Paper Info
Title
2DHOOF-2DPCA contour based optical flow algorithm for human activity recognition
Abstract
A novel algorithm for human activity recognition is presented in this paper. This approach is based on a new 2D representation for the Histogram of Oriented Optical Flow (2DHOOF) describing the motion of the actor's contour, where one multi-layer 2D-histogram per video is constructed. Each histogram layer consists of 2D bins (layers) that represent different range of angles. Applying our 2DHOOF features descriptors on the actor's contour reduces the storage requirement and the computation complexity since a sparse optical flow is calculated instead of dense optical flow. In addition, it is robust to variations in the background, actor's appearance, and imperfections in actor's contour. This new 2D representation allows the usage of the Two Dimensional Principle Component Analyses (2DPCA) which maintains the spatial relation of the motion, and provides further high accuracy and low computation complexity. Experimental results applied on the Weizmann and IXMAS datasets achieved the highest reported recognition accuracy and the fastest runtime compared to recent methods.
Year
DOI
Venue
2013
10.1109/MWSCAS.2013.6674896
Midwest Symposium on Circuits and Systems Conference Proceedings
Keywords
Field
DocType
principal component analysis,object recognition,computational complexity
Spatial relation,Histogram,Computer science,Artificial intelligence,Computer vision,Activity recognition,Pattern recognition,Algorithm,Optical flow,Principal component analysis,Computation complexity,Computational complexity theory,Cognitive neuroscience of visual object recognition
Conference
ISSN
Citations 
PageRank 
1548-3746
1
0.34
References 
Authors
11
3
Name
Order
Citations
PageRank
fadwa fawzy110.34
Moataz M. Abdelwahab2288.48
Wasfy B. Mikhael37676.27