Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning

Sadegh, Norouzzadeh, Mohammed; Nguyen, A. D.; Kosmala, Margaret; Swanson, Alexandra; Palmer, Meredith S.; Packer, Craig; Clune, Jeff

doi:10.48550/arxiv.1703.05830

Cited by 9 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Camera traps are not new to the computer vision community [16,17,18,19,20,21,22,23,24,25,26,27,2]. Our work is the first to identify camera traps as a unique opportunity to study generalization, and we offer the first study of generalization to new environments in this controlled setting.…”

Section: Introductionmentioning

confidence: 88%

“…[27] show classification results on both Snapshot Serengeti and data from jungles in Panama, and saw a boost in classification performance from providing animal segmentations. [2] show 94.9% top-1 accuracy using an ensemble of models for classification on the Snapshot Serengeti dataset. None of the previous works show results on unseen test locations.…”

Section: Classificationmentioning

confidence: 99%

“…Automated visual recognition algorithms have recently achieved human expert performance at visual classification tasks in field biology [1,2,3] and medicine [4,5]. Thanks to the combination of deep learning [6,7], Moore's law [8] and very large annotated datasets [9,10] enormous progress has been made during the past 10 years.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recognition in Terra Incognita

Beery

Horn

Perona

2018

Computer Vision – ECCV 2018

395

402

View full text Add to dashboard Cite

It is desirable for detection and classification algorithms to generalize to unfamiliar environments, but suitable benchmarks for quantitatively studying this phenomenon are not yet available. We present a dataset designed to measure recognition generalization to novel environments. The images in our dataset are harvested from twenty camera traps deployed to monitor animal populations. Camera traps are fixed at one location, hence the background changes little across images; capture is triggered automatically, hence there is no human bias. The challenge is learning recognition in a handful of locations, and generalizing animal detection and classification to new locations where no training data is available. In our experiments state-of-the-art algorithms show excellent performance when tested at the same location where they were trained. However, we find that generalization to new locations is poor, especially for classification systems. 1

show abstract

Section: Introductionmentioning

confidence: 88%

Section: Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Recognition in Terra Incognita

Beery

Horn

Perona

2018

Computer Vision – ECCV 2018

395

402

View full text Add to dashboard Cite

show abstract

“…Automating camera trap labeling is not a new challenge for the computer vision community [1,[3][4][5][6][7][8][9][10][12][13][14][15][16][17]. However, most of the proposed solutions have used the same camera locations for both training and testing the performance of an automated system.…”

Section: Introductionmentioning

confidence: 99%

The iWildCam 2019 Challenge Dataset

Beery¹,

Morris²,

Perona³

2019

Preprint

View full text Add to dashboard Cite

Camera Traps (or Wild Cams) enable the automatic collection of large quantities of image data. Biologists all over the world use camera traps to monitor biodiversity and population density of animal species. The computer vision community has been making strides towards automating the species classification challenge in camera traps, but as we try to expand the scope of these models from specific regions where we have collected training data to different areas we are faced with an interesting problem: how do you classify a species in a new region that you may not have seen in previous training data?In order to tackle this problem, we have prepared a dataset and challenge where the training data and test data are from different regions, namely The American Southwest and the American Northwest. We use the Caltech Camera Traps dataset, collected from the American Southwest, as training data. We add a new dataset from the American Northwest, curated from data provided by the Idaho Department of Fish and Game (IDFG), as our test dataset. The test data has some class overlap with the training data, some species are found in both datasets, but there are both species seen during training that are not seen during test and vice versa. To help fill the gaps in the training species, we allow competitors to utilize transfer learning from two alternate domains: human-curated images from iNaturalist and synthetic images from Microsoft's TrapCam-AirSim simulation environment.

show abstract

“…They can be tuned for wildlife monitoring, and there is a growing body of work focused around camera trap data. [6] used deep models for classifying across 48 different animal species. Another recent study from Tabak et.…”

mentioning

confidence: 99%

Unifying data for fine-grained visual species classification

Kulkarni¹,

Gadot²,

Chen³

et al. 2020

Preprint

View full text Add to dashboard Cite

Wildlife monitoring is crucial to nature conservation and has been done by manual observations from motion-triggered camera traps deployed in the field. Widespread adoption of such in-situ sensors has resulted in unprecedented data volumes being collected over the last decade. A significant challenge exists to process and reliably identify what is in these images efficiently. Advances in computer vision are poised to provide effective solutions with custom AI models built to automatically identify images of interest and label the species in them. Here we outline the data unification effort for the Wildlife Insights platform from various conservation partners, and the challenges involved. Then we present an initial deep convolutional neural network model, trained on 2.9M images across 465 fine-grained species, with a goal to reduce the load on human experts to classify species in images manually. The longterm goal is to enable scientists to make conservation recommendations from near real-time analysis of species abundance and population health. CCS CONCEPTS• Computing methodologies → Supervised learning by classification; Neural networks.

show abstract

Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning

Cited by 9 publications

References 0 publications

Recognition in Terra Incognita

Recognition in Terra Incognita

The iWildCam 2019 Challenge Dataset

Unifying data for fine-grained visual species classification

Contact Info

Product

Resources

About