Brief Announcement: Optimized GPU-accelerated Feature Extraction for ORB-SLAM Systems
Open Access
- 17 June 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 299-302
Abstract
Reducing the execution time of ORB-SLAM algorithm is a crucial aspect of autonomous vehicles since it is computationally intensive for embedded boards. We propose a parallel GPU-based implementation, able to run on embedded boards, of the Tracking part of the ORB-SLAM2/3 algorithm. Our implementation is not simply a GPU port of the tracking phase. Instead, we propose a novel method to accelerate image Pyramid construction on GPUs. Comparison against state-of-the-art CPU and GPU implementations, considering both computational time and trajectory errors shows improvement on execution time in well-known datasets, such as KITTI and EuRoC.Keywords
Funding Information
- Electronic Components and Systems for European Leadership (101007311)
This publication has 18 references indexed in Scilit:
- Direct Sparse MappingIEEE Transactions on Robotics, 2020
- Autonomous Cars: Research Results, Issues, and Future ChallengesIEEE Communications Surveys & Tutorials, 2018
- ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D CamerasIEEE Transactions on Robotics, 2017
- Visual SLAM algorithms: a survey from 2010 to 2016IPSJ Transactions on Computer Vision and Applications, 2017
- ORB-SLAM: A Versatile and Accurate Monocular SLAM SystemIEEE Transactions on Robotics, 2015
- LSD-SLAM: Large-Scale Direct Monocular SLAM2014
- Visual SLAM: Why filter?Image and Vision Computing, 2012
- ORB: An efficient alternative to SIFT or SURF2011
- Parallel Tracking and Mapping for Small AR Workspaces2007
- Measuring Corner PropertiesComputer Vision and Image Understanding, 1999