Cargando…
An approach to rapid processing of camera trap images with minimal human input
1. Camera traps have become an extensively utilized tool in ecological research, but the manual processing of images created by a network of camera traps rapidly becomes an overwhelming task, even for small camera trap studies. 2. We used transfer learning to create convolutional neural network (CNN...
Autores principales: | , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
John Wiley and Sons Inc.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8427629/ https://www.ncbi.nlm.nih.gov/pubmed/34522360 http://dx.doi.org/10.1002/ece3.7970 |
_version_ | 1783750214922797056 |
---|---|
author | Duggan, Matthew T. Groleau, Melissa F. Shealy, Ethan P. Self, Lillian S. Utter, Taylor E. Waller, Matthew M. Hall, Bryan C. Stone, Chris G. Anderson, Layne L. Mousseau, Timothy A. |
author_facet | Duggan, Matthew T. Groleau, Melissa F. Shealy, Ethan P. Self, Lillian S. Utter, Taylor E. Waller, Matthew M. Hall, Bryan C. Stone, Chris G. Anderson, Layne L. Mousseau, Timothy A. |
author_sort | Duggan, Matthew T. |
collection | PubMed |
description | 1. Camera traps have become an extensively utilized tool in ecological research, but the manual processing of images created by a network of camera traps rapidly becomes an overwhelming task, even for small camera trap studies. 2. We used transfer learning to create convolutional neural network (CNN) models for identification and classification. By utilizing a small dataset with an average of 275 labeled images per species class, the model was able to distinguish between species and remove false triggers. 3. We trained the model to detect 17 object classes with individual species identification, reaching an accuracy up to 92% and an average F1 score of 85%. Previous studies have suggested the need for thousands of images of each object class to reach results comparable to those achieved by human observers; however, we show that such accuracy can be achieved with fewer images. 4. With transfer learning and an ongoing camera trap study, a deep learning model can be successfully created by a small camera trap study. A generalizable model produced from an unbalanced class set can be utilized to extract trap events that can later be confirmed by human processors. |
format | Online Article Text |
id | pubmed-8427629 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | John Wiley and Sons Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-84276292021-09-13 An approach to rapid processing of camera trap images with minimal human input Duggan, Matthew T. Groleau, Melissa F. Shealy, Ethan P. Self, Lillian S. Utter, Taylor E. Waller, Matthew M. Hall, Bryan C. Stone, Chris G. Anderson, Layne L. Mousseau, Timothy A. Ecol Evol Original Research 1. Camera traps have become an extensively utilized tool in ecological research, but the manual processing of images created by a network of camera traps rapidly becomes an overwhelming task, even for small camera trap studies. 2. We used transfer learning to create convolutional neural network (CNN) models for identification and classification. By utilizing a small dataset with an average of 275 labeled images per species class, the model was able to distinguish between species and remove false triggers. 3. We trained the model to detect 17 object classes with individual species identification, reaching an accuracy up to 92% and an average F1 score of 85%. Previous studies have suggested the need for thousands of images of each object class to reach results comparable to those achieved by human observers; however, we show that such accuracy can be achieved with fewer images. 4. With transfer learning and an ongoing camera trap study, a deep learning model can be successfully created by a small camera trap study. A generalizable model produced from an unbalanced class set can be utilized to extract trap events that can later be confirmed by human processors. John Wiley and Sons Inc. 2021-08-02 /pmc/articles/PMC8427629/ /pubmed/34522360 http://dx.doi.org/10.1002/ece3.7970 Text en © 2021 The Authors. Ecology and Evolution published by John Wiley & Sons Ltd. https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Original Research Duggan, Matthew T. Groleau, Melissa F. Shealy, Ethan P. Self, Lillian S. Utter, Taylor E. Waller, Matthew M. Hall, Bryan C. Stone, Chris G. Anderson, Layne L. Mousseau, Timothy A. An approach to rapid processing of camera trap images with minimal human input |
title | An approach to rapid processing of camera trap images with minimal human input |
title_full | An approach to rapid processing of camera trap images with minimal human input |
title_fullStr | An approach to rapid processing of camera trap images with minimal human input |
title_full_unstemmed | An approach to rapid processing of camera trap images with minimal human input |
title_short | An approach to rapid processing of camera trap images with minimal human input |
title_sort | approach to rapid processing of camera trap images with minimal human input |
topic | Original Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8427629/ https://www.ncbi.nlm.nih.gov/pubmed/34522360 http://dx.doi.org/10.1002/ece3.7970 |
work_keys_str_mv | AT dugganmatthewt anapproachtorapidprocessingofcameratrapimageswithminimalhumaninput AT groleaumelissaf anapproachtorapidprocessingofcameratrapimageswithminimalhumaninput AT shealyethanp anapproachtorapidprocessingofcameratrapimageswithminimalhumaninput AT selflillians anapproachtorapidprocessingofcameratrapimageswithminimalhumaninput AT uttertaylore anapproachtorapidprocessingofcameratrapimageswithminimalhumaninput AT wallermatthewm anapproachtorapidprocessingofcameratrapimageswithminimalhumaninput AT hallbryanc anapproachtorapidprocessingofcameratrapimageswithminimalhumaninput AT stonechrisg anapproachtorapidprocessingofcameratrapimageswithminimalhumaninput AT andersonlaynel anapproachtorapidprocessingofcameratrapimageswithminimalhumaninput AT mousseautimothya anapproachtorapidprocessingofcameratrapimageswithminimalhumaninput AT dugganmatthewt approachtorapidprocessingofcameratrapimageswithminimalhumaninput AT groleaumelissaf approachtorapidprocessingofcameratrapimageswithminimalhumaninput AT shealyethanp approachtorapidprocessingofcameratrapimageswithminimalhumaninput AT selflillians approachtorapidprocessingofcameratrapimageswithminimalhumaninput AT uttertaylore approachtorapidprocessingofcameratrapimageswithminimalhumaninput AT wallermatthewm approachtorapidprocessingofcameratrapimageswithminimalhumaninput AT hallbryanc approachtorapidprocessingofcameratrapimageswithminimalhumaninput AT stonechrisg approachtorapidprocessingofcameratrapimageswithminimalhumaninput AT andersonlaynel approachtorapidprocessingofcameratrapimageswithminimalhumaninput AT mousseautimothya approachtorapidprocessingofcameratrapimageswithminimalhumaninput |