Accurate detection and identification of insects from camera trap images with deep learning
PLOS Sustainability and Transformation · 15.03.2023 · 2 (3) · e0000051
DOI: 10.1371/journal.pstr.0000051 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Sustainability and Transformation, online erschienen am 15.03.2023. Verfasst von Kim Bjerge und 5 weiteren Autor:innen. Die Arbeit wurde bisher 136-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Horizon 2020 Framework Programme.
Abstract (Originalsprache)
Reported insect declines have dramatically increased the global demand for standardized insect monitoring data. Image-based monitoring can generate such data cost-efficiently and non-invasively. However, extracting ecological data from images is more challenging for insects than for vertebrates because of their small size and great diversity. Deep learning facilitates fast and accurate insect detection and identification, but the lack of training data for coveted deep learning models is a major obstacle for their application. We present a large annotated image dataset of functionally important insect taxa. The primary dataset consists of 29,960 annotated insects representing nine taxa including bees, hoverflies, butterflies and beetles across more than two million images recorded with ten time-lapse cameras mounted over flowers during the summer of 2019. The insect image dataset was extracted using an iterative approach: First, a preliminary detection model identified candidate insects. Second, candidate insects were manually screened by users of an online citizen science platform. Finally, all annotations were quality checked by experts. We used the dataset to train and compare the performance of selected You Only Look Once (YOLO) deep learning algorithms. We show that these models detect and classify small insects in complex scenes with unprecedented accuracy. The best performing YOLOv5 model consistently identifies nine dominant insect species that play important roles in pollination and pest control across Europe. The model reached an average precision of 92.7% and recall of 93.8% in detection and classification across species. Importantly, when presented with uncommon or unclear insects not seen during training, our model detects 80% of individuals and usually interprets them as closely related species. This is a useful property to (1) detect rare insects for which training data are absent, and (2) generate new training data to correctly identify those insects in future. Our camera system, dataset and deep learning framework show promising results in non-destructive monitoring of insects. Furthermore, resulting data are useful to quantify phenology, abundance, and foraging behaviour of flower-visiting insects. Above all, this dataset represents a critical first benchmark for future development and evaluation of deep learning models for insect detection and identification.
Förderung
- Horizon 2020 Framework Programme
Zitieren
APA
Bjerge, K., Alison, J., Dyrmann, M., Frigaard, C. E., Mann, H. M. R., & Høye, T. T. (2023). Accurate detection and identification of insects from camera trap images with deep learning. PLOS Sustainability and Transformation, 2(3), e0000051. https://doi.org/10.1371/journal.pstr.0000051
Vancouver
Bjerge K, Alison J, Dyrmann M, Frigaard CE, Mann HMR, Høye TT. Accurate detection and identification of insects from camera trap images with deep learning. PLOS Sustainability and Transformation. 2023;2(3):e0000051. doi:10.1371/journal.pstr.0000051
BibTeX
@article{Bjerge2023,
author = {Bjerge, Kim and Alison, Jamie and Dyrmann, Mads and Frigaard, Carsten Eie and Mann, Hjalte M. R. and Høye, Toke Thomas},
title = {Accurate detection and identification of insects from camera trap images with deep learning},
journal = {PLOS Sustainability and Transformation},
year = {2023},
volume = {2},
number = {3},
pages = {e0000051},
doi = {10.1371/journal.pstr.0000051}
}
EUVIMED