|
Title:
|
OBTAINING HUMAN BEHAVIOR PATTERNS USING HIDDEN MARKOV MODELS IN VIDEO A VIDEO VIGILANCE CONTEXT |
|
Author(s):
|
Héctor Gómez, Susana Arias, Ronaldo C. Prati |
|
ISBN:
|
978-989-8533-06-7 |
|
Editors:
|
Hans Weghorn, Leonardo Azevedo and Pedro Isaías |
|
Year:
|
2011 |
|
Edition:
|
Single |
|
Keywords:
|
Video vigilance; human behavior; Hidden Markov Model |
|
Type:
|
Short Paper |
|
First Page:
|
481 |
|
Last Page:
|
485 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
This paper uses Hidden Markov Models (HMMs) to obtain patterns of human behavior that can be used to distinguish between a normal and suspicious behavior into a video vigilance application problem. To this end, we have hand labeled the actions (events) that in videos where people are acting in either suspicious or normal manner. These labeled sequences are used to estimate transition probabilities for applying HMMs. These patterns are used to classify new test instances, obtaining classification errors of 17% for normal behavior and 20% for suspicious behavior. |
|
|
|
|
|
|
