No publicly available, ML ready datasets exist for wildlife health conditions in camera trap imagery, creating a fundamental barrier to automated health screening. We present a pipeline for generating synthetic training images depicting alopecia and body condition deterioration in wildlife from real camera trap photographs. Our pipeline constructs a curated base image set from iWildCam using MegaDetector derived bounding boxes and center frame weighted stratified sampling across 8 North American species. A generative phenotype editing system produces controlled severity variants depicting hair loss consistent with mange and emaciation. An adaptive scene drift quality control system uses a sham prefilter and decoupled mask then score approach with complementary day or night metrics to reject images where the generative model altered the original scene. We frame the pipeline explicitly as a screening data source. From 201 base images across 4 species, we generate 553 QC passing synthetic variants with an overall pass rate of 83 percent. A sim to real transfer experiment training exclusively on synthetic data and testing on real camera trap images of suspected health conditions achieves 0.85 AUROC, demonstrating that the synthetic data captures visual features sufficient for screening.
RareSpot: Spotting Small and Rare Wildlife in Aerial Imagery with Multi-Scale Consistency and Context-Aware Augmentation
University of California, Santa Barbara（加州大学圣芭芭拉分校）；Smithsonian National Zoo and Conservation Biology Institute（史密森尼国家动物园与保护生物学研究所）；Stanford University（斯坦福大学）
Improving Object Detection for Time-Lapse Imagery Using Temporal Features in Wildlife Monitoring
School of Computing Sciences, University of East Anglia (UEA)（东英吉利大学计算科学学院）；School of Biological Sciences, University of East Anglia (UEA)（东英吉利大学生物科学学院）；Institute of Zoology, Zoological Society of London（伦敦动物学会动物学研究所）；Durrell Wildlife Conservation Trust（杜雷尔野生动物保护信托基金）；Mauritian Wildlife Foundation（毛里求斯野生动物基金会）；National Parks and Conservation Service (Government of Mauritius)（毛里求斯政府国家公园与保护局）
Trail camera imagery has increasingly gained popularity amongst biologists for conservation and ecological research. Minimal human interference required to operate camera traps allows capturing unbiased species activities. Several studies - based on human and wildlife interactions, migratory patterns of various species, risk of extinction in endangered populations - are limited by the lack of rich data and the time-consuming nature of manually annotating trail camera imagery. We introduce a challenging wildlife camera trap classification dataset collected from two different locations in Southw…
RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagery
University of California, Santa Barbara（加州大学圣芭芭拉分校）；Smithsonian National Zoo and Conservation Biology Institute（史密森尼国家动物园与保护生物学研究所）；Stanford University（斯坦福大学）；The Doris Duke Foundation（多里斯·杜克基金会）
A unified three-branch deep learning framework for automated detection and counting of wildlife in aerial imagery
School of Geospatial Engineering and Science, Sun Yat-Sen University（中山大学地理空间工程与科学学院）；Faculty of Geo-Information Science and Earth Observation, University of Twente（特温特大学地球信息科学与对地观测学院）；Boma and Badingilo National Parks, African Parks（博马和巴丁吉洛国家公园，非洲公园组织）；Department of Ecology and Evolutionary Biology, Princeton University（普林斯顿大学生态与进化生物学系）；Lolldaiga Hills Research Programme（洛尔迪加山研究项目）；School of Biological, Earth & Environmental Sciences, Environmental Research Institute, University College Cork（科克大学环境研究所生物、地球与环境科学学院）
Automated animal censuses with aerial imagery are a vital ingredient towards wildlife conservation. Recent models are generally based on deep learning and thus require vast amounts of training data. Due to their scarcity and minuscule size, annotating animals in aerial imagery is a highly tedious process. In this project, we present a methodology to reduce the amount of required training data by resorting to self-supervised pretraining. In detail, we examine a combination of recent contrastive learning methodologies like Momentum Contrast (MoCo) and Cross-Level Instance-Group Discrimination (C…
Automated Detection of Salvin's Albatrosses: Improving Deep Learning Tools for Aerial Wildlife Surveys
Centre for Data Science and Artificial Intelligence（数据科学与人工智能中心）；University of Otago（奥塔哥大学）；Princeton University（普林斯顿大学）；Marine Bycatch and Threats – Department of Conservation（海洋误捕与威胁——保护部门）；Antarctic Research Trust（南极研究信托）；The Tawaki Trust（塔瓦基信托）；Global Penguin Society（全球企鹅协会）
Lacking Data? No worries! How synthetic images can alleviate image scarcity in wildlife surveys: a case study with muskox (Ovibos moschatus)
