Common-sense reasoning for human action recognition

作     者：del Rincon, Jesus Martinez Santofimia, Maria J. Nebel, Jean-Christophe 

作者机构：Queens Univ Belfast Inst Elect Commun & Informat Technol ECIT Belfast BT3 9DT Antrim North Ireland Univ Castilla La Mancha Comp Engn Sch Dept Technol & Informat Syst E-13071 Ciudad Real Spain Univ Kingston Digital Imaging Res Ctr London KT1 2EE England 

出 版 物：《PATTERN RECOGNITION LETTERS》 (模式识别快报)

年 卷 期：2013年第34卷第15期

页      面：1849-1860页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Spanish Ministry of Economy and Competitiveness [DREAMS TEC2011-28666-C04-03] EPSRC [EP/K004379/1, EP/H049606/1, EP/J006238/1, EP/G034303/1] Funding Source: UKRI 

主　　题：Common sense Artificial intelligence Action recognition Bag of words Computer vision 

摘      要：This paper presents a novel method that leverages reasoning capabilities in a computer vision system dedicated to human action recognition. The proposed methodology is decomposed into two stages. First, a machine learning based algorithm - known as bag of words - gives a first estimate of action classification from video sequences, by performing an image feature analysis. Those results are afterward passed to a common-sense reasoning system, which analyses, selects and corrects the initial estimation yielded by the machine learning algorithm. This second stage resorts to the knowledge implicit in the rationality that motivates human behaviour. Experiments are performed in realistic conditions, where poor recognition rates by the machine learning techniques are significantly improved by the second stage in which common-sense knowledge and reasoning capabilities have been leveraged. This demonstrates the value of integrating common-sense capabilities into a computer vision pipeline. (C) 2012 Elsevier B.V. All rights reserved.