Application of physical video features in classification problem

Roman Kazantsev, Sergey Zvezdakov, Dmitriy Vatolin

Abstract


In this paper we propose hand-crafted physical features for video that can be used in a wide range of different regression and classification problems in video processing. For evaluation of resulted set of features we consider video genre classification problem among four classes: animation, drone video, computer game and sports. In this work we describe an automatic approach for video dataset creation, its augmentation and anomaly detection. In order to arrange the experiment we create dataset from 14271 samples, having a minimal number of samples per class is equal to 2700. Using gradient boosting we trained decision tree ensemble model with average precision and recall equal to 86.15% and 86.12% on test dataset. Also, other machine learning methods such as linear regression, naïve Gaussian classificator, support vector machine and random forest demonstrated worse results. The most relevant physical video features are two blur metrics using Laplacian operator and based on re-blur effect.

Full Text:

PDF (Russian)

References


K. Sivaraman, G. Somappa, “Moviescope: Movie trailer classification using deep neural networks,” University of Virginia, 2016.

R. Zumer, S. Ratté, “Color-independent classification of animation video,” IJMIR, pp. 187–196, 2018.

Narra Dhana Lakshmi, Y. Madhavee Latha, A. Damodaram, K. Lakshmi Prasanna, “Implementation of Content Based Video Classification using Hidden Markov Model,” IEEE 7th International Advance Computing Conference, 2017.

K. Simonyan, A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” International Conference on Learning Representations, 2015.

O. Murashko, “Using machine learning to select and optimise multiple objectives in media compression,” PhD thesis, University of St. Andrews, 2018.

K. Simonyan, S. Grishin, D. Vatolin, D. Popov, “Fast video super-resolution via classification,” 15th IEEE International Conference on Image Processing, pp. 349–352, 2008.

F. Crete, T. Dolmiere, P. Ladret, M. Nicolas, “The Blur Effect: Perception and Estimation with a New No-Reference Perceptual Blur Metric,” Human Vision and Electronic Imaging XII, pp. 1–11, 2007.

R. Bansal, G. Raj, T. Choudhury, “Blur image detection using Laplacian operator and Open-CV,” IEEE System Modeling & Advancement in Research Trends, pp. 63–67, 2016.

TU-T Recommendation P.910: Subjective video quality assessment methods for multimedia applications, 1999. – 37 p.

Brailovskij I., Solomeshh N. Modelirovanie kachestva dlja videokodirovanija // Informacionnye tehnologii. – 2012. — #1 – S. 42–48.

Habibullina N.A., “Razrabotka novyh metodov analiza kachestva videokodekov i optimizacija sistem szhatija videoinformacii, Dissertacija na soiskanie uchenoj stepeni kandidata tehnicheskih nauk,” MFTI, 2014.

Parshin A. E., Glazistov I. V. Algoritm poiska dublikatov v baze videoposledovatel'nostej na osnove sopostavlenija ierarhii smen scen // Novye informacionnye tehnologii v avtomatizirovannyh sistemah. – 2009. – # 12. – S. 51–61.

Pedregosa et al., “Scikit-learn: Machine Learning in Python,” JMLR 12, pp. . 2825–2830, 2011.

T. Chen, C. Guestrin, “Xgboost: A scalable tree boosting system,” arXiv:1603.02754, 2016

K. Sivaraman, G. Somappa, MovieScope, GitHub repository, https://github.com/maximus009/MovieScope

x264, https://www.videolan.org/developers/x264.html

youtube-dl, https://rg3.github.io/youtube-dl/


Refbacks

  • There are currently no refbacks.


Abava   FRUCT 2019

ISSN: 2307-8162