File(s) under permanent embargo
Fast binary-based video descriptors for action recognition
conference contribution
posted on 2016-01-01, 00:00 authored by R Leyva, V Sanchez, Chang-Tsun LiChang-Tsun LiAction recognition is one of the top challenges in computer vision. In this paper, we present two binary-based video descriptors with outstanding characteristics in terms of recognition rate, computational times and memory requirements. The descriptors are called Binary Wavelet Differences (BWD) and Binary Dense Trajectories (BDT). Our proposed descriptors are based on the local binary patterns and produce binary vectors with a very low dimensionality. Specifically, we propose to analyze the spatio-temporal support regions of a video sequence to generate binary strings via wavelets patterns. We also propose to encode the motion information obtained from optical flow into a compact binary representation. Our evaluations on the KTH and UCF50 datasets demonstrate that our proposed descriptors achieve very competitive recognition accuracy. Moreover, they are able to attain shorter computational times and smaller memory requirements. Specifically, our proposed descriptors can be calculated up to 20X faster than orientation-based descriptors and require up to 225X less memory. Due to its binary nature, associated calculations in action recognition, e.g. clustering and classification, can be done up to 40X faster than state-of-the-art descriptors. Finally, our descriptors require codebooks with 2X fewer words than those required by other state-of-the-art descriptors.
History
Event
International Association for Pattern Recognition. Conference (2016 : Gold Coast, Qld.)Series
International Association for Pattern Recognition ConferencePagination
1 - 8Publisher
Institute of Electrical and Electronics EngineersLocation
Gold Coast, Qld.Place of publication
Piscataway, N.J.Publisher DOI
Start date
2016-11-30End date
2016-12-02ISBN-13
9781509028962Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
2016, IEEEEditor/Contributor(s)
A Liew, B Lovell, C Fookes, J Zhou, Y Gao, M Blumenstein, Z WangTitle of proceedings
DICTA 2016 : Proceedings of the 2016 International Conference on Digital Image Computing: Techniques and ApplicationsUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC