AI-based 3D detection of parked vehicles on a mobile mapping platform using edge computing
Loading...
Author (Corporation)
Publication date
2022
Typ of student thesis
Course of study
Collections
Type
04B - Conference paper
Editors
Editor (Corporation)
Supervisor
Parent work
The international archives of the photogrammetry, remote sensing and spatial information sciences
Special issue
DOI of the original publication
Link
Series
Series number
Volume
XLIII-B1-2022
Issue / Number
Pages / Duration
437-445
Patent number
Publisher / Publishing institution
Place of publication / Event location
Nice
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
In this paper we present an edge-based hardware and software framework for the 3D detection and mapping of parked vehicles on a mobile mapping platform for the use case of on-street parking statistics. First, we investigate different point cloud-based 3D object detection methods on our extremely dense and noisy depth maps obtained from low-cost RGB-D sensors to find a suitable object detector and determine the optimal preparation of our data. We then retrain the chosen object detector to detect all types of vehicles, rather than standard cars only. Finally, we design and develop a software framework integrating the newly trained object detector. By repeating the parking statistics of our previous work (Nebiker et al., 2021), our software is tested regarding the detection accuracy. With our edge-based framework, we achieve a precision and recall of 100% and 98% respectively on any parking configuration and vehicle type, outperforming all other known work on on-street parking statistics. Furthermore, our software is evaluated in terms of processing speed and volume of generated data. While the processing speed reaches only 1.9 frames per second due to limited computing resources, the amount of data generated is just 0.25 KB per frame.
Keywords
3D vehicle detection, Deep neural networks, Edge computing, Mobile mapping, RGB-D, Robot operating system, Point clouds
Subject (DDC)
Event
XXIVth ISPRS Congress
Exhibition start date
Exhibition end date
Conference start date
06.06.2022
Conference end date
11.06.2022
Date of the last check
ISBN
ISSN
Language
English
Created during FHNW affiliation
Yes
Strategic action fields FHNW
Publication status
Published
Review
Peer review of the complete publication
Open access category
Gold
Citation
Meyer, J., Blaser, S., & Nebiker, S. (2022). AI-based 3D detection of parked vehicles on a mobile mapping platform using edge computing. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B1-2022, 437–445. https://doi.org/10.5194/isprs-archives-xliii-b1-2022-437-2022