CameraTrapDetectoR Pig Model

This dataset contains the model weights, architecture, and class label dictionary for CameraTrapDetectoR pig-only model version 1. The model architecture is a FasterRCNN object detection model with a ResNet50 backbone. This model identifies and counts wild pigs in camera trap images. It also includes categories for non-pig detections (animal, human, or vehicle), 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

List of Resources:

pig_v1.zip is a folder containing the model architecture, model weights, and class label dictionary used to deploy the pig-only model version 1 in CameraTrapDetectoR

See all >>

Pig Model V1zip
This folder contains the model weights, architecture, and class label...
MD5:
Explore Data 294.98 MB
Download All

Field	Value
Tags	computer vision animal behavior deep learning camera trapping machine learning classification CameraTrapDetectoR NP215 wild pigs
Modified	2023-05-12
Release Date	2023-05-12
Frequency	Not Planned
Identifier	834a9538-f786-43f5-b96e-97b63af58109
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) Miller, Ryan (ORCID) Wilmer, Hailey (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)
Peer Reviewed	No
Intended Use	The dataset supports the R package CameraTrapDetectoR with model architecture, model weights, and class label dictionary for the pig-only 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/1528996
Product Type	Model

Field	Value
OSTI Identifier
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 swine prediction user interface
Ag Data Commons Keywords	Agroecosystems & Environment Agroecosystems & Environment Plant and animal Agroecosystems & Environment Plant and animal Species composition Maps & Multimedia Images (non-GIS) Maps & Multimedia Images (non-GIS) Organisms

License

Other Access

Data Extent