High resolution environmental monitoring of pollinator insects through macro camera trapping and AI

Insect identification using camera traps has been neglected due to traditional sensors’ inability to detect cold-blooded organisms. However, insects are essential for ecosystem services like pollination, making accurate detection crucial. This study uses advancements in computer vision, specifically convolutional neural networks (CNNs), to develop an automated insect identification algorithm. High-resolution time-lapse images from camera traps in the Austrian Alps were annotated and processed with LabelBox and YOLOv8, achieving order-level insect classification. Results showed a high diversity of insects with a peak mean Average Precision (mAP) of 54.23% at an Intersection over Union (IoU) threshold of 0.5, indicating the method’s potential for precise species-level data collection. Despite challenges like background misclassification, the approach offers a robust framework for insect detection and valuable insights for refinement. YOLO-generated data enable comprehensive time series analysis, aiding in effective monitoring and management strategies. This study supports CNN-based methods in ecological monitoring, relevant for pest management and identifying key species.