Detecting Moving Objects from Infrared Image Sequence on Displacing Background
Cao Ju①②; Tan Yi-hua②; Ma Jie②; Tian Jin-wen②
①Beijing Aerospace Autocontrol Institute; Beijing 100854 China;②State Key Laboratory of Education Ministry for Image Processing and Intelligent Control Inst.for Pattern Recognition and Artificial Intelligence HUST Wuhan 430074 China
Abstract:An approach to detecting moving objects from infrared image sequence on displacing background is proposed in this paper. First the correlation matching technique is used for registering five pictures with the sixth one. Then the registered images are processed to calculate the image differences between the first and fourth, the second and fifth, the third and sixth. After these difference images are multiplied, a very high correlation peak is obtained. Using this method a central point for tracking window can be provided. The experimental results illustrate that this approach is available to this situation.