ORB-based SLAM accelerator on SoC FPGA

TL;DR

This paper presents an FPGA-based acceleration of ORB-SLAM for low-power embedded systems, significantly improving speed and accuracy for autonomous navigation in drones.

Contribution

It introduces a hardware-accelerated ORB-SLAM system on SoC FPGA, enhancing real-time performance and accuracy over existing CPU and FPGA implementations.

Findings

8.5x faster than ARM CPU

1.55x faster than Intel Desktop CPU

2x improvement in accuracy over prior FPGA work

Abstract

Simultaneous Localization and Mapping (SLAM) is one of the main components of autonomous navigation systems. With the increase in popularity of drones, autonomous navigation on low-power systems is seeing widespread application. Most SLAM algorithms are computationally intensive and struggle to run in real-time on embedded devices with reasonable accuracy. ORB-SLAM is an open-sourced feature-based SLAM that achieves high accuracy with reduced computational complexity. We propose an SoC based ORB-SLAM system that accelerates the computationally intensive visual feature extraction and matching on hardware. Our FPGA system based on a Zynq-family SoC runs 8.5x, 1.55x and 1.35x faster compared to an ARM CPU, Intel Desktop CPU, and a state-of-the-art FPGA system respectively, while averaging a 2x improvement in accuracy compared to prior work on FPGA.