Fusing Animal Biometrics with Autonomous Robotics: Drone-based Search and Individual ID of Friesian Cattle (Extended Abstract)

William Andrew, Colin Greatwood, Tilo Burghardt; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2020, pp. 38-43

This work covers the robotic drone integration of a re-identification system for Friesian Cattle. We have built a computationally-enhanced M100 UAV platform with an onboard deep learning inference system for integrated computer vision and navigation able to autonomously find and visually identify by coat pattern individual Holstein Friesian cattle in freely moving herds. For autonomous drone-based identification we describe an approach that utilises three deep convolutional neural network architectures running live onboard the aircraft; that is, a YoloV2-based species detector, a dual-stream Convolutional Neural Network (CNN) delivering exploratory agency and an InceptionV3-based biometric Long-term Recurrent Convolutional Network (LRCN) for individual animal identification. We evaluate the performance of components offline, and also online via real-world field tests of autonomous low-altitude flight in a farm environment. The presented proof-of-concept system is a successful step towards autonomous biometric identification of individual animals fromthe air in open pasture environments and inside farms for tag-less AI support in farming and ecology. The work is published in full in IROS 2019.