Multistrategy fusion using mixture model for moving object detection

Nadimi, S.; Bhanu, Bir

doi:10.1109/mfi.2001.1013554

Cited by 24 publications

(12 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, camera configuration can be thought of as either cooperative or competitive in a fusion strategy scheme. Results [122] indicate that a AND strategy is a viable fusion strategy for relatively small moving objects at intermediate distances.…”

Section: A Different Features-cameras Strategies: Stauffer Andmentioning

confidence: 94%

See 1 more Smart Citation

Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey

Bouwmans¹,

Baf²,

Vachon

2008

CSENG

359

127

View full text Add to dashboard Cite

Abstract:Mixture of Gaussians is a widely used approach for background modeling to detect moving objects from static cameras. Numerous improvements of the original method developed by Stauffer and Grimson [1] have been proposed over the recent years and the purpose of this paper is to provide a survey and an original classification of these improvements. We also discuss relevant issues to reduce the computation time. Firstly, the original MOG are reminded and discussed following the challenges met in video sequences. Then, we categorize the different improvements found in the literature. We have classified them in term of strategies used to improve the original MOG and we have discussed them in term of the critical situations they claim to handle. After analyzing the strategies and identifying their limitations, we conclude with several promising directions for future research.

show abstract

Section: A Different Features-cameras Strategies: Stauffer Andmentioning

confidence: 94%

“…One feature -Multiple Cameras: Nadimi and Bhanu [122] use different sensors but only the color features are used. Indeed, the sensors are visible spectrum cameras and the RGB components are used as features but the cameras have different spectral sensitivities.…”

Section: A Different Features-cameras Strategies: Stauffer Andmentioning

confidence: 99%

Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey

Bouwmans¹,

Baf²,

Vachon

2008

CSENG

359

127

View full text Add to dashboard Cite

show abstract

“…Sensor fusion techniques [8] are applied within a mixture model-based framework [16] in RGB space for the initial object detection. In this algorithm, each pixel is viewed as an independent process.…”

Section: Physics-based Shadow Detectionmentioning

confidence: 99%

“…The moving object detection algorithm is initialized by first collecting t initial frames, and then estimating the parameters of the mixture for each pixel by K-means clustering technique. We use the AND strategy [8] which specifies that an incoming pixel value must be within three standard deviations of any of its g models in all three (independent R, G, B) channels to be considered a background pixel; otherwise, it is classified as a moving pixel. This strategy provides the highest detection rate in comparison to other fusion strategies [8].…”

Section: Physics-based Shadow Detectionmentioning

confidence: 99%

“…Recently, statistical-based approaches using a mixture model have shown that many problematic phenomena such as repetitive motion of the background (e.g., swaying trees), sudden illumination changes (e.g., cloud cover), and sensor noise can be modeled [4], [8], [16]. Despite this success, a statistical-based approach fails to distinguish between the actual moving object and its shadow silhouette.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Physical models for moving shadow and object detection in video

Nadimi

Bhanu

2004

IEEE Trans. Pattern Anal. Machine Intell.

Self Cite

238

116

View full text Add to dashboard Cite

Abstract-Current moving object detection systems typically detect shadows cast by the moving object as part of the moving object. In this paper, the problem of separating moving cast shadows from the moving objects in an outdoor environment is addressed. Unlike previous work, we present an approach that does not rely on any geometrical assumptions such as camera location and ground surface/object geometry. The approach is based on a new spatio-temporal albedo test and dichromatic reflection model and accounts for both the sun and the sky illuminations. Results are presented for several video sequences representing a variety of ground materials when the shadows are cast on different surface types. These results show that our approach is robust to widely different background and foreground materials, and illuminations.

show abstract

Fusion of Color/Infrared Video for Human Detection

Bhanu

Han

2010

Human Recognition at a Distance in Video

View full text Add to dashboard Cite

Multistrategy fusion using mixture model for moving object detection

Cited by 24 publications

References 6 publications

Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey

Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey

Physical models for moving shadow and object detection in video

Fusion of Color/Infrared Video for Human Detection

Contact Info

Product

Resources

About