performance analysis of the sift operator for automatic feature extraction and matching in photogrammetric applications性能分析筛选操作符的自动特征提取和匹配在摄影测量应用.pdf

Sensors 2009, 9, 3745-3766; doi:10.3390/ OPEN ACCESS sensors ISSN 1424-8220 /journal/sensors Article Performance Analysis of the SIFT Operator for Automatic Feature Extraction and Matching in Photogrammetric Applications Andrea Lingua, Davide Marenchino * and Francesco Nex Politecnico di Torino, DITAG, C.so Duca degli Abruzzi, 24 – 10129, Torino, Italy; E-Mails: andrea.lingua@polito.it (A.L.); francesco.nex@polito.it (F.N.) * Author to whom correspondence should be addressed; E-Mail: davide.marenchino@polito.it; Tel. +39-011-090-7657; Fax: +39-011-090-7699 Received: 21 April 2009; in revised form: 12 May 2009 / Accepted: 18 May 2009 / Published: 18 May 2009 Abstract: In the photogrammetry field, interest in region detectors, which are widely used in Computer Vision, is quickly increasing due to the availability of new techniques. Images acquired by Mobile Mapping Technology, Oblique Photogrammetric Cameras or Unmanned Aerial Vehicles do not observe normal acquisition conditions. Feature extraction and matching techniques, which are traditionally used in photogrammetry, are usually inefficient for these applications as they are unable to provide reliable results under extreme geometrical conditions (convergent taking geometry, strong affine transformations, etc.) and for bad-textured images. A performance analysis of the SIFT technique in aerial and close-range photogrammetric applications is presented in t