Video Classification by Partitioned Frequency Spectra of Repeating Movements
In this paper we present a system for classifying videos
by frequency spectra. Many videos contain activities with repeating
movements. Sports videos, home improvement videos, or videos
showing mechanical motion are some example areas. Motion of these
areas usually repeats with a certain main frequency and several side
frequencies. Transforming repeating motion to its frequency domain
via FFT reveals these frequencies. Average amplitudes of frequency
intervals can be seen as features of cyclic motion. Hence determining
these features can help to classify videos with repeating movements.
In this paper we explain how to compute frequency spectra for video
clips and how to use them for classifying. Our approach utilizes series
of image moments as a function. This function again is transformed
into its frequency domain.
[1] Alfamovie. Media LLC. www.alfamovie.com.
[2] K. Ayyildiz and S. Conrad. Video Classification by Main Frequencies
of Repeating Movements. In 12th International Workshop on Image
Analysis for Multimedia Interactive Services (WIAMIS 2011), 2011.
[3] R. Babu and K. Ramakrishnan. Compressed domain human motion
recognition using motion history. In ICIP03, pages 321-324, 2003.
[4] F. Cheng, W. Christmas, and J. Kittler. Periodic human motion
description for sports video databases. In International Conference on
Pattern Recognition, 3:870-873, 2004.
[5] R. Cutler and L. S. Davis. Robust real-time periodic motion detection,
analysis, and applications. In IEEE Transactions on Pattern Analysis
and Machine Intelligence, 22(8):781-796, 2000.
[6] Dailymotion. Dailymotion S.A. www.dailymotion.com.
[7] Q. He and C. Debrunner. Individual recognition from periodic activity
using hidden markov models. In Workshop on Human Motion, pages
47-52, 2000.
[8] R. Lienhart. Indexing and retrieval of digital video sequences based on
automatic text recognition. In Fourth ACM international conference on
multimedia, pages 419-420, 1996.
[9] Q. Meng, B. Li, and H. Holstein. Recognition of human periodic movements
from unstructured information using a motion-based frequency
domain approach. In IVC, pages 795-809, 2006.
[10] N. Patel and I. Sethi. Audio characterization for video indexing. In
SPIE on Storage and Retrieval for Still Image and Video Databases,
pages 373-384, 1996.
[11] S. Pei and F. Chen. Semantic scenes detection and classification in
sports videos. In Conference on Computer Vision, Graphics and Image
Processing, pages 210-217, 2003.
[12] R. Polana and A. Nelson. Detection and recognition of periodic, nonrigid
motion. In International Journal of Computer Vision, 23:261-282, 1997.
[13] P. Tsai, M. Shah, K. Keiter, and T. Kasparis. Cyclic motion detection.
In Pattern Recognition, pages 1591-1603, 1994.
[14] W. Wong, W. Siu, and K. Lam. Generation of moment invariants and
their uses for character recognition. In Pattern Recognition Letters,
16:115-123, 1995.
[15] YouTube LLC. Youtube: Broadcast yourself. www.youtube.com.
[1] Alfamovie. Media LLC. www.alfamovie.com.
[2] K. Ayyildiz and S. Conrad. Video Classification by Main Frequencies
of Repeating Movements. In 12th International Workshop on Image
Analysis for Multimedia Interactive Services (WIAMIS 2011), 2011.
[3] R. Babu and K. Ramakrishnan. Compressed domain human motion
recognition using motion history. In ICIP03, pages 321-324, 2003.
[4] F. Cheng, W. Christmas, and J. Kittler. Periodic human motion
description for sports video databases. In International Conference on
Pattern Recognition, 3:870-873, 2004.
[5] R. Cutler and L. S. Davis. Robust real-time periodic motion detection,
analysis, and applications. In IEEE Transactions on Pattern Analysis
and Machine Intelligence, 22(8):781-796, 2000.
[6] Dailymotion. Dailymotion S.A. www.dailymotion.com.
[7] Q. He and C. Debrunner. Individual recognition from periodic activity
using hidden markov models. In Workshop on Human Motion, pages
47-52, 2000.
[8] R. Lienhart. Indexing and retrieval of digital video sequences based on
automatic text recognition. In Fourth ACM international conference on
multimedia, pages 419-420, 1996.
[9] Q. Meng, B. Li, and H. Holstein. Recognition of human periodic movements
from unstructured information using a motion-based frequency
domain approach. In IVC, pages 795-809, 2006.
[10] N. Patel and I. Sethi. Audio characterization for video indexing. In
SPIE on Storage and Retrieval for Still Image and Video Databases,
pages 373-384, 1996.
[11] S. Pei and F. Chen. Semantic scenes detection and classification in
sports videos. In Conference on Computer Vision, Graphics and Image
Processing, pages 210-217, 2003.
[12] R. Polana and A. Nelson. Detection and recognition of periodic, nonrigid
motion. In International Journal of Computer Vision, 23:261-282, 1997.
[13] P. Tsai, M. Shah, K. Keiter, and T. Kasparis. Cyclic motion detection.
In Pattern Recognition, pages 1591-1603, 1994.
[14] W. Wong, W. Siu, and K. Lam. Generation of moment invariants and
their uses for character recognition. In Pattern Recognition Letters,
16:115-123, 1995.
[15] YouTube LLC. Youtube: Broadcast yourself. www.youtube.com.
@article{"International Journal of Information, Control and Computer Sciences:62378", author = "Kahraman Ayyildiz and Stefan Conrad", title = "Video Classification by Partitioned Frequency Spectra of Repeating Movements", abstract = "In this paper we present a system for classifying videos
by frequency spectra. Many videos contain activities with repeating
movements. Sports videos, home improvement videos, or videos
showing mechanical motion are some example areas. Motion of these
areas usually repeats with a certain main frequency and several side
frequencies. Transforming repeating motion to its frequency domain
via FFT reveals these frequencies. Average amplitudes of frequency
intervals can be seen as features of cyclic motion. Hence determining
these features can help to classify videos with repeating movements.
In this paper we explain how to compute frequency spectra for video
clips and how to use them for classifying. Our approach utilizes series
of image moments as a function. This function again is transformed
into its frequency domain.", keywords = "action recognition, frequency feature, motion recognition,
repeating movement, video classification", volume = "6", number = "4", pages = "516-6", }