Keke-Aware Vehicle Counting Dataset for Traffic Measurement

Moses Akujobi created a 1.1 GB dataset for vehicle detection, tracking, and counting from roadside video. It includes a dedicated class for keke (auto-rickshaw/tricycle), which is not a standard class in common international benchmarks. The dataset was last updated on April 9, 2026 and includes train/validation/test splits with YOLO-format labels.

Use Cases

• Vehicle detection and counting based on roadside video footage mentioned in the description
• Training object detection models for a dedicated auto-rickshaw class
• Evaluating traffic measurement algorithms using the provided train/validation/test splits
• Benchmarking YOLO-based models for region-specific vehicle types

Strengths

• Dataset size is 1.1 GB, indicating substantial video content
• Includes a dedicated class for keke (auto-rickshaw/tricycle), addressing a gap in common benchmarks
• Provides pre-defined train/validation/test splits and YOLO-format labels

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• Data may reflect geographic bias inherent to figshare

Provenance

Source

figshare

Collection Method

Created for the study 'Keke-Aware Vehicle Counting for Traffic Measurement Using YOLO: Dataset and Field Evaluation'

Freshness

Last updated 2026-04-09 03:19:10