Mines: RGB and Depth Images of Annotated Landmines Captured with iPhone LiDAR

A repository of RGB and depth frames depicting TM-62P3, PMN-4, PTM-1G, and PFM-1 landmines, annotated with bounding boxes. Images were captured using an iPhone 16 with its LiDAR sensor. The dataset was created by Gabryte and last updated on December 5, 2025.

Use Cases

• Train object detection models based on the bounding box annotations for landmine types.
• Develop depth-aware detection systems based on the paired RGB and depth frames.
• Test sensor fusion algorithms based on data captured with a LiDAR sensor.
• Benchmark model performance in challenging outdoor environments based on the real-world imagery.

Strengths

• Contains paired RGB and depth data, enabling multimodal analysis.
• Includes bounding box annotations for four specific landmine models (TM-62P3, PMN-4, PTM-1G, PFM-1).
• Data was captured with a specific sensor (iPhone 16 LiDAR), providing consistency.

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.
• Geographic and environmental context for the image capture is unspecified, which may affect generalizability.

Provenance

Source

huggingface, author Gabryte.

Collection Method

Images taken using an iPhone 16 with its LiDAR sensor and annotated with the CVAT tool.

Time Range

null

Freshness

Last updated 2025-12 05 13:03:59.

Geography

null