Ungulate Detection and Species Classification from Camera Trap Images Using RetinaNet and Faster R-CNN
Changes in the ungulate population density in the wild has impacts on both the wildlife and human society. In order to control the ungulate population movement, monitoring systems such as camera trap networks have been implemented in a non-invasive setup. However, such systems produce a large number...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-02-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/24/3/353 |
_version_ | 1797471737275744256 |
---|---|
author | Alekss Vecvanags Kadir Aktas Ilja Pavlovs Egils Avots Jevgenijs Filipovs Agris Brauns Gundega Done Dainis Jakovels Gholamreza Anbarjafari |
author_facet | Alekss Vecvanags Kadir Aktas Ilja Pavlovs Egils Avots Jevgenijs Filipovs Agris Brauns Gundega Done Dainis Jakovels Gholamreza Anbarjafari |
author_sort | Alekss Vecvanags |
collection | DOAJ |
description | Changes in the ungulate population density in the wild has impacts on both the wildlife and human society. In order to control the ungulate population movement, monitoring systems such as camera trap networks have been implemented in a non-invasive setup. However, such systems produce a large number of images as the output, hence making it very resource consuming to manually detect the animals. In this paper, we present a new dataset of wild ungulates which was collected in Latvia. Moreover, we demonstrate two methods, which use RetinaNet and Faster R-CNN as backbones, respectively, to detect the animals in the images. We discuss the optimization of training and impact of data augmentation on the performance. Finally, we show the result of aforementioned tune networks over the real world data collected in Latvia. |
first_indexed | 2024-03-09T19:52:27Z |
format | Article |
id | doaj.art-b7b1bc87b6e94ace92f7efc1261d920e |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-09T19:52:27Z |
publishDate | 2022-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-b7b1bc87b6e94ace92f7efc1261d920e2023-11-24T01:07:10ZengMDPI AGEntropy1099-43002022-02-0124335310.3390/e24030353Ungulate Detection and Species Classification from Camera Trap Images Using RetinaNet and Faster R-CNNAlekss Vecvanags0Kadir Aktas1Ilja Pavlovs2Egils Avots3Jevgenijs Filipovs4Agris Brauns5Gundega Done6Dainis Jakovels7Gholamreza Anbarjafari8Institute for Environmental Solutions, LV-4126 Cēsis, LatviaiCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaiCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaiCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaInstitute for Environmental Solutions, LV-4126 Cēsis, LatviaInstitute for Environmental Solutions, LV-4126 Cēsis, LatviaLatvian State Forest Research Institute “Silava”, LV-2169 Salaspils, LatviaInstitute for Environmental Solutions, LV-4126 Cēsis, LatviaInstitute for Environmental Solutions, LV-4126 Cēsis, LatviaChanges in the ungulate population density in the wild has impacts on both the wildlife and human society. In order to control the ungulate population movement, monitoring systems such as camera trap networks have been implemented in a non-invasive setup. However, such systems produce a large number of images as the output, hence making it very resource consuming to manually detect the animals. In this paper, we present a new dataset of wild ungulates which was collected in Latvia. Moreover, we demonstrate two methods, which use RetinaNet and Faster R-CNN as backbones, respectively, to detect the animals in the images. We discuss the optimization of training and impact of data augmentation on the performance. Finally, we show the result of aforementioned tune networks over the real world data collected in Latvia.https://www.mdpi.com/1099-4300/24/3/353RetinaNetFaster R-CNNanimal detectioncamera trapsungulates |
spellingShingle | Alekss Vecvanags Kadir Aktas Ilja Pavlovs Egils Avots Jevgenijs Filipovs Agris Brauns Gundega Done Dainis Jakovels Gholamreza Anbarjafari Ungulate Detection and Species Classification from Camera Trap Images Using RetinaNet and Faster R-CNN Entropy RetinaNet Faster R-CNN animal detection camera traps ungulates |
title | Ungulate Detection and Species Classification from Camera Trap Images Using RetinaNet and Faster R-CNN |
title_full | Ungulate Detection and Species Classification from Camera Trap Images Using RetinaNet and Faster R-CNN |
title_fullStr | Ungulate Detection and Species Classification from Camera Trap Images Using RetinaNet and Faster R-CNN |
title_full_unstemmed | Ungulate Detection and Species Classification from Camera Trap Images Using RetinaNet and Faster R-CNN |
title_short | Ungulate Detection and Species Classification from Camera Trap Images Using RetinaNet and Faster R-CNN |
title_sort | ungulate detection and species classification from camera trap images using retinanet and faster r cnn |
topic | RetinaNet Faster R-CNN animal detection camera traps ungulates |
url | https://www.mdpi.com/1099-4300/24/3/353 |
work_keys_str_mv | AT alekssvecvanags ungulatedetectionandspeciesclassificationfromcameratrapimagesusingretinanetandfasterrcnn AT kadiraktas ungulatedetectionandspeciesclassificationfromcameratrapimagesusingretinanetandfasterrcnn AT iljapavlovs ungulatedetectionandspeciesclassificationfromcameratrapimagesusingretinanetandfasterrcnn AT egilsavots ungulatedetectionandspeciesclassificationfromcameratrapimagesusingretinanetandfasterrcnn AT jevgenijsfilipovs ungulatedetectionandspeciesclassificationfromcameratrapimagesusingretinanetandfasterrcnn AT agrisbrauns ungulatedetectionandspeciesclassificationfromcameratrapimagesusingretinanetandfasterrcnn AT gundegadone ungulatedetectionandspeciesclassificationfromcameratrapimagesusingretinanetandfasterrcnn AT dainisjakovels ungulatedetectionandspeciesclassificationfromcameratrapimagesusingretinanetandfasterrcnn AT gholamrezaanbarjafari ungulatedetectionandspeciesclassificationfromcameratrapimagesusingretinanetandfasterrcnn |