Optimizing the Accuracy and Efficiency of Camera Trap Image Analysis: Evaluating AI Model Performance and a Semi-Automated Workflow

The widespread adoption of camera trap surveys for wildlife monitoring has generated a substantial volume of ecological data, yet processing constraints persist due to the time-consuming process of manual image classification and the reliability of automated systems. This study assesses the performance of Conservation AI’s UK Mammals model in classifying three species—Western European hedgehogs (Erinaceus europaeus), red foxes (Vulpes vulpes), and European badgers (Meles meles)—from a subsample of 234 records from camera trap images collected through a citizen science initiative across residential gardens. This analysis was repeated after retraining the model to assess improvement in model performance. Initial model outputs demonstrated high precision (>0.80) for foxes and hedgehogs but low recall (<0.50) for hedgehogs, with the lowest recall probability of 0.12 at the 95% confidence threshold (CT). Following retraining, model performance improved substantially across all metrics, with average F1-scores (weighted average of precision and recall across the three species tested) improving at all CTs, though discrepancies with human classifications remained statistically significant. Based on performance results from this study, we present a semi-automated, three-step workflow incorporating an artificially intelligent (AI) generalist object detector (MegaDetector), an AI species-specific classifier (Conservation AI), and manual validation. Where privacy concerns restrict citizen science contributions, our pipeline offers an alternative that accelerates camera trap data analysis whilst maintaining classification accuracy. The findings provide baseline performance estimates of Conservation AI’s UK Mammals model and present an approach that offers a practical solution to improve the efficiency of using camera traps in ecological research and conservation planning. We also highlight the importance of continuous AI model training, the value of citizen science in expanding training datasets, and the need for adaptable workflows in camera trap studies.