Real Infrared Maritime Vessel Imagery for Detection and Classification

Real infrared imagery of maritime vessels provided in three forms: full-frame detection images, per-object classification crops, and a hand-curated subset. The dataset includes seven vessel classes: liner, bulk carrier, warship, sailboat, canoe, container ship, and fishing boat. It was created by hanchong and last updated on Hugging Face in July 2026.

Use Cases

• Train object detection models based on full-frame infrared images with bounding-box labels.
• Develop vessel classification models based on the seven specified vessel classes.
• Benchmark infrared image recognition algorithms using the hand-curated subset.
• Study domain adaptation for computer vision models using real infrared sensor data.

Strengths

• Contains real infrared imagery, which is a specific and less common sensor modality.
• Offers data in three structured forms: full-frame detection, classification crops, and a curated subset.
• Defines seven distinct maritime vessel classes for classification tasks.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and dataset size are unknown, which may limit suitability assessment.

Provenance

Source

huggingface

Collection Method

Likely collected from infrared sensors observing maritime environments.

Freshness

Last updated 2026-07-07 05:37:48; freshness should be verified.