A Light Field Front-end for Robust SLAM in Dynamic Environments

TL;DR

This paper introduces a Light Field SLAM front-end that uses synthetic aperture imaging and semantic segmentation to improve robustness and accuracy of visual SLAM in dynamic urban environments, operating at near real-time speeds.

Contribution

It presents a novel Light Field SLAM front-end that detects and sees through dynamic objects using SAI and semantic guidance, eliminating the need for static scene initialization.

Findings

Improved robustness in dynamic environments.

Achieves near real-time processing at 4 fps.

Outperforms state-of-the-art SLAM algorithms in accuracy.

Abstract

There is a general expectation that robots should operate in urban environments often consisting of potentially dynamic entities including people, furniture and automobiles. Dynamic objects pose challenges to visual SLAM algorithms by introducing errors into the front-end. This paper presents a Light Field 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. We simultaneously estimate both the depth map and the refocused image of the static background in a single step eliminating the need for static scene initialization. The GPU implementation of the algorithm facilitates running at close to real time speeds of 4 fps. We demonstrate that our method results in improved robustness and accuracy of pose estimation in dynamic environments by comparing it with state of the art SLAM algorithms.