Feature Extraction Based on Color Difference Algorithm for Moving Target Detection System
Hu Xu, Xiao Bo Mao · Applied Mechanics and Materials · 2013
To improve the accuracy and robustness of the moving object detection in the image sequence, the author improves the traditional algorithm which is based on the gray-value difference. The author makes good use of the color information of images and applies the pixels in red, green, blue the three component value as its identifying information. According to the background image color composition, it adapts and adjusts the proportion of the three groups. Dynamic threshold is used to do the binarization separation of the background difference image. The simulation experiment shows, this algorithm makes full use of the color features of image and achieve the expected goal of high recognizability and good robustness.