Background Subtraction for Effective Object Detection Using GMM&LIBS
R. Pradeep Kumar Reddy R. Lakshmi Pravallika, G. L. N. Murthy, P. G. Student · 2015
Object detection and tracking is a challenging problem in numerous applications like video surveillance, human computer interaction, video indexing and retrieval. In the current paper, an intensity range based object detection scheme is proposed. The proposed object detection scheme consists of two steps: the first one models the background from initial few frames and the second one extracts the objects based on local thresholding. The strength of this scheme lies in its simplicity and the fact that it defines an intensity range for each pixel location in the background to accommodate illumination variation as well as motion in the background. In this paper, Gaussian Mixture Model and Local Illumination Based Background Subtraction model are to be analyzed and compared using kappa coefficient parameter values for effective object detection.