Image Enhancement Preprocessing for Improving Visual Localization and Mapping

We present an enhancement to the ORB-SLAM3 visual localization and mapping algorithm for mobile robots that helps the algorithm to work in conditions of low light or rapid movement. We tested the practicality of the algorithm when used on a low-cost mobile robot platform with limited computational power. We successfully showed that image enhancement can improve the consistency of results in feature extraction and matching. The percentage of matched points between keyframes in the static tests was improved by up to 95% in light conditions and 57% in dark conditions. The image enhancement algorithms improved path quality by 50% - 70% in the rotational tests, and by up to 50% in the zig-zag path following tests. Image enhancement as a pre-feature extraction step in the ORB-SLAM3 algorithm therefore shows promise as a method to improve localization in conditions of low light or rapid movement.