Statistical Results for a UAV-Based Rooftop Photovoltaic Detection Model

Statistical results from evaluating a lightweight YOLOv11-based detection network for rooftop photovoltaic panels using a specialized UAV dataset. The dataset, authored by Jiajun Zhu and last updated in May 2026, contains performance metrics from the model's experimental validation. It is a small dataset, 5.5 KB in size, stored in an XLS file.

Use Cases

• Benchmarking lightweight object detection models based on reported precision, recall, and mAP metrics.
• Analyzing the trade-off between model size and accuracy for edge computing applications based on the reported parameters and storage footprint.
• Studying detection performance on small-scale targets in cluttered environments based on the described challenges of rooftop PV inspection.

Strengths

• Performance metrics are explicitly reported, including a precision of 96.32%, recall of 95.74%, and [email protected] of 98.5%.
• Model efficiency metrics are provided, including 2.04 M parameters, a 4.5 MB storage footprint, and an inference speed of 115 FPS.
• Dataset is openly licensed under CC-BY-4.0.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (5.5 KB), indicating limited scope, likely containing only summary statistics.

Provenance

Source

figshare, author Jiajun Zhu.

Collection Method

Experimental results from a proposed computer vision model evaluated on a specialized UAV-based rooftop PV dataset.

Time Range

null

Freshness

Last updated 2026-05-06 17:27:39; freshness should be verified.

Geography

null