Robust background subtraction and maintenance

Zang, Qi; Klette, Reinhard

doi:10.1109/icpr.2004.1334047

Cited by 42 publications

(32 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Region tracking approaches (Matthews et al, 2004) might be less useful recorded for analysing behaviour patterns. Considering the above, here the object tracking methodology utilises the tracking principle proposed by Yang et al (2005) together with the improvements in Herath et al (2014), which is capable of detecting object-events such as merges and splits. The colour histogram based object identity recall mechanism included has enabled to keep track on objects even under temporary losses from the scene.…”

Section: Journal Of the National Science Foundation Of Sri Lanka 44(4)mentioning

confidence: 99%

“…Employment of a single background has long gone obsolete due to its inability to capture gradual changes in the background. Rahman et al (2010) and Yang et al (2005) have proposed remedies to absorb the background illumination change into the background reference model. But both these methods are ineffective when external objects are introduced to the background.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online tracking and event clustering for vision systems

Perera¹,

Herath²,

Fernando³

et al. 2016

J. Natn. Sci. Foundation Sri Lanka

View full text Add to dashboard Cite

This paper proposes a comprehensive method for online-event clustering in videos. Adaptive Gaussian mixture of foreground and they were modelled using the time series modelling technique. A cross-substitution based model comparison method was employed to compare the disparity between events. Spectral clustering (SC) was utilised to cluster events, and methods for SC initial parameter selection have been proposed. A method for cluster identity assignment in consecutive clustering iterations is also utilised to handle the evolving nature of the unsupervised learning methodology adopted. The proposed method is capable of producing reliable clustering results online, amidst a number of complications including dynamic backgrounds, object shadows, camera distortions, sudden foreground bursts and inter-object interactions.Event clustering, foreground estimation, trajectory modelling. INTRODUCTIONHumans are capable of identifying similarities and dissimilarities between the events they perceive. The objective of event clustering is to produce a set of event clusters to follow human heuristics through an automated process. Such systems are widely applied in (Gowsikhaa et al., 2014), bio vision applications (Jiang et al., 2013; Aqel et al., 2016) and abnormal event detection (Archetti et al., 2006 ; Guo et al., 2013;Ranjith et al., 2015). of activities performed by an object (Porikli & Haga, 2004;Utsumi et al., 2013). An event is described using a set of temporal features of the relevant object such as its location, velocity and size. Therefore, obtaining various feature variations of objects under consideration becomes one of the primary exercises in event clustering. In order to construct the necessary feature space, the desired foreground objects need to be segmented and tracked throughout the video. Therefore, any event detection practice comprises a series of sub processes, namely, foreground estimation, construction and clustering. The paper proposes a comprehensive methodology, which addresses each of these sub processes in a sequential manner to arrive at a robust event clustering system. Most of the previously proposed foreground estimation methods utilise the principle of background subtraction (Zang & Klette, 2004;Qin et al., 2013). Employment of a single background has long gone obsolete due to its inability to capture gradual changes in the background. Rahman et al. (2010) and Yang et al. (2005) have proposed remedies to absorb the background illumination change into the background reference model. But both these methods are ineffective when external objects are introduced to the background. The method proposed in Stauffer and Grimson (2000) is capable of tackling the issue of gradual background changes by modelling each pixel as a mixture of Gaussian distributions.

show abstract

Section: Journal Of the National Science Foundation Of Sri Lanka 44(4)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Online tracking and event clustering for vision systems

Perera¹,

Herath²,

Fernando³

et al. 2016

J. Natn. Sci. Foundation Sri Lanka

View full text Add to dashboard Cite

show abstract

“…step1: filling small gaps A 3 3 × or 5 5 × window is employed to remove the small gaps [7]. We set each foreground pixel at the center of the window, and if there are more than half of the foreground pixels contained in the window, then we will fill the gaps within the window.…”

Section: The Combination Of the Two Methodsmentioning

confidence: 99%

“…The Frame Difference Method [7] is based on the fact that these is nearly no variation of background in consecutive two or three frames. So the moving objects can be simply extracted by the difference of the current frame and the previous frame.…”

Section: Running Gaussian Average Model and Frame Differencementioning

confidence: 99%

Background Subtraction Using Running Gaussian Average and Frame Difference

Tang

Miao

Wan

2007

Entertainment Computing – ICEC 2007

View full text Add to dashboard Cite

Abstract. Background Subtraction methods are wildly used to detect moving object from static cameras. It has many applications such as traffic monitoring, human motion capture and recognition, and video surveillance. It is hard to propose a background model which works well under all different situations. Actually, there is no need to propose a pervasive model; it is a good model as long as it works well under a special situation. In this paper, a new method combining Gaussian Average and Frame Difference is proposed. Shadow suppression is not specifically dealt with, because it is considered to be part of the background, and can be subtracted by using an appropriate threshold. At last, a new method is raised to fill small gaps that the detected foreground or the moving objects may contain.

show abstract

“…The probability density function for each pixel intensity is evaluated using directly from the data instead of any parameter assumption. In [9] [10], Nonparametric kernal density estimation technique was proposed. In [11], The background model is estimated using pixel by pixel basis and samples at each pixel is clustered into the set of codeword.…”

Section: Related Work 21 Object Detectionmentioning

confidence: 99%

Multiple Object Detection using GMM Technique and Tracking using Kalman Filter

Chavan¹,

Gengaje²

2017

IJCA

View full text Add to dashboard Cite

The continuous research in the technology of video acquisition devices increases the number of applications with best performance and less cost. For object recognition, navigation and surveillance systems, object detection and tracking are the indispensable steps. Object detection means segmentation of images between foreground and background objects. Object tracking establish the correspondence between the objects in successive frames of video sequence. In this paper, we have proposed algorithms consists of two stages i.e. object detection using Gaussian Mixture Model (GMM) and multiple moving objects tracking using Kalman filter. While tracking the moving object, problems occur during occlusion of persons with each other. However, it can be effectively deal with various video sequences such as indoor, outdoor and cluttered scenes. The experimental results shows that proposed algorithm achieve accurate, robust and efficient results for detection as well as for tracking the foreground objects from complex and dynamics scenes. General TermsSegmentation, Gaussian Mixture Model, Occlusion, Kalman Filter.

show abstract

Robust background subtraction and maintenance

Cited by 42 publications

References 8 publications

Online tracking and event clustering for vision systems

Online tracking and event clustering for vision systems

Background Subtraction Using Running Gaussian Average and Frame Difference

Multiple Object Detection using GMM Technique and Tracking using Kalman Filter

Contact Info

Product

Resources

About