東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Mapping Sub-Saharan African Agricult...

Debats, Stephanie Renee.

Linked to FindBook

Google Book

Amazon

博客來

Mapping Sub-Saharan African Agriculture in High-Resolution Satellite Imagery with Computer Vision & Machine Learning.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Mapping Sub-Saharan African Agriculture in High-Resolution Satellite Imagery with Computer Vision & Machine Learning./
Author:	Debats, Stephanie Renee.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
Description:	97 p.
Notes:	Source: Dissertation Abstracts International, Volume: 78-11(E), Section: B.
Contained By:	Dissertation Abstracts International78-11B(E).
Subject:	Remote sensing. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10284969
ISBN:	9780355041743

Mapping Sub-Saharan African Agriculture in High-Resolution Satellite Imagery with Computer Vision & Machine Learning.
Debats, Stephanie Renee.

Mapping Sub-Saharan African Agriculture in High-Resolution Satellite Imagery with Computer Vision & Machine Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 97 p.

Source: Dissertation Abstracts International, Volume: 78-11(E), Section: B.

Thesis (Ph.D.)--Princeton University, 2017.

Smallholder farms dominate in many parts of the world, including Sub-Saharan Africa. These systems are characterized by small, heterogeneous, and often indistinct field patterns, requiring a specialized methodology to map agricultural landcover. In this thesis, we developed a benchmark labeled data set of high-resolution satellite imagery of agricultural fields in South Africa. We presented 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. The algorithm achieved similar high performance across agricultural types, including spectrally indistinct smallholder fields, and demonstrated the ability to generalize across large geographic areas. In sensitivity analyses, we determined multi-temporal images provided greater performance gains than the addition of multi-spectral bands.

ISBN: 9780355041743Subjects--Topical Terms:

535394
Remote sensing.

Mapping Sub-Saharan African Agriculture in High-Resolution Satellite Imagery with Computer Vision & Machine Learning.
LDR:03020nmm a2200325 4500 001 2126945
005 20171128112458.5
008 180830s2017 ||||||||||||||||| ||eng d
020 $a 9780355041743
035 $a (MiAaPQ)AAI10284969
035 $a AAI10284969
040 $a MiAaPQ $c MiAaPQ
100 1 $a Debats, Stephanie Renee. $3 3289052
245 1 0 $a Mapping Sub-Saharan African Agriculture in High-Resolution Satellite Imagery with Computer Vision & Machine Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 97 p.
500 $a Source: Dissertation Abstracts International, Volume: 78-11(E), Section: B.
500 $a Adviser: Kelly K. Caylor.
502 $a Thesis (Ph.D.)--Princeton University, 2017.
520 $a Smallholder farms dominate in many parts of the world, including Sub-Saharan Africa. These systems are characterized by small, heterogeneous, and often indistinct field patterns, requiring a specialized methodology to map agricultural landcover. In this thesis, we developed a benchmark labeled data set of high-resolution satellite imagery of agricultural fields in South Africa. We presented 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. The algorithm achieved similar high performance across agricultural types, including spectrally indistinct smallholder fields, and demonstrated the ability to generalize across large geographic areas. In sensitivity analyses, we determined multi-temporal images provided greater performance gains than the addition of multi-spectral bands.
520 $a We also demonstrated how active learning can be incorporated in the algorithm to create smaller, more efficient training data sets, which reduced computational resources, minimized the need for humans to hand-label data, and boosted performance. We designed a patch-based uncertainty metric to drive the active learning framework, based on the regular grid of a crowdsourcing platform, and demonstrated how subject matter experts can be replaced with fleets of crowdsourcing workers. Our active learning algorithm achieved similar performance as an algorithm trained with randomly selected data, but with 62% less data samples.
520 $a This thesis furthers the goal of providing accurate agricultural landcover maps, at a scale that is relevant for the dominant smallholder class. Accurate maps are crucial for monitoring and promoting agricultural production. Furthermore, improved agricultural landcover maps will aid a host of other applications, including landcover change assessments, cadastral surveys to strengthen smallholder land rights, and constraints for crop modeling and famine prediction.
590 $a School code: 0181.
650 4 $a Remote sensing. $3 535394
650 4 $a Computer science. $3 523869
650 4 $a Environmental engineering. $3 548583
690 $a 0799
690 $a 0984
690 $a 0775
710 2 $a Princeton University. $b Civil and Environmental Engineering. $3 2095365
773 0 $t Dissertation Abstracts International $g 78-11B(E).
790 $a 0181
791 $a Ph.D.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10284969