753 substation images with polygon mask annotations across 18 object categories, plus three additional subsets for transmission line classification and detection. The collection features drone-captured imagery specifically targeting power system infrastructure for computer vision applications.
Use Cases
- Train instance segmentation models for infrastructure monitoring using the polygon mask annotations and 18 object categories
- Develop automated inspection tools for power grids using the drone-captured transmission line images
- Build classification algorithms to distinguish between different types of transmission line infrastructure using the classification subset
Strengths
- 753 substation images featuring detailed polygon mask annotations
- 18 distinct object categories including capacitors and substation hardware
- Includes a dedicated subset of drone-captured transmission line imagery
- Four distinct subsets covering both classification and object detection tasks for power systems