Université de Sherbrooke（舍布鲁克大学）；Ministère de l’Environnement, de la Lutte contre les Changements Climatiques, de la Faune et des Parcs (MELCCFP)（环境、应对气候变化、野生动物与公园部）；Quebec Centre for Biodiversity Science (QCBS)（魁北克生物多样性科学中心）；McGill University（麦吉尔大学）
Automated animal censuses with aerial imagery are a vital ingredient towards wildlife conservation. Recent models are generally based on supervised learning and thus require vast amounts of training data. Due to their scarcity and minuscule size, annotating animals in aerial imagery is a highly tedious process. In this project, we present a methodology to reduce the amount of required training data by resorting to self-supervised pretraining. In detail, we examine a combination of recent contrastive learning methodologies like Momentum Contrast (MoCo) and Cross-Level Instance-Group Discriminat…
The ongoing biodiversity crisis calls for accurate estimation of animal density and abundance to identify sources of biodiversity decline and effectiveness of conservation interventions. Camera traps together with abundance estimation methods are often employed for this purpose. The necessary distances between camera and observed animals are traditionally derived in a laborious, fully manual or semi-automatic process. Both approaches require reference image material, which is both difficult to acquire and not available for existing datasets. We propose a fully automatic approach we call AUtoma…
UC Berkeley（加州大学伯克利分校）；Nanyang Tech. Univ.（南洋理工大学）；UC Santa Barbara（加州大学圣塔芭芭拉分校）；Princeton University（普林斯顿大学）；Univ. KwaZulu-Natal（夸祖鲁-纳塔尔大学）
Camera trapping is increasingly used to monitor wildlife, but this technology typically requires extensive data annotation. Recently, deep learning has significantly advanced automatic wildlife recognition. However, current methods are hampered by a dependence on large static data sets when wildlife data is intrinsically dynamic and involves long-tailed distributions. These two drawbacks can be overcome through a hybrid combination of machine learning and humans in the loop. Our proposed iterative human and automated identification approach is capable of learning from wildlife imagery data wit…
Advancing Wildlife Monitoring: Drone-Based Sampling for Roe Deer Density Estimation
Office for Wildlife Ecology and Forestry（野生动物生态与林业办公室）；University of Applied Sciences Upper Austria（上奥地利应用科技大学）；Austrian Research Centre for Forests BFW（奥地利森林研究中心）
Fusion or Confusion? Assessing the impact of visible-thermal image fusion for automated wildlife detection
Department of Applied Geomatics, Université de Sherbrooke（舍布鲁克大学应用地理信息学系）；Quebec Centre for Biodiversity Science, McGill University（麦吉尔大学魁北克生物多样性科学中心）；Ministère de l’Environnement, de la Lutte contre les Changements Climatiques, de la Faune et des Parcs (MELCCFP)（魁北克省环境、气候变化、野生动物和公园部）；Centre d'enseignement et de recherche en foresterie de Sainte-Foy（圣福瓦林业教学与研究中心）
Weakly supervised framework for wildlife detection and counting in challenging Arctic environments: a case study on caribou (Rangifer tarandus)
Department of Applied Geomatics, Université de Sherbrooke（应用测绘系，谢伯罗克大学）；Quebec Centre for Biodiversity Science (QCBS), Stewart Biology, McGill University（魁北克生物多样性科学中心（QCBS）、斯图尔特生物学、麦吉尔大学）
Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images
Microsoft AI for Good Lab, Redmond（微软人工智能公益实验室）；University of Southern California, Los Angeles（南加州大学）；Microsoft Research, Redmond（微软研究院）；Nanyang Technological University, Singapore（南洋理工大学）；Universidad de Los Andes, Colombia（洛斯安第斯大学）
Predicting butterfly species presence from satellite imagery using soft contrastive regularisation
The Alan Turing Institute, the UK（英国阿尔安·图灵研究所）；Wageningen University & Research, the NL（瓦赫宁根大学与研究中心）；University College London, the UK（伦敦大学学院）；UK Centre for Ecology & Hydrology, the UK（英国生态与水文研究中心）
Delft University of Technology（代尔夫特理工大学）；California Institute of Technology（加州理工学院）
The natural world is long-tailed: rare classes are observed orders of magnitudes less frequently than common ones, leading to highly-imbalanced data where rare classes can have only handfuls of examples. Learning from few examples is a known challenge for deep learning based classification algorithms, and is the focus of the field of low-shot learning. One potential approach to increase the training data for these rare classes is to augment the limited real data with synthetic samples. This has been shown to help, but the domain shift between real and synthetic hinders the approaches' efficacy…
A Data-Driven RetinaNet Model for Small Object Detection in Aerial Images
Department of Electrical Engineering and Computer Science（电气工程与计算机科学系）；University of Missouri（密苏里大学）；Computer Science University of Missouri Columbia, MO, USA（计算机科学密苏里大学哥伦比亚分校）
