立体目标的宽基线图像匹配

doi:10.3724/SP.J.1087.2013.00635

计算机应用 ›› 2013, Vol. 33 ›› Issue (03): 635-639.DOI: 10.3724/SP.J.1087.2013.00635

立体目标的宽基线图像匹配

李威^1,2,3*,史泽林^1,2,尹健⁴

1.中国科学院沈阳自动化研究所,沈阳 110016;
2.中国科学院光电信息处理重点实验室,沈阳 110016; 3.中国科学院大学计算机与控制学院,北京 100049;
4.空军装备研究院总体所,北京 100076

收稿日期:2012-09-11 修回日期:2012-10-09 出版日期:2013-03-01 发布日期:2013-03-01
通讯作者: 李威
作者简介:李威(1982-),男,河南唐河人,博士研究生,主要研究方向:自动目标识别与跟踪; 史泽林(1965-),男,江苏宜兴人,研究员,博士生导师,主要研究方向:光电成像、光电跟踪、图像处理、目标识别。
基金资助:
国家973计划项目; 中国科学院国防科技创新基金资助项目(CXJJ-11)。

Wide baseline image matching for 3D objects

LI Wei^1,2,3*, SHI Zelin^1,2, YIN Jian⁴

1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang Liaoning 110016, China;
2.Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang Liaoning 110016, China;
3.School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100049, China;
4.Research Institute on General Development and Argumentation of Equipment of Air Force, Beijing 100076, China

Received:2012-09-11 Revised:2012-10-09 Online:2013-03-01 Published:2013-03-01
Contact: LI WEI

摘要/Abstract

摘要： 为了匹配立体目标的图像特征,提出一种仿射不变的局部特征提取算法。根据高斯滤波器的形状和大小要与图像结构相适应的原理,该算法利用图像中的最大稳定极值区域(MSER)的协方差矩阵衡量局部图像结构,并将局部图像结构变换到圆形高斯滤波器适用的形式下,以解决视角和尺度变化问题。为了保证图像变换的正确性,采用旋转压缩的方式将各向异性的图像结构变换为各向同性的图像结构。最后在各向同性的图像结构上提取尺度不变特征变换(SIFT)特征点,并将SIFT特征点的坐标变回原图像坐标。实验结果表明该算法提取的局部特征是完全仿射不变的,在立体目标的宽基线图像匹配中表现出良好的效果。

关键词: 立体目标图像匹配, 宽基线, 仿射不变, 局部特征提取, 各向异性

Abstract: An affine invariant local feature detector has been put forward for 3D object image matching. In order to cope with view angle and scale changes, this algorithm changed the image structure to fit the circular Gaussian filter according to the principle that Gaussian filter and image structure should be compatible. Local image structures were measured by covariance matrixes of Maximally Stable Extremal Regions (MSER) having been detected in the image. Anisotropic image structures must be rotated and squeezed into isotropic image structures to guarantee the correctness of image transformation. Finally, Scale Invariant Feature Transform (SIFT) features were extracted on isotropic image structures. Coordinates of SIFT features should be changed into the original image coordinates after being extracted. The experimental results indicate that the local features extracted by this algorithm are fully affine invariant. They are suitable to be used in wide baseline image matching for 3D objects.

Key words: 3D object image matching, wide baseline, affine invariant, local feature extraction, anisotropic

中图分类号:

李威史泽林尹健. 立体目标的宽基线图像匹配[J]. 计算机应用, 2013, 33(03): 635-639.

LI Wei SHI Zelin YIN Jian. Wide baseline image matching for 3D objects[J]. Journal of Computer Applications, 2013, 33(03): 635-639.

