Interactive Segmentation for Shape From Shading Over HR SAR Images

Franco MARCHESONI-ACLAND; Marie D'AUTUME; Gabriele FACCIOLO; Carlo DE FRANCHIS; Jean-Michel MOREL; Enric MEINHARDT-LLOPIS

doi:10.1109/IGARSS46834.2022.9884193

Interactive Segmentation for Shape From Shading Over HR SAR Images

Franco MARCHESONI-ACLAND, Marie D'AUTUME, Gabriele FACCIOLO, Carlo DE FRANCHIS, Jean-Michel MOREL, Enric MEINHARDT-LLOPIS

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

Abstract

Shape from shading (SfS) enables 3D reconstruction of stockpiles from a single image. However, this method requires proper boundary conditions to work properly. Obtaining such Dirichlet and Neumann conditions is equivalent to a segmentation of the heaps. To get a fast and accurate 3D reconstruction, we propose a simple and interactive segmentation method. SfS is then applied on 0.5-meter resolution Synthetic Aperture Radar (SAR) images with more precise boundary conditions. The results show that prior segmentation is preferable to no segmentation for the stockpiles volume estimation problem. Furthermore, we show that the proposed interactive segmentation method reduces the annotation time needed for such a prior segmentation.

Original language	English
Title of host publication	IGARSS 2022: 2022 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	IEEE
Pages	975-978
Number of pages	4
ISBN (Electronic)	9781665427920
ISBN (Print)	9781665427937
DOIs	https://doi.org/10.1109/IGARSS46834.2022.9884193
Publication status	Published - 2022
Externally published	Yes

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2022-July

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Funding

This work was partially financed by IDEX Paris-Saclay IDI 2016, ANR-11-IDEX-0003-02, Office of Naval research grant N00014-17-1-2552, STIC-Amsud 20-STIC-04, DGA Astrid project ”filmer la Terre” no ANR-17-ASTR-0013-01, MENRT. This work was also using HPC resources from GENCI–IDRIS (grant 2021-AD011011801R1).

Keywords

Dirichlet-Neumann boundary conditions
interactive segmentation
Shape-from-shading
Synthetic Aperture Radar

Access to Document

10.1109/IGARSS46834.2022.9884193

Cite this

MARCHESONI-ACLAND, F., D'AUTUME, M., FACCIOLO, G., DE FRANCHIS, C., MOREL, J.-M., & MEINHARDT-LLOPIS, E. (2022). Interactive Segmentation for Shape From Shading Over HR SAR Images. In IGARSS 2022: 2022 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 975-978). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2022-July). IEEE. https://doi.org/10.1109/IGARSS46834.2022.9884193

@inproceedings{c14e096994ca492a886573bbdb82c390,

title = "Interactive Segmentation for Shape From Shading Over HR SAR Images",

abstract = "Shape from shading (SfS) enables 3D reconstruction of stockpiles from a single image. However, this method requires proper boundary conditions to work properly. Obtaining such Dirichlet and Neumann conditions is equivalent to a segmentation of the heaps. To get a fast and accurate 3D reconstruction, we propose a simple and interactive segmentation method. SfS is then applied on 0.5-meter resolution Synthetic Aperture Radar (SAR) images with more precise boundary conditions. The results show that prior segmentation is preferable to no segmentation for the stockpiles volume estimation problem. Furthermore, we show that the proposed interactive segmentation method reduces the annotation time needed for such a prior segmentation.",

keywords = "Dirichlet-Neumann boundary conditions, interactive segmentation, Shape-from-shading, Synthetic Aperture Radar",

author = "Franco MARCHESONI-ACLAND and Marie D'AUTUME and Gabriele FACCIOLO and \{DE FRANCHIS\}, Carlo and Jean-Michel MOREL and Enric MEINHARDT-LLOPIS",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.",

year = "2022",

doi = "10.1109/IGARSS46834.2022.9884193",

language = "English",

isbn = "9781665427937",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "IEEE",

pages = "975--978",

booktitle = "IGARSS 2022: 2022 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

}

MARCHESONI-ACLAND, F, D'AUTUME, M, FACCIOLO, G, DE FRANCHIS, C, MOREL, J-M & MEINHARDT-LLOPIS, E 2022, Interactive Segmentation for Shape From Shading Over HR SAR Images. in IGARSS 2022: 2022 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2022-July, IEEE, pp. 975-978. https://doi.org/10.1109/IGARSS46834.2022.9884193

Interactive Segmentation for Shape From Shading Over HR SAR Images. / MARCHESONI-ACLAND, Franco; D'AUTUME, Marie; FACCIOLO, Gabriele et al.
IGARSS 2022: 2022 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. IEEE, 2022. p. 975-978 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2022-July).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - Interactive Segmentation for Shape From Shading Over HR SAR Images

AU - MARCHESONI-ACLAND, Franco

AU - D'AUTUME, Marie

AU - FACCIOLO, Gabriele

AU - DE FRANCHIS, Carlo

AU - MOREL, Jean-Michel

AU - MEINHARDT-LLOPIS, Enric

PY - 2022

Y1 - 2022

N2 - Shape from shading (SfS) enables 3D reconstruction of stockpiles from a single image. However, this method requires proper boundary conditions to work properly. Obtaining such Dirichlet and Neumann conditions is equivalent to a segmentation of the heaps. To get a fast and accurate 3D reconstruction, we propose a simple and interactive segmentation method. SfS is then applied on 0.5-meter resolution Synthetic Aperture Radar (SAR) images with more precise boundary conditions. The results show that prior segmentation is preferable to no segmentation for the stockpiles volume estimation problem. Furthermore, we show that the proposed interactive segmentation method reduces the annotation time needed for such a prior segmentation.

AB - Shape from shading (SfS) enables 3D reconstruction of stockpiles from a single image. However, this method requires proper boundary conditions to work properly. Obtaining such Dirichlet and Neumann conditions is equivalent to a segmentation of the heaps. To get a fast and accurate 3D reconstruction, we propose a simple and interactive segmentation method. SfS is then applied on 0.5-meter resolution Synthetic Aperture Radar (SAR) images with more precise boundary conditions. The results show that prior segmentation is preferable to no segmentation for the stockpiles volume estimation problem. Furthermore, we show that the proposed interactive segmentation method reduces the annotation time needed for such a prior segmentation.

KW - Dirichlet-Neumann boundary conditions

KW - interactive segmentation

KW - Shape-from-shading

KW - Synthetic Aperture Radar

UR - https://www.scopus.com/pages/publications/85140384250

U2 - 10.1109/IGARSS46834.2022.9884193

DO - 10.1109/IGARSS46834.2022.9884193

M3 - Conference paper (refereed)

AN - SCOPUS:85140384250

SN - 9781665427937

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 975

EP - 978

BT - IGARSS 2022: 2022 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - IEEE

ER -

MARCHESONI-ACLAND F, D'AUTUME M, FACCIOLO G, DE FRANCHIS C, MOREL JM, MEINHARDT-LLOPIS E. Interactive Segmentation for Shape From Shading Over HR SAR Images. In IGARSS 2022: 2022 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. IEEE. 2022. p. 975-978. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS46834.2022.9884193

Interactive Segmentation for Shape From Shading Over HR SAR Images

Abstract

Publication series

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this