Call for Paper

CAE solicits original research papers for the October 2021 Edition. Last date of manuscript submission is September 30, 2021.

Read More

A Framework for Event Classification from Video Sequences using Bayesian Neural Network

Putte Gowda D., Padma M. C.. Published in Networks.

Communications on Applied Electronics
Year of Publication: 2016
Publisher: Foundation of Computer Science (FCS), NY, USA
Authors: Putte Gowda D., Padma M. C.
10.5120/cae2016652229

Putte Gowda D. and Padma M C.. A Framework for Event Classification from Video Sequences using Bayesian Neural Network. Communications on Applied Electronics 5(2):1-5, May 2016. BibTeX

@article{10.5120/cae2016652229,
	author = {Putte Gowda D. and Padma M. C.},
	title = {A Framework for Event Classification from Video Sequences using Bayesian Neural Network},
	journal = {Communications on Applied Electronics},
	issue_date = {May 2016},
	volume = {5},
	number = {2},
	month = {May},
	year = {2016},
	issn = {2394-4714},
	pages = {1-5},
	numpages = {5},
	url = {http://www.caeaccess.org/archives/volume5/number2/593-2016652229},
	doi = {10.5120/cae2016652229},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

Due to immense growth happened in multimedia field, research with videos and images have been received significant attention among the researchers. The automatic detection of the events presented in the video content may provide more useful information to the target audience. The motivation behind this approach is to design and develop a system for video event classification through video content analysis method using Bayesian neural network. Initially, the background from the video frames is estimated which is then segmented. Subsequently, features are extracted from the tracked objects and are classified to normal or abnormal event by applying Bayesian neural network classifier.UCSD Anomaly Detection Datasets is used for implementation. The performance of the proposed system is validated through the ROC curves and classification accuracy. From the comparative analysis made, the proposed technique obtained better results.

References

  1. UCSD Anomaly Detection Dataset from http://www.svcl.ucsd.edu/projects/anomaly/dataset.htm
  2. G. Lavee, E. Rivlin, M. Rudzsky, Understanding video events: a survey of methods for automatic interpretation of semantic occurrences in video, IEEE Trans. Syst. Man Cybern. Part C: Appl. Rev., vol. 39, no. 5, pp. 489504, 2009.
  3. P. Turaga, R. Chellappa, V. Subrahmanian, O. Udrea, Machine recognition of human activities: a survey, IEEE Trans. Circuits Syst. Video Technol., vol. 18, no. 11, pp. 14731488, 2008.
  4. Juan C. SanMiguel, Jos M. Martnez, ”A semantic-based probabilistic approach for real-time video event recognition”, Computer Vision and Image Understanding, vol. 116, pp.937952, 2012.
  5. Somboon Hongeng, Ram Nevatia, Francois Bremond, ”Video-based event recognition: activity representation and probabilistic recognition methods”, Computer Vision and Image Understanding, vol. 96, pp. 129162, 2004.
  6. Hsuan-Sheng Chen, Wen-Jiin Tsai, ”A framework for video event classification by modeling temporal context of multimodal features using HMM”, J. Vis. Commun. Image R., vol. 25, pp. 285295, 2014.
  7. Cheng-Chang Lien, Chiu-Lung Chiang, Chang-Hsing Lee, ”Scene-based event detection for baseball videos”, J. Vis. Commun. Image R., vol. 18, pp. 114, 2007.
  8. Gaurav Srivastava, Josiah A. Yoder, Johnny Park, Avinash C. Kak, ”Using objective ground-truth labels created by multiple annotators for improved video classification: A comparative study”, Computer Vision and Image Understanding, vol. 117, pp. 13841399, 2013.
  9. Jingen Liu, Qian Yu, Omar Javed, Saad Ali, Amir Tamrakar, Ajay Divakaran, Hui Cheng and Harpreet Sawhney, ”Video event recognition using concept attributes, IEEE Workshop on Applications of Computer Vision , pp.339-346, 2013.
  10. Xiang Ma,Schonfeld, D. ; Khokhar, A.A.,”Video Event Classification and Image Segmentation Based on Noncausal Multidimensional Hidden Markov Models,”IEEE Transactions on Image Processing,Vol.18,No.6,2009.
  11. Mao-Hsiung Hung and Chaur-Heh Hsieh, Event Detection of Broadcast Baseball Videos, Circuits and Systems for Video Technology, IEEE Transactions on, Vol.18 ,no. 12,pp. 1713 1726,2008.
  12. Weixin Li, Vijay Mahadevan, Member, and Nuno Vasconcelos,” Anomaly Detection and Localizationin Crowded Scenes, IEEE Transactions On Pattern Analysis And Machine Intelligence, Vol. 35,pp. 1-15, 2013.

Keywords

Bayesian Neural Network, Feature extraction, Object Segmentation, Tracking, Video Classification