Salient Bundle Adjustment for Visual SLAM

TL;DR

This paper introduces Salient Bundle Adjustment, a novel approach that weights feature points by saliency in visual SLAM, improving accuracy by emphasizing scene-important features, validated on KITTI and EuRoc datasets.

Contribution

It proposes a saliency-based weighting scheme for bundle adjustment in SLAM, integrating scene semantic and geometric info for enhanced performance.

Findings

Outperforms existing SLAM algorithms in accuracy

Effective in both indoor and outdoor environments

Provides open-source dataset and code for future research

Abstract

Recently, the philosophy of visual saliency and attention has started to gain popularity in the robotics community. Therefore, this paper aims to mimic this mechanism in SLAM framework by using saliency prediction model. Comparing with traditional SLAM that treated all feature points as equal important in optimization process, we think that the salient feature points should play more important role in optimization process. Therefore, we proposed a saliency model to predict the saliency map, which can capture both scene semantic and geometric information. Then, we proposed Salient Bundle Adjustment by using the value of saliency map as the weight of the feature points in traditional Bundle Adjustment approach. Exhaustive experiments conducted with the state-of-the-art algorithm in KITTI and EuRoc datasets show that our proposed algorithm outperforms existing algorithms in both indoor and outdoor environments. Finally, we will make our saliency dataset and relevant source code open-source for enabling future research.