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 this paper. The goal is to establish the suitability of the SIFT technique for automatic tie point extraction and approximate DSM (Digital Surface Model) generation. First, the performances of the SIFT operator have been compared with those provided by feature extraction and matching techniques used in photogrammetry. All these techniques have been implemented by the authors and validated on aerial and terrestrial images. Moreover, an auto-adaptive version of the SIFT operator has been developed, in order to improve the performances of the SIFT detector in relation to the texture of the images. The Auto-Adaptive SIFT operator (A2 SIFT) has been validated on several aerial images, with particular attention to large scale aerial images acquired using mini-UAV systems.
Highlights
Introduction and State of the ArtFeature extraction is one of the main topics in Photogrammetry and Computer Vision (CV)
The SIFT algorithm has been tested on a set of images and compared with the performances of the traditional feature extraction and matching algorithms used in photogrammetry
A comparison with algorithms commonly used in the photogrammetric community (Forstner operator, Least Square Matching (LSM) technique) has underlined the capacity of SIFT to extract and match homologous points on image pairs with large geometric and photometric distortions
Summary
Feature extraction is one of the main topics in Photogrammetry and Computer Vision (CV). The test results, highlighted optimal performances of the region detectors (in particular SIFT) as far as the number of points extracted is concerned, even though the accuracy was not as high as that of the interest operator ones. In [18] the importance of contrast thresholds of the SIFT in relation to the number of extracted points has been underlined This aspect influences the performances of the SIFT detector, especially in aerial applications over non-urban areas, such as grasslands, ploughed fields or wooded zones. These algorithms usually extract an approximate DSM through a pyramid approach [34]; this approach is useless if a high number of points has already been extracted by SIFT For this reason, a complete and reliable comparison between the SIFT operator and traditional photogrammetric feature extraction and matching techniques has been carried out. The algorithms, the testing methodology and the achieved results will be presented in more detail
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
