Work-in-Progress: Smart data reduction in SLAM methods for embedded systems - Archive ouverte HAL Access content directly
Conference Poster Year : 2022

Work-in-Progress: Smart data reduction in SLAM methods for embedded systems

(1) , (2) , (1) , (2) , (2) , (3)
1
2
3

Abstract

Visual-inertial simultaneous localization and mapping methods (SLAM) process and store large amounts of data based on image sequences to estimate accurate and robust real-time trajectories. Real-time performances, memory management and low power consumption are critical for embedded SLAM with restrictive hardware resources. We aim at reducing the amount of injected input data in SLAM algorithms and, thereby, the memory footprint while providing improved real-time performances. Two decimation approaches are used, constant filtering and adaptive filtering. The first one decimates input images to reduce frame rate (from 20 to 10, 7, 5 and 2 fps). The latter one uses inertial measurements to reduce the frame rate when no significant motion is detected. Applied to SLAM methods, it produces more accurate trajectories than the constant filtering approach, while further reducing the amount of injected data up to 85%. It also impacts the resource utilization by reducing up to an average of 91% the peak of memory consumption.
Embargoed file
Embargoed file
0 9 11
Year Month Jours
Avant la publication

Dates and versions

cea-03858796 , version 1 (17-11-2022)

Identifiers

Cite

Quentin Picard, Stephane Chevobbe, Mehdi Darouich, Zoe Mandelli, Mathieu Carrier, et al.. Work-in-Progress: Smart data reduction in SLAM methods for embedded systems. CASES 2022 - International Conferenceon Compilers, Architectures, and Synthesis for Embedded Systems, Oct 2022, Shanghai (virtual event), China. IEEE, pp.23-24, 2022, 2022 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems (CASES). ⟨10.1109/CASES55004.2022.00018⟩. ⟨cea-03858796⟩
0 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More