A generalized computer vision approach to mapping crop fields in heterogeneous agricultural landscapes

REMOTE SENSING OF ENVIRONMENT

卷:179

Article

Debats, Stephanie R.¹  Luo, Dee²  Estes, Lyndon D.¹  Fuchs, Thomas J.³  Caylor, Kelly K.¹ 

[1] Princeton Univ, Dept Civil & Environm Engn, Princeton, NJ 08544 USA

[2] Princeton Univ, Dept Operat Res & Financial Engn, Princeton, NJ 08544 USA

[3] NASA, Jet Prop Lab, Pasadena, CA 91109 USA

关键词: Land cover;    Agriculture;    Sub-Saharan Africa;    Computer vision;    Machine learning;   

DOI  :  10.1016/j.rse.2016.03.010

来源: Elsevier

【 摘 要 】

Smallholder farms dominate in many parts of the world, particularly Sub-Saharan Africa. These systems are characterized by small, heterogeneous, and often indistinct field patterns, requiring a specialized methodology to map agricultural land cover. Using a variety of sites in South Africa, we present a new approach to mapping agricultural fields, based on efficient extraction of a vast set of simple, highly correlated, and interdependent features, followed by a random forest classifier. We achieved similar high performance across agricultural types, including the spectrally indistinct smallholder fields as well as the more easily distinguishable commercial fields, and demonstrated the ability to generalize performance across large geographic areas. In sensitivity analyses, we determined multi-temporal information provided greater gains in performance than the addition of multi-spectral bands available in DigitalGlobe Worldview-2 imagery. (C) 2016 Elsevier Inc. All rights reserved.

【 授权许可】

Free