GSL-VO: A Geometric-Semantic Information Enhanced Lightweight Visual Odometry in Dynamic Environments

Recently, learning-based visual odometry (VO) has attained remarkable success in vision-based measurement, especially in indoor robotics. Unfortunately, existing methods usually underexplore geometric-semantic (G-S) information, thus resulting in inefficient perception in unseen dynamic environments. Meanwhile, they are usually time-consuming, since they typically rely on high-complexity semantic segmentation models, resulting in concurrence reduction. In this article, we develop a G-S information enhanced lightweight VO (GSL-VO) that can work particularly well in dynamic environments. Specifically, on the one hand, to improve the robustness of VO through G-S information, we first come up with a novel image enhancement module to tackle motion blur, thus enabling accurate geometric and semantic information extraction. Second, we design an adaptive G-S information processing module that combines geometric and semantic information to retain reliable features for pose measurement. Moreover, semantic information is expressed via a probability framework for accurate and robust movable object extraction. On the other hand, we further propose a lightweight semantic segmentation model that enjoys an efficient multilevel feature aggregation capability to address the speed bottleneck of VO. A series of experiments on two well-known RGB-D dynamic datasets indicate that our proposed method is both accurate and fast: while achieving a significant average improvement of 70.5% in absolute trajectory error (ATE) over state-of-the-art learning-based VO on Bonn RGB-D Dynamic dataset, GSL-VO leads to high 22.3 FPS on a low-cost platform, which makes it well-suited for practical scenarios. Remarkably, on a challenging dynamic sequence of TUM RGB-D dataset, GSL-VO improves the baseline VO by 88.9% in ATE.

Duke Scholars

Author Kaizhu Huang DKU Faculty