Image Classification Data and Covariates for Assessing Efficacy of Machine Learning Image Classification for Automated Occupancy-based Monitoring
We used camera data for three sympatric species black-tailed jackrabbits (Lepus californicus), kit foxes (Vulpes macrotis), and pronghorns (Antilocapra americana) to evaluate the influence of competing image classification approaches on estimates of occupancy and inferences about space use. We classified images with: (i) single review (manual), (ii) double review (manual by two observers), (iii) an automated-manual review (machine learning to cull empty images and single review of remaining images), (iv) a pre-trained machine-learning algorithm that classifies images to species (base model), (v) the base model accepting only classifications with ≥95% confidence, (vi) the base model trained with regional images (trained model), and (vii) the trained model accepting only classifications with ≥95% confidence. We compared species-specific results from alternative approaches to results from double review, which reduces the potential for misclassifications and was assumed to be the best approximation of truth.
The zip file (2MB) contains the following files:
Larson, Randy T. and Dart, Marlin, "Image Classification Data and Covariates for Assessing Efficacy of Machine Learning Image Classification for Automated Occupancy-based Monitoring" (2023). NRM Departmental Data Sets. 9.