基于多方向结构张量积的快速角点检测算法

Fast Corner Detection Based on Multi-Directional Structure Tensor

针对各向异性高斯方向导数滤波器运算量大、耗时长的问题,利用盒式滤波器拟合出各向异性高斯方向导数滤波模板,并结合积分图像,提出一种性能优良的快速角点检测算法。利用盒式滤波器设计了6个方向的导数滤波模板,并结合积分图像,快速计算输入图像在各个方向上的导数响应;基于角点的稀疏特性,提出一种候选点粗筛选机制,快速筛选出候选角点区域像素以减少后续运算所涉及的像素数量;针对每一个候选像素,利用各个方向的导数响应构建多方向结构张量积,生成角点测度。将提出的算法与9种经典的检测器在仿射变换、高斯噪声干扰等条件下进行性能评估,在尺寸不同的测试图集上进行耗时对比。实验结果表明,新提出的算法具有优良的检测性能,耗时少,满足实时处理的需求。

In order to solve the problem of large amount of calculation and time-consuming of the anisotropic Gaussian directional derivative filter,this paper uses the box filter to fit the anisotropic Gaussian directional derivative filter template,and proposes a new fast corner detection algorithm with excellent performance by combining template with the integral image.First,six directional derivative filter templates are designed by using box filter,and the derivative response of input image in each direction is calculated quickly by combining with integral image;second,a coarse selection mechanism of candidate pixels is proposed based on the sparsity of corners,which can quickly receive candidate pixels to reduce the number of pixels involved in subsequent operations.For each candidate pixel,the multi-directional structure tensor product is constructed by synthesizing the derivative response of each direction,and the corner measure map is generated.The performance of the proposed algorithm and 9 classical detection algorithms is evaluated under the conditions of affine transformation and Gaussian noise interference,and time-consuming comparisons are carried out on the test image set of different sizes.The experimental results show that the newly proposed algorithm has excellent detection performance and less timeconsuming,and meets the needs of real-time processing.