A computer vision for animal ecology.

By Ben. G. Weinstein. 2018

393 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Ecological Modeling, Ecology, Plant Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Jitendra Malik
3. Trevor Darrell
4. Dacheng Tao
5. Li Fei-Fei
6. Bernt Schiele
7. Cordelia Schmid
8. Sergey Levine

In Ecological Modeling

1. Patrick Mäder
2. Jana Wäldchen
3. R. Kays
4. Per Berggren
5. Georgia Atkinson
6. A. C. Burton
7. Cameron Trotter
8. Kirsten Richardson

In Ecology

1. Margaret C. Crofoot
2. Martin Wikelski
3. R. Kays
4. Per Berggren
5. Georgia Atkinson
6. A. C. Burton
7. Cameron Trotter
8. Kirsten Richardson

In Plant Science

1. Patrick Mäder
2. Jana Wäldchen
3. Sara Beery
4. Per Berggren
5. Georgia Atkinson
6. Cameron Trotter
7. Kirsten Richardson
8. Nick Wright

Citations in the corpus

• NDD20: A large-scale few-shot dolphin dataset for coarse and fine-grained categorisation (2020, methodology): “As such it is believed that an automated photo-id process is achievable using computer vision (19), with work already beginning in this area (3, 5, 6, 18).”
• WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, positive): “To better understand and monitor wildlife biodiversity loss, ecologists commonly deploy camera traps— heat or motion-activated static cameras placed in the wild (Wearn & Glover-Kapfer, 2017)—and then use ML models to process the data collected (Weinstein, 2018; Norouzzadeh et al., 2019; Tabak et al.”
• Use of object detection in camera trap image identification: assessing a method to rapidly and accurately classify human and animal detections for research and application in recreation ecology (2022, background): “A rapidly expanding subfield of this technology is computer vision, where a multilayered model is trained on a large number of previously classified images, and then applied to new images in order to assign classifications without human interaction (Weinstein, 2018).”
• Perspectives in machine learning for wildlife conservation (2021, background): “A growing body of literature promotes the use of ML in various ecological subfields by educating domain experts about ML approaches (35, 49, 50), their utility in capitalizing on big data (32, 51), and, more recently, their potential for ecolog-”
• Machine learning for image based species identification (2018, background): “…based species identification tasks are manifold and were comprehensively surveyed before, e.g. by Cope, Corney, Clark, Remagnino, and Wilkin (2012); Moniruzzaman, Islam, Bennamoun, and Lavery (2017); Seeland, Rzanny, Alaqraa, Wäldchen, and Mäder (2017); Wäldchen and Mäder (2018); Weinstein (2018).”