A Background Modeling and Foreground Detection Algorithm Using Scaling Coefficients Defined With a Color Model Called Lightness-Red-Green-Blue - 2018

PROJECT TITLE :

A Background Modeling and Foreground Detection Algorithm Using Scaling Coefficients Defined With a Color Model Called Lightness-Red-Green-Blue - 2018

ABSTRACT:

This Project presents an algorithm for background modeling and foreground detection that uses scaling coefficients, that are defined with a brand new color model referred to as lightness-red-inexperienced-blue (LRGB). They're employed to compare 2 pictures by finding pixels with scaled lightness. Three backgrounds are used: one) verified background with pixels that are thought-about as background; two) testing background with pixels that are tested many times to check if they belong to the background; and three) final background that's a combination of the testing and verified background (the testing background is used in places, where the verified background is not outlined). If a testing background pixel matches pixels from previous frames (the match is tested using scaling coefficients), it's copied to the verified background, otherwise the pixel is set because the weighted average of the corresponding pixels of the last input images. Once the background is computed, foreground objects are detected by using the scaling coefficients and additional criteria. The algorithm was evaluated using the SABS information set, Wallflower knowledge set and a subset of the CDnet 2014 data set. The typical F measure and sensitivity with the SABS Data set were zero.7109 and zero.8725, respectively. Within the Wallflower knowledge set, the full range of errors was 5280 and the whole F-measure was zero.9089. Within the CDnet 2014 knowledge set, the F-measure for the baseline test case was 0.8887 and for the shadow check case was 0.8300.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here