参考文献

[1]TUYTELAARS T, MIKOLAJCZYK K. Local invariant feature detectors: a survey [J]. Foundations and Trends in Computer Graphics and Vision, 2008, 3(3):177-280.
[2]MIKOLAJCZYK K, TUYTELAARS T, SCHMID C, et al. A comparison of affine region detectors [J]. International Journal of Computer Vision, 2005, 65(1): 43-72.
[3]MIKOLAJCZYK K, SCHMID C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005, 27(10): 1615-1630.
[4]LOWE D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[5]LINDEBERG T. Feature detection with automatic scale selection [J]. International Journal of Computer Vision, 1998, 30(2): 79-116.
[6]MOREL J M, YU G S. Is SIFT scale invariant?[J]. Inverse Problems and Imaging, 2011,5(1): 115-136.
[7]LINDEBERG T, GARDING J. Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure [J]. Image and Vision Computing, 1997, 15(6): 415-434.
[8]MIKOLAJCZYK K, SCHMID C. Scale & affine invariant interest point detectors [J]. International Journal of Computer Vision, 2004, 60(1): 63-86.
[9]RUAN L, SRIDHA S, CLINTON F. Hessian-based affine adaptation of salient local image features [J]. Journal of Mathematical Imaging and Vision, 2012, 44(2):150-167.
[10]YU G S, MOREL J M. ASIFT: a new framework for fully affine invariant image comparison [J]. SIAM Journal on Imaging Sciences, 2009, 2(2):438-469.
[11]MATAS J, CHUM O, URBAN M, et al. Robust wide-baseline stereo from maximally stable extremal regions [J]. Image and Vision Computing, 2004, 22(10): 761-767.
[12]GRDING J, LINDEBERG T. Direct computation of shape cues using scale-adapted spatial derivative operators [J]. International Journal of Computer Vision, 1996, 17(2): 163-191.
[13]FISCHLER M A, BOLLES R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography [J]. Communications of the ACM, 1981, 24(6): 381-395.

[1]	邱云飞, 刘兴. 具有抗仿射性的局部特征点匹配方法[J]. 计算机应用, 2020, 40(4): 1133-1137.
[2]	杨文霞, 张亮. 基于对数函数的非局部总变分图像修复模型[J]. 计算机应用, 2018, 38(6): 1784-1789.
[3]	黄志标, 姚宇. 基于像素聚类的超声图像分割[J]. 计算机应用, 2017, 37(2): 569-573.
[4]	海涛, 席志红. 各向异性四阶偏微分方程耦合二阶偏微分方程的图像放大[J]. 计算机应用, 2015, 35(4): 1084-1088.
[5]	刘建磊, 刘晓亮. 基于拐点线的大雾能见度检测算法[J]. 计算机应用, 2015, 35(2): 528-530.
[6]	张芳崔学英张权董婵婵刘祎孙未雅白云蛟桂志国. 基于变指数各向异性扩散和非局部的最大似然期望最大低剂量CT重建算法[J]. 计算机应用, 2014, 34(12): 3605-3608.
[7]	陈劲源李建华郭卫斌. 改进的硅各向异性腐蚀GPU并行模拟[J]. 计算机应用, 2013, 33(12): 3317-3320.
[8]	刘欢朱平肖蓉唐卫东. 基于立体视觉的新组合不变矩腹部体型重建[J]. 计算机应用, 2013, 33(11): 3183-3186.
[9]	吴世彬陈波董万利高小明. 基于Mallat-Zhong离散小波变换小波的超声图像各向异性扩散抑噪方法[J]. 计算机应用, 2013, 33(11): 3201-3203.
[10]	刘琬臻付忠良. 基于局部方差改进的超声图像各向异性扩散去噪算法[J]. 计算机应用, 2013, 33(09): 2599-2602.
[11]	上官宏刘祎张权桂志国. 基于解剖非局部先验的模糊扩散PET重建算法[J]. 计算机应用, 2013, 33(09): 2627-2630.
[12]	马阿敏杨荣骞宁海白红民黎丽华吴效明. 脑部MRI图像头皮三维提取及重建[J]. 计算机应用, 2013, 33(05): 1439-1442.
[13]	李晓红张权刘祎桂志国. 基于小波收缩和正逆扩散结合的优质中值先验图像重建算法[J]. 计算机应用, 2012, 32(12): 3357-3360.
[14]	杨金刘志勤王耀彬高小明. 基于对数压缩的超声各向异性扩散去噪方法[J]. 计算机应用, 2012, 32(11): 3218-3220.
[15]	柯丹丹蔡光程曹倩倩. 基于图像特征的各向异性扩散去噪方法[J]. 计算机应用, 2012, 32(03): 742-745.

立体目标的宽基线图像匹配

Wide baseline image matching for 3D objects

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics