High-Speed Stereo Visual SLAM for Low-Powered Computing Devices

TL;DR

Jetson-SLAM is a GPU-accelerated stereo visual SLAM system optimized for low-powered devices, achieving high frame rates and accuracy through novel techniques like Bounded Rectification and PyCA, validated on multiple challenging datasets.

Contribution

Introduces Jetson-SLAM, a novel GPU-accelerated stereo SLAM system with innovative features for high speed and accuracy on embedded devices.

Findings

Achieves over 60FPS on Jetson-NX and 200FPS on desktop GPUs.

Outperforms existing SLAM systems in speed and accuracy on multiple datasets.

Demonstrates resource efficiency with data-sharing mechanisms.

Abstract

We present an accurate and GPU-accelerated Stereo Visual SLAM design called Jetson-SLAM. It exhibits frame-processing rates above 60FPS on NVIDIA's low-powered 10W Jetson-NX embedded computer and above 200FPS on desktop-grade 200W GPUs, even in stereo configuration and in the multiscale setting. Our contributions are threefold: (i) a Bounded Rectification technique to prevent tagging many non-corner points as a corner in FAST detection, improving SLAM accuracy. (ii) A novel Pyramidal Culling and Aggregation (PyCA) technique that yields robust features while suppressing redundant ones at high speeds by harnessing a GPU device. PyCA uses our new Multi-Location Per Thread culling strategy (MLPT) and Thread-Efficient Warp-Allocation (TEWA) scheme for GPU to enable Jetson-SLAM achieving high accuracy and speed on embedded devices. (iii) Jetson-SLAM library achieves resource efficiency by having a data-sharing mechanism. Our experiments on three challenging datasets: KITTI, EuRoC, and KAIST-VIO, and two highly accurate SLAM backends: Full-BA and ICE-BA show that Jetson-SLAM is the fastest available accurate and GPU-accelerated SLAM system (Fig. 1).