Predicting Human Actions Taking into Account Object Affordances

Vibekananda Dutta , Teresa Zielińska

Abstract

Anticipating human intentional actions is essential for many applications involving service robots and social robots. Nowadays assisting robots must do reasoning beyond the present with predicting future actions. It is difficult due to its non-Markovian property and the rich contextual information. This task requires the subtle details inherent in human movements that may imply a future action. This paper presents a probabilistic method for action prediction in human-object interactions. The key idea of our approach is the description of the so-called object affordance, the concept which allows us to deliver a trajectory visualizing a possible future action. Extensive experiments were conducted to show the effectiveness of our method in action prediction. For evaluation we applied a new RGB-D activity video dataset recorded by the Sez3D depth sensors. The dataset contains several human activities composed out of different actions.
Author Vibekananda Dutta (FPAE)
Vibekananda Dutta,,
- Faculty of Power and Aeronautical Engineering
, Teresa Zielińska (FPAE / IAAM)
Teresa Zielińska,,
- The Institute of Aeronautics and Applied Mechanics
Journal seriesJournal of Intelligent & Robotic Systems, [Journal of Intelligent and Robotic Systems: Theory and Applications], ISSN 0921-0296, e-ISSN 1573-0409
Issue year2019
Vol93
No3-4
Pages745-761
Publication size in sheets0.8
Keywords in EnglishIntention recognition, Human-object relation, Object affordance, Action prediction, Feature extraction, Probability distribution
Keywords in original languageIntention recognition, Human-object relation, Object affordance, Action prediction, Feature extraction, Probability distribution
ASJC Classification1702 Artificial Intelligence; 1712 Software; 2207 Control and Systems Engineering; 2208 Electrical and Electronic Engineering; 2209 Industrial and Manufacturing Engineering; 2210 Mechanical Engineering
Abstract in original languageAnticipating human intentional actions is essential for many applications involving service robots and social robots. Nowadays assisting robots must do reasoning beyond the present with predicting future actions. It is difficult due to its non-Markovian property and the rich contextual information. This task requires the subtle details inherent in human movements that may imply a future action. This paper presents a probabilistic method for action prediction in human-object interactions. The key idea of our approach is the description of the so-called object affordance, the concept which allows us to deliver a trajectory visualizing a possible future action. Extensive experiments were conducted to show the effectiveness of our method in action prediction. For evaluation we applied a new RGB-D activity video dataset recorded by the Sez3D depth sensors. The dataset contains several human activities composed out of different actions.
DOIDOI:10.1007/s10846-018-0815-7
URL https://link.springer.com/article/10.1007%2Fs10846-018-0815-7
Languageen angielski
Score (nominal)100
Score sourcejournalList
ScoreMinisterial score = 100.0, 06-07-2020, ArticleFromJournal
Publication indicators WoS Citations = 3; GS Citations = 7.0; Scopus Citations = 3; Scopus SNIP (Source Normalised Impact per Paper): 2018 = 1.438; WoS Impact Factor: 2018 = 2.02 (2) - 2018=2.41 (5)
Citation count*7 (2020-06-22)
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back
Confirmation
Are you sure?