Classification of Indecent Video by Low Complexity Repetitive Motion Detection
(2008) 37th Applied Imagery Pattern Recognition Workshop p.1-7- Abstract
- This paper proposes a fast method for detection of indecent video content using repetitive motion analysis. Unlike skin detection, motion will provide invariant features irrespective of race and color. The video material to be evaluated is divided into short fixed-length sections. By filtering different combinations of B-frame motion vectors using adjacency in time and space, one dominant motion vector is constructed for each frame. The power spectral density estimate of this dominant motion vector is then computed using a periodogram with a Hamming window. The resulting power spectrum is then subjected to a Slepian selection window to restrict the spectrum to a limited frequency range typical of indecent movement, as empirically derived... (More)
- This paper proposes a fast method for detection of indecent video content using repetitive motion analysis. Unlike skin detection, motion will provide invariant features irrespective of race and color. The video material to be evaluated is divided into short fixed-length sections. By filtering different combinations of B-frame motion vectors using adjacency in time and space, one dominant motion vector is constructed for each frame. The power spectral density estimate of this dominant motion vector is then computed using a periodogram with a Hamming window. The resulting power spectrum is then subjected to a Slepian selection window to restrict the spectrum to a limited frequency range typical of indecent movement, as empirically derived by us. A threshold detector is then applied to detect repetitive motion in video sections. However, there are instances where repetitive motion occurs in these shorter sections without the video as a whole being indecent. As a second step, an additional detector can be employed to determine if the sections over a longer period of time can be classified as containing indecent material. The proposed method is resource efficient and do not require the typical IDCT step of video decoding. Further, the computationally expensive spectral estimation calculations are done using only one value per frame. Evaluations performed using a restricted set of videos show promising results with high true positive probability (>85%) for a low false positive probability (<10%) for the repetitive motion detection. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1274728
- author
- Endeshaw, Tadilo
; Garcia, Johan
and Jakobsson, Andreas
LU
- organization
- publishing date
- 2008
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- video coding, indecent video classification, repetitive motion detection, indecent video content detection, B-frame motion vector filtering, power spectral density estimation, periodogram, Hamming window, Slepian selection window, threshold detector
- host publication
- 2008 37th IEEE Applied Imagery Pattern Recognition Workshop
- pages
- 1 - 7
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 37th Applied Imagery Pattern Recognition Workshop
- conference dates
- 2008-10-15
- external identifiers
-
- scopus:69949099874
- ISSN
- 1550-5219
- language
- English
- LU publication?
- yes
- id
- 8ffc7bfb-576c-4972-b9c9-df7663f56250 (old id 1274728)
- alternative location
- http://ieeexplore.ieee.org/stampPDF/getPDF.jsp?tp=&arnumber=04906438&isnumber=4906435&tag=1
- date added to LUP
- 2016-04-01 14:25:05
- date last changed
- 2022-03-21 23:56:18
@inproceedings{8ffc7bfb-576c-4972-b9c9-df7663f56250, abstract = {{This paper proposes a fast method for detection of indecent video content using repetitive motion analysis. Unlike skin detection, motion will provide invariant features irrespective of race and color. The video material to be evaluated is divided into short fixed-length sections. By filtering different combinations of B-frame motion vectors using adjacency in time and space, one dominant motion vector is constructed for each frame. The power spectral density estimate of this dominant motion vector is then computed using a periodogram with a Hamming window. The resulting power spectrum is then subjected to a Slepian selection window to restrict the spectrum to a limited frequency range typical of indecent movement, as empirically derived by us. A threshold detector is then applied to detect repetitive motion in video sections. However, there are instances where repetitive motion occurs in these shorter sections without the video as a whole being indecent. As a second step, an additional detector can be employed to determine if the sections over a longer period of time can be classified as containing indecent material. The proposed method is resource efficient and do not require the typical IDCT step of video decoding. Further, the computationally expensive spectral estimation calculations are done using only one value per frame. Evaluations performed using a restricted set of videos show promising results with high true positive probability (>85%) for a low false positive probability (<10%) for the repetitive motion detection.}}, author = {{Endeshaw, Tadilo and Garcia, Johan and Jakobsson, Andreas}}, booktitle = {{2008 37th IEEE Applied Imagery Pattern Recognition Workshop}}, issn = {{1550-5219}}, keywords = {{video coding; indecent video classification; repetitive motion detection; indecent video content detection; B-frame motion vector filtering; power spectral density estimation; periodogram; Hamming window; Slepian selection window; threshold detector}}, language = {{eng}}, pages = {{1--7}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Classification of Indecent Video by Low Complexity Repetitive Motion Detection}}, url = {{http://ieeexplore.ieee.org/stampPDF/getPDF.jsp?tp=&arnumber=04906438&isnumber=4906435&tag=1}}, year = {{2008}}, }