Web of Science: 1 citations, Scopus: 6 citations, Google Scholar: citations
Human action recognition based on estimated weak poses
Gong, Wenjuan (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Gonzàlez i Sabaté, Jordi (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Roca i Marvà, Francesc Xavier (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)

Date: 2012
Abstract: We present a novel method for human action recognition (HAR) based on estimated poses from image sequences. We use 3D human pose data as additional information and propose a compact human pose representation, called a weak pose, in a low-dimensional space while still keeping the most discriminative information for a given pose. With predicted poses from image features, we map the problem from image feature space to pose space, where a Bag of Poses (BOP) model is learned for the final goal of HAR. The BOP model is a modified version of the classical bag of words pipeline by building the vocabulary based on the most representative weak poses for a given action. Compared with the standard k-means clustering, our vocabulary selection criteria is proven to be more efficient and robust against the inherent challenges of action recognition. Moreover, since for action recognition the ordering of the poses is discriminative, the BOP model incorporates temporal information: in essence, groups of consecutive poses are considered together when computing the vocabulary and assignment. We tested our method on two well-known datasets: HumanEva and IXMAS, to demonstrate that weak poses aid to improve action recognition accuracies. The proposed method is scene-independent and is comparable with the state-of-art method.
Note: Altres ajuts: Avanza I+D ViCoMo (TSI-020400-2009-133) and DiCoMa (TSI-020400-2011-55)
Note: Número d'acord de subvenció MICINN/CSD2007-00018
Note: Número d'acord de subvenció MICINN/TIN2009-14501-C02-01
Note: Número d'acord de subvenció MICINN/TIN2009-14501-C02-02
Rights: Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original. Creative Commons
Language: Anglès.
Document: article ; recerca ; publishedVersion
Subject: Bag of words ; Gaussian process regression ; Human action recognition ; Human pose estimation
Published in: Eurasip Journal on Advances in Signal Processing, Vol. 2012 (July 2012) , art. 162, ISSN 1687-6180

DOI: 10.1186/1687-6180-2012-162

14 p, 2.2 MB

The record appears in these collections:
Articles > Research articles
Articles > Published articles

 Record created 2019-04-25, last modified 2019-05-23

   Favorit i Compartir