CARD-Germany-Batch1: Multi-Modal Driving Data from Germany

Germany is the geographic scope for this multi-modal driving dataset. It contains 28 sequences of sensor data, including stereo camera images, LiDAR, and depth annotations. The dataset was created by CARD-Data and was last updated on May 16, 2026.

Use Cases

• Train object detection models based on YOLO-format annotations mentioned in the description
• Develop depth estimation algorithms based on aggregated depth point clouds
• Research sensor fusion techniques based on the combination of stereo cameras and LiDAR data
• Benchmark autonomous driving perception systems based on real-world driving sequences

Strengths

• Contains 28 distinct driving sequences
• Includes multiple sensor modalities: stereo cameras, LiDAR, and depth annotations
• Provides trajectory and calibration data for sensor alignment

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 and total data size are unknown, which may limit suitability assessment

Provenance

Source

CARD-Data

Freshness

Last updated 2026-05-16 15:06:54; freshness should be verified

Geography

Germany