Paper Info
Title
VisLoiter+: An Entropy Model-Based Loiterer Retrieval System with User-Friendly Interfaces.
Abstract
It is very difficult to fully automate the detection of loitering behavior in video surveillance, therefore humans are often required for monitoring. Alternatively, we could provide a list of potential loiterer candidates for a final yes/no judgment of a human operator. Our system, VisLoiter+, realizes this idea with a unique, user-friendly interface and by employing an entropy model for improved loitering analysis. Rather than using only frequency of appearance, we expand the loiter analysis with new methods measuring the amount of person movements across multiple camera views. The interface gives an overview of loiterer candidates to show their behavior at a glance, complemented by a lightweight video playback for further details about why a candidate was selected. We demonstrate that our system outperforms state-of-the-art solutions using real-life data sets.
Year
DOI
Venue
2018
10.1145/3206025.3206091
ICMR '18: International Conference on Multimedia Retrieval Yokohama Japan June, 2018
Keywords
Field
DocType
Loiterer Retrieval, Loitering Discovery, Video Surveillance, Entropy Model, Heatmap, Ranking System
Data set,Human operator,Ranking,Computer science,Loiter,Human–computer interaction,Artificial intelligence,User Friendly,Machine learning
Conference
ISBN
Citations 
PageRank 
978-1-4503-5046-4
0
0.34
References 
Authors
7
4
Name
Order
Citations
PageRank
Maguell L. T. L. Sandifort100.34
Jianquan Liu233.13
Shoji Nishimura332.79
Wolfgang Hürst447056.75