Towards automated delineation of smallholder farm fields from VHR images using convolutional networks

C. Persello; V. Tolpekin; J.R. Bergado; R.A. De By

doi:10.1109/IGARSS.2019.8897979

Towards automated delineation of smallholder farm fields from VHR images using convolutional networks

C. Persello, V. Tolpekin, J.R. Bergado, R.A. De By

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

66 Downloads (Pure)

Abstract

Automated delineation of smallholder farm fields is difficult because of their small size, irregular shape and the use of mixed-cropping systems. Edges between smallholder plots are often indistinct in satellite imagery and contours have to be identified by considering the transition of the complex textural patterns of the fields. We introduce a strategy to delineate field boundaries using a fully convolutional network in combination with a globalization and grouping algorithm to produce a hierarchical segmentation of the fields. We carry out an experimental analysis in a study area in Kofa, Nigeria, using a WorldView-3 image, comparing several state-of-the-art contour detection algorithms. The proposed strategy outperforms state-of-the-art computer vision methods and shows promising results by automatically delineating field boundaries with an accuracy close to human level photo-interpretation.

Original language	English
Title of host publication	2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Subtitle of host publication	Proceedings
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	3836-3839
Number of pages	4
ISBN (Electronic)	978-1-5386-9154-0, 978-1-5386-9153-3 (USB)
ISBN (Print)	978-1-5386-9155-7
DOIs	https://doi.org/10.1109/IGARSS.2019.8897979
Publication status	Published - Jul 2019
Event	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan Duration: 28 Jul 2019 → 2 Aug 2019 Conference number: 39

Publication series

Name	Proceedings International Geoscience and Remote Sensing Symposium (IGARSS)
Publisher	IEEE
Volume	2019
ISSN (Print)	2153-6996
ISSN (Electronic)	2153-7003

Conference

Conference	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Abbreviated title	IGARSS 2019
Country/Territory	Japan
City	Yokohama
Period	28/07/19 → 2/08/19

Keywords

Agriculture and food security
Convolutional neural networks
Deep Learning (DL)
Field boundary extraction
Remote sensing
Smallholder farming
22/3 OA procedure

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/IGARSS.2019.8897979

ArticleFinal published version, 455 KBLicence: Taverne

Cite this

Persello, C., Tolpekin, V., Bergado, J. R., & De By, R. A. (2019). Towards automated delineation of smallholder farm fields from VHR images using convolutional networks. In 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019: Proceedings (pp. 3836-3839). Article 8897979 (Proceedings International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2019). IEEE. https://doi.org/10.1109/IGARSS.2019.8897979

@inproceedings{a463e6bb4aea4c84ae9d66f33be3de9a,

title = "Towards automated delineation of smallholder farm fields from VHR images using convolutional networks",

abstract = "Automated delineation of smallholder farm fields is difficult because of their small size, irregular shape and the use of mixed-cropping systems. Edges between smallholder plots are often indistinct in satellite imagery and contours have to be identified by considering the transition of the complex textural patterns of the fields. We introduce a strategy to delineate field boundaries using a fully convolutional network in combination with a globalization and grouping algorithm to produce a hierarchical segmentation of the fields. We carry out an experimental analysis in a study area in Kofa, Nigeria, using a WorldView-3 image, comparing several state-of-the-art contour detection algorithms. The proposed strategy outperforms state-of-the-art computer vision methods and shows promising results by automatically delineating field boundaries with an accuracy close to human level photo-interpretation.",

keywords = "Agriculture and food security, Convolutional neural networks, Deep Learning (DL), Field boundary extraction, Remote sensing, Smallholder farming, 22/3 OA procedure",

author = "C. Persello and V. Tolpekin and J.R. Bergado and {De By}, R.A.",

year = "2019",

month = jul,

doi = "10.1109/IGARSS.2019.8897979",

language = "English",

isbn = "978-1-5386-9155-7",

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

publisher = "IEEE",

pages = "3836--3839",

booktitle = "2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019",

address = "United States",

note = "39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, IGARSS 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

}

Persello, C, Tolpekin, V, Bergado, JR & De By, RA 2019, Towards automated delineation of smallholder farm fields from VHR images using convolutional networks. in 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019: Proceedings., 8897979, Proceedings International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2019, IEEE, Piscataway, NJ, pp. 3836-3839, 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan, 28/07/19. https://doi.org/10.1109/IGARSS.2019.8897979

Towards automated delineation of smallholder farm fields from VHR images using convolutional networks. / Persello, C.; Tolpekin, V.; Bergado, J.R. et al.
2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019: Proceedings. Piscataway, NJ: IEEE, 2019. p. 3836-3839 8897979 (Proceedings International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Towards automated delineation of smallholder farm fields from VHR images using convolutional networks

AU - Persello, C.

AU - Tolpekin, V.

AU - Bergado, J.R.

AU - De By, R.A.

N1 - Conference code: 39

PY - 2019/7

Y1 - 2019/7

N2 - Automated delineation of smallholder farm fields is difficult because of their small size, irregular shape and the use of mixed-cropping systems. Edges between smallholder plots are often indistinct in satellite imagery and contours have to be identified by considering the transition of the complex textural patterns of the fields. We introduce a strategy to delineate field boundaries using a fully convolutional network in combination with a globalization and grouping algorithm to produce a hierarchical segmentation of the fields. We carry out an experimental analysis in a study area in Kofa, Nigeria, using a WorldView-3 image, comparing several state-of-the-art contour detection algorithms. The proposed strategy outperforms state-of-the-art computer vision methods and shows promising results by automatically delineating field boundaries with an accuracy close to human level photo-interpretation.

AB - Automated delineation of smallholder farm fields is difficult because of their small size, irregular shape and the use of mixed-cropping systems. Edges between smallholder plots are often indistinct in satellite imagery and contours have to be identified by considering the transition of the complex textural patterns of the fields. We introduce a strategy to delineate field boundaries using a fully convolutional network in combination with a globalization and grouping algorithm to produce a hierarchical segmentation of the fields. We carry out an experimental analysis in a study area in Kofa, Nigeria, using a WorldView-3 image, comparing several state-of-the-art contour detection algorithms. The proposed strategy outperforms state-of-the-art computer vision methods and shows promising results by automatically delineating field boundaries with an accuracy close to human level photo-interpretation.

KW - Agriculture and food security

KW - Convolutional neural networks

KW - Deep Learning (DL)

KW - Field boundary extraction

KW - Remote sensing

KW - Smallholder farming

KW - 22/3 OA procedure

U2 - 10.1109/IGARSS.2019.8897979

DO - 10.1109/IGARSS.2019.8897979

M3 - Conference contribution

AN - SCOPUS:85077722319

SN - 978-1-5386-9155-7

T3 - Proceedings International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 3836

EP - 3839

BT - 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019

PB - IEEE

CY - Piscataway, NJ

T2 - 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Persello C, Tolpekin V, Bergado JR , De By RA. Towards automated delineation of smallholder farm fields from VHR images using convolutional networks. In 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019: Proceedings. Piscataway, NJ: IEEE. 2019. p. 3836-3839. 8897979. (Proceedings International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2019.8897979

Towards automated delineation of smallholder farm fields from VHR images using convolutional networks

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this