Improved adaptive Gaussian mixture model for background subtraction

Zivkovic, Z.

doi:10.1109/icpr.2004.1333992

Cited by 1,831 publications

(1,185 citation statements)

References 9 publications

Supporting

Mentioning

1,108

Contrasting

Unclassified

Order By: Relevance

“…The strength of each method is tunable depending on the exact application. For videos, we apply a mixture of Gaussian (MOG) [23] (i.e. an adaptive background subtraction method).…”

Section: Our Proposed De-genderization Methodsmentioning

confidence: 99%

De-genderization by body contours reshaping

Ruchaud

Dugelay

2017

2017 IEEE International Conference on Identity, Security and Behavior Analysis (ISBA)

View full text Add to dashboard Cite

This paper deals with privacy protection in video surveillance. More specifically, the main goal of this work is to make the gender of people no more recognizable while preserving enough information concerning body shape and motion of people for action classification. We denote this processing as de-genderization. Regarding the current state-of-art methods, most of them have privacy filters only dedicated to de-identify people. These methods do not automatically imply the suppression of visual semantic traits such as gender. Therefore, we propose two approaches that modify the visual appearance of the body shape in order to de-genderize people while keeping the possibility to interpret the video. In both methods we start by extracting the contour points attached to the body shape of people in videos. Then we either mix the coordinates of the body shape and a predefined model, or we smooth the body shape by successive polygonal approximations based on convexity. Our results demonstrate that both proposed approaches protect the gender information while preserving the global body movement. The second approach based on convexity better preserves the visibility of human activities.

show abstract

“…The strength of each method is tunable depending on the exact application. For videos, we apply a mixture of Gaussian (MOG) [23] (i.e. an adaptive background subtraction method).…”

Section: Our Proposed De-genderization Methodsmentioning

confidence: 99%

De-genderization by body contours reshaping

Ruchaud

Dugelay

2017

2017 IEEE International Conference on Identity, Security and Behavior Analysis (ISBA)

View full text Add to dashboard Cite

show abstract

“…The chosen algorithms for the simulation are: Fuzzy Gaussian [14] (FG), Advanced MOG [6] (MOG), Gaussian Mixture Model [5] (GMM), Multi-Layer Background subtraction [15] (ML). The parameters of each algorithm are setup according to author's propositions.…”

Section: A Comparative Experimentsmentioning

confidence: 99%

“…This model can lessen the effect of small repetitive motions; for example, lightly swaying trees and bushes or small displacement of camera. KaewTraKulPong and Bowden [5] as well as Zoran Zivkovic [6] presented methods which improve the computation performance by reinvestigating the update equations. Fuzzy is also implemented to the background subtraction, each step must be designed and the features in relation has to be chosen in relation to the critical situation [7], [8].…”

Section: Introductionmentioning

confidence: 99%

Subsequent Processing of Background Modeling for Traffic Surveillance System

Tran¹,

Nguyên²,

Nhu³

et al. 2016

IJCTE

View full text Add to dashboard Cite

Abstract-The background model finds difficult to extract the good foreground if it is implemented in real-time, the change of light and weather that make the detected-foreground unclear, has countless noise. Therefore, to avoid that problem, the Mixture of Gaussian need subsequent processing step to make the foreground better. The paper proposes a method, degrades several drawbacks of Background Subtraction, which intended to be used in urban traffic scenes.

show abstract

“…The fusion process consists of a logical OR of the two approaches' foreground masks and then the use of heuristic reasoning to permit the motion detector's regions to split change regions that have inhomogeneous motion, while the regions of the change detector are permitted to merge motion regions that show homogeneous motion. For this work, change detection is performed using the Adaptive Gaussian Mixture Model of [1], while real-time optical flow is provided by OpenCV's GPU implementation of [19].…”

Section: Object Detectionmentioning

confidence: 99%

“…Together with the variations in which threats may occur, a thorough interpretation of the observed cues is required, beyond simple rules on simple cues. Yet, the popular approach in computer vision for recognizing human behaviour is to start with low-level entities, the most common ones are trajectories resulting from tracking, e.g., [1], and hand-crafted features, e.g., STIP [2]. Such lowlevel features are very useful, because they capture essential details about trajectories, local shape, motion, and they are localized in space and/or time.…”

Section: Introductionmentioning

confidence: 99%

Instantaneous threat detection based on a semantic representation of activities, zones and trajectories

Burghouts¹,

Schutte²,

Hove³

et al. 2014

SIViP

View full text Add to dashboard Cite

Threat detection is a challenging problem, because threats appear in many variations and differences to normal behaviour can be very subtle. In this paper, we consider threats on a parking lot, where theft of a truck's cargo occurs. The theft takes place in very different forms, in the midst of many people who pose no threat. The threats range from explicit, e.g., a person attacking the truck driver, to implicit, e.g., somebody loitering and then fiddling with the exterior of the truck in order to open it. Our goal is a system that is able to recognize a threat instantaneously as they develop. Typical observables of the threats are a person's activity, presence in a particular zone, and the trajectory. The novelty of this paper is an encoding of these threat observables in a semantic, intermediate-level representation, based on low-level visual features that have no intrinsic semantic meaning themselves. The semantic representation encodes the notions of trajectories, zones and activities. The aim of this representation is to bridge the semantic gap between the low-level tracks and motion and the higher-level notion of threats. In our experiments, we demonstrate that our semantic representation is more descriptive for threat detection than directly using low-level features. We find that a person's activities are the most important elements of this semantic representation, followed by the person's trajectory. The proposed threat detection system is very accurate: 96.6% of the tracks are correctly interpreted, when considering the temporal context.

show abstract

Improved adaptive Gaussian mixture model for background subtraction

Cited by 1,831 publications

References 9 publications

De-genderization by body contours reshaping

De-genderization by body contours reshaping

Subsequent Processing of Background Modeling for Traffic Surveillance System

Instantaneous threat detection based on a semantic representation of activities, zones and trajectories

Contact Info

Product

Resources

About