Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle
(2023)- Abstract
- It is difficult to perform 3D reconstruction from on-vehicle gathered video due to the large forward motion of the vehicle. Even object detection and human sensing models perform significantly worse on onboard videos when compared to standard benchmarks because objects often appear far away from the camera compared to the standard object detection benchmarks, image quality is often decreased by motion blur and occlusions occur often. This has led to the popularisation of traffic data-specific benchmarks. Recently Light Detection And Ranging (LiDAR) sensors have become popular to directly estimate depths without the need to perform 3D reconstructions. However, LiDAR-based methods still lack in articulated human detection at a distance when... (More)
- It is difficult to perform 3D reconstruction from on-vehicle gathered video due to the large forward motion of the vehicle. Even object detection and human sensing models perform significantly worse on onboard videos when compared to standard benchmarks because objects often appear far away from the camera compared to the standard object detection benchmarks, image quality is often decreased by motion blur and occlusions occur often. This has led to the popularisation of traffic data-specific benchmarks. Recently Light Detection And Ranging (LiDAR) sensors have become popular to directly estimate depths without the need to perform 3D reconstructions. However, LiDAR-based methods still lack in articulated human detection at a distance when compared to image-based methods. We hypothesize that benchmarks targeted at articulated human sensing from LiDAR data could bring about increased research in human sensing and prediction in traffic and could lead to improved traffic safety for pedestrians. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/6ebb84e3-b766-413f-8fc9-f0c58e6755f8
- author
- Priisalu, Maria LU
- organization
- publishing date
- 2023-09-12
- type
- Book/Report
- publication status
- published
- subject
- keywords
- pedestrian detection, autonomous vehicles
- pages
- 53 pages
- publisher
- arXiv.org
- DOI
- 10.48550/arXiv.2309.06313
- project
- Semantic Mapping and Visual Navigation for Smart Robots
- Modelling Pedestrians in Autonomous Vehicle Testing
- language
- English
- LU publication?
- yes
- id
- 6ebb84e3-b766-413f-8fc9-f0c58e6755f8
- date added to LUP
- 2023-10-09 14:21:53
- date last changed
- 2023-11-08 10:48:54
@techreport{6ebb84e3-b766-413f-8fc9-f0c58e6755f8,
abstract = {{It is difficult to perform 3D reconstruction from on-vehicle gathered video due to the large forward motion of the vehicle. Even object detection and human sensing models perform significantly worse on onboard videos when compared to standard benchmarks because objects often appear far away from the camera compared to the standard object detection benchmarks, image quality is often decreased by motion blur and occlusions occur often. This has led to the popularisation of traffic data-specific benchmarks. Recently Light Detection And Ranging (LiDAR) sensors have become popular to directly estimate depths without the need to perform 3D reconstructions. However, LiDAR-based methods still lack in articulated human detection at a distance when compared to image-based methods. We hypothesize that benchmarks targeted at articulated human sensing from LiDAR data could bring about increased research in human sensing and prediction in traffic and could lead to improved traffic safety for pedestrians.}},
author = {{Priisalu, Maria}},
institution = {{arXiv.org}},
keywords = {{pedestrian detection; autonomous vehicles}},
language = {{eng}},
month = {{09}},
title = {{Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle}},
url = {{http://dx.doi.org/10.48550/arXiv.2309.06313}},
doi = {{10.48550/arXiv.2309.06313}},
year = {{2023}},
}