Towards Robust VSLAM in Dynamic Environments: A Light Field Approach

Abstract

There is a general expectation that robots should operate in urban environments often consisting of potentially dynamic entities like people, automobiles etc. Dynamic objects pose challenges to visual SLAM algorithms by introducing errors into the front-end. This paper presents a Light Field powered SLAM front-end which is robust to dynamic environments. A Light Field captures a bundle of light rays emerging from a single point in space, allowing us to see through dynamic objects occluding the static background via Synthetic Aperture Imaging (SAI). We detect apriori dynamic objects using semantic segmentation and perform semantic guided SAI on the Light Field acquired from a linear camera array. The combined use of SAI with semantic segmentation results in a significant reduction of the dynamic content and also adds valuable observations from the occluded static parts of the scene. The GPU implementation of our algorithm facilitates running at a speed of ~6 fps. We demonstrate considerable improvement in robustness and accuracy of pose estimation in dynamic environments by comparing it with state of the art VSLAM algorithms. Link to video demo: https://rb.gy/mwt5tv