2012 |
Christos Georgakis, Petros Maragos, Georgios Evangelopoulos, Dimitrios Dimitriadis Dominant spatio-temporal modulations and energy tracking in videos: Application to interest point detection for action recognition Conference Proceedings - International Conference on Image Processing, ICIP, 2012, ISSN: 15224880. Abstract | BibTeX | Links: [PDF] @conference{176, title = {Dominant spatio-temporal modulations and energy tracking in videos: Application to interest point detection for action recognition}, author = { Christos Georgakis and Petros Maragos and Georgios Evangelopoulos and Dimitrios Dimitriadis}, url = {http://robotics.ntua.gr/wp-content/uploads/publications/GMED_SpatioTemporModulationsEnergyTrackVideos-InterestPointDetectActionRecogn_ICIP2012.pdf}, doi = {10.1109/ICIP.2012.6466966}, issn = {15224880}, year = {2012}, date = {2012-01-01}, booktitle = {Proceedings - International Conference on Image Processing, ICIP}, pages = {741--744}, abstract = {The presence of multiband amplitude and frequency modulations (AM-FM) in wideband signals, such as textured images or speech, has led to the development of efficient multicomponent modulation models for low-level image and sound analysis. Moreover, compact yet descriptive representations have emerged by tracking, through non-linear energy operators, the dominant model components across time, space or frequency.In this paper, we propose a generalization of such approaches in the 3D spatio-temporal domain and explore the benefits of incorporating the Dominant Component Analysis scheme for interest point detection in videos for action recognition. Within this framework, actions are implicitly considered as manifestations of spatio-temporal oscillations in the dynamic visual stream. Multiband filtering and energy operators are applied to track the source energy in both spatial and temporal frequency bands. A new measure for extracting keypoint locations is formulated as the temporal dominant energy computed over the locally dominant modulation components, in terms of spatial modulation energy, of the input video frames. Theoretical formulation is supported by evaluation and comparisons in human action classification, which demonstrate the potential of the proposed detector.}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The presence of multiband amplitude and frequency modulations (AM-FM) in wideband signals, such as textured images or speech, has led to the development of efficient multicomponent modulation models for low-level image and sound analysis. Moreover, compact yet descriptive representations have emerged by tracking, through non-linear energy operators, the dominant model components across time, space or frequency.In this paper, we propose a generalization of such approaches in the 3D spatio-temporal domain and explore the benefits of incorporating the Dominant Component Analysis scheme for interest point detection in videos for action recognition. Within this framework, actions are implicitly considered as manifestations of spatio-temporal oscillations in the dynamic visual stream. Multiband filtering and energy operators are applied to track the source energy in both spatial and temporal frequency bands. A new measure for extracting keypoint locations is formulated as the temporal dominant energy computed over the locally dominant modulation components, in terms of spatial modulation energy, of the input video frames. Theoretical formulation is supported by evaluation and comparisons in human action classification, which demonstrate the potential of the proposed detector. |
Copyright Notice:
Some material presented is available for download to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
The work already published by the IEEE is under its copyright. Personal use of such material is permitted. However, permission to reprint/republish the material for advertising or promotional purposes, or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of the work in other works must be obtained from the IEEE.