# Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning

arXiv: https://arxiv.org/abs/1806.11368 · HTML: https://mlsanity.com/paper/1806.11368/

## Key facts

- Cited by 27 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 29 Jun 2018.

## Built on by (most cited first, 27 of 27)

- [Seeing biodiversity: perspectives in machine learning for wildlife conservation](https://mlsanity.com/paper/2110.12951/) (2021)
- [TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios](https://mlsanity.com/paper/2108.11539/) (2021)
- [A Review on Deep Learning in UAV Remote Sensing](https://mlsanity.com/paper/2101.10861/) (2021)
- [The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting](https://mlsanity.com/paper/2207.09295/) (2022)
- [Remote Sensing Object Detection Meets Deep Learning: A Meta-review of Challenges and Advances](https://mlsanity.com/paper/2309.06751/) (2023)
- [Self-Supervised Pretraining and Controlled Augmentation Improve Rare Wildlife Recognition in UAV Images](https://mlsanity.com/paper/2108.07582/) (2021)
- [Federated Learning for UAV Swarms Under Class Imbalance and Power Consumption Constraints](https://mlsanity.com/paper/2108.10748/) (2021)
- [Automated Aerial Animal Detection When Spatial Resolution Conditions Are Varied](https://mlsanity.com/paper/2110.01329/) (2021)
- [Robust Tiny Object Detection in Aerial Images amidst Label Noise](https://mlsanity.com/paper/2401.08056/) (2024)
- [POLO -- Point-based, multi-class animal detection](https://mlsanity.com/paper/2410.11741/) (2024)
- [Small or Far Away? Exploiting Deep Super-Resolution and Altitude Data for Aerial Animal Surveillance](https://mlsanity.com/paper/2111.06830/) (2021)
- [FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications](https://mlsanity.com/paper/2209.03157/) (2022)
- [Rare Wildlife Recognition with Self-Supervised Representation Learning](https://mlsanity.com/paper/2211.05636/) (2022)
- [Teaching Computer Vision for Ecology](https://mlsanity.com/paper/2301.02211/) (2023)
- [RareSpot: Spotting Small and Rare Wildlife in Aerial Imagery with Multi-Scale Consistency and Context-Aware Augmentation](https://mlsanity.com/paper/2506.19087/) (2025)
- [Oh Deer, How Should I Handle This? Seasonal Priors for Selective Wildlife Annotation and Classification](https://mlsanity.com/paper/2608.02762/) (2026)
- [Deep Learning and Earth Observation to Support the Sustainable Development Goals](https://mlsanity.com/paper/2112.11367/) (2021)
- [Cattle Detection Occlusion Problem](https://mlsanity.com/paper/2212.11418/) (2022)
- [An empirical study of automatic wildlife detection using drone thermal imaging and object detection](https://mlsanity.com/paper/2310.11257/) (2023)
- [SaRPFF: A Self-Attention with Register-based Pyramid Feature Fusion module for enhanced RLD detection](https://mlsanity.com/paper/2402.16291/) (2024)
- [Partial Label Learning with Focal Loss for Sea Ice Classification Based on Ice Charts](https://mlsanity.com/paper/2406.03645/) (2024)
- [Systematic Literature Review of Vision-Based Approaches to Outdoor Livestock Monitoring with Lessons from Wildlife Studies](https://mlsanity.com/paper/2410.05041/) (2024)
- [Artificial Intelligence for Sustainable Urban Biodiversity: A Framework for Monitoring and Conservation](https://mlsanity.com/paper/2501.14766/) (2024)
- [OpenWildlife: Open-Vocabulary Multi-Species Wildlife Detector for Geographically-Diverse Aerial Imagery](https://mlsanity.com/paper/2506.19204/) (2025)
- [Fusion or Confusion? Assessing the impact of visible-thermal image fusion for automated wildlife detection](https://mlsanity.com/paper/2511.22768/) (2025)
- [RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagery](https://mlsanity.com/paper/2604.20000/) (2026)
- [Cross-Domain Dead Tree Detection via Knowledge Distillation in Aerial Imagery](https://mlsanity.com/paper/2606.02303/) (2026)

## Abstract (arXiv)

Knowledge over the number of animals in large wildlife reserves is a vital necessity for park rangers in their efforts to protect endangered species. Manual animal censuses are dangerous and expensive, hence Unmanned Aerial Vehicles (UAVs) with consumer level digital cameras are becoming a popular alternative tool to estimate livestock. Several works have been proposed that semi-automatically process UAV images to detect animals, of which some employ Convolutional Neural Networks (CNNs), a recent family of deep learning algorithms that proved very effective in object detection in large datasets from computer vision. However, the majority of works related to wildlife focuses only on small datasets (typically subsets of UAV campaigns), which might be detrimental when presented with the sheer scale of real study areas for large mammal census. Methods may yield thousands of false alarms in such cases. In this paper, we study how to scale CNNs to large wildlife census tasks and present a number of recommendations to train a CNN on a large UAV dataset. We further introduce novel evaluation protocols that are tailored to censuses and model suitability for subsequent human verification of detections. Using our recommendations, we are able to train a CNN reducing the number of false positives by an order of magnitude compared to previous state-of-the-art. Setting the requirements at 90% recall, our CNN allows to reduce the amount of data required for manual verification by three times, thus making it possible for rangers to screen all the data acquired efficiently and to detect almost all animals in the reserve automatically.