SRVIO: Super Robust Visual Inertial Odometry for dynamic environments and challenging Loop-closure conditions

TL;DR

This paper introduces SRVIO, a hybrid visual-inertial odometry framework combining geometric and deep learning methods to achieve robust localization in dynamic and challenging environments, outperforming existing approaches.

Contribution

The paper presents a novel hybrid framework based on Vins-Mono that integrates DNNs with geometric SLAM to handle complex real-world challenges more effectively.

Findings

Achieves state-of-the-art results on multiple datasets.

Robustly handles dynamic objects and challenging lighting conditions.

Performs well in extreme simulated scenarios.

Abstract

There has been extensive research on visual localization and odometry for autonomous robots and virtual reality during the past decades. Traditionally, this problem has been solved with the help of expensive sensors, such as lidars. Nowadays, the focus of the leading research in this field is on robust localization using more economic sensors, such as cameras and IMUs. Consequently, geometric visual localization methods have become more accurate in time. However, these methods still suffer from significant loss and divergence in challenging environments, such as a room full of moving people. Scientists started using deep neural networks (DNNs) to mitigate this problem. The main idea behind using DNNs is to better understand challenging aspects of the data and overcome complex conditions such as the movement of a dynamic object in front of the camera that covers the full view of the camera, extreme lighting conditions, and high speed of the camera. Prior end-to-end DNN methods have overcome some of these challenges. However, no general and robust framework is available to overcome all challenges together. In this paper, we have combined geometric and DNN-based methods to have the generality and speed of geometric SLAM frameworks and overcome most of these challenging conditions with the help of DNNs and deliver the most robust framework so far. To do so, we have designed a framework based on Vins-Mono, and show that it is able to achieve state-of-the-art results on TUM-Dynamic, TUM-VI, ADVIO, and EuRoC datasets compared to geometric and end-to-end DNN based SLAMs. Our proposed framework could also achieve outstanding results on extreme simulated cases resembling the aforementioned challenges.