Automated Bird Counting with Deep Learning for Regional Bird Distribution Mapping
A challenging problem in the field of avian ecology is deriving information on bird population movement trends. This necessitates the regular counting of birds which is usually not an easily-achievable task. A promising attempt towards solving the bird counting problem in a more consistent and fast...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-07-01
|
Series: | Animals |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-2615/10/7/1207 |
_version_ | 1797562359803281408 |
---|---|
author | Hüseyin Gökhan Akçay Bekir Kabasakal Duygugül Aksu Nusret Demir Melih Öz Ali Erdoğan |
author_facet | Hüseyin Gökhan Akçay Bekir Kabasakal Duygugül Aksu Nusret Demir Melih Öz Ali Erdoğan |
author_sort | Hüseyin Gökhan Akçay |
collection | DOAJ |
description | A challenging problem in the field of avian ecology is deriving information on bird population movement trends. This necessitates the regular counting of birds which is usually not an easily-achievable task. A promising attempt towards solving the bird counting problem in a more consistent and fast way is to predict the number of birds in different regions from their photos. For this purpose, we exploit the ability of computers to learn from past data through deep learning which has been a leading sub-field of AI for image understanding. Our data source is a collection of on-ground photos taken during our long run of birding activity. We employ several state-of-the-art generic object-detection algorithms to learn to detect birds, each being a member of one of the 38 identified species, in natural scenes. The experiments revealed that computer-aided counting outperformed the manual counting with respect to both accuracy and time. As a real-world application of image-based bird counting, we prepared the spatial bird order distribution and species diversity maps of Turkey by utilizing the geographic information system (GIS) technology. Our results suggested that deep learning can assist humans in bird monitoring activities and increase citizen scientists’ participation in large-scale bird surveys. |
first_indexed | 2024-03-10T18:28:04Z |
format | Article |
id | doaj.art-dd5c364c4f3d4e29b2f317bfd4c550d5 |
institution | Directory Open Access Journal |
issn | 2076-2615 |
language | English |
last_indexed | 2024-03-10T18:28:04Z |
publishDate | 2020-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Animals |
spelling | doaj.art-dd5c364c4f3d4e29b2f317bfd4c550d52023-11-20T06:54:42ZengMDPI AGAnimals2076-26152020-07-01107120710.3390/ani10071207Automated Bird Counting with Deep Learning for Regional Bird Distribution MappingHüseyin Gökhan Akçay0Bekir Kabasakal1Duygugül Aksu2Nusret Demir3Melih Öz4Ali Erdoğan5Department of Computer Engineering, Akdeniz University, Antalya 07058, TurkeyDepartment of Biology, Akdeniz University, Antalya 07058, TurkeyDepartment of Space Science and Technologies, Akdeniz University, Antalya 07058, TurkeyDepartment of Space Science and Technologies, Akdeniz University, Antalya 07058, TurkeyDepartment of Computer Engineering, Akdeniz University, Antalya 07058, TurkeyDepartment of Biology, Akdeniz University, Antalya 07058, TurkeyA challenging problem in the field of avian ecology is deriving information on bird population movement trends. This necessitates the regular counting of birds which is usually not an easily-achievable task. A promising attempt towards solving the bird counting problem in a more consistent and fast way is to predict the number of birds in different regions from their photos. For this purpose, we exploit the ability of computers to learn from past data through deep learning which has been a leading sub-field of AI for image understanding. Our data source is a collection of on-ground photos taken during our long run of birding activity. We employ several state-of-the-art generic object-detection algorithms to learn to detect birds, each being a member of one of the 38 identified species, in natural scenes. The experiments revealed that computer-aided counting outperformed the manual counting with respect to both accuracy and time. As a real-world application of image-based bird counting, we prepared the spatial bird order distribution and species diversity maps of Turkey by utilizing the geographic information system (GIS) technology. Our results suggested that deep learning can assist humans in bird monitoring activities and increase citizen scientists’ participation in large-scale bird surveys.https://www.mdpi.com/2076-2615/10/7/1207computer visionmachine learningdeep learningbird detectionbird countingbird monitoring |
spellingShingle | Hüseyin Gökhan Akçay Bekir Kabasakal Duygugül Aksu Nusret Demir Melih Öz Ali Erdoğan Automated Bird Counting with Deep Learning for Regional Bird Distribution Mapping Animals computer vision machine learning deep learning bird detection bird counting bird monitoring |
title | Automated Bird Counting with Deep Learning for Regional Bird Distribution Mapping |
title_full | Automated Bird Counting with Deep Learning for Regional Bird Distribution Mapping |
title_fullStr | Automated Bird Counting with Deep Learning for Regional Bird Distribution Mapping |
title_full_unstemmed | Automated Bird Counting with Deep Learning for Regional Bird Distribution Mapping |
title_short | Automated Bird Counting with Deep Learning for Regional Bird Distribution Mapping |
title_sort | automated bird counting with deep learning for regional bird distribution mapping |
topic | computer vision machine learning deep learning bird detection bird counting bird monitoring |
url | https://www.mdpi.com/2076-2615/10/7/1207 |
work_keys_str_mv | AT huseyingokhanakcay automatedbirdcountingwithdeeplearningforregionalbirddistributionmapping AT bekirkabasakal automatedbirdcountingwithdeeplearningforregionalbirddistributionmapping AT duygugulaksu automatedbirdcountingwithdeeplearningforregionalbirddistributionmapping AT nusretdemir automatedbirdcountingwithdeeplearningforregionalbirddistributionmapping AT melihoz automatedbirdcountingwithdeeplearningforregionalbirddistributionmapping AT alierdogan automatedbirdcountingwithdeeplearningforregionalbirddistributionmapping |