Robust Stereo Feature Descriptor for Visual Odometry

TL;DR

This paper introduces a stereo camera-based feature descriptor that leverages 3D information to enhance robustness against scale changes, significantly improving feature matching and visual odometry accuracy.

Contribution

It presents a novel method utilizing stereo data to normalize feature scale, boosting the performance of SIFT and FREAK descriptors in visual odometry tasks.

Findings

Scale normalization improves SIFT by 8.75%

FREAK descriptor improves by 28.65%

Visual odometry accuracy increases by 23%

Abstract

In this paper, we propose a simple way to utilize stereo camera data to improve feature descriptors. Computer vision algorithms that use a stereo camera require some calculations of 3D information. We leverage this pre-calculated information to improve feature descriptor algorithms. We use the 3D feature information to estimate the scale of each feature. This way, each feature descriptor will be more robust to scale change without significant computations. In addition, we use stereo images to construct the descriptor vector. The Scale-Invariant Feature Transform (SIFT) and Fast Retina Keypoint (FREAK) descriptors are used to evaluate the proposed method. The scale normalization technique in feature tracking test improves the standard SIFT by 8.75% and improves the standard FREAK by 28.65%. Using the proposed stereo feature descriptor, a visual odometry algorithm is designed and tested on the KITTI dataset. The stereo FREAK descriptor raises the number of inlier matches by 19% and consequently improves the accuracy of visual odometry by 23%.