Exploring trace transform for robust human action recognition

doi:10.1016/j.patcog.2013.06.006

2013-12-01

PRE

Stefanos Kollias

DOI：10.1016/j.patcog.2013.06.006

原文链接

原文求助

摘要

En 中文

Machine based human action recognition has become very popular in the last decade. Automatic unattended surveillance systems, interactive video games, machine learning and robotics are only few of the areas that involve human action recognition. This paper examines the capability of a known transform, the so-called Trace, for human action recognition and proposes two new feature extraction methods based on the specific transform. The first method extracts Trace transforms from binarized silhouettes, representing different stages of a single action period. A final history template composed from the above transforms, represents the whole sequence containing much of the valuable spatiotemporal information contained in a human action. The second, involves Trace for the construction of a set of invariant features that represent the action sequence and can cope with variations usually appeared in video capturing. The specific method takes advantage of the natural specifications of the Trace transform, to produce noise robust features that are invariant to translation, rotation, scaling and are effective, simple and fast to create. Classification experiments performed on two well known and challenging action datasets (KTH and Weizmann) using Radial Basis Function (RBF) Kernel SVM provided very competitive results indicating the potentials of the proposed techniques. (C) 2013 Elsevier Ltd. All rights reserved.

Keyword:

Human action recognition

Motion analysis

Action classification

Trace transform

AI总结

对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Pattern Recognition

IF:

7.6

论文数:

1.3W

被引数:

4.5W

机构

National Technical University of Athens

学者数:

9.7K

论文数: 9.5K

被引数: 8.2K

引用论文

Ru^IIcomplexes of 1,2,3-triazole appended tertiary phosphines, [P(Ph){(o-C₆H₄)(1,2,3-N₃C(Ph)CH}₂] and [P(Ph){o-C₆H₄(CCH)-(1,2,3-N₃-Ph)}₂]: highly active catalysts for transfer hydrogenation of carbonyl/nitro compounds and for α-alkylation of ketones

Dalton Transactions

IF0

2022-01-01

PREAI

Pavan K. Namdeo; Sonu Sheokand; Basvaraj S. Kote; Latchupatula Radhakrishna; Harish S. Kunchur; Prateek Saini; Srinivasan Ramakrishnan; Maravanji S. Balakrishna

City models in theory and practice: a cross-cultural perspective

Urban Morphology

IF0

2011-03-11