An Algorithm for Moving Target Detection in Dynamic Background Based on Gray-Weighted Kernel Function
Lu Ping Wang, Lu Ping Zhang, Ming Hua Zhao · Advanced materials research · 2013
A new detecting algorithm based on gray-weighted kernel function is proposed for the moving target detection (MTD) in dynamic series of image.This algorithm firstly realizes image sequence registration by using the biggest gradient point. Then divides the image into 32*32 sub-images. The moving target can be finally detected based on the changes of gray-weighted kernel function. The testing result shows that the algorithm can detect the moving target in real-time and can suppress the influence caused by image registration error and gray fluctuation effectively.