abstract

Brief Announcement: Optimized GPU-accelerated Feature Extraction for ORB-SLAM Systems

Authors:

Filippo Muzzini,

Nicola Capodieci,

Roberto Cavicchioli,

Benjamin RouxelAuthors Info & Claims

SPAA '23: Proceedings of the 35th ACM Symposium on Parallelism in Algorithms and Architectures

Pages 299 - 302

https://doi.org/10.1145/3558481.3591310

Published: 17 June 2023 Publication History

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.

Supplemental Material

MP4 File

In this presentation, I briefly describe our work on the acceleration of ORB feature extraction for ORB-SLAM systems. We exploit CUDA-capable GPU to accelerate the ORB extraction phase of the ORB-SLAM system. The acceleration is performed by exploiting CUDA Streams to compute concurrently the independent tasks. Moreover, we identify which tasks can be parallelized computing independently each pixel of the image. Lastly, we propose a novel parallel method to compute the Image Pyramid. The result on well-known datasets shows that our proposal outperforms other state-of-the-art implementations of the ORB-SLAM system.

Download
8.21 MB

References

[1]

Stefano Aldegheri, Nicola Bombieri, Domenico D. Bloisi, and Alessandro Farinelli. 2019. Data Flow ORB-SLAM for Real-time Performance on Embedded GPU Boards. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 5370--5375. https://doi.org/10.1109/IROS40897.2019.8967814

Digital Library

[2]

Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua. 2010. BRIEF: Binary Robust Independent Elementary Features. In Computer Vision -- ECCV 2010, Kostas Daniilidis, Petros Maragos, and Nikos Paragios (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 778--792.

[3]

Carlos Campos, Richard Elvira, Juan J. Gómez Rodríguez, José M. M. Montiel, and Juan D. Tardós. 2021. ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual--Inertial, and Multimap SLAM. IEEE Transactions on Robotics 37, 6 (2021), 1874--1890. https://doi.org/10.1109/TRO.2021.3075644

[4]

Nicola Capodieci, Roberto Cavicchioli, and Andrea Marongiu. 2021. A taxonomy of modern GPGPU programming methods: on the benefits of a unified specification. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 41, 6 (2021), 1649--1662.

[5]

Nicola Capodieci, Roberto Cavicchioli, Ignacio Sañudo Olmedo, Marco Solieri, and Marko Bertogna. 2020. Contending memory in heterogeneous SoCs: Evolution in NVIDIA Tegra embedded platforms. In 2020 IEEE 26th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA). IEEE, 1--10.

[6]

Jakob Engel, Thomas Schöps, and Daniel Cremers. 2014. LSD-SLAM: Large-scale direct monocular SLAM. In European conference on computer vision. Springer, 834--849.

[7]

Andreas Geiger, Philip Lenz, and Raquel Urtasun. 2012. Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In Conference on Computer Vision and Pattern Recognition (CVPR).

Digital Library

[8]

Zhaowei Huang, Yunzhi Chen, and Yiyou Jiang. 2016. ORB-SLAM2 GPU Optimization. http://http://yunchih.github.io/ORB-SLAM2-GPU2016-final/

[9]

Rasheed Hussain and Sherali Zeadally. 2018. Autonomous cars: Research results, issues, and future challenges. IEEE Communications Surveys & Tutorials 21, 2 (2018), 1275--1313.

[10]

Jinwoo Jeon, Sungwook Jung, Eungchang Lee, Duckyu Choi, and Hyun Myung. 2021. Run Your Visual-Inertial Odometry on NVIDIA Jetson: Benchmark Tests on a Micro Aerial Vehicle. IEEE Robotics and Automation Letters 6, 3 (2021), 5332--5339. https://doi.org/10.1109/LRA.2021.3075141

[11]

Georg Klein and David Murray. 2007. Parallel tracking and mapping for small AR workspaces. In 2007 6th IEEE and ACM international symposium on mixed and augmented reality. IEEE, 225--234.

Digital Library

[12]

Zhenzhen Li, Lei Zhang, Chenglong Xu, Fengshan Zou, Jilai Song, and Daji Tian. 2019. An Acceleration Method Using CUDA based on ORB-SLAM2. In 2019 IEEE 9th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER). 1441--1446. https://doi.org/10.1109/ CYBER46603.2019.9066525

[13]

Mamri, Ayoub, Abouzahir, Mohamed, Ramzi, Mustapha, and Latif, Rachid. 2021. ORB-SLAM accelerated on heterogeneous parallel architectures. E3S Web Conf. 229 (2021), 01055. https://doi.org/10.1051/e3sconf/202122901055

[14]

Ra'ul Mur-Artal, J. M. M. Montiel, and Juan D. Tard'os. 2015. ORB-SLAM: a Versatile and Accurate Monocular SLAM System. IEEE Transactions on Robotics 31, 5 (2015), 1147--1163. https://doi.org/10.1109/TRO.2015.2463671

Digital Library

[15]

Ra'ul Mur-Artal and Juan D. Tard'os. 2017. ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras. IEEE Transactions on Robotics 33, 5 (2017), 1255--1262. https://doi.org/10.1109/TRO.2017.2705103

Digital Library

[16]

Ignacio Sañudo Olmedo, Nicola Capodieci, Jorge Luis Martinez, Andrea Marongiu, and Marko Bertogna. 2020. Dissecting the CUDA scheduling hierarchy: a performance and predictability perspective. In 2020 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS). IEEE, 213--225.

[17]

Stefan Peters. 2013. Quadtree- and octree-based approach for point data selection in 2D or 3D. Annals of GIS 19, 1 (2013), 37--44.https://doi.org/10.1080/19475683. 2012.758171 arXiv:https://doi.org/10.1080/19475683.2012.758171

[18]

Paul L Rosin. 1999. Measuring corner properties. Computer Vision and Image Understanding 73, 2 (1999), 291--307.

Digital Library

[19]

Edward Rosten and Tom Drummond. 2006. Machine Learning for High-Speed Corner Detection. In Computer Vision -- ECCV 2006, Ale? Leonardis, Horst Bischof, and Axel Pinz (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 430--443.

Digital Library

[20]

Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. 2011. ORB: An efficient alternative to SIFT or SURF. In 2011 International Conference on Computer Vision. 2564--2571. https://doi.org/10.1109/ICCV.2011.6126544

Digital Library

[21]

P.R. Smith. 1981. Bilinear interpolation of digital images. Ultramicroscopy 6, 2 (1981), 201--204. https://doi.org/10.1016/0304--3991(81)90061--9

[22]

Hauke Strasdat, José MM Montiel, and Andrew J Davison. 2012. Visual SLAM: why filter? Image and Vision Computing 30, 2 (2012), 65--77.

Digital Library

[23]

Magnus Strengert, Martin Kraus, and Thomas Ertl. 2006. Pyramid methods in GPU-based image processing. Proceedings vision, modeling, and visualization 2006 (2006), 169--176.

[24]

Takafumi Taketomi, Hideaki Uchiyama, and Sei Ikeda. 2017. Visual SLAM algorithms: A survey from 2010 to 2016. IPSJ Transactions on Computer Vision and Applications 9, 1 (2017), 1--11.

[25]

Sebastian Thrun. 2007. Simultaneous localization and mapping. In Robotics and cognitive approaches to spatial mapping. Springer, 13--41.

[26]

Huangying Zhan, Chamara Saroj Weerasekera, Jiawang Bian, and Ian Reid. 2019. Visual Odometry Revisited: What Should Be Learnt? arXiv preprint arXiv:1909.09803 (2019).

[27]

Jon Zubizarreta, Iker Aguinaga, and Jose Maria Martinez Montiel. 2020. Direct sparse mapping. IEEE Transactions on Robotics 36, 4 (2020), 1363--1370

Digital Library

Cited By

Giovagnola JCuéllar MSantos D(2024)Context-Adaptable Deployment of FastSLAM 2.0 on Graphic Processing Unit with Unknown Data AssociationApplied Sciences10.3390/app14231146614:23(11466)Online publication date: 9-Dec-2024
https://doi.org/10.3390/app142311466
Muzzini FCapodieci NCavicchioli RRouxel B(2024)High-Performance Feature Extraction for GPU -Accelerated ORB-SLAMx2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)10.23919/DATE58400.2024.10546618(1-2)Online publication date: 25-Mar-2024
https://doi.org/10.23919/DATE58400.2024.10546618

Index Terms

Brief Announcement: Optimized GPU-accelerated Feature Extraction for ORB-SLAM Systems
1. Computer systems organization
  1. Architectures
    1. Parallel architectures
      1. Single instruction, multiple data
  2. Embedded and cyber-physical systems
    1. Embedded systems
      1. Embedded software
    2. Robotics

Recommendations

SIMD Monte-Carlo Numerical Simulations Accelerated on GPU and Xeon Phi

The efficiency of a pleasingly parallel application is studied for several computing platforms. A real world problem, i.e., Monte-Carlo numerical simulations of stratospheric balloon envelope drift descent is considered. We detail the optimization of ...
Electronic poster: a massively parallel lattice Monte Carlo algorithm in CUDA for thermal conduction simulations
SC '11 Companion: Proceedings of the 2011 companion on High Performance Computing Networking, Storage and Analysis Companion

We present a highly parallel CUDA kernel based on the Lattice Monte Carlo (LMC) method for transient thermal conduction, which achieves a peak acceleration of more than 100x over a single-threaded Fortran version. A number of memory and branching ...
Architecture-Aware Mapping and Optimization on a 1600-Core GPU
ICPADS '11: Proceedings of the 2011 IEEE 17th International Conference on Parallel and Distributed Systems

The graphics processing unit (GPU) continues to make in-roads as a computational accelerator for high-performance computing (HPC). However, despite its increasing popularity, mapping and optimizing GPU code remains a difficult task, it is a multi-...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

SPAA '23: Proceedings of the 35th ACM Symposium on Parallelism in Algorithms and Architectures

June 2023

504 pages

ISBN:9781450395458

DOI:10.1145/3558481

General Chair:
Kunal Agrawal
Washington University in St. Louis, USA
,
Program Chair:
Julian Shun
MIT, USA

Copyright © 2023 Owner/Author.

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Sponsors

SIGACT: ACM Special Interest Group on Algorithms and Computation Theory
SIGARCH: ACM Special Interest Group on Computer Architecture
EATCS: European Association for Theoretical Computer Science

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 June 2023

Check for updates

Author Tags

Qualifiers

Abstract

Data Availability

In this presentation, I briefly describe our work on the acceleration of ORB feature extraction for ORB-SLAM systems. We exploit CUDA-capable GPU to accelerate the ORB extraction phase of the ORB-SLAM system. The acceleration is performed by exploiting CUDA Streams to compute concurrently the independent tasks. Moreover, we identify which tasks can be parallelized computing independently each pixel of the image. Lastly, we propose a novel parallel method to compute the Image Pyramid. The result on well-known datasets shows that our proposal outperforms other state-of-the-art implementations of the ORB-SLAM system. https://dl.acm.org/doi/10.1145/3558481.3591310#SPAA23-spaaba014.mp4

Funding Sources

Electronic Components and Systems for European Leadership

Conference

SPAA '23

Sponsor:

SPAA '23: 35th ACM Symposium on Parallelism in Algorithms and Architectures

June 17 - 19, 2023

FL, Orlando, USA

Acceptance Rates

Overall Acceptance Rate 447 of 1,461 submissions, 31%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
219
Total Downloads

Downloads (Last 12 months)109
Downloads (Last 6 weeks)10

Reflects downloads up to 31 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Giovagnola JCuéllar MSantos D(2024)Context-Adaptable Deployment of FastSLAM 2.0 on Graphic Processing Unit with Unknown Data AssociationApplied Sciences10.3390/app14231146614:23(11466)Online publication date: 9-Dec-2024
https://doi.org/10.3390/app142311466
Muzzini FCapodieci NCavicchioli RRouxel B(2024)High-Performance Feature Extraction for GPU -Accelerated ORB-SLAMx2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)10.23919/DATE58400.2024.10546618(1-2)Online publication date: 25-Mar-2024
https://doi.org/10.23919/DATE58400.2024.10546618

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents