梯度算子对反向合成梯度算法的影响

反向合成梯度算法是一种基于局部指向性的反向合成图像对齐算法。与传统的反向合成图像对齐算法相比,该算法可有效地克服光照变化对匹配结果的影响1]。由于局部指向性的计算在本质上是梯度的计算,而图像梯度的计算可以采用不同的梯度算子,因此采用4种不同的梯度算子(一阶差分算子,Roberts算子,Sobel算子和Prewitt算子)来计算局部指向性,并通过实验比较分析了4种梯度算子对反向合成梯度算法的影响。

Influence of gradient operators on inverse compositional gradient algorithm

Inverse Compositional Gradient(ICG) algorithm is a novel Inverse Compositional Image Alignment(ICIA) algorithm based on the local orientation.Compared with the traditional ICIA algorithm,it gives more accurate and reliable matching results under different lighting conditions1].The evaluation of the local orientation and gradient is essentially equivalent.Hence 4 different gradient operators(first order difference operator,Roberts operator,Sobel operator and Prewitt operator) are used to compute the local orientation,and then it is compared that the performance of ICG algorithm using the above 4 gradient operators through an experiment.