Modification Color Filtering in HSV Color Space

Abstract

Abstract The health condition of plants can be determined by calculating the vegetation index. A healthy plant is identified from photosynthetic activity that reflects a lot of green and absorbs red and blue. Image information from a visible light camera will provide a Red-Green-Blue (RGB) value for each pixel which will be used to calculate the vegetation index. RGB values are largely determined by lighting conditions (scene) at the time of shooting by the camera. Plant images are influenced by high variability of illumination conditions due to changes in natural lighting conditions; bright, cloudy or nearby object illumination. RGB represents a non-uniform color space, thereby needing transformation to other color spaces. The purpose of color space transformation is to replicate the original information from the real world without changing any actual information. Color space transformation often causes information loss, including when mapping colors. The main contribution of this study is the simplification and improvement to the selection speed of desired colors in the HSV color space using the Heaviside step function. Modification was performed by sorting out the green color at a hue value of 90°-150°. The modified results showed that green can be distinguished from other colors. The experimental results on images taken using an unmanned aerial vehicle (UAV) showed that the results of the proposed modification increase the speed of computation time by an average of 16.60%.