Tampere University of Technology

TUTCRIS Research Portal

Automatic image-based identification and biomass estimation of invertebrates

Research output: Contribution to journalArticleScientificpeer-review

Standard

Automatic image-based identification and biomass estimation of invertebrates. / Ärje, Johanna; Melvad, Claus; Rosenhøj Jeppesen, Mads; Madsen, Sigurd Agerskov; Raitoharju, Jenni; Strandgård Rasmussen, Maria; Iosifidis, Alexandros; Meissner, Kristian; Tirronen, Ville; Gabbouj, Moncef; Høye, Toke Thomas.

In: Methods in Ecology and Evolution, Vol. 11, No. 8, 2020, p. 922-931.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Ärje, J, Melvad, C, Rosenhøj Jeppesen, M, Madsen, SA, Raitoharju, J, Strandgård Rasmussen, M, Iosifidis, A, Meissner, K, Tirronen, V, Gabbouj, M & Høye, TT 2020, 'Automatic image-based identification and biomass estimation of invertebrates', Methods in Ecology and Evolution, vol. 11, no. 8, pp. 922-931. https://doi.org/10.1111/2041-210X.13428

APA

Ärje, J., Melvad, C., Rosenhøj Jeppesen, M., Madsen, S. A., Raitoharju, J., Strandgård Rasmussen, M., ... Høye, T. T. (2020). Automatic image-based identification and biomass estimation of invertebrates. Methods in Ecology and Evolution, 11(8), 922-931. https://doi.org/10.1111/2041-210X.13428

Vancouver

Ärje J, Melvad C, Rosenhøj Jeppesen M, Madsen SA, Raitoharju J, Strandgård Rasmussen M et al. Automatic image-based identification and biomass estimation of invertebrates. Methods in Ecology and Evolution. 2020;11(8):922-931. https://doi.org/10.1111/2041-210X.13428

Author

Ärje, Johanna ; Melvad, Claus ; Rosenhøj Jeppesen, Mads ; Madsen, Sigurd Agerskov ; Raitoharju, Jenni ; Strandgård Rasmussen, Maria ; Iosifidis, Alexandros ; Meissner, Kristian ; Tirronen, Ville ; Gabbouj, Moncef ; Høye, Toke Thomas. / Automatic image-based identification and biomass estimation of invertebrates. In: Methods in Ecology and Evolution. 2020 ; Vol. 11, No. 8. pp. 922-931.

Bibtex - Download

@article{50ba4aacb1a24f28bb2b1317fc4ce882,
title = "Automatic image-based identification and biomass estimation of invertebrates",
abstract = "Understanding how biological communities respond to environmental changes is a key challenge in ecology and ecosystem management. The apparent decline of insect populations necessitates more biomonitoring but the time-consuming sorting and identification of taxa pose strong limitations on how many insect samples can be processed. In turn, this affects the scale of efforts to map invertebrate diversity altogether. Given recent advances in computer vision, we propose to replace the standard manual approach of human expert-based sorting and identification with an automatic image-based technology. We describe a robot-enabled image-based identification machine, which can automate the process of invertebrate identification, biomass estimation and sample sorting. We use the imaging device to generate a comprehensive image database of terrestrial arthropod species. We use this database to test the classification accuracy i.e. how well the species identity of a specimen can be predicted from images taken by the machine. We also test sensitivity of the classification accuracy to the camera settings (aperture and exposure time) in order to move forward with the best possible image quality. We use state-of-the-art Resnet-50 and InceptionV3 Convolutional Neural Networks (CNNs) for the classification task. The results for the initial dataset are very promising (ACC = 0.980). The system is general and can easily be used for other groups of invertebrates as well. As such, our results pave the way for generating more data on spatial and temporal variation in invertebrate abundance, diversity and biomass.",
author = "Johanna {\"A}rje and Claus Melvad and {Rosenh{\o}j Jeppesen}, Mads and Madsen, {Sigurd Agerskov} and Jenni Raitoharju and {Strandg{\aa}rd Rasmussen}, Maria and Alexandros Iosifidis and Kristian Meissner and Ville Tirronen and Moncef Gabbouj and H{\o}ye, {Toke Thomas}",
note = "EXT={"}Raitoharju, Jenni{"} EXT={"}Iosifidis, Alexandros{"}",
year = "2020",
doi = "10.1111/2041-210X.13428",
language = "English",
volume = "11",
pages = "922--931",
journal = "Methods in Ecology and Evolution",
issn = "2041-210X",
publisher = "Wiley",
number = "8",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Automatic image-based identification and biomass estimation of invertebrates

