When to use what feature? SIFT, SURF, ORB, or A-KAZE features for monocular visual odometry

Image feature-based ego-motion estimation has been dominating the development of visual odometry (VO) visual simultaneously localisation and mapping (V-SLAM) and structure-from-motion (SfM) for several years. The detection extraction or representation of image features play crucial roles when solving camera pose estimation problems in terms of accuracy and computational cost. In this paper we review three popular classes of image features namely SIFT SURF and ORB as well as the recently proposed A-KAZE features. These image features are evaluated using the KITTI benchmark dataset to conclude about reasons for deciding about the selection of a particular feature when implementing monocular visual odometry.