Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Monocular Estimation of Translation, Pose and 3D Shape on Detected Objects using a Convolutional Autoencoder

Persson, Ivar LU ; Ahrnbom, Martin LU orcid and Nilsson, Mikael LU (2022) 17th International Conference on Computer Vision Theory and Applications, VISAPP 2022
 5. p.390-396
Abstract
This paper present a 6DoF-positioning method and shape estimation method for cars from monocular images.
We pre-learn principal components, using Principal Component Analysis (PCA), from the shape of cars and
use a learnt encoder-decoder structure in order to position the cars and create binary masks of each camera instance. The proposed method is tailored towards usefulness for autonomous driving and traffic safety
surveillance. The work introduces a novel encoder-decoder framework for this purpose, thus expanding and
extending state-of-the-art models for the task. Quantitative and qualitative analysis is performed on the Apolloscape dataset, showing promising results, in particular regarding rotations and segmentation... (More)
This paper present a 6DoF-positioning method and shape estimation method for cars from monocular images.
We pre-learn principal components, using Principal Component Analysis (PCA), from the shape of cars and
use a learnt encoder-decoder structure in order to position the cars and create binary masks of each camera instance. The proposed method is tailored towards usefulness for autonomous driving and traffic safety
surveillance. The work introduces a novel encoder-decoder framework for this purpose, thus expanding and
extending state-of-the-art models for the task. Quantitative and qualitative analysis is performed on the Apolloscape dataset, showing promising results, in particular regarding rotations and segmentation masks. (Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Autoencoder, 6DoF-positioning, Traffic Surveillance, Autonomous Vehicles, 6DoF Pose Estimation
host publication
Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications: VISAPP
volume
5
pages
7 pages
publisher
SciTePress
conference name
17th International Conference on Computer Vision Theory and Applications, VISAPP 2022<br/>
conference location
Virtual, Online Streaming
conference dates
2022-02-06 - 2022-02-08
external identifiers
  • scopus:85184963542
ISBN
978-989-758-555-5
DOI
10.5220/0010826600003124
language
English
LU publication?
yes
id
7826f5f8-3e05-4064-b472-8bc9772a9157
date added to LUP
2022-04-04 16:35:26
date last changed
2024-04-12 04:01:24
@inproceedings{7826f5f8-3e05-4064-b472-8bc9772a9157,
  abstract     = {{This paper present a 6DoF-positioning method and shape estimation method for cars from monocular images.<br/>We pre-learn principal components, using Principal Component Analysis (PCA), from the shape of cars and<br/>use a learnt encoder-decoder structure in order to position the cars and create binary masks of each camera instance. The proposed method is tailored towards usefulness for autonomous driving and traffic safety<br/>surveillance. The work introduces a novel encoder-decoder framework for this purpose, thus expanding and<br/>extending state-of-the-art models for the task. Quantitative and qualitative analysis is performed on the Apolloscape dataset, showing promising results, in particular regarding rotations and segmentation masks.}},
  author       = {{Persson, Ivar and Ahrnbom, Martin and Nilsson, Mikael}},
  booktitle    = {{Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications: VISAPP}},
  isbn         = {{978-989-758-555-5}},
  keywords     = {{Autoencoder; 6DoF-positioning; Traffic Surveillance; Autonomous Vehicles; 6DoF Pose Estimation}},
  language     = {{eng}},
  month        = {{02}},
  pages        = {{390--396}},
  publisher    = {{SciTePress}},
  title        = {{Monocular Estimation of Translation, Pose and 3D Shape on Detected Objects using a Convolutional Autoencoder}},
  url          = {{http://dx.doi.org/10.5220/0010826600003124}},
  doi          = {{10.5220/0010826600003124}},
  volume       = {{5}},
  year         = {{2022}},
}