摘要
图像定位是图像处理的一个重要环节,然而噪声干扰以及计算成本制约着图像定位的广泛应用与深度发展。从频域内的信号相位信息与空域内位移量的关联性入手,建立相对关联函数(RCF),通过寻找其能量分布函数在低维空间的峰值响应,计算图像的偏移量。实验证明这种方法精度高,计算成本较低,且不依赖参考点,稳健性较强。
Image locating is an necessary step for image processing.However,noise interrupt and computation cost are unavoidable obstacles for its wide application and further development.From correlation between signal phase in frequency domain and displacement in time domain,a Delative Correlation Function(RCF) is set up and image displacement is measured by searching the peak output of RCF' s energy distribution in lower-dimension space.Experimental results show that this algorithm with a high accuracy and low computation cost is independent on reference points and has good robustness.
出处
《电视技术》
北大核心
2010年第S1期65-68,共4页
Video Engineering
关键词
图像定位
傅里叶变换
相位
时频关联性
image locating
Fourier transform
phase
time-frequency correlation
