ForestFireInsights-Eval: UAV Imagery for Wildfire Model Evaluation

ForestFireInsights-Eval contains original UAV images gathered by the Evolonic student team at FAU Erlangen and Fraunhofer IISB. The dataset is formatted for use with ForestFireVLMs, including 7B and 3B parameter models. Data from the Center for Wildfire Research at University of Split is also included.

Use Cases

• Evaluate wildfire detection models based on UAV imagery.
• Benchmark multimodal vision-language models on remote sensing tasks.
• Train or fine-tune models for fire segmentation or classification based on drone-captured data.

Strengths

• Includes original UAV images gathered by a named student team.
• Formatted for use with specific, named ForestFireVLM models.
• Incorporates data from a dedicated wildfire research center.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect geographic or temporal bias inherent to the specific collection sources.

Provenance

Source

Center for Wildfire Research at University of Split; Evolonic student team at FAU Erlangen and Fraunhofer IISB.

Collection Method

UAV images gathered by named individuals using various drones.

Freshness

Last updated 2025-03-16 23:54:11.