Annotated Bridge Inspection Imagery and Videos From AI-Powered Defect Detection in Kansas Bridges [Dataset]

Details

• Alternative Title:
  Drone-based AI Bridge Inspection Dataset (Kansas NCRPC SMART Stage 1) [Dataset]
• Creators:
  Tsegaye, Natnael Taye
• Corporate Creators:
  University of Maryland (College Park, Md.)
• Corporate Publisher:
  North Central Regional Planning Commission
• Contributor:
  Cui, Qingbin ; Zhang, Yunfeng
• Corporate Contributors:
  Strengthening Mobility and Revolutionizing Transportation (SMART) Program
• Subject/TRT Terms:
  • Datasets
  • Bridges
  • Structural health monitoring
  • Concrete
  • Drones
  • Unmanned aircraft systems
  • Artificial intelligence
• DOI:
  https://doi.org/10.5281/zenodo.17477701
• Resource Type:
  Dataset
• Right Statement:
  Open Access; https://creativecommons.org/licenses/by/4.0/
• Geographical Coverage:
  United States ; Kansas
• Edition:
  v1.1
• Description:
  This dataset contains annotated images and videos generated from drone-collected bridge inspection imagery used in AI-based defect detection research across four Kansas counties. The files include visual outputs from YOLOv11 instance segmentation models trained to identify and outline eight types of concrete surface defects: Crack, ACrack, Efflorescence, WConccor, Spalling, Wetspot, Rust, and ExposedRebars. Each annotated image shows detection polygons with defect labels and per-image class counts. Supplementary TXT files summarize per-image defect counts.
  
  Additional Dataset Zip Files may be downloaded from Zenodo:
  
  BridgeDefects_Inference_Videos1_2025.zip (8.3 GB):
  
  https://zenodo.org/records/23482965/files/BridgeDefects_Inference_Videos1_2025.zip?download=1;
  
  BridgeDefects_Inference_Videos2_2025.zip (12.4 GB):
  
  https://zenodo.org/records/23482965/files/BridgeDefects_Inference_Videos2_2025.zip?download=1;
  
  BridgeDefects_Inference_Videos3_2025.zip (4.5 GB):
  
  https://zenodo.org/records/23482965/files/BridgeDefects_Inference_Videos3_2025.zip?download=1
  
  These data were collected as part of research on AI-powered bridge condition assessment conducted at the University of Maryland in collaboration with Kansas counties. The dataset supports reproducibