TY - GEN
T1 - FSLAM
T2 - 21st International Conference on Field-Programmable Technology, FPT 2022
AU - Vemulapati, Vibhakar
AU - Chen, Deming
N1 - Funding Information:
This work is supported in part by the AMD/Xilinx Center of Excellence and the HACC (Heterogenous Accelerated Compute Cluster) at University of Illinois at Urbana-Champaign.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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 accu-racy. ORB-SLAM is an open-sourced feature-based SLAM that achieves high accuracy with reduced computational complexity. We propose an FPGA based ORB-SLAM system, named FSLAM, that accelerates the computationally intensive visual feature extraction and matching on hardware. FSLAM is based on a Zynq-family SoC and 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.
AB - 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 accu-racy. ORB-SLAM is an open-sourced feature-based SLAM that achieves high accuracy with reduced computational complexity. We propose an FPGA based ORB-SLAM system, named FSLAM, that accelerates the computationally intensive visual feature extraction and matching on hardware. FSLAM is based on a Zynq-family SoC and 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.
KW - Autonomous Navigation
KW - Computer Vision
KW - FPGA Accelerator
UR - http://www.scopus.com/inward/record.url?scp=85145616427&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85145616427&partnerID=8YFLogxK
U2 - 10.1109/ICFPT56656.2022.9974562
DO - 10.1109/ICFPT56656.2022.9974562
M3 - Conference contribution
AN - SCOPUS:85145616427
T3 - FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings
BT - FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 5 December 2022 through 9 December 2022
ER -