Data for Cooperative Perception of Road-Side Unit and On-board Equipment with Edge Artific

Data collected by the Mobile Unit for Sensing Traffic (MUST) project at the University of Washington testbed for cooperative perception research. The collection includes raw image data and corresponding detection results generated by edge artificial intelligence systems. This dataset supports the development of driving assistance systems that integrate roadside and on-board sensor data.

Use Cases

• Training object detection models for traffic scenes based on the collected image data.
• Developing sensor fusion algorithms for cooperative perception between roadside units and vehicles.
• Benchmarking edge AI inference performance for real-time driving assistance applications.
• Simulating and testing V2X (Vehicle-to-Everything) communication scenarios using real-world sensor data.

Strengths

• Data originates from a controlled testbed at the University of Washington, suggesting a structured collection environment.
• Includes both raw sensor data (images) and processed detection outputs, providing a pipeline for analysis.

Limitations

• Row count, file size, and specific file formats are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Mobile Unit for Sensing Traffic (MUST) project, University of Washington.

Collection Method

Collected from a testbed, likely involving roadside units and on-board equipment.

Geography

University of Washington testbed.