Two-Stage Wildlife Event Classification for Edge Deployment

Camera-based wildlife monitoring is often overwhelmed by non-target triggers and slowed by manual review or cloud-dependent inference, which can prevent timely intervention for high stakes human-wildlife conflicts. Our key contribution is a deployable, fully offline edge vision sensor that achieves near-real-time, highly accurate wildlife event classification by combining detector-based empty-frame suppression with a lightweight classifier trained with a staged transfer-learning curriculum. Our design is robust to low-quality nighttime monochrome imagery (motion blur, low contrast, illumination artifacts, and partial-body captures) and operates using commercially available components in connectivity-limited settings. In field deployments running since May 2025, end-to-end latency from camera trigger to action command is approximately 4 seconds. Ablation studies using a dataset of labeled wildlife images (pumas, not pumas) show that the two-stage approach substantially reduces false alarms in identifying pumas relative to a full-frame classifier while maintaining high recall. The system can be easily adapted for other species, as demonstrated by rapid retraining of the second stage to classify ringtails. Downstream responses (e.g., notifications and optional audio/light outputs) provide flexible actuation capabilities that can be configured to support intervention.