APPLYING A PHENOLOGICAL OBJECT-BASED IMAGE ANALYSIS (PHENOBIA) FOR AGRICULTURAL LAND CLASSIFICATION: A STUDY CASE IN THE BRAZILIAN CERRADO

被引：2

作者：

Bendini, Hugo N. ^{[1
]}

Fonseca, Leila M. G. ^{[1
]}

Soares, Anderson R. ^{[1
]}

Rufin, Philippe ^{[2
,3
]}

Schwieder, Marcel ^{[2
]}

Rodrigues, Marcos A. ^{[1
]}

Maretto, Raian, V ^{[1
]}

Korting, Thales S. ^{[1
]}

Leitao, Pedro J. ^{[2
,4
]}

Sanches, Ieda D. A. ^{[1
]}

Hostert, Patrick ^{[2
,3
]}

机构：

[1] Brazilian Natl Inst Space Res INPE, Sao Jose Dos Campos, Brazil

[2] Humboldt Univ, Geog Dept, Unter Linden 6, D-10099 Berlin, Germany

[3] Humboldt Univ, Integrat Res Inst Transformat Human Environm Syst, Unter Linden 6, D-10099 Berlin, Germany

[4] Tech Univ Braunschwieg, Dept Landscape Ecol & Environm Syst Anal, Langer Kamp 19c, D-38106 Braunschweig, Germany

来源：

IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2020年

基金：

巴西圣保罗研究基金会;

关键词：

Big data; Time-series mining; Phenometrics; OBIA;

D O I：

10.1109/IGARSS39084.2020.9323184

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：1078 / 1081

页数：4

共 18 条

[1]

Baatz M., 2004, ECOGNITION PROFESSIO

[2]

Baatz M., 2000, Journal of Photogrammetry and Remote Sensing, V58, P12

[3] Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis [J].

Belgiu, Mariana ;

Csillik, Ovidiu .

REMOTE SENSING OF ENVIRONMENT, 2018, 204 :509-523

[4] Detailed agricultural land classification in the Brazilian cerrado based on phenological information from dense satellite image time series [J].

Bendini, Hugo do Nascimento ;

Fonseca, Leila Maria Garcia ;

Schwieder, Marcel ;

Korting, Thales Sehn ;

Rufin, Philippe ;

Sanches, Ieda Del Arco ;

Leitao, Pedro J. ;

Hostert, Patrick .

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2019, 82

[5] Object based image analysis for remote sensing [J].

Blaschke, T. .

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2010, 65 (01) :2-16

[6]

Breiman L., 2001, IEEE Trans. Broadcast., V45, P5

[7] Automated parameterisation for multi-scale image segmentation on multiple layers [J].

Dragut, L. ;

Csillik, O. ;

Eisank, C. ;

Tiede, D. .

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2014, 88 :119-127

[8]

Hall M.A., 1998, CORRELATION BASED FE

[9]

Jonsson P., 2015, TIMESAT 3 2 PARALLEL, P22

[10] GeoDMA-Geographic Data Mining Analyst [J].

Koerting, Thales Sehn ;

Garcia Fonseca, Leila Maria ;

Camara, Gilberto .

COMPUTERS & GEOSCIENCES, 2013, 57 :133-145

← 1 2 →