AU - Ärje, Johanna

AU - Melvad, Claus

AU - Rosenhøj Jeppesen, Mads

AU - Madsen, Sigurd Agerskov

AU - Raitoharju, Jenni

AU - Strandgård Rasmussen, Maria

AU - Iosifidis, Alexandros

AU - Meissner, Kristian

AU - Tirronen, Ville

AU - Gabbouj, Moncef

AU - Høye, Toke Thomas

N1 - EXT="Raitoharju, Jenni" EXT="Iosifidis, Alexandros"

PY - 2020

Y1 - 2020

N2 - Understanding how biological communities respond to environmental changes is a key challenge in ecology and ecosystem management. The apparent decline of insect populations necessitates more biomonitoring but the time-consuming sorting and identification of taxa pose strong limitations on how many insect samples can be processed. In turn, this affects the scale of efforts to map invertebrate diversity altogether. Given recent advances in computer vision, we propose to replace the standard manual approach of human expert-based sorting and identification with an automatic image-based technology. We describe a robot-enabled image-based identification machine, which can automate the process of invertebrate identification, biomass estimation and sample sorting. We use the imaging device to generate a comprehensive image database of terrestrial arthropod species. We use this database to test the classification accuracy i.e. how well the species identity of a specimen can be predicted from images taken by the machine. We also test sensitivity of the classification accuracy to the camera settings (aperture and exposure time) in order to move forward with the best possible image quality. We use state-of-the-art Resnet-50 and InceptionV3 Convolutional Neural Networks (CNNs) for the classification task. The results for the initial dataset are very promising (ACC = 0.980). The system is general and can easily be used for other groups of invertebrates as well. As such, our results pave the way for generating more data on spatial and temporal variation in invertebrate abundance, diversity and biomass.

AB - Understanding how biological communities respond to environmental changes is a key challenge in ecology and ecosystem management. The apparent decline of insect populations necessitates more biomonitoring but the time-consuming sorting and identification of taxa pose strong limitations on how many insect samples can be processed. In turn, this affects the scale of efforts to map invertebrate diversity altogether. Given recent advances in computer vision, we propose to replace the standard manual approach of human expert-based sorting and identification with an automatic image-based technology. We describe a robot-enabled image-based identification machine, which can automate the process of invertebrate identification, biomass estimation and sample sorting. We use the imaging device to generate a comprehensive image database of terrestrial arthropod species. We use this database to test the classification accuracy i.e. how well the species identity of a specimen can be predicted from images taken by the machine. We also test sensitivity of the classification accuracy to the camera settings (aperture and exposure time) in order to move forward with the best possible image quality. We use state-of-the-art Resnet-50 and InceptionV3 Convolutional Neural Networks (CNNs) for the classification task. The results for the initial dataset are very promising (ACC = 0.980). The system is general and can easily be used for other groups of invertebrates as well. As such, our results pave the way for generating more data on spatial and temporal variation in invertebrate abundance, diversity and biomass.

U2 - 10.1111/2041-210X.13428

DO - 10.1111/2041-210X.13428

M3 - Article

VL - 11

SP - 922

EP - 931

JO - Methods in Ecology and Evolution

JF - Methods in Ecology and Evolution

SN - 2041-210X

IS - 8

ER -