ArTuga: Early Fusion Datasets for UAV Landing with LiDAR, Visual, and Thermal Images

Four datasets created by Francisco Neves for UAV landing operations using a multimodal fiducial marker called ArTuga. The collection includes spatially aligned RGB images from LiDAR, visual, and thermal sensors, as well as an early-fused multimodal version. The datasets are hosted on paperswithcode under an Open Access (green) license.

Use Cases

• Training computer vision models for fiducial marker detection based on the described visual images.
• Developing sensor fusion algorithms for robotic navigation based on the early-fused multimodal images.
• Benchmarking thermal imaging performance in UAV operations based on the unimodal thermal dataset.
• Evaluating LiDAR-based perception for landing scenarios based on the unimodal LiDAR images.

Strengths

• Provides four distinct, spatially aligned datasets enabling comparative studies.
• Includes an early-fused multimodal dataset combining LiDAR, visual, and thermal information.
• Uses a specifically designed multimodal fiducial marker (ArTuga) for data collection.

Limitations

• Dataset size, row count, and file formats are unknown, limiting suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Francisco Neves via paperswithcode

Collection Method

Likely collected using a UAV equipped with LiDAR, visual, and thermal sensors and the ArTuga fiducial marker.