Near Infrared Imaging and Image Pre-Processing to Improve the Automatic Detection of Canada Geese
Migratory shorebirds populations are adversely affected by climate change and loss of habitat thus careful monitoring of their populations is important for early detection of population loss. Current counting methods generally rely on intrusive and time-consuming manual identification. This work is...
Main Author: | |
---|---|
Format: | Thesis |
Language: | unknown |
Published: |
2022
|
Subjects: | |
Online Access: | https://curve.carleton.ca/036d1038-c4f0-4740-984d-094d9d16ce45 https://doi.org/10.22215/etd/2022-15218 https://ocul-crl.primo.exlibrisgroup.com/permalink/01OCUL_CRL/j2o5om/alma991023043899005153 |
id |
ftcarletonuniv:oai:curve.carleton.ca:41724 |
---|---|
record_format |
openpolar |
spelling |
ftcarletonuniv:oai:curve.carleton.ca:41724 2023-05-15T15:46:17+02:00 Near Infrared Imaging and Image Pre-Processing to Improve the Automatic Detection of Canada Geese Szeto, Jacqueline 2022 https://curve.carleton.ca/036d1038-c4f0-4740-984d-094d9d16ce45 https://doi.org/10.22215/etd/2022-15218 https://ocul-crl.primo.exlibrisgroup.com/permalink/01OCUL_CRL/j2o5om/alma991023043899005153 unknown https://curve.carleton.ca/036d1038-c4f0-4740-984d-094d9d16ce45 https://doi.org/10.22215/etd/2022-15218 https://ocul-crl.primo.exlibrisgroup.com/permalink/01OCUL_CRL/j2o5om/alma991023043899005153 Thesis/Dissertation 2022 ftcarletonuniv https://doi.org/10.22215/etd/2022-15218 2023-02-05T00:05:21Z Migratory shorebirds populations are adversely affected by climate change and loss of habitat thus careful monitoring of their populations is important for early detection of population loss. Current counting methods generally rely on intrusive and time-consuming manual identification. This work is part of a larger project to develop automated classification and counting methods using a remotely piloted aircraft system (RPAS). In addition to the use of RPAS, this work will also investigate if near-infrared (NIR) imaging captured by the RPAS yields detection improvements. Healthy vegetation reflects NIR wavelengths of light which can potentially create a greater contrast between an object and the surrounding vegetation. Pre-processing NIR raw images to enhance the contrast between vegetation and Canada geese (Branta canadensis) to improve object detection using the convolutional neural network (CNN) YOLOv4-Tiny have been investigated in this study. Thesis Branta canadensis CURVE - Carleton University Research Virtual Environment Canada |
institution |
Open Polar |
collection |
CURVE - Carleton University Research Virtual Environment |
op_collection_id |
ftcarletonuniv |
language |
unknown |
description |
Migratory shorebirds populations are adversely affected by climate change and loss of habitat thus careful monitoring of their populations is important for early detection of population loss. Current counting methods generally rely on intrusive and time-consuming manual identification. This work is part of a larger project to develop automated classification and counting methods using a remotely piloted aircraft system (RPAS). In addition to the use of RPAS, this work will also investigate if near-infrared (NIR) imaging captured by the RPAS yields detection improvements. Healthy vegetation reflects NIR wavelengths of light which can potentially create a greater contrast between an object and the surrounding vegetation. Pre-processing NIR raw images to enhance the contrast between vegetation and Canada geese (Branta canadensis) to improve object detection using the convolutional neural network (CNN) YOLOv4-Tiny have been investigated in this study. |
format |
Thesis |
author |
Szeto, Jacqueline |
spellingShingle |
Szeto, Jacqueline Near Infrared Imaging and Image Pre-Processing to Improve the Automatic Detection of Canada Geese |
author_facet |
Szeto, Jacqueline |
author_sort |
Szeto, Jacqueline |
title |
Near Infrared Imaging and Image Pre-Processing to Improve the Automatic Detection of Canada Geese |
title_short |
Near Infrared Imaging and Image Pre-Processing to Improve the Automatic Detection of Canada Geese |
title_full |
Near Infrared Imaging and Image Pre-Processing to Improve the Automatic Detection of Canada Geese |
title_fullStr |
Near Infrared Imaging and Image Pre-Processing to Improve the Automatic Detection of Canada Geese |
title_full_unstemmed |
Near Infrared Imaging and Image Pre-Processing to Improve the Automatic Detection of Canada Geese |
title_sort |
near infrared imaging and image pre-processing to improve the automatic detection of canada geese |
publishDate |
2022 |
url |
https://curve.carleton.ca/036d1038-c4f0-4740-984d-094d9d16ce45 https://doi.org/10.22215/etd/2022-15218 https://ocul-crl.primo.exlibrisgroup.com/permalink/01OCUL_CRL/j2o5om/alma991023043899005153 |
geographic |
Canada |
geographic_facet |
Canada |
genre |
Branta canadensis |
genre_facet |
Branta canadensis |
op_relation |
https://curve.carleton.ca/036d1038-c4f0-4740-984d-094d9d16ce45 https://doi.org/10.22215/etd/2022-15218 https://ocul-crl.primo.exlibrisgroup.com/permalink/01OCUL_CRL/j2o5om/alma991023043899005153 |
op_doi |
https://doi.org/10.22215/etd/2022-15218 |
_version_ |
1766380988087140352 |