Evaluation of Stereo Images Matching

Abstract

Image matching and finding correspondence between a stereo image pair is an essential task in digital photogrammetry and computer vision. Stereo images represent the same scene from two different perspectives, and therefore they typically contain a high degree of redundancy. This paper includes an evaluation of implementing manual as well as auto-match between a pair of images that acquired with an overlapped area. Particular target points are selected to be matched manually (22 target points). Auto-matching, based on feature-based matching (FBM) method, has been applied to these target points by using BRISK, FAST, Harris, and MinEigen algorithms. Auto matching is conducted with two main phases: extraction (detection and description) and matching features. The matching techniques used by the prevalent algorithms depend on local point (corner) features. Also, the performance of the algorithms is assessed according to the results obtained from various criteria, such as the number of auto-matched points and the target points that auto-matched. This study aims to determine and evaluate the total root mean square error (RMSE) by comparing coordinates of manual matched target points with those obtained from auto-matching by each of the algorithms. According to the experimental results, the BRISK algorithm gives the higher number of auto-matched points, which equals 2942, while the Harris algorithm gives 378 points representing the lowest number of auto-matched points. All target points are auto-matched with BRISK and FAST algorithms, while 3 and 9 target points only auto-matched with Harris and MinEigen algorithms, respectively. Total RMSE in its minimum value is given by FAST and manual match in the first image, it is 0.002651206 mm, and Harris and manual match provide the minimum value of total RMSE in the second image is 0.002399477 mm.

Two-View Structure-from-Motion with Multiple Feature Detector Operators

“…The acquired set of data can relate to the sensor, among others, as mono-one sensor [8,9] or stereo-two sensors [10,11]. Further, the size of the used dataset can vary for both mono and stereo, so that single view [12,13], two-view [14][15][16] and multi-view [17,18] SfM algorithms are in use.…”

“…Relational matching detects and describes geometric or other patterns, whereas the area-based approach takes the whole image into account to detect patterns based on the intensity values like Grey-Level-Cooccurrence Matrix (GLCM). In contrast, a feature-based process proceeds pixel-wise in order to detect key points, edges and similar smaller units [10]. Several versatile studies have been conducted around the topic of feature detection and matching, i.e., a benchmark, different sensors or applications including a benchmark for consumer cameras datasets to evaluate local features concerning the application [30]; and the choice of a feature detector operator for seasonal change in satellite imagery [31].…”