CameraTrapDetectoR Family Model

This dataset contains the model weights, architecture, and class label dictionary for CameraTrapDetectoR family model version 1. The model architecture is a FasterRCNN object detection model with a ResNet50 backbone. This model identifies and counts animals from 33 North American taxonomic families in camera trap images, including humans vehicles and a background class. Additional information about the R package and the training data can be found in the package's Github repository: https://github.com/CameraTrapDetectoR/CameraTrapDetectoR

Resources in this dataset:

family_v1.zip is a folder containing the model architecture, model weights, and class label dictionary required to deploy the first generation family model in CameraTrapDetectoR

See all >>

Family Model V1zip
This folder contains the model architecture, model weights, and class label...
MD5:
Explore Data 294.99 MB
Download All

Field	Value
Tags	computer vision animal behavior deep learning camera trapping machine learning classification CameraTrapDetectoR NP215
Modified	2023-05-09
Release Date	2023-05-09
Frequency	Not Planned
Identifier	c0e2890f-bdc2-43a9-bdd2-c11328147a39
Spatial / Geographical Coverage Area	POLYGON ((-161.89453125 70.470124401839, -161.89453125 57.474889007664, -144.66796875 60.549536115658, -103.53515625 10.758479494301, -55.01953125 46.747889039741, -87.36328125 69.009872311641))
Publisher	Ag Data Commons
Spatial / Geographical Coverage Location	North America
Temporal Coverage	January 1, 2022
License	GNU General Public License
Contact Name	Burns, Amira
Contact Email	Amira.Burns@usda.gov
Public Access Level	Public
Program Code	005:037 - Department of Agriculture - Research and Education
Bureau Code	005:32 - Animal and Plant Health Inspection Service

Extended Metadata:

Field	Value
Authors	Burns, Amira L. (ORCID) Tabak, Michael (ORCID) Falbel, Daniel Hamzeh, Tess Brook, Ryan K. (ORCID) Goolsby, John A. (Scopus Author ID) Zoromski, Lisa D. (ORCID) Boughton, Raoul (ORCID) Snow, Nathan (ORCID) VerCauteren, Kurt (ORCID) Miller, Ryan (ORCID) Wilmer, Hailey (ORCID)
Peer Reviewed	No
Intended Use	The dataset supports the R package CameraTrapDetectoR with model architecture, model weights, and class label dictionary for the taxonomic family model version 1, launched January 2022.
Equipment or Software Used	PyTorch v1.9.1
Funding Sources	Animal and Plant Health Inspection Service Center for Epidemiology and Animal Health
Primary Article	Tabak, M. A., Falbel, D., Hamzeh, T., Brook, R. K., Goolsby, J. A., Zoromski, L. D., Boughton, R. K., Snow, N. P., VerCauteren, K. C., & Miller, R. S. (2022). CameraTrapDetectoR: Automatically detect, classify, and count animals in camera trap images using artificial intelligence. Cold Spring Harbor Laboratory. https://doi.org/10.1101/2022.02.07.479461
Dataset DOI (digital object identifier)	10.15482/USDA.ADC/1528979
Product Type	Model
Related Content	CameraTrapDetectoR GitHub repository

Field	Value
ISO Topic(s)	biota environment geoscientificInformation health
State or Territory	North America
National Agricultural Library Thesaurus Term	data collection models cameras species identification ecology animals automation taxonomy wildlife management environmental monitoring computer vision humans birds reptiles Ursidae prediction user interface
Ag Data Commons Keywords	Agroecosystems & Environment Agroecosystems & Environment Plant and animal Agroecosystems & Environment Plant and animal Species composition Maps & Multimedia Maps & Multimedia Images (non-GIS) Maps & Multimedia Images (non-GIS) Organisms

License

Other Access

Data Extent