一种基于非线性扩散滤波的图像特征检测算法  

Nonlinear-Diffusion-Filtering-Based Feature Detection Algorithm

作　　者：汪方斌 储朱涛[1,2] 朱达荣 刘涛 孙凡[1,2] 冯康康 Wang Fangbin;Chu Zhutao;Zhu Darong;Liu Tao;Sun Fan;Feng Kangkang(School of Mechanical and Electrical Engineering,Anhui Jianzhu University,Hefei,Anhui 230601,China;Key Laboratory of Construction Machinery Fault Diagnosis and Early Warning Technology,Anhui Jianzhu University,Hefei,Anhui 230601,China)

机构地区：[1]安徽建筑大学机械与电气工程学院,安徽合肥230601 [2]安徽建筑大学建筑机械故障诊断与预警重点实验室,安徽合肥230601

出　　处：《激光与光电子学进展》2019年第11期116-122,共7页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61871002);安徽省高校自然科学研究重大项目(KJ2017ZD42);安徽省自然科学基金项目(1808085ME125);安徽省科技强警计划项目(1604d0802013)

摘　　要：利用非线性扩散滤波构造尺度空间,将Hessian矩阵的弱边缘检测能力与Laplace算子的强边缘检测能力相结合,以Hessian矩阵行列式与Laplace算子之比作为特征判据,提出了一种基于非线性扩散滤波的图像特征检测算法,并对点和线仿真图像、Mikolajczyk标准数据库、SALSA偏振相机获取的真实场景图像进行了性能验证。结果表明,所提算法能够检测出图像的强边缘、弱边缘和角点特征,受光照、对比度影响较小,稳健性好。A nonlinear diffusion-filtering based feature detection algorithm was proposed with the scale space constructed by nonlinear diffusion-filtering,in which the ability of Hessian matrix weak edge detection and that of Laplace operator strong edge detection was combined,and the ratio of the Hessian matrix determinant to the Laplace operator was set as feature detection criterion.The performance of the proposed algorithm was validated with the images from simulated points and lines,Mikolajczyk standard database and the real scenes through SALSA polarization camera.The results demonstrated that the proposed algorithm can detect the strong and weak edges and corner points of an image with good robustness less affected by bad illumination or low contrast.

关 键 词：图像处理 特征检测与描述 偏振图像 非线性尺度空间 图像匹配 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]