Video Flash Matting: Video Foreground Object Extraction Using an Intermittent Flash

Afifi, Mahmoud

doi:10.1007/978-3-319-26690-9_10

Cited by 1 publication

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Video segmentation has been a focus of computer vision and image processing, and it plays a key role in some fields such as the target classification, tracking and recognition [9], [10]. In recent years, some related works have been proposed, such as the optical flow [11], temporal difference [12] and background subtraction [13]- [15]. Stauffer et al propose the GMM [16], an adaptive background mixture model for the real-time tracking, where each pixel is modeled as a mixture of Gaussians and is classified based on whether the Gaussian distribution which represents it most effectively is considered part of the background model.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A GMM-Based Segmentation Method for the Detection of Water Surface Floats

2019

View full text Add to dashboard Cite

Gaussian Mixture Model (GMM) is a widely used approach for the background subtraction and the moving objects detection. However, the classical GMM probably detects incorrectly and cannot deal with the shadows with a pixel-level and time-domain classification, and thus it cannot monitor the water surface floats effectively. To solve this problem, an improved GMM-based automatic segmentation method (IGASM) is proposed to detect the water surface floats in this paper, where the background updating strategy is improved to segment the water surface floats more effectively. Besides, the GMM results are mapped into an HSV color space, and a light-shadow discriminant function is applied to solve the problems of light and shadow. Then, a morphological method is used to smooth the extracted foregrounds. Finally, Graph Cuts algorithm is applied to optimized the segmentation results according to the spatial information of video images. Experimental results demonstrate that IGASM can detect the water surface floats quickly and accurately, and the influences of light, shadows and ripples of water surface can be eliminated as much as possible. INDEX TERMS Background subtraction, Gaussian mixture model, graph cuts, light-shadow discriminant function, video segmentation, water surface floats.

show abstract

Section: Related Workmentioning

confidence: 99%

“…represent the current pixel value and the background pixel value, respectively. The light-shadow discriminant function is given as follows: (11) where L (x, y) denotes the pixel of light and shadow, T V is the threshold of V , which is related to the intensity of light. A stronger light gives rise to a larger T V .…”

Section: B Light-shadow Discriminant Functionmentioning

confidence: 99%