Publication Type : Conference Paper
Publisher : 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Source : 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA) (2013)
Url : http://ieeexplore.ieee.org/document/6691507/?arnumber=6691507
Keywords : bag-of-words framework, behavioural sciences computing, Biological system modeling, densely sampled based representations, Detectors, Feature extraction, Harris 3D points information, Hidden Markov models, Histograms, HMDB51 dataset, human action recognition, human behaviour analysis methods, human behaviour recognition, human body parts, image motion analysis, image representation, local representation, region-of-interest representation, ROI based feature representation, spatio-temporal interest points representation, STIP representation, Three-dimensional displays, Trajectory, UCF50 dataset, video collections, Video signal processing, Videos, YouTube
Campus : Coimbatore
School : School of Engineering
Department : Electrical and Electronics
Verified : Yes
Year : 2013
Abstract : Automatic analysis of human behaviour in large collections of videos is gaining interest, even more so with the advent of file sharing sites such as YouTube. Human behaviour analysis methods can be categorised into three classes based on the type of features. The three representations are local, region of interest and densely sampled based representations. Local feature representation, such as Spatio-Temporal Interest Points (STIP), are quite popular for modelling temporal aspects in human action recognition. Region of Interest (ROI) based feature representations try to capture and represent human body part regions. Densely sampled representations capture information at uniformly spaced intervals spread in space and temporal directions of the given video. In this paper, we investigate the effect of human body part (ROI) information in large scale action recognition. Further, we also investigate the effect of its fusion with Harris 3D points (local representation) information and densely sampled representations. All experiments use a Bag-of-Words framework. We present our results on large class benchmark databases such as the UCF50 and HMDB51 datasets.
Cite this Research Publication : Dr. Oruganti Venkata Ramana Murthy, Radwan, I., Dhall, A., and Goecke, R., “On the Effect of Human Body Parts in Large Scale Human Behaviour Recognition”, in 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2013.