Spotting east African mammals in open savannah from space. Yang, Z. A. W., Tiejun AND Skidmore, A. K. A. d. L., & Jan AND Said, M. Y. A. F. PLoS ONE, 9:e115989, Public Library of Science, 2014.
Paper doi abstract bibtex Knowledge of population dynamics is essential for managing and conserving wildlife. Traditional methods of counting wild animals such as aerial survey or ground counts not only disturb animals, but also can be labour intensive and costly. New, commercially available very high-resolution satellite images offer great potential for accurate estimates of animal abundance over large open areas. However, little research has been conducted in the area of satellite-aided wildlife census, although computer processing speeds and image analysis algorithms have vastly improved. This paper explores the possibility of detecting large animals in the open savannah of Maasai Mara National Reserve, Kenya from very high-resolution GeoEye-1 satellite images. A hybrid image classification method was employed for this specific purpose by incorporating the advantages of both pixel-based and object-based image classification approaches. This was performed in two steps: firstly, a pixel-based image classification method, i.e., artificial neural network was applied to classify potential targets with similar spectral reflectance at pixel level; and then an object-based image classification method was used to further differentiate animal targets from the surrounding landscapes through the applications of expert knowledge. As a result, the large animals in two pilot study areas were successfully detected with an average count error of 8.2%, omission error of 6.6% and commission error of 13.7%. The results of the study show for the first time that it is feasible to perform automated detection and counting of large wild animals in open savannahs from space, and therefore provide a complementary and alternative approach to the conventional wildlife survey techniques.
@ARTICLE{Yang2014,
author = {Yang, Zheng AND Wang, Tiejun AND Skidmore, Andrew K. AND de Leeuw,
Jan AND Said, Mohammed Y. AND Freer, Jim},
title = {Spotting east {A}frican mammals in open savannah from space},
journal = {PLoS ONE},
year = {2014},
volume = {9},
pages = {e115989},
abstract = {<p>Knowledge of population dynamics is essential for managing and
conserving wildlife. Traditional methods of counting wild animals
such as aerial survey or ground counts not only disturb animals,
but also can be labour intensive and costly. New, commercially available
very high-resolution satellite images offer great potential for accurate
estimates of animal abundance over large open areas. However, little
research has been conducted in the area of satellite-aided wildlife
census, although computer processing speeds and image analysis algorithms
have vastly improved. This paper explores the possibility of detecting
large animals in the open savannah of Maasai Mara National Reserve,
Kenya from very high-resolution GeoEye-1 satellite images. A hybrid
image classification method was employed for this specific purpose
by incorporating the advantages of both pixel-based and object-based
image classification approaches. This was performed in two steps:
firstly, a pixel-based image classification method, i.e., artificial
neural network was applied to classify potential targets with similar
spectral reflectance at pixel level; and then an object-based image
classification method was used to further differentiate animal targets
from the surrounding landscapes through the applications of expert
knowledge. As a result, the large animals in two pilot study areas
were successfully detected with an average count error of 8.2%, omission
error of 6.6% and commission error of 13.7%. The results of the study
show for the first time that it is feasible to perform automated
detection and counting of large wild animals in open savannahs from
space, and therefore provide a complementary and alternative approach
to the conventional wildlife survey techniques.</p>},
doi = {10.1371/journal.pone.0115989},
file = {:journal.pone.0115989.pdf:PDF},
owner = {Tiago Marques},
publisher = {Public Library of Science},
timestamp = {2015.02.01},
url = {http://dx.doi.org/10.1371%2Fjournal.pone.0115989}
}
Downloads: 0
{"_id":"jqWex8SQK5yQe4Kv7","bibbaseid":"yang-tiejunandskidmore-janandsaid-spottingeastafricanmammalsinopensavannahfromspace-2014","authorIDs":[],"author_short":["Yang, Z. A. W.","Tiejun AND Skidmore, A. K. A. d. L.","Jan AND Said, M. Y. A. F."