Towards Robust Visual-Inertial Odometry with Multiple Non-Overlapping Monocular Cameras

We present a Visual-Inertial Odometry (VIO) algorithm with multiple non-overlapping monocular cameras aiming at improving the robustness of the VIO algorithm. An initialization scheme and tightly-coupled bundle adjustment for multiple non-overlapping monocular cameras are proposed. With more stable features captured by multiple cameras, VIO can maintain stable state estimation, especially when one of the cameras tracked unstable or limited features. We also address the high CPU usage rate brought by multiple cameras by proposing a GPU-accelerated frontend. Finally, we use our pedestrian carried system to evaluate the robustness of the VIO algorithm in several challenging environments. The results show that the multi-camera setup yields significantly higher estimation robustness than a monocular system while not increasing the CPU usage rate (reducing the CPU resource usage rate and computational latency by 40.4% and 50.6% on each camera). A demo video can be found at https://youtu.be/r7QvPth1m10.

Automated summary

This paper presents a Visual-Inertial Odometry (VIO) algorithm with multiple non-overlapping monocular cameras to improve the robustness of the VIO algorithm. The algorithm utilizes multiple cameras to capture more stable features, enabling stable state estimation even when some cameras track unstable or limited features. To address the high CPU usage caused by multiple cameras, a GPU-accelerated frontend is proposed. Experimental results using a pedestrian carried system demonstrate that the multi-camera setup significantly improves estimation robustness without increasing CPU usage.