Launch and use the CameraTrapDetectoR Shiny application as a standalone desktop app. No coding or R interface needed!
Use deep learning computer vision models to automatically detect, count, and classify common North American domestic and wild species in camera trap images.
Four types of models are available: a taxonomic class model that classifies objects as mammal or avian; a taxonomic family model that recognizes 31 mammal, avian, and reptile families; a pig-only model that recognizes wild pigs and classifies all other detections as not-pig; a species model that recognizes 75 unique domestic and wild species including all North American wild cat species, bear species, and Canid species. Each model also includes a category for vehicles and empty images.
See the wiki for complete installation and user instructions.
Click here to download the desktop application.
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 (p. 2022.02.07.479461). bioRxiv. link to manuscript
Or @article {Tabak2022.02.07.479461, author = {Tabak, Michael A and Falbel, Daniel and Hamzeh, Tess and Brook, Ryan K and Goolsby, John A and Zoromski, Lisa D and Boughton, Raoul K and Snow, Nathan P and VerCauteren, Kurt C and Miller, Ryan S}, title = {CameraTrapDetectoR: Automatically detect, classify, and count animals in camera trap images using artificial intelligence}, elocation-id = {2022.02.07.479461}, year = {2022}, doi = {10.1101/2022.02.07.479461}, publisher = {Cold Spring Harbor Laboratory},, URL = {https://www.biorxiv.org/content/10.1101/2022.02.07.479461v1}, eprint = {https://www.biorxiv.org/content/10.1101/2022.02.07.479461v1.full.pdf}, journal = {bioRxiv} }