Robust spatio-temporal multimodal background subtraction for video surveillance

Poppe, Chris; Martens, Gaëtan; Bruyne, Sarah De; Lambert, Peter; Walle, Rik Van de

doi:10.1117/1.3002325

Cited by 12 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SMM models consist of an average, an upper and lower threshold, a maximum difference with the last background value, and an illumination allowance based on Skellam parameters. In many cases, only performing temporal background subtraction is insufficient, so SMM is extended with spatial information, i.e., [17] show that this advanced MGM method is more robust than 'standard' MGM and more recent techniques, resulting in less false positives and negatives. This is also the reason why SMM is selected as one of the non-wavelet based BG subtraction methods in our evaluation.…”

Section: Methodsmentioning

confidence: 96%

“…To overcome the complexity of the traditional MGM, a simple mixture of models technique (SMM) is proposed by Poppe et al [17]. The SMM models consist of an average, an upper and lower threshold, a maximum difference with the last background value, and an illumination allowance based on Skellam parameters.…”

Section: Methodsmentioning

confidence: 99%

“…(12), (13), (14) and (15), (16), (17) we were able to distinguish between the different detected foreground objects and register their positions on the scene map for Frame CAM1 and Frame CAM2.…”

Section: Scene Map: a Holistic Geometrical Approachmentioning

confidence: 95%

“…(15), (16), (17) above can be proven by replacing with the co-ordinates values the equations' variables that are uniquely satisfied by the detected object's co-ordinates and not by any other detected object in the scene of FRAME CAM2.…”

Section: Scene Map: a Holistic Geometrical Approachmentioning

confidence: 99%

“…(12), (13), (14) for FRAME CAM1 and eqns. (15), (16), (17) for FRAME CAM2 are simultaneously satisfied only by Object 1 (linear algebraic Gauss system solution).…”

Section: Scene Map: a Holistic Geometrical Approachmentioning

confidence: 99%

See 4 more Smart Citations

Automatic Passengers Counting In Public Rail Transport Using Wavelets

et al. 2012

Self Cite

View full text Add to dashboard Cite

Original scientific paperPreviously, we introduced a passengers' counting algorithm in public rail transport. The main disadvantage of that algorithm is it lacks automatic event detection. In this article, we implement two automatic wavelet-based passengers counting algorithms. The new algorithms employ the spatial-domain Laplacian-of-Gaussian-based wavelet, and the frequency-domain applied Non-Linear Difference of Gaussians-based wavelet bandpass video scene filters to extract illumination invariant scene features and to combine them efficiently into the background reference frame. Manual segmentation of the scene into rectangles and tiles for detecting an object as seated is no longer needed as we now apply a boundary box tracker on the segmented moving objects' blobs. A scene map is combined with the wavelet-based methods and the boundary box for multi-camera object registration. We have developed a novel holistic geometrical approach for exploiting the scene map and the recorded video sequences from both cameras installed in each train coach to separate the detected objects and locate their positions on the scene map. We test all the algorithms with several video sequences recorded from the both cameras installed in each train coach. We compare the previously developed non-automatic passengers' counting algorithm with the two new automatic wavelet-based passengers' counting algorithms, and an additional spatial-domain automatic non-wavelet based Simple Mixture of Gaussian Models algorithm. Automatsko brojanje putnika u javnom željezničkom prijevozu uporabom waveleta. U prethodnim radovima uveli smo algoritam za brojanje putnika u javnom željezničkom prijevozu. Glavna manjkavost dosadašn-jeg algoritma odsustvo je sustava za automatsko otkrivanje doga aja. U ovom radu implementirali smo dva algoritma za automatsko brojanje putnika temeljena na waveletima. Novi algoritmi koriste LoG (Laplacian-ofGaussian-based) wavelete u prostornoj domeni i pojasne filtre temeljene na waveletima nastalim na nelinearnim razlikama Gaussovih funkcija u frekvencijskoj domeni, pomoću kojih se izdvajaju značajke neosjetljive na razlike u osvjetljenju iz pojedine scene. Te značajke kombiniraju se u referentnu sliku koja prikazuje pozadinu scene. Ručna segmentacija scene u pravokutnike korištena u prethodnom algoritmu više nije potrebna jer se sada koristi automatsko praćenje rubova na segmentiranim objektima. Mapa scene kombinirana je s wavelet metodama i okvirom granica slike u svrhu registracije objekata pomoću više kamera. Razvili smo i novi cjeloviti geometrijski pristup koji koristi mapu scene i snimljeni videozapis iz dvije kamere postavljene u svakom vagonu vlaka pomoću kojeg možemo odvojiti detektirane objekte i locirati njihove položaje na mapi scene. Algoritmi su ispitani na nekoliko videosekvenci snimljenih s dvije kamere u vagonima. Usporedili smo ranije razvijene neautomatske algoritme za brojanje putnika s dva nova algoritma i s jednostavnim MoG algoritmom u prostornoj domeni.Ključne riječi: analiza videozapisa, otkriva...

show abstract

Section: Methodsmentioning

confidence: 96%

Section: Methodsmentioning

confidence: 99%

Section: Scene Map: a Holistic Geometrical Approachmentioning

confidence: 95%

Section: Scene Map: a Holistic Geometrical Approachmentioning

confidence: 99%

“…(12), (13), (14) for FRAME CAM1 and eqns. (15), (16), (17) for FRAME CAM2 are simultaneously satisfied only by Object 1 (linear algebraic Gauss system solution).…”

Section: Scene Map: a Holistic Geometrical Approachmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Passengers Counting In Public Rail Transport Using Wavelets

et al. 2012

Self Cite

View full text Add to dashboard Cite

show abstract

Skellam process with resetting: a neural spike train model

2016

View full text Add to dashboard Cite

This paper introduces the Skellam process with resetting. Resetting is a modification that accommodates the modeling of neural spike trains. We show this as a biologically plausible model, which codes the information content of neural spike trains with three, potentially, time-varying functions. We show that the interspike interval distribution under this model follows a mixture of gamma distributions, a flexible class covering a wide range of commonly used models. Through simulation studies and the analyses of connected retinal ganglion and lateral geniculate nucleus cells, we evaluate the performance of this model. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Change detection for moving object segmentation with robust background construction under Wronskian framework

Subudhi

Ghosh

2013

Machine Vision and Applications

View full text Add to dashboard Cite

Robust spatio-temporal multimodal background subtraction for video surveillance

Cited by 12 publications

References 18 publications

Automatic Passengers Counting In Public Rail Transport Using Wavelets

Automatic Passengers Counting In Public Rail Transport Using Wavelets

Skellam process with resetting: a neural spike train model

Change detection for moving object segmentation with robust background construction under Wronskian framework

Contact Info

Product

Resources

About