Data

UAV-ForestOD: A Multi-Class Annotated Dataset for UAV Obstacle Detection in Forest Environments

Central Queensland University
Shouthiri Partheepan (Aggregated by)
Viewed: [[ro.stat.viewed]] Cited: [[ro.stat.cited]] Accessed: [[ro.stat.accessed]]
ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rfr_id=info%3Asid%2FANDS&rft_id=info:doi10.25946/33921154.v1&rft.title=UAV-ForestOD: A Multi-Class Annotated Dataset for UAV Obstacle Detection in Forest Environments&rft.identifier=10.25946/33921154.v1&rft.publisher=Central Queensland University&rft.description=UAV-ForestOD is a multi-class annotated image dataset developed for UAV-based obstacle detection and autonomous navigation in complex forest environments. The dataset contains 7,055 images with 19,226 bounding-box annotations representing a range of obstacle categories relevant to UAV operations, including drones, planes, helicopters, birds, wild animals, trees, tree trunks, tree branches, and rocks. The dataset was prepared to support the development and evaluation of deep learning-based object detection models for real-time UAV navigation. Images were standardised to a resolution of 1024 × 1024 pixels, with padding applied where necessary to preserve aspect ratios. The dataset was divided into training, validation, and testing subsets using an 80:10:10 split.&rft.creator=Shouthiri Partheepan&rft.date=2026&rft_rights= https://creativecommons.org/licenses/by/4.0/&rft_subject=Deep learning&rft_subject=Reinforcement learning&rft_subject=Planning and decision making&rft_subject=Autonomous agents and multiagent systems&rft_subject=Unmanned Aerial Vehicle (UAV)&rft_subject=Obstacle Detection&rft_subject=Forest Environment&rft_subject=Autonomous Navigation&rft_subject=YOLO&rft_subject=Bounding Box Annotation&rft_subject=Deep Learning&rft.type=dataset&rft.language=English Access the data
Cite Saved to MyRDA Save to MyRDA

Licence & Rights:

Other view details

Access:

Open

Full description

UAV-ForestOD is a multi-class annotated image dataset developed for UAV-based obstacle detection and autonomous navigation in complex forest environments. The dataset contains 7,055 images with 19,226 bounding-box annotations representing a range of obstacle categories relevant to UAV operations, including drones, planes, helicopters, birds, wild animals, trees, tree trunks, tree branches, and rocks.

The dataset was prepared to support the development and evaluation of deep learning-based object detection models for real-time UAV navigation. Images were standardised to a resolution of 1024 × 1024 pixels, with padding applied where necessary to preserve aspect ratios. The dataset was divided into training, validation, and testing subsets using an 80:10:10 split.

This dataset is part of a larger collection

Click to explore relationships graph
Help

Related People

Related Websites

  • Supplements Evaluating YOLO Variants With Transfer Learning for Real-Time UAV Obstacle Detection in Simulated Forest Environments
    10779/cqu.29434118
  • Supplements Evaluating YOLO Variants With Transfer Learning for Real-Time UAV Obstacle Detection in Simulated Forest Environments
    10779/cqu.29434118
Subjects
Autonomous Navigation | Autonomous agents and multiagent systems | Bounding Box Annotation | Deep Learning | Deep learning | Forest Environment | Obstacle Detection | Planning and decision making | Reinforcement learning | Unmanned Aerial Vehicle (UAV) | YOLO |

User Contributed Tags    

Login to tag this record with meaningful keywords to make it easier to discover

Identifiers
ACN 633 798 857