Analysis of feature detector and descriptor combinations with a localization experiment for various performance metrics

Abstract

The purpose of this study is to provide a detailed performance comparison of feature detector/descriptor methods, particularly when their various combinations are used for image-matching. The localization experiments of a mobile robot in an indoor environment are presented as a case study. In these experiments, 3090 query images and 127 dataset images were used. This study includes five methods for feature detectors (features from accelerated segment test (FAST), oriented FAST and rotated binary robust independent elementary features (BRIEF) (ORB), speeded-up robust features (SURF), scale invariant feature transform (SIFT), and binary robust invariant scalable keypoints (BRISK)) and five other methods for feature descriptors (BRIEF, BRISK, SIFT, SURF, and ORB). These methods were used in 23 different combinations and it was possible to obtain meaningful and consistent comparison results using the performance criteria defined in this study. All of these methods were used independently and separately from each other as either feature detector or descriptor. The performance analysis shows the discriminative power of various combinations of detector and descriptor methods. The analysis is completed using five parameters: (i) accuracy, (ii) time, (iii) angle difference between keypoints, (iv) number of correct matches, and (v) distance between correctly matched keypoints. In a range of 60°, covering five rotational pose points for our system, the FAST-SURF combination had the lowest distance and angle difference values and the highest number of matched keypoints. SIFT-SURF was the most accurate combination with a 98.41% correct classification rate. The fastest algorithm was ORB-BRIEF, with a total running time of 21,303.30 s to match 560 images captured during motion with 127 dataset images.