AUTH-Sheep: An Annotated Video Dataset for Detection and Tracking of Sheep in UAV Imagery
Year: 2024
Type: conference-paper
Abstract: Object detection and tracking in drone imagery is still an open research field, especially for livestockmonitoring and when detection is carried out on the drone itself. In this paper, we present the firstannotated aerial video dataset of sheep, which we will make publicly available to the research communityto foster further research in this field. Our AUTH-Sheep dataset consists of 4 videos with frame-accurateannotations of oriented bounding boxes and consistent track IDs per object and video. Furthermore, wedeveloped a full detection and tracking pipeline as a baseline implementation to give other researchers areference approach to compare their algorithms against. For this, we compared horizontal and orientedbounding box detection for the task at hand. Therefor, the YOLOv8 nano detector is utilized, whichwas pre-trained on a different dataset. To be able to train this detector of oriented bounding boxes, wesemi-automatically created new oriented annotations for an existing dataset of sheep images.
Authors: Doll, Oliver, Loos, Alexander
Institution: Fraunhofer Institute for Digital Media Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
SDG: Zero hunger
Open Access status: green
Funder: European Commission
OpenAlex ID: W6930662255
FWCI:
Cites:
Cited by:
Related to: