FVessel: Benchmark for Vessel Detection and Tracking in Inland Waterways

FVessel is a benchmark dataset for evaluating the reliability of Automatic Identification System (AIS) and video data in vessel traffic surveillance. It was introduced in a 2023 IEEE Transactions on Intelligent Transportation Systems paper by Yu Guo, Ryan Wen Liu, and colleagues. The dataset is hosted on Hugging Face by user gy65896 and was last updated in August 2025.

Use Cases

• Benchmarking vessel detection algorithms based on video surveillance data
• Evaluating vessel tracking reliability based on AIS and video data fusion
• Developing asynchronous trajectory matching models for inland waterway traffic
• Training models for maritime traffic surveillance and anomaly detection

Strengths

• Serves as a published benchmark for a specific research problem in intelligent transportation systems
• Designed for multimodal data fusion, combining AIS and video data sources
• Focuses on a specific application domain: vessel traffic surveillance in inland waterways

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• The dataset's scale and specific file formats are not described in the provided metadata

Provenance

Source

Associated with a research paper published in IEEE Transactions on Intelligent Transportation Systems (TITS 2023).

Collection Method

Likely collected for evaluating data fusion methods for maritime surveillance.

Time Range

The dataset was introduced in a 2023 publication.

Freshness

Last updated 2025-08-27 02:52:44; freshness should be verified

Geography

Focuses on inland waterways; specific geographic coverage is not detailed.