A survey about view-invariant human action recognition

Human action recognition has been extensively studied with a lot of real life application. Many methods have been proposed and achieved promising results when the input video captured from the same viewpoints. However, their accuracy decreases significantly under viewpoint changing. The reason is th...

Full description

Saved in:
Bibliographic Details
Published in2017 56th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE) pp. 699 - 704
Main Authors Trong, Nghia Pham, Minh, Anh Truong, Nguyen, Hung, Kazunori, Kotani, Le Hoai, Bac
Format Conference Proceeding
LanguageEnglish
Published The Society of Instrument and Control Engineers - SICE 01.09.2017
Subjects
Biological system modeling
cross-view action recognition
Feature extraction
Hidden Markov models
multi-view action dataset
multi-view action recognition
review
Robustness
Skeleton
Survey
Testing
Three-dimensional displays
Online AccessGet full text

Cover

More Information
Summary:Human action recognition has been extensively studied with a lot of real life application. Many methods have been proposed and achieved promising results when the input video captured from the same viewpoints. However, their accuracy decreases significantly under viewpoint changing. The reason is that action appearance is quite different when looking from a different angle. To overcome this problem, many researchers have shifted their focus on how to develop a robust action recognition method where training and testing are carried on a different viewpoint. The aim of this paper is to give a systematic review of current methods for view-invariant action recognition and how they overcome the viewpoint change. Moreover, this paper also introduces multi-view action recognition datasets which are widely used for testing the view-invariant ability. Benchmarks of various techniques on these datasets are also provided to show the current state of research.
DOI:10.23919/SICE.2017.8105762