Dataset Information

Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna.

ABSTRACT: Camera traps can be used to address large-scale questions in community ecology by providing systematic data on an array of wide-ranging species. We deployed 225 camera traps across 1,125?km(2)?in Serengeti National Park, Tanzania, to evaluate spatial and temporal inter-species dynamics. The cameras have operated continuously since 2010 and had accumulated 99,241 camera-trap days and produced 1.2 million sets of pictures by 2013. Members of the general public classified the images via the citizen-science website www.snapshotserengeti.org. Multiple users viewed each image and recorded the species, number of individuals, associated behaviours, and presence of young. Over 28,000 registered users contributed 10.8 million classifications. We applied a simple algorithm to aggregate these individual classifications into a final 'consensus' dataset, yielding a final classification for each image and a measure of agreement among individual answers. The consensus classifications and raw imagery provide an unparalleled opportunity to investigate multi-species dynamics in an intact ecosystem and a valuable resource for machine-learning and computer-vision research.

SUBMITTER: Swanson A

PROVIDER: S-EPMC4460915 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna.

Swanson Alexandra A Kosmala Margaret M Lintott Chris C Simpson Robert R Smith Arfon A Packer Craig C

Scientific data 20150609

Camera traps can be used to address large-scale questions in community ecology by providing systematic data on an array of wide-ranging species. We deployed 225 camera traps across 1,125 km(2) in Serengeti National Park, Tanzania, to evaluate spatial and temporal inter-species dynamics. The cameras have operated continuously since 2010 and had accumulated 99,241 camera-trap days and produced 1.2 million sets of pictures by 2013. Members of the general public classified the images via the citizen ...[more]

PMID: 26097743

Similar Datasets

Project description:Wild animals are essential for ecosystem structuring and stability, and thus they are important for ecological research. Since most wild animals have high athletic or concealable abilities or both, it is used to be relatively difficult to acquire evidence of animal appearances before applications of camera traps in ecological researches. However, a single camera trap may produce thousands of animal images in a short period of time and inevitably ends up with millions of images requiring classification. Although there have been many methods developed for classifying camera trap images, almost all of them follow the pattern of a very deep convolutional neural network processing all camera trap images. Consequently, the corresponding surveillance area may need to be delicately controlled to match the network capability, and it may be difficult to expand the area in the future. In this study, we consider a scenario in which camera traps are grouped into independent clusters, and images produced by a cluster are processed by an edge device installed with a customized network. Accordingly, edge devices in this scenario may be highly heterogeneous due to cluster scales. Resultantly, networks popular in the classification of camera trap images may not be deployable for edge devices without modifications requiring the expertise which may be hard to obtain. This motivates us to automatize network design via neural architecture search for edge devices. However, the search may be costly due to the evaluations of candidate networks, and its results may be infeasible without considering the resource limits of edge devices. Accordingly, we propose a search method using regression trees to evaluate candidate networks to lower search costs, and candidate networks are built based on a meta-architecture automatically adjusted regarding to the resource limits. In experiments, the search consumes 6.5 hours to find a network applicable to the edge device Jetson X2. The found network is then trained on camera trap images through a workstation and tested on Jetson X2. The network achieves competitive accuracies compared with the automatically and the manually designed networks.

Project description:A time-consuming challenge faced by camera trap practitioners is the extraction of meaningful data from images to inform ecological management. An increasingly popular solution is automated image classification software. However, most solutions are not sufficiently robust to be deployed on a large scale due to lack of location invariance when transferring models between sites. This prevents optimal use of ecological data resulting in significant expenditure of time and resources to annotate and retrain deep learning models.We present a method ecologists can use to develop optimized location invariant camera trap object detectors by (a) evaluating publicly available image datasets characterized by high intradataset variability in training deep learning models for camera trap object detection and (b) using small subsets of camera trap images to optimize models for high accuracy domain-specific applications.We collected and annotated three datasets of images of striped hyena, rhinoceros, and pigs, from the image-sharing websites FlickR and iNaturalist (FiN), to train three object detection models. We compared the performance of these models to that of three models trained on the Wildlife Conservation Society and Camera CATalogue datasets, when tested on out-of-sample Snapshot Serengeti datasets. We then increased FiN model robustness by infusing small subsets of camera trap images into training.In all experiments, the mean Average Precision (mAP) of the FiN trained models was significantly higher (82.33%-88.59%) than that achieved by the models trained only on camera trap datasets (38.5%-66.74%). Infusion further improved mAP by 1.78%-32.08%.Ecologists can use FiN images for training deep learning object detection solutions for camera trap image processing to develop location invariant, robust, out-of-the-box software. Models can be further optimized by infusion of 5%-10% camera trap images into training data. This would allow AI technologies to be deployed on a large scale in ecological applications. Datasets and code related to this study are open source and available on this repository: https://doi.org/10.5061/dryad.1c59zw3tx.

Project description:Camera traps are a unique survey tool used to monitor a wide variety of mammal species. Camera trap (CT) data can be used to estimate animal distribution, density, and behaviour. Attractants, such as scent lures, are often used in an effort to increase CT detections; however, the degree which the effects of attractants vary across species is not well understood. We investigated the effects of scent lure on mammal detections by comparing detection rates between 404 lured and 440 unlured CT stations sampled in Alberta, Canada over 120 day survey periods between February and August in 2015 and 2016. We used zero-inflated negative binomial generalized linear mixed models to test the effect of lure on detection rates for a) all mammals, b) six functional groups (all predator species, all prey, large carnivores, small carnivores, small mammals, ungulates), and c) four varied species of management interest (fisher, Pekania pennanti; gray wolf, Canis lupus; moose, Alces alces; and Richardson's ground squirrel; Urocitellus richardsonii). Mammals were detected at 800 of the 844 CTs, with nearly equal numbers of total detections at CTs with (7110) and without (7530) lure, and variable effects of lure on groups and individual species. Scent lure significantly increased detections of predators as a group, including large and small carnivore sub-groups and fisher specifically, but not of gray wolf. There was no effect of scent lure on detections of prey species, including the small mammal and ungulate sub-groups and moose and Richardson's ground squirrel specifically. We recommend that researchers explicitly consider the variable effects of scent lure on CT detections across species when designing, interpreting, or comparing multi-species surveys. Additional research is needed to further quantify variation in species responses to scent lures and other attractants, and to elucidate the effect of attractants on community-level inferences from camera trap surveys.

Dataset Information

Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna.

Publications

Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets