Mixture of Gaussians Exploiting Histograms of Oriented Gradients for Background Subtraction

Fabián, Tomáš

doi:10.1007/978-3-642-17274-8_70

Cited by 5 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, Mason and Duric [340] used an intersection measure to compare Local Color Histograms (LCH). In an other work, Fabian [133] first used simple metric to compare Histograms of Oriented Gradients (HOG) in a discrete metric space. But, this metric made no difference between two different bins.…”

Section: C) Similarities For Histogram Casementioning

confidence: 99%

“…But, this metric made no difference between two different bins. Due solve to this problem, Fabian [133] proposed a complex metric. Several works [84][381] [303] [609][610] [632][202] used the Bhattacharyya distance as can be seen in Table 8.…”

Section: C) Similarities For Histogram Casementioning

confidence: 99%

Section: Local Histogram Of Gradientmentioning

confidence: 99%

“…-Local Histogram of Oriented Gradient: Fabian [133] presented a MOG based background subtraction which exploits Histograms of Oriented Gradients (HoG) instead of intensity to deal with camera jitter, automatic iris adjustment and exposure control. Thus, Fabian [133] avoided false detections of foreground mask. Practically, the brightness value is replaced by a local image gradient because image gradient and its orientation are invariant against changes in brightness.…”

Section: Local Histogram Of Gradientmentioning

confidence: 99%

“…In practice, this assumption is quite suitable and allow the method to reduce the effects of automatic control. Futhermore, to deal with camera jitter, Fabian [133] handled small image movements. For this, the gradient is measured for squared area of size 8 × 8 called cell.…”

Section: Local Histogram Of Gradientmentioning

confidence: 99%

See 4 more Smart Citations

On the Role and the Importance of Features for Background Modeling and Foreground Detection

Bouwmans¹,

Silva²,

Marghes³

et al. 2016

Preprint

View full text Add to dashboard Cite

Background modeling has emerged as a popular foreground detection technique for various applications in video surveillance. Background modeling methods have become increasing efficient in robustly modeling the background and hence detecting moving objects in any visual scene. Although several background subtraction and foreground detection have been proposed recently, no traditional algorithm today still seem to be able to simultaneously address all the key challenges of illumination variation, dynamic camera motion, cluttered background and occlusion. This limitation can be attributed to the lack of systematic investigation concerning the role and importance of features within background modeling and foreground detection. With the availability of a rather large set of invariant features, the challenge is in determining the best combination of features that would improve accuracy and robustness in T. Bouwmans Lab. MIA,

show abstract

Section: C) Similarities For Histogram Casementioning

confidence: 99%

Section: C) Similarities For Histogram Casementioning

confidence: 99%

Section: Local Histogram Of Gradientmentioning

confidence: 99%

Section: Local Histogram Of Gradientmentioning

confidence: 99%

Section: Local Histogram Of Gradientmentioning

confidence: 99%

See 3 more Smart Citations

On the Role and the Importance of Features for Background Modeling and Foreground Detection

Bouwmans¹,

Silva²,

Marghes³

et al. 2016

Preprint

View full text Add to dashboard Cite

show abstract

On the role and the importance of features for background modeling and foreground detection

Bouwmans

Silva

Marghes

et al. 2018

Computer Science Review

View full text Add to dashboard Cite

The effect of color space and block size on foreground detection

Balcilar

Sonmez

2013

2013 21st Signal Processing and Communications Applications Conference (SIU)

View full text Add to dashboard Cite

Özetçe-Arkaplan çıkarım yöntemleri, hareket eden objeleri bulmak amacıyla, bilgisayarlı görü uygulamalarında oldukça yaygın olarak kullanılır. Özellikle statik olmayan arka planları içeren videolarda bu işlem hala daha zor bir problemdir. Genel bir arkaplan çıkarım yönteminin en kritik alt görevleri arkaplanın nasıl temsil edileceğini belirleyen arkaplan modelleme aşaması ve bu modelden önemli derecede farklılık gösteren önplan bölgelerinin tesbit aşamasıdır. Hem modellemede hemde önplan tesbitinde piksel yada alt bölgelerin hangi özelliklerinin kullanılacağı önemli bir araştırma konusudur. Bu çalışmanın amacı, arkaplan modelinden bağımsız olarak önplan tesbitinde kullanılacak en efektif renk uzayını, alt-bölge boyutunu, ve uzaklık metriğini belirlemektir. Görüntünün arkaplan modeline olan uzaklığı sınıflama kriteri olarak kullanılmıştır. Çalışmada performans metriği olarak Receiver Operating Characteristic (ROC) eğrisi altında kalan alan kullanılmıştır. Testler I2R datasetine bulunan 9 farklı statik olmayan arka plana sahip videolar ile yapılmıştır. Anahtar Kelimeler -Arkaplan Çıkarımı, Önplan Tesbiti, Renk Uzayları, ROC analizi.Abstract-Background subtraction techniques, in order to identify moving objects, are commonly used in computer vision applications. This is still a challenging problem especially when there is a non-stationary background. Two most significant tasks of generic background subtraction techniques are the background modeling, which determines how background will be represented and detect the foreground region, which significantly differ from the background model. The problem with which features will be represented in both background modeling and foreground detection is an important research topic. The purpose of this study is to determine the most effective color space, region block size and distance metric for foreground detection regardless of the background model. As a performance metric, the area under the Receiver Operating Characteristic (ROC) curve is used. Tests were performed over 9 different videos which have non-static background in I2R dataset.

show abstract

Mixture of Gaussians Exploiting Histograms of Oriented Gradients for Background Subtraction

Cited by 5 publications

References 8 publications

On the Role and the Importance of Features for Background Modeling and Foreground Detection

On the Role and the Importance of Features for Background Modeling and Foreground Detection

On the role and the importance of features for background modeling and foreground detection

The effect of color space and block size on foreground detection

Contact Info

Product

Resources

About