AOW-YOLO: Model Performance Metrics for Smoking Detection on Construction Sites

Ruishi Liang's research dataset, last updated May 6, 2026, compares the performance of the novel AOW-YOLO model against other lightweight models for detecting smoking behavior in complex construction site environments. The dataset likely contains tabular experimental results, including metrics like mAP50 and inference speed. It is shared under a CC-BY-4.0 license on figshare.

Use Cases

• Benchmarking lightweight object detection models based on reported mAP50 and mAP50:95 metrics.
• Evaluating model inference speed for real-time applications based on the 31.6% speed improvement claim.
• Researching methods to improve detection of small objects in cluttered backgrounds, as described for construction sites.

Strengths

• Includes specific performance metrics (mAP50, mAP50:95) and a reported 31.6% inference speed improvement.
• Dataset is small (5.5 KB) and available in a common XLS format for easy access.

Limitations

• Row count and specific column definitions are unknown, limiting assessment of data granularity.
• The dataset's scope is limited to the specific experimental results of the described model comparison.

Provenance

Source

Ruishi Liang via figshare.

Collection Method

Likely generated from experimental evaluation of the proposed AOW-YOLO model against baseline models.

Freshness

Last updated 2026-05-06 17:45:46.