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Yang"],"firstnames":["Zheng","AND","Wang"],"suffixes":[]},{"propositions":[],"lastnames":["Tiejun","AND","Skidmore"],"firstnames":["Andrew","K.","AND","de","Leeuw"],"suffixes":[]},{"propositions":[],"lastnames":["Jan","AND","Said"],"firstnames":["Mohammed","Y.","AND","Freer"],"suffixes":[]}],"title":"Spotting east African mammals in open savannah from space","journal":"PLoS ONE","year":"2014","volume":"9","pages":"e115989","abstract":"<p>Knowledge of population dynamics is essential for managing and conserving wildlife. Traditional methods of counting wild animals such as aerial survey or ground counts not only disturb animals, but also can be labour intensive and costly. New, commercially available very high-resolution satellite images offer great potential for accurate estimates of animal abundance over large open areas. However, little research has been conducted in the area of satellite-aided wildlife census, although computer processing speeds and image analysis algorithms have vastly improved. This paper explores the possibility of detecting large animals in the open savannah of Maasai Mara National Reserve, Kenya from very high-resolution GeoEye-1 satellite images. A hybrid image classification method was employed for this specific purpose by incorporating the advantages of both pixel-based and object-based image classification approaches. This was performed in two steps: firstly, a pixel-based image classification method, i.e., artificial neural network was applied to classify potential targets with similar spectral reflectance at pixel level; and then an object-based image classification method was used to further differentiate animal targets from the surrounding landscapes through the applications of expert knowledge. As a result, the large animals in two pilot study areas were successfully detected with an average count error of 8.2%, omission error of 6.6% and commission error of 13.7%. The results of the study show for the first time that it is feasible to perform automated detection and counting of large wild animals in open savannahs from space, and therefore provide a complementary and alternative approach to the conventional wildlife survey techniques.</p>","doi":"10.1371/journal.pone.0115989","file":":journal.pone.0115989.pdf:PDF","owner":"Tiago Marques","publisher":"Public Library of Science","timestamp":"2015.02.01","url":"http://dx.doi.org/10.1371%2Fjournal.pone.0115989","bibtex":"@ARTICLE{Yang2014,\r\n author = {Yang, Zheng AND Wang, Tiejun AND Skidmore, Andrew K. AND de Leeuw,\r\n\tJan AND Said, Mohammed Y. AND Freer, Jim},\r\n title = {Spotting east {A}frican mammals in open savannah from space},\r\n journal = {PLoS ONE},\r\n year = {2014},\r\n volume = {9},\r\n pages = {e115989},\r\n abstract = {<p>Knowledge of population dynamics is essential for managing and\r\n\tconserving wildlife. Traditional methods of counting wild animals\r\n\tsuch as aerial survey or ground counts not only disturb animals,\r\n\tbut also can be labour intensive and costly. New, commercially available\r\n\tvery high-resolution satellite images offer great potential for accurate\r\n\testimates of animal abundance over large open areas. However, little\r\n\tresearch has been conducted in the area of satellite-aided wildlife\r\n\tcensus, although computer processing speeds and image analysis algorithms\r\n\thave vastly improved. This paper explores the possibility of detecting\r\n\tlarge animals in the open savannah of Maasai Mara National Reserve,\r\n\tKenya from very high-resolution GeoEye-1 satellite images. A hybrid\r\n\timage classification method was employed for this specific purpose\r\n\tby incorporating the advantages of both pixel-based and object-based\r\n\timage classification approaches. This was performed in two steps:\r\n\tfirstly, a pixel-based image classification method, i.e., artificial\r\n\tneural network was applied to classify potential targets with similar\r\n\tspectral reflectance at pixel level; and then an object-based image\r\n\tclassification method was used to further differentiate animal targets\r\n\tfrom the surrounding landscapes through the applications of expert\r\n\tknowledge. As a result, the large animals in two pilot study areas\r\n\twere successfully detected with an average count error of 8.2%, omission\r\n\terror of 6.6% and commission error of 13.7%. The results of the study\r\n\tshow for the first time that it is feasible to perform automated\r\n\tdetection and counting of large wild animals in open savannahs from\r\n\tspace, and therefore provide a complementary and alternative approach\r\n\tto the conventional wildlife survey techniques.</p>},\r\n doi = {10.1371/journal.pone.0115989},\r\n file = {:journal.pone.0115989.pdf:PDF},\r\n owner = {Tiago Marques},\r\n publisher = {Public Library of Science},\r\n timestamp = {2015.02.01},\r\n url = {http://dx.doi.org/10.1371%2Fjournal.pone.0115989}\r\n}\r\n\r\n","author_short":["Yang, Z. A. W.","Tiejun AND Skidmore, A. K. A. d. L.","Jan AND Said, M. Y. A. F."],"key":"Yang2014","id":"Yang2014","bibbaseid":"yang-tiejunandskidmore-janandsaid-spottingeastafricanmammalsinopensavannahfromspace-2014","role":"author","urls":{"Paper":"http://dx.doi.org/10.1371%2Fjournal.pone.0115989"},"downloads":0,"html":""},"bibtype":"article","biburl":"http://distancelive.xyz/MainBibFile.bib","creationDate":"2020-06-16T14:23:38.684Z","downloads":0,"keywords":[],"search_terms":["spotting","east","african","mammals","open","savannah","space","yang","tiejun and skidmore","jan and said"],"title":"Spotting east African mammals in open savannah from space","year":2014,"dataSources":["RjvoQBP8rG4o3b4Wi"]}