New Feature Detection Mechanism for Extended Kalman Filter Based Monocular SLAM with 1-Point RANSAC

TL;DR

This paper introduces a novel feature detection method using KAZE features and 1-point RANSAC to enhance monocular SLAM accuracy, especially under motion blur, outperforming traditional detectors like FAST.

Contribution

The authors propose replacing traditional feature detectors with KAZE features and a rigorous rejection routine to improve SLAM accuracy with fewer features.

Findings

Improved localization accuracy over FAST detector.

Enhanced feature matching in motion blur conditions.

Significant reduction in outliers with 1-point RANSAC.

Abstract

We present a different approach of feature point detection for improving the accuracy of SLAM using single, monocular camera. Traditionally, Harris Corner detection, SURF or FAST corner detectors are used for finding feature points of interest in the image. We replace this with another approach, which involves building a non-linear scale-space representation of images using Perona and Malik Diffusion equation and computing the scale normalized Hessian at multiple scale levels (KAZE feature). The feature points so detected are used to estimate the state and pose of a mono camera using extended Kalman filter. By using accelerated KAZE features and a more rigorous feature rejection routine combined with 1-point RANSAC for outlier rejection, short baseline matching of features are significantly improved, even with a lesser number of feature points, especially in the presence of motion blur. We present a comparative study of our proposal with FAST and show improved localization accuracy in terms of absolute trajectory error.