Democratising Camera Trap AI: An Open-Source Model for Detecting UK Mammals

2026-06-09

AI Summary

This study addresses the long-standing gap in open-source, locally adapted AI models for camera trap-based ecological monitoring in the United Kingdom, where existing solutions often rely on commercial platforms or non-native species data. Leveraging a decade of fieldwork, the authors present and release the first high-accuracy object detection model tailored to 31 common British mammal and bird species, built on the YOLOv8x architecture and distributed in ONNX format to enable deployment on desktop systems and real-time camera traps—even by researchers without machine learning expertise. Evaluated on a validation set, the model achieves an mAP@0.5 of 0.984 (mAP@0.5–0.95: 0.956), with average confidence scores between 0.96 and 0.99 and a false negative rate of only 0.17%, significantly advancing the localization and democratization of ecological monitoring in the UK.

Abstract

Camera traps have become a cornerstone of biodiversity monitoring, but the artificial intelligence that turns vast quantities of images into usable ecological data is often locked behind commercial platforms or trained on fauna that does not match that of the British Isles. In an attempt to remove barriers and increase uptake, we release an open-source object detection model for 31 classes, 28 common UK mammal and bird species, plus utility classes for humans, calibration poles, and vehicles, drawn from a curated dataset of 48,165 labelled instances assembled from multiple sites over a decade of operational deployment through Conservation AI and its successor, Trap Tracker. The model, a YOLO26x detector trained and tested on an 80/10/10 class-stratified split, achieves a mean Average Precision of 0.984 at Intersection over Union (IoU) of 0.5 (0.956 at IoU 0.5-0.95) on the held-out validation set, with precision 0.988 and recall 0.965. On an unseen held-out test split, mean per-species confidence ranged from 0.96 to 0.99 across the 31 classes, with a 0.17% false-negative rate concentrated in difficult night-time, distant, or occluded images. These metrics are from data from the same pool of sites and cameras as training, so performance at entirely new sites is left to future work. We release the trained weights in ONNX format under a non-commercial licence, with local desktop and real-time camera support, aimed explicitly at ecologists with no machine-learning experience. This release is a deliberate counterweight to the multiple paid for models that have developed over the last decade.

Problem

• camera trap
• biodiversity monitoring
• UK mammals
• open-source AI
• object detection

Innovation

• open-source AI
• camera trap
• YOLO object detection
• biodiversity monitoring
• UK mammals