Fully convolutional networks for street furniture identification in panorama images

Y. Ao, J. Wang, M. Zhou, R. C. Lindenbergh, M. Y. Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

6 Downloads (Pure)

Abstract

Panoramic images are widely used in many scenes, especially in virtual reality and street view capture. However, they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images. This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks (FCN). FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction. In this study, we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data. The results show that in both pre-trained model and fine-tuning, transformed images have better prediction results than panoramic images.
Original languageEnglish
Title of host publicationThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Subtitle of host publicationISPRS Geospatial Week 2019
PublisherInternational Society for Photogrammetry and Remote Sensing (ISPRS)
Pages13-20
Number of pages8
Volume42
Edition2/W13
DOIs
Publication statusPublished - 4 Jun 2019
Event4th ISPRS Geospatial Week 2019 - University of Twente, Enschede, Netherlands
Duration: 10 Jun 201914 Jun 2019
Conference number: 4
https://www.gsw2019.org/

Publication series

NameInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
PublisherCopernicus
ISSN (Print)2194-9034

Conference

Conference4th ISPRS Geospatial Week 2019
CountryNetherlands
CityEnschede
Period10/06/1914/06/19
Internet address

Fingerprint

Semantics
Traffic signs
Virtual reality
Poles
Tuning
Pixels
Scanning
Lasers
Deep learning

Keywords

  • ITC-GOLD

Cite this

Ao, Y., Wang, J., Zhou, M., Lindenbergh, R. C., & Yang, M. Y. (2019). Fully convolutional networks for street furniture identification in panorama images. In The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences: ISPRS Geospatial Week 2019 (2/W13 ed., Vol. 42, pp. 13-20). (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences). International Society for Photogrammetry and Remote Sensing (ISPRS). https://doi.org/10.5194/isprs-archives-XLII-2-W13-13-2019
Ao, Y. ; Wang, J. ; Zhou, M. ; Lindenbergh, R. C. ; Yang, M. Y. / Fully convolutional networks for street furniture identification in panorama images. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences: ISPRS Geospatial Week 2019. Vol. 42 2/W13. ed. International Society for Photogrammetry and Remote Sensing (ISPRS), 2019. pp. 13-20 (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences).
@inproceedings{f3dc682e4da14fd6a9b619b4550542f9,
title = "Fully convolutional networks for street furniture identification in panorama images",
abstract = "Panoramic images are widely used in many scenes, especially in virtual reality and street view capture. However, they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images. This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks (FCN). FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction. In this study, we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data. The results show that in both pre-trained model and fine-tuning, transformed images have better prediction results than panoramic images.",
keywords = "ITC-GOLD",
author = "Y. Ao and J. Wang and M. Zhou and Lindenbergh, {R. C.} and Yang, {M. Y.}",
year = "2019",
month = "6",
day = "4",
doi = "10.5194/isprs-archives-XLII-2-W13-13-2019",
language = "English",
volume = "42",
series = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences",
publisher = "International Society for Photogrammetry and Remote Sensing (ISPRS)",
pages = "13--20",
booktitle = "The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences",
edition = "2/W13",

}

Ao, Y, Wang, J, Zhou, M, Lindenbergh, RC & Yang, MY 2019, Fully convolutional networks for street furniture identification in panorama images. in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences: ISPRS Geospatial Week 2019. 2/W13 edn, vol. 42, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, International Society for Photogrammetry and Remote Sensing (ISPRS), pp. 13-20, 4th ISPRS Geospatial Week 2019, Enschede, Netherlands, 10/06/19. https://doi.org/10.5194/isprs-archives-XLII-2-W13-13-2019

Fully convolutional networks for street furniture identification in panorama images. / Ao, Y.; Wang, J.; Zhou, M.; Lindenbergh, R. C.; Yang, M. Y.

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences: ISPRS Geospatial Week 2019. Vol. 42 2/W13. ed. International Society for Photogrammetry and Remote Sensing (ISPRS), 2019. p. 13-20 (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Fully convolutional networks for street furniture identification in panorama images

AU - Ao, Y.

AU - Wang, J.

AU - Zhou, M.

AU - Lindenbergh, R. C.

AU - Yang, M. Y.

PY - 2019/6/4

Y1 - 2019/6/4

N2 - Panoramic images are widely used in many scenes, especially in virtual reality and street view capture. However, they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images. This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks (FCN). FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction. In this study, we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data. The results show that in both pre-trained model and fine-tuning, transformed images have better prediction results than panoramic images.

AB - Panoramic images are widely used in many scenes, especially in virtual reality and street view capture. However, they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images. This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks (FCN). FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction. In this study, we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data. The results show that in both pre-trained model and fine-tuning, transformed images have better prediction results than panoramic images.

KW - ITC-GOLD

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2019/chap/yang_ful.pdf

U2 - 10.5194/isprs-archives-XLII-2-W13-13-2019

DO - 10.5194/isprs-archives-XLII-2-W13-13-2019

M3 - Conference contribution

VL - 42

T3 - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SP - 13

EP - 20

BT - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

PB - International Society for Photogrammetry and Remote Sensing (ISPRS)

ER -

Ao Y, Wang J, Zhou M, Lindenbergh RC, Yang MY. Fully convolutional networks for street furniture identification in panorama images. In The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences: ISPRS Geospatial Week 2019. 2/W13 ed. Vol. 42. International Society for Photogrammetry and Remote Sensing (ISPRS). 2019. p. 13-20. (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences). https://doi.org/10.5194/isprs-archives-XLII-2-W13-13-2019