous multimedia news. In ACM MM, pages 449--450. ACM, 2013.
11. L. R. Rabiner and B.-H. Juang. An introduction to hidden markov models. ASSP Magazine, IEEE, 3(1):4--16, 1986.
12. L. Rokach. Ensemble-based classifiers. Artif. Intell. Rev., 33(1--2):1--39, 2010.
13. M. Szummer and R. W. Picard. Indoor-outdoor image classification. In Workshop on Content-Based Access of Image and Video Database, pages 42--51. IEEE.
14. S. Vishwanathan, A. J. Smola, et al. Fast kernels for string and tree matching. Kernel methods in computational biology, pages 113--130, 2004.
15. Wikipedia. Dayparting -- Wikipedia, the free encyclopedia. https://en.wikipedia.org/wiki/Dayparting, 2016. {Online; accessed 22-July-2016}.
16. S. Xu, B. Feng, Z. Chen, and B. Xu. A general framework of video segmentation to logical unit based on conditional random fields. In ICMR, pages 247--254, 2013.
17. A. Yanagawa, W. Hsu, and S.-F. Chang. Anchor shot detection in trecvid-2005 broadcast news videos. Technical report, Columbia ADVENT Technical Report, 2005.
18. L. Zhang, Z. Zhu, and Y. Zhao. Robust commercial detection system. In ICME, pages 587--590, 2007.
19. H. Zhou, T. Hermans, A. V. Karandikar, and J. M. Rehg. Movie genre classification via scene categorization. In ACM MM, pages 747--750. ACM, 2010.
20. T. Zlitni, B. Bouaziz, and W. Mahdi. Automatic topics segmentation for tv news video using prior knowledge. Multimedia Tools and Applications, pages 1--28, 2015.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Computer vision

      • Computer vision problems

        • Video segmentation

      • Computer vision tasks

        • Scene understanding

  • Machine learning

    • Learning paradigms

      • Supervised learning

        • Structured outputs

        • Supervised learning by classification

      • Unsupervised learning

        • Topic modeling

    • Learning settings

      • Batch learning

    • Machine learning algorithms

      • Feature selection

    • Machine learning approaches

      • Bio-inspired approaches

        • Generative and developmental approaches

      • Markov decision processes

      • Rule learning