Loading...
Loading...
Dataset URI:
10.6084/m9.figshare.34329402.v1PD-Defect is a curated multi-module dataset of smartphone images for AI-assisted inspection of power distribution infrastructure. The images were captured by the project team and utility field personnel of the Eastern Power Distribution Company of Andhra Pradesh Limited (APEPDCL), using smartphones under natural lighting conditions. The imagery covers distribution poles, crossarms, overhead conductors with surrounding vegetation, and plinth-mounted distribution-transformer (DTR) installations, and reflects the variability of field capture, including illumination, background clutter, occlusion, and viewing perspective.The release contains 20,476 annotated images organized into task-specific subsets. A field photograph may appear in more than one subset. The subsets support pole detection and pole-lean assessment; tilt assessment of crossarms, and top-cleats; voltage-level classification; vegetation and conductor segmentation for clearance-risk analysis; pole and plinth localization for DTR–ground clearance assessment; and perspective validation of full images, pole-top regions, and DTR scenes.PD-Defect is publicly released to support reproducible research in AI-assisted inspection of power distribution infrastructure.
Keyword(s):
computer vision; Computer vision; deep learning; defect detection; Electrical energy transmission, networks and systems.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)