Title: Shape-based features for reliable action recognition using spectral regression discriminant analysis

Authors: G. Glorindal Selvam; D. Gnanadurai

Addresses: Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Tirunelveli, Tamil Nadu, India ' J.P. College of Engineering, Tenkasi, Tirunelveli District, Tamil Nadu, India

Abstract: This paper deals with the classification task of human activities in videos with learning using different image sequences as input methods. Image sequences of purely binary silhouette (or shape), that is Raw Silhouette Representation (RSR), distance transform (DT) images of RSR, edge images of RSR, Silhouette History Image (SHI) and Silhouette Energy Image (SEI), image sequences of Wavelet Transform (WT) are used for training and testing using spectral regression discriminant analysis. Hausdorff distance was used for similarity measures to match the embedded action trajectories. Then action classification is achieved in a K-nearest neighbour framework. Using these different input methods we achieved 100% for all the cases except WT cases. From the results, it is evident that SHI and SEI are effective input method in terms of time and space consumption.

Keywords: action recognition; SEI; silhouette energy image; SHI; silhouette history image; SRDA; spectral regression discriminant analysis; edge representation; distance transform; wavelet transform; shape features; action classification; human activities; videos; image sequences; similarity measures; K-nearest neighbour; k-NN.

DOI: 10.1504/IJSISE.2016.080271

International Journal of Signal and Imaging Systems Engineering, 2016 Vol.9 No.6, pp.379 - 387

Received: 15 Aug 2013
Accepted: 22 May 2014

Published online: 10 Nov 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article