Detecting Anomalies from Human Activities by an Autonomous Mobile Robot based on “Fast and Slow” Thinking

Muhammad Fikko Fadjrimiratno, Yusuke Hatae, Tetsu Matsukawa, Einoshin Suzuki

2021

Abstract

In this paper, we propose an anomaly detection method from human activities by an autonomous mobile robot which is based on “Fast and Slow Thinking”. Our previous method employes deep captioning and detects anomalous image regions based on image visual features, caption features, and coordinate features. However, detecting anomalous image region pairs is a more challenging problem due to the larger number of candidates. Moreover, realizing reminiscence, which represents re-checking past, similar examples to cope with overlooking, is another challenge for a robot operating in real-time. Inspired by “Fast and Slow Thinking” from the dual process theory, we achieve detection of these kinds of anomalies in real-time onboard an autonomous mobile robot. Our method consists of a fast module which models caption-coordinate features to detect single-region anomalies, and a slow module which models image visual features and overlapping image regions to detect also neighboring-region anomalies. The reminiscence is triggered by the fast module as a result of its anomaly detection and the slow module seeks for single-region anomalies in recent images. Experiments with a real robot platform show the superiority of our method to the baseline methods in terms of recall, precision, and AUC.

Download


Paper Citation


in Harvard Style

Fadjrimiratno M., Hatae Y., Matsukawa T. and Suzuki E. (2021). Detecting Anomalies from Human Activities by an Autonomous Mobile Robot based on “Fast and Slow” Thinking. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 943-953. DOI: 10.5220/0010313509430953


in Bibtex Style

@conference{visapp21,
author={Muhammad Fikko Fadjrimiratno and Yusuke Hatae and Tetsu Matsukawa and Einoshin Suzuki},
title={Detecting Anomalies from Human Activities by an Autonomous Mobile Robot based on “Fast and Slow” Thinking},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={943-953},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010313509430953},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Detecting Anomalies from Human Activities by an Autonomous Mobile Robot based on “Fast and Slow” Thinking
SN - 978-989-758-488-6
AU - Fadjrimiratno M.
AU - Hatae Y.
AU - Matsukawa T.
AU - Suzuki E.
PY - 2021
SP - 943
EP - 953
DO - 10.5220/0010313509430953
PB - SciTePress