Perspectives in machine learning for wildlife conservation

Tuia, Devis; Kellenberger, Benjamin; Beery, Sara; Costelloe, Blair R.; Zuffi, Silvia; Risse, Benjamin; Mathis, Alexander; Langevelde, Frank van; Burghardt, Tilo; Kays, Roland; Klinck, Holger; Wikelski, Martin; Couzin, Iain D.; Horn, Grant Van; Crofoot, Margaret C.; Stewart, Charles; Berger-Wolf, Tanya Y.

doi:10.1038/s41467-022-27980-y

Cited by 338 publications

(253 citation statements)

References 153 publications

Supporting

Mentioning

250

Contrasting

Unclassified

Order By: Relevance

“…The full potential of camera-traps is however only realized when the hundreds of thousands of images, many being empty from spurious detections, can be rapidly classified with minimal human intervention (Chen et al, 2014; Schneider et al, 2019; Wearn et al, 2019; Tuia et al, 2021). Since the beginning, machine learning approaches, and in particular deep learning methods, have held the promise to solve this issue.…”

Section: Introductionmentioning

confidence: 99%

The DeepFaune initiative: a collaborative effort towards the automatic identification of French fauna in camera-trap images

Rigoudy

Benyoub²,

Besnard

et al. 2022

Preprint

View full text Add to dashboard Cite

Camera-traps have revolutionized the way ecologists monitor biodiversity and population abundances. Their full potential is however only realized when the hundreds of thousands of images collected can be rapidly classified with minimal human intervention. Machine learning approaches, and in particular deep learning methods, have allowed extraordinary progress towards this end. Trained classification models remain rare however, and for instance are only emerging for the European fauna. This can be explained by the technical expertise they require but also by the limited availability of large datasets of annotated pictures, which are key to obtaining successful recognition models.In this context, we set-up the DeepFaune initiative (https://deepfaune.cnrs.fr), a large-scale collaboration between dozens of partners involved in research, conservation and management of wildlife in France. The aim of DeepFaune is to aggregate individual datasets of annotated pictures to train species classification models based on convolutional neural networks, an established deeplearning approach.Here we report on our first milestone, a two-step pipeline built upon the MegaDetector algorithm for detection (discarding empty pictures and cropping the animal) and a classification model for 18 species or higher-level taxa as well as people and vehicles. The classification model achieved 92% validation accuracy and showed > 90% sensitivity and specificity for many classes. Most importantly, these performances were generally conserved when tested on an independent out-of-sample dataset. In addition, we developed a cross-platform graphical-user-interface that allows running the pipeline on images stored locally on a personal computer.In conclusion, the DeepFaune initiative provides a freely available (for non-commercial purposes) toolbox with high performance to classify the French fauna in camera-trap images.

show abstract

Section: Introductionmentioning

confidence: 99%

The DeepFaune initiative: a collaborative effort towards the automatic identification of French fauna in camera-trap images

Rigoudy

Benyoub²,

Besnard

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Animal pose estimation is an important tool to study animal behavior (1)(2)(3)(4). Compared to human pose estimation, animal pose estimation has unique challenges when it comes to dataset creation and generalization of the model to unseen animals.…”

Section: Introductionmentioning

confidence: 99%

SuperAnimal models pretrained for plug-and-play analysis of animal behavior

Ye¹,

Mathis²,

Mathis³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Animal pose estimation is critical in applications ranging from life science research, agriculture, to veterinary medicine. Compared to human pose estimation, the performance of animal pose estimation is limited by the size of available datasets and the generalization of a model across datasets. Typically different keypoints are labeled regardless of whether the species are the same or not, leaving animal pose datasets to have disjoint or partially overlapping keypoints. As a consequence, a model cannot be used as a plug-and-play solution across datasets. This reality motivates us to develop panoptic animal pose estimation models that are able to predict keypoints defined in all datasets. In this work we propose a simple yet effective way to merge differentially labeled datasets to obtain the largest quadruped and lab mouse pose dataset. Using a gradient masking technique, so called SuperAnimal-models are able to predict keypoints that are distributed across datasets and exhibit strong zero-shot performance. The models can be further improved by (pseudo) labeled fine-tuning. These models outperform ImageNet-initialized models.

show abstract

“…States 19 , and a report on renal lesions followed by neoplastic and inflammatory responses in captive wild felids in Germany 20 . Studies of these animals can provide unique insights into the biology and evolution of cancer across the tree of life towards improving animal welfare by early detection and helping conserve endangered species 21,22 .…”

Section: Introductionmentioning

confidence: 99%

“…Animals managed in zoological institutes also exhibit occurrence of neoplastic growth according to several international studies, including, a 10-year survey in the Taipei zoo, Taiwan 17 , a study of cancer development in vertebrates in French zoological parks 18 , a 42-years of mammals necropsy data compilation from the San Diego Zoo, United States 19 , and a report on renal lesions followed by neoplastic and inflammatory responses in captive wild felids in Germany 20 . Studies of these animals can provide unique insights into the biology and evolution of cancer across the tree of life towards improving animal welfare by early detection and helping conserve endangered species 21,22 .…”

Section: Introductionmentioning

confidence: 99%

AI-powered pan-species computational pathology: bridging clinic and wildlife care

AbdulJabbar

Castillo

Hughes

et al. 2022

Preprint

View full text Add to dashboard Cite

Cancers occur across species. Understanding what is consistent and varies across species can provide new insights into cancer initiation and evolution, with significant implications for animal welfare and wildlife conservation. We built the pan-species cancer digital pathology atlas (PANCAD) and conducted the first pan-species study of computational comparative pathology using a supervised convolutional neural network algorithm trained on human samples. The artificial intelligence algorithm achieves high accuracy in measuring immune response through single-cell classification for two transmissible cancers (canine transmissible venereal tumour, 0.94; Tasmanian devil facial tumour disease, 0.88). Furthermore, in 18 other vertebrate species (mammalia=11, reptilia=4, aves=2, and amphibia=1), accuracy (0.57-0.94) was influenced by cell morphological similarity preserved across different taxonomic groups, tumour sites, and variations in the immune compartment. A new metric, named morphospace overlap, was developed to guide veterinary pathologists towards rational deployment of this technology on new samples. This study provides the foundation and guidelines for transferring artificial intelligence technologies to veterinary pathology based on a new understanding of morphological conservation, which could vastly accelerate new developments in veterinary medicine and comparative oncology.

show abstract

Perspectives in machine learning for wildlife conservation

Cited by 338 publications

References 153 publications

The DeepFaune initiative: a collaborative effort towards the automatic identification of French fauna in camera-trap images

The DeepFaune initiative: a collaborative effort towards the automatic identification of French fauna in camera-trap images

SuperAnimal models pretrained for plug-and-play analysis of animal behavior

AI-powered pan-species computational pathology: bridging clinic and wildlife care

Contact Info

Product

Resources

About