Life Sciences Commons^™

Road Hogs: Implications From Gps Collared Feral Swine In Pastureland Habitat On The General Utility Of Road-Based Observation Techniques For Assessing Abundance, Raoul K. Boughton, Benjamin L. Allen, Eric A. Tillman, Samantha M. Wisely, Richard M. Engeman

USDA Wildlife Services: Staff Publications

Feral swine are among the world’s most destructive invasive species, and monitoring their populations is essential for research and management purposes. Observation stations located along primitive roads have been an efficient and effective means to intercept the daily activities of many animal species for collecting data from which abundance indices can be validly calculated. Feral swine are among the many species documented to use primitive (dirt), low-use roads as routes to easily traverse surrounding habitats and thus be well-monitored in various habitats globally by using road-based observation stations such as camera traps or tracking plots. However, there are relatively few …

Machine Learning To Classify Animal Species In Camera Trap Images: Applications In Ecology, Michael A. Tabak, Mohammad S. Norouzzadeh, David W. Wolfson, Steven J. Sweeney, Kurt C. Vercauteren, Nathan P. Snow, Joseph M. Halseth, Paul A. Di Salvo, Jesse S. Lewis, Michael D. White, Ben Teton, James C. Beasley, Peter E. Schlichting, Raoul K. Boughton, Bethany Wight, Eric S. Newkirk, Jacob S. Ivan, Eric A. Odell, Ryan K. Brook, Paul M. Lukacs, Anna K. Moeller, Elizabeth G. Mandeville, Jeff Clune, Ryan S. Miller

USDA Wildlife Services: Staff Publications

1. Motion-activated cameras (“camera traps”) are increasingly used in ecological and management studies for remotely observing wildlife and are amongst the most powerful tools for wildlife research. However, studies involving camera traps result in millions of images that need to be analysed, typically by visually observing each image, in order to extract data that can be used in ecological analyses.

2. We trained machine learning models using convolutional neural networks with the ResNet-18 architecture and 3,367,383 images to automatically classify wildlife species from camera trap images obtained from five states across the United States. We tested our model on an …