Applying a phenological object-based image analysis (phenobia) for agricultural land classification: A study case in the Brazilian Cerrado

Hugo N. Bendini; Leila M.G. Fonseca; Anderson R. Soares; Philippe Rufin; Marcel Schwieder; Marcos A. Rodrigues; R.V. Maretto; Thales S. Korting; Pedro J. Leitao; Ieda D.A. Sanches; Patrick Hostert

doi:10.1109/IGARSS39084.2020.9323184

Applying a phenological object-based image analysis (phenobia) for agricultural land classification: A study case in the Brazilian Cerrado

Hugo N. Bendini^*, Leila M.G. Fonseca, Anderson R. Soares, Philippe Rufin, Marcel Schwieder, Marcos A. Rodrigues, R.V. Maretto, Thales S. Korting, Pedro J. Leitao, Ieda D.A. Sanches, Patrick Hostert

^*Corresponding author for this work

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

2 Citations (Scopus)

Abstract

Mapping agriculture with high accuracy is important to generate reliable information about crop production. Pixel-based methods still present problems with noise and usually require post-processing approaches to reach satisfactory results. Object-based Image Analysis (OBIA) enable the detection of homogeneous objects in remote sensing images based on spectral similarity. However, traditional OBIA does not consider the multi-temporal characteristics of land cover or land use, such as agriculture. The objective of this study is to evaluate a phenological object-based approach with dense Landsat image time series for mapping agriculture in different level of detail in the Brazilian Cerrado. We derived pixel-wise EVI fitted time series with 8-day temporal resolution and applied multi-resolution segmentation using all image bands to incorporate the influence of space and time. Then we generated phenological metrics and applied OBIA of agricultural lands in Brazil using a hierarchical classification scheme. The overall accuracies for each hierarchical level were around 90%, and the spatial consistency of the generated maps is promising.

Original language	English
Title of host publication	2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings
Publisher	IEEE
Pages	1078-1081
Number of pages	4
ISBN (Electronic)	9781728163741
DOIs	https://doi.org/10.1109/IGARSS39084.2020.9323184
Publication status	Published - 26 Sep 2020
Externally published	Yes
Event	2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Virtual, Waikoloa, United States Duration: 26 Sep 2020 → 2 Oct 2020

Conference

Conference	2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
Abbreviated title	IGARSS 2020
Country/Territory	United States
City	Virtual, Waikoloa
Period	26/09/20 → 2/10/20

Keywords

Big data
OBIA
Phenometrics
Time-series mining
ITC-CV
n/a OA procedure

Access to Document

10.1109/IGARSS39084.2020.9323184

Cite this

Bendini, H. N., Fonseca, L. M. G., Soares, A. R., Rufin, P., Schwieder, M., Rodrigues, M. A., Maretto, R. V., Korting, T. S., Leitao, P. J., Sanches, I. D. A., & Hostert, P. (2020). Applying a phenological object-based image analysis (phenobia) for agricultural land classification: A study case in the Brazilian Cerrado. In 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings (pp. 1078-1081). [9323184] IEEE. https://doi.org/10.1109/IGARSS39084.2020.9323184

@inproceedings{a8d8d55adb0d4302a64b64af0a321808,

title = "Applying a phenological object-based image analysis (phenobia) for agricultural land classification: A study case in the Brazilian Cerrado",

abstract = "Mapping agriculture with high accuracy is important to generate reliable information about crop production. Pixel-based methods still present problems with noise and usually require post-processing approaches to reach satisfactory results. Object-based Image Analysis (OBIA) enable the detection of homogeneous objects in remote sensing images based on spectral similarity. However, traditional OBIA does not consider the multi-temporal characteristics of land cover or land use, such as agriculture. The objective of this study is to evaluate a phenological object-based approach with dense Landsat image time series for mapping agriculture in different level of detail in the Brazilian Cerrado. We derived pixel-wise EVI fitted time series with 8-day temporal resolution and applied multi-resolution segmentation using all image bands to incorporate the influence of space and time. Then we generated phenological metrics and applied OBIA of agricultural lands in Brazil using a hierarchical classification scheme. The overall accuracies for each hierarchical level were around 90%, and the spatial consistency of the generated maps is promising.",

keywords = "Big data, OBIA, Phenometrics, Time-series mining, ITC-CV, n/a OA procedure",

author = "Bendini, {Hugo N.} and Fonseca, {Leila M.G.} and Soares, {Anderson R.} and Philippe Rufin and Marcel Schwieder and Rodrigues, {Marcos A.} and R.V. Maretto and Korting, {Thales S.} and Leitao, {Pedro J.} and Sanches, {Ieda D.A.} and Patrick Hostert",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020, IGARSS 2020 ; Conference date: 26-09-2020 Through 02-10-2020",

