Abstract
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.
Highlights
With the rapid development of industrialization, the human beings have caused serious pollutions to the environments
This paper proposes an improved Gaussian Mixture Model (GMM)-based automatic segmentation method (IGASM) for the detection of water surface floats
This paper improves the updating strategy of the GMM algorithm, and a light-shadow discriminant function is used to divide the foreground pixels into two parts: with regard to those ‘‘false’’ foreground pixels caused by the light and shadow, we update their distribution parameters by the original updating strategy; with regard to those ‘‘real’’ foreground pixels, we will not update their distribution parameters to prevent them from being merged into the background
Summary
With the rapid development of industrialization, the human beings have caused serious pollutions to the environments. Note that the classical GMM algorithm considers the difference of pixel’s characteristics in time-domain when extracting the foreground objects, whereas the spatial information of video images is ignored [8], which gives rise to the detection inaccuracy of water surface floats. To this end, this paper proposes an improved GMM-based automatic segmentation method (IGASM) for the detection of water surface floats. The paper is organized as follows: in Section II, we introduce some existing foreground segmentation methods and the related works of water surface floats detection.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
