CFORB: Circular FREAK-ORB Visual Odometry

TL;DR

CFORB is a novel visual odometry algorithm combining ORB features and FREAK descriptors, utilizing new geometric constraints and circular matching to improve robustness in diverse environments, tested on KITTI and indoor datasets.

Contribution

The paper introduces CFORB, a visual odometry method that integrates ORB and FREAK features with innovative geometric constraints and circular matching, enhancing performance in varied terrains.

Findings

Achieves 3.73% translational error on KITTI dataset.

Attains 0.0107 deg/m rotational error on KITTI.

Performs well in indoor and textured environments.

Abstract

We present a novel Visual Odometry algorithm entitled Circular FREAK-ORB (CFORB). This algorithm detects features using the well-known ORB algorithm [12] and computes feature descriptors using the FREAK algorithm [14]. CFORB is invariant to both rotation and scale changes, and is suitable for use in environments with uneven terrain. Two visual geometric constraints have been utilized in order to remove invalid feature descriptor matches. These constraints have not previously been utilized in a Visual Odometry algorithm. A variation to circular matching [16] has also been implemented. This allows features to be matched between images without having to be dependent upon the epipolar constraint. This algorithm has been run on the KITTI benchmark dataset and achieves a competitive average translational error of $3.73 \%$ and average rotational error of $0.0107 deg/m$. CFORB has also been run in an indoor environment and achieved an average translational error of $3.70 \%$. After running CFORB in a highly textured environment with an approximately uniform feature spread across the images, the algorithm achieves an average translational error of $2.4 \%$ and an average rotational error of $0.009 deg/m$.