Drone videos and images of sheep in various conditions (for computer vision purpose) - Part II

This dataset was developed within the framework of the European Horizon 2020 project ICAERUS, specifically for the livestock monitoring use case. The objective of this work is to explore the potential of drone-based computer vision methods for monitoring small ruminants in real farming environments.

More information about the project is available on the project website: https://icaerus.eu

Objective

Counting sheep and goats is a significant operational challenge for farmers managing flocks that may contain hundreds of animals. Traditional counting methods are time-consuming and prone to errors. The objective of this work is to develop a computer vision–based methodology capable of automatically detecting, tracking, and counting sheep and goats when animals pass through a corridor, gate, or other naturally constrained passage.

The proposed approach relies on low-altitude aerial videos (<15 m) acquired using drones, providing a top-down perspective that facilitates the detection and counting of animals.

Progress and Enhancements

Our work includes the development of datasets and models dedicated to low-altitude aerial imagery of sheep (<15 m).

• Datasets contributions:

Multiple datasets either with or without annotations, have been produced and enriched as part of this work during the 2023-2026 period (see the summary table).

• Model Development:

We developed computer vision models for small ruminant detection (0.99 mAP50 in its version 4), tracking, and counting.
The models and associated code are available on GitHub:
https://github.com/ICAERUS-EU/UC3_Livestock_Monitoring

To improve the performance and robustness of detection models such as YOLO, the datasets were enriched to increase variability in:

• Environmental conditions (background types and lighting conditions)
• Animal appearance, including non-white sheep and goats, which are often underrepresented in existing datasets.

 Data set description

This dataset is the second part of “Drone videos and images of sheep in various conditions (for computer vision purpose)” dataset where we offer large diversity of sheep aerial images along farms and seasons. The dataset includes:

• Background diversity: grey rangelands and diverse green pastures
• Lighting diversity: varying weather and illumination conditions
• Animal distribution: dispersed and highly clustered groups of sheep
• Additional objects: dogs, humans, and farm equipment visible in some scenes

This dataset encompasses the following data:

• Ferme EPLEFPA de Carmejane: a directory encompassing 100 images and 20 videos from a sheep farm in France, Provence from various situations and time.
• Ferme EPLEFPA de Saint Gaudens: a directory encompassing 1579 images and 27 videos from a sheep farm in France, Haute-Garonne from various situations and time.

Future Work

Part of this data is available with annotations in another dataset (see the table above). Following extensive efforts in data collection and annotation, our next objective is to finalize and deploy the sheep counting pipeline on an edge computing solution, enabling real-time livestock monitoring in operational farm environments.

In parallel, additional projects are exploring other computer vision applications in sheep farming, expanding the potential use cases of this technology.

Acknowledgments

The authors would like to acknowledge Thomas Jegorel (EPLEFPA de Saint-Gaudens) and the project F.A.A.N., for the valuable contribution to this work. As an external contributor to the ICAERUS project, he generously provided access to a substantial amount of field data and facilitated the collection of drone imagery in operational and diverse farm conditions.

The authors also thank all the farm staff and technical teams involved in the data acquisition campaigns for their assistance in enabling drone flights and data collection under real farming conditions.

Collaboration and Contact

We welcome collaborations on this topic. For inquiries or further information, please contact:
Adrien Lebreton
Email: adrien.lebreton@idele.fr