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

• URL: http://arxiv.org/abs/2606.10940v1
• Date: Tue, 09 Jun 2026 14:47:24 GMT
• Title: Democratising Camera Trap AI: An Open-Source Model for Detecting UK Mammals
• Abstract summary: 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.<n>The model 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.<n>We release the trained weights in ONNX format under a non-commercial licence, with local desktop and real-time camera support.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Continuously Evolving Deepfake Detection: An Architecture and Public-Benchmark Evaluation of a Dynamic Detection System [0.0]
  Deepfake detectors that achieve near-perfect scores on academic benchmarks collapse on real-world content.<n>We argue this gap is structural: static detectors are trained once against a moving generative frontier.<n>We present BitMind Forensics (BMF), trained through Bittensor SN34, an open adversarial competition that continually refreshes the training distribution.
  arXiv  Detail & Related papers  (2026-07-14T19:53:09Z)
• Weakly supervised framework for wildlife detection and counting in challenging Arctic environments: a case study on caribou (Rangifer tarandus) [0.0]
  We propose a weakly supervised patch-level pretraining based on a detection network's architecture.<n>This dataset includes five caribou herds distributed across Alaska.
  arXiv  Detail & Related papers  (2026-01-26T19:02:18Z)
• Zero-Shot Wildlife Sorting Using Vision Transformers: Evaluating Clustering and Continuous Similarity Ordering [0.0]
  Camera traps generate millions of wildlife images, yet many datasets contain species that are absent from existing classifiers.<n>This work evaluates zero-shot approaches for organizing unlabeled wildlife imagery using self-supervised vision transformers.
  arXiv  Detail & Related papers  (2025-10-16T11:59:18Z)
• Improved detection of discarded fish species through BoxAL active learning [0.2544632696242629]
  In this study, we present an active learning technique, named BoxAL, which includes estimation of epistemic certainty of the Faster R-CNN object-detection model. The method allows selecting the most uncertain training images from an unlabeled pool, which are then used to train the object-detection model. Our study additionally showed that the sampled new data is more valuable for training than the remaining unlabeled data.
  arXiv  Detail & Related papers  (2024-10-07T10:01:30Z)
• Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification [71.06194656633447]
  We establish an uncertainty-inspired open-set (UIOS) model, which was trained with fundus images of 9 retinal conditions. Our UIOS model with thresholding strategy achieved an F1 score of 99.55%, 97.01% and 91.91% for the internal testing set. UIOS correctly predicted high uncertainty scores, which would prompt the need for a manual check in the datasets of non-target categories retinal diseases, low-quality fundus images, and non-fundus images.
  arXiv  Detail & Related papers  (2023-04-08T10:47:41Z)
• To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection [95.21700830273221]
  Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. We propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions. We prove that even a much smaller dataset with well-matched annotations can facilitate models to achieve better performance as well as generalizability.
  arXiv  Detail & Related papers  (2021-09-04T02:45:22Z)
• Florida Wildlife Camera Trap Dataset [48.99466876948454]
  We introduce a challenging wildlife camera trap classification dataset collected from two different locations in Southwestern Florida. The dataset consists of 104,495 images featuring visually similar species, varying illumination conditions, skewed class distribution, and including samples of endangered species.
  arXiv  Detail & Related papers  (2021-06-23T18:53:15Z)
• Filtering Empty Camera Trap Images in Embedded Systems [0.0]
  We present a comparative study on animal recognition models to analyze the trade-off between precision and inference latency on edge devices. The experiments show that, when using the same set of images for training, detectors achieve superior performance. Considering the high cost of generating labels for the detection problem, when there is a massive number of images labeled for classification, classifiers are able to reach results comparable to detectors but with half latency.
  arXiv  Detail & Related papers  (2021-04-18T13:56:22Z)
• Intra-Inter Camera Similarity for Unsupervised Person Re-Identification [50.85048976506701]
  We study a novel intra-inter camera similarity for pseudo-label generation. We train our re-id model in two stages with intra-camera and inter-camera pseudo-labels, respectively. This simple intra-inter camera similarity produces surprisingly good performance on multiple datasets.
  arXiv  Detail & Related papers  (2021-03-22T08:29:04Z)
• A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery [56.10033255997329]
  We propose a novel deep learning method based on a Convolutional Neural Network (CNN) It simultaneously detects and geolocates plantation-rows while counting its plants considering highly-dense plantation configurations. The proposed method achieved state-of-the-art performance for counting and geolocating plants and plant-rows in UAV images from different types of crops.
  arXiv  Detail & Related papers  (2020-12-31T18:51:17Z)
• An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation [80.02124918255059]
  Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. We learn two networks to mutually teach each other. The more reliable predictions on easy images in each network are used to teach the other network to learn about the corresponding hard images.
  arXiv  Detail & Related papers  (2020-11-25T03:29:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.