ViBe: A Universal Background Subtraction Algorithm for Video Sequences

This paper presents a technique for motion detection that incorporates several innovative mechanisms. For example, our proposed technique stores, for each pixel, a set of values taken in the past at the same location or in the neighborhood. It then compares this set to the current pixel value in ord...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing Vol. 20; no. 6; pp. 1709 - 1724
Main Authors: Barnich, O, Van Droogenbroeck, M
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.06.2011
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Adaptation model
Algorithm
Algorithms
Applied sciences
Artificial Intelligence
Background
Background model
Background subtraction
Benchmarking
C code
C/C++
Code
Comparision
Computation
Computational modeling
Computer science; control theory; systems
Computer vision
Detection, estimation, filtering, equalization, prediction
Electrical & electronics engineering
Embedded systems
Engineering, computing & technology
Estimation
Exact sciences and technology
Exponential filtering
Fast algorithm
Foreground
Ghost
Image color analysis
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
image motion analysis
Image processing
image segmentation
Information, signal and communications theory
Ingénierie électrique & électronique
Ingénierie, informatique & technologie
Initialization
Kernel density estimation
Learning
learning (artificial intelligence)
Lighting
Mathematical models
Mixture of Gaussians
Motion
Motion analysis
Motion detection
OpenCV
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
Pixel
Pixel classification
Pixels
Pseudo-code
Random sampling
Real-time processing
real-time systems
Reproducibility of Results
Segmentation
Sensitivity and Specificity
Signal and communications theory
Signal processing
Signal Processing, Computer-Assisted
Signal representation. Spectral analysis
Signal, noise
Smart camera
State of the art
Stores
Studies
Subtraction
Subtraction Technique
Subtraction techniques
surveillance
Telecommunications and information theory
ViBe
Video processing
Video Recording - methods
video signal processing
vision and scene understanding
Performance evaluation
State of the art
Image processing
Video signal
Video signal processing
Learning
Credal approach
Image sequence
vision and scene understanding
pixel classification
Motion detection
surveillance
Localization
learning (artificial intelligence)
Monitoring
Computer vision
Background
Background subtraction
Algorithm
Real time system
Image motion analysis
Image segmentation
real-time systems
Signal processing
Artificial intelligence
ISSN:1057-7149, 1941-0042, 1941-0042
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a technique for motion detection that incorporates several innovative mechanisms. For example, our proposed technique stores, for each pixel, a set of values taken in the past at the same location or in the neighborhood. It then compares this set to the current pixel value in order to determine whether that pixel belongs to the background, and adapts the model by choosing randomly which values to substitute from the background model. This approach differs from those based upon the classical belief that the oldest values should be replaced first. Finally, when the pixel is found to be part of the background, its value is propagated into the background model of a neighboring pixel. We describe our method in full details (including pseudo-code and the parameter values used) and compare it to other background subtraction techniques. Efficiency figures show that our method outperforms recent and proven state-of-the-art methods in terms of both computation speed and detection rate. We also analyze the performance of a downscaled version of our algorithm to the absolute minimum of one comparison and one byte of memory per pixel. It appears that even such a simplified version of our algorithm performs better than mainstream techniques.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Article-2
ObjectType-Feature-1
scopus-id:2-s2.0-79957497122
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2010.2101613