year = "2020",

month = sep,

day = "26",

doi = "10.1109/IGARSS39084.2020.9323184",

language = "English",

pages = "1078--1081",

booktitle = "2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings",

publisher = "IEEE",

}

Bendini, HN, Fonseca, LMG, Soares, AR, Rufin, P, Schwieder, M, Rodrigues, MA, Maretto, RV, Korting, TS, Leitao, PJ, Sanches, IDA & Hostert, P 2020, Applying a phenological object-based image analysis (phenobia) for agricultural land classification: A study case in the Brazilian Cerrado. in 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings., 9323184, IEEE, pp. 1078-1081, 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020, Virtual, Waikoloa, United States, 26/09/20. https://doi.org/10.1109/IGARSS39084.2020.9323184

Applying a phenological object-based image analysis (phenobia) for agricultural land classification : A study case in the Brazilian Cerrado. / Bendini, Hugo N.; Fonseca, Leila M.G.; Soares, Anderson R. et al.

2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings. IEEE, 2020. p. 1078-1081 9323184.

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

TY - GEN

T1 - Applying a phenological object-based image analysis (phenobia) for agricultural land classification

T2 - 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020

AU - Bendini, Hugo N.

AU - Fonseca, Leila M.G.

AU - Soares, Anderson R.

AU - Rufin, Philippe

AU - Schwieder, Marcel

AU - Rodrigues, Marcos A.

AU - Maretto, R.V.

AU - Korting, Thales S.

AU - Leitao, Pedro J.

AU - Sanches, Ieda D.A.

AU - Hostert, Patrick

PY - 2020/9/26

Y1 - 2020/9/26

N2 - Mapping agriculture with high accuracy is important to generate reliable information about crop production. Pixel-based methods still present problems with noise and usually require post-processing approaches to reach satisfactory results. Object-based Image Analysis (OBIA) enable the detection of homogeneous objects in remote sensing images based on spectral similarity. However, traditional OBIA does not consider the multi-temporal characteristics of land cover or land use, such as agriculture. The objective of this study is to evaluate a phenological object-based approach with dense Landsat image time series for mapping agriculture in different level of detail in the Brazilian Cerrado. We derived pixel-wise EVI fitted time series with 8-day temporal resolution and applied multi-resolution segmentation using all image bands to incorporate the influence of space and time. Then we generated phenological metrics and applied OBIA of agricultural lands in Brazil using a hierarchical classification scheme. The overall accuracies for each hierarchical level were around 90%, and the spatial consistency of the generated maps is promising.

AB - Mapping agriculture with high accuracy is important to generate reliable information about crop production. Pixel-based methods still present problems with noise and usually require post-processing approaches to reach satisfactory results. Object-based Image Analysis (OBIA) enable the detection of homogeneous objects in remote sensing images based on spectral similarity. However, traditional OBIA does not consider the multi-temporal characteristics of land cover or land use, such as agriculture. The objective of this study is to evaluate a phenological object-based approach with dense Landsat image time series for mapping agriculture in different level of detail in the Brazilian Cerrado. We derived pixel-wise EVI fitted time series with 8-day temporal resolution and applied multi-resolution segmentation using all image bands to incorporate the influence of space and time. Then we generated phenological metrics and applied OBIA of agricultural lands in Brazil using a hierarchical classification scheme. The overall accuracies for each hierarchical level were around 90%, and the spatial consistency of the generated maps is promising.

KW - Big data

KW - OBIA

KW - Phenometrics

KW - Time-series mining

KW - ITC-CV

KW - n/a OA procedure

UR - https://ezproxy2.utwente.nl/login?url=https://doi.org/10.1109/IGARSS39084.2020.9323184

U2 - 10.1109/IGARSS39084.2020.9323184

DO - 10.1109/IGARSS39084.2020.9323184

M3 - Conference contribution

AN - SCOPUS:85102014101

SP - 1078

EP - 1081

BT - 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings

PB - IEEE

Y2 - 26 September 2020 through 2 October 2020

ER -

Bendini HN, Fonseca LMG, Soares AR, Rufin P, Schwieder M, Rodrigues MA et al. Applying a phenological object-based image analysis (phenobia) for agricultural land classification: A study case in the Brazilian Cerrado. In 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings. IEEE. 2020. p. 1078-1081. 9323184 doi: 10.1109/IGARSS39084.2020.9323184

Applying a phenological object-based image analysis (phenobia) for agricultural land classification: A study case in the Brazilian Cerrado

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this