Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A MULTI-PERSPECTIVE APPROACH TO ANOMALY DETECTION FOR SELF-AWARE EMBODIED AGENTS

Abstract: 

This paper focuses on multi-sensor anomaly detection for moving cognitive agents using both external and private first-person visual observations. Both observation types are used to characterize agents’ motion in a given environment. The proposed method generates locally uniform motion models by dividing a Gaussian process that approximates agents’ displacements on the scene and provides a Shared Level (SL) self-awareness based on Environment Centered (EC) models. Such models are then used to train in a semi-unsupervised way a set of Generative Adversarial Networks (GANs) that produce an estimation of external and internal parameters of moving agents. Obtained results exemplify the feasibility of using multi-perspective data for predicting and analyzing trajectory information.

up
0 users have voted:

Paper Details

Authors:
Mohamad Baydoun, Mahdyar Ravanbakhsh, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Andrea Cavallaro, Carlo S. Regazzoni
Submitted On:
18 April 2018 - 10:40am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Lucio Marcenaro
Paper Code:
SS-L2.5
Document Year:
2018
Cite

Document Files

SS-L2.5 A MULTI-PERSPECTIVE APPROACH TO ANOMALY DETECTION FOR SELF-AWARE EMBODIED AGENTS.pdf

(4)

Subscribe

[1] Mohamad Baydoun, Mahdyar Ravanbakhsh, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Andrea Cavallaro, Carlo S. Regazzoni, "A MULTI-PERSPECTIVE APPROACH TO ANOMALY DETECTION FOR SELF-AWARE EMBODIED AGENTS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2964. Accessed: Apr. 20, 2019.
@article{2964-18,
url = {http://sigport.org/2964},
author = {Mohamad Baydoun; Mahdyar Ravanbakhsh; Damian Campo; Pablo Marin; David Martin; Lucio Marcenaro; Andrea Cavallaro; Carlo S. Regazzoni },
publisher = {IEEE SigPort},
title = {A MULTI-PERSPECTIVE APPROACH TO ANOMALY DETECTION FOR SELF-AWARE EMBODIED AGENTS},
year = {2018} }
TY - EJOUR
T1 - A MULTI-PERSPECTIVE APPROACH TO ANOMALY DETECTION FOR SELF-AWARE EMBODIED AGENTS
AU - Mohamad Baydoun; Mahdyar Ravanbakhsh; Damian Campo; Pablo Marin; David Martin; Lucio Marcenaro; Andrea Cavallaro; Carlo S. Regazzoni
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2964
ER -
Mohamad Baydoun, Mahdyar Ravanbakhsh, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Andrea Cavallaro, Carlo S. Regazzoni. (2018). A MULTI-PERSPECTIVE APPROACH TO ANOMALY DETECTION FOR SELF-AWARE EMBODIED AGENTS. IEEE SigPort. http://sigport.org/2964
Mohamad Baydoun, Mahdyar Ravanbakhsh, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Andrea Cavallaro, Carlo S. Regazzoni, 2018. A MULTI-PERSPECTIVE APPROACH TO ANOMALY DETECTION FOR SELF-AWARE EMBODIED AGENTS. Available at: http://sigport.org/2964.
Mohamad Baydoun, Mahdyar Ravanbakhsh, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Andrea Cavallaro, Carlo S. Regazzoni. (2018). "A MULTI-PERSPECTIVE APPROACH TO ANOMALY DETECTION FOR SELF-AWARE EMBODIED AGENTS." Web.
1. Mohamad Baydoun, Mahdyar Ravanbakhsh, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Andrea Cavallaro, Carlo S. Regazzoni. A MULTI-PERSPECTIVE APPROACH TO ANOMALY DETECTION FOR SELF-AWARE EMBODIED AGENTS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2964