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

facebooktwittermailshare

An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation

Abstract: 

This paper presents a novel problem of detection and localization of anomalous events due to a certain class of objects in video data with applications to smart surveillance. A baseline system is proposed that uses a convolutional neural network (CNN) to generate pixel level masks corresponding to objects of a class of interest. A Restricted Boltzmann Machine (RBM) is then trained on the mask to learn patterns of normal behavior. The free energy of the RBM is used to detect the presence of an anomaly while the reconstruction error is used to localize the anomaly. Our approach is scalable to a low power and energy constrained setting with 1930.48 ms of latency and 4826 mJ energy consumed per frame on a mGPU.

up
0 users have voted:

Paper Details

Authors:
Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay
Submitted On:
16 April 2018 - 11:54am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Burhan Ahmad Mudassar
Paper Code:
MLSP-P6
Document Year:
2018
Cite

Document Files

ICASSP 2018 Poster.pptx

(4 downloads)

Subscribe

[1] Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay, "An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2895. Accessed: Apr. 20, 2018.
@article{2895-18,
url = {http://sigport.org/2895},
author = {Burhan Ahmad Mudassar; Jong Hwan Ko; Saibal Mukhopadhyay },
publisher = {IEEE SigPort},
title = {An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation},
year = {2018} }
TY - EJOUR
T1 - An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation
AU - Burhan Ahmad Mudassar; Jong Hwan Ko; Saibal Mukhopadhyay
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2895
ER -
Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay. (2018). An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation. IEEE SigPort. http://sigport.org/2895
Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay, 2018. An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation. Available at: http://sigport.org/2895.
Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay. (2018). "An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation." Web.
1. Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay. An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2895