#286: Evaluation of feature matching in aerial imagery for Structure-from Motion and bundle adjustment

K. Gao, H. AliAkbarpour, K. Palaniappan, and G. Seetharaman

International Society for Optics and Photonics, Volume 10645, pgs. 106450J, 2018

feature matching, evaluation, structure-from-motion, 3d reconstruction

PlainText, Bibtex, PDF, URL, DOI, Google Scholar


Local feature matching has been proven to be successful for computer vision tasks such as Structure-from-Motion (SfM) and 3D reconstruction. Reliability of features in terms of being precisely detected and persistently matched along a sequence can have a great impact on the quality of the SfM and even on its convergence. Since many feature detectors and descriptors are exclusively designed for specific applications, it is important to find a feature detector-descriptor combination that performs well for SfM. In this paper we evaluate the quality of different image features such as FAST, SIFT, SURF, and BRISK and their effects on the Structure-from-Motion performance. To do this end, we design and perform two evaluation procedures to assess a feature matching result on a wide area motion imagery dataset. A matching result is represented in the form of feature track and a track is a collection of continuously matched feature points along the sequence. First we use the concept of Epipolar geometry to measure errors in each correspondence (matching pair). The distance from a matched feature point to the corresponding epipolar line is measured as the error metric. Second, we compute an optimized metadata from SfM using feature matching tracks and then compare it with the ground truth metadata for evaluation. Experimental results demonstrate that SURF detector combined with SURF descriptor generates the longest feature tracks while FAST detector plus SIFT descriptor produces the highest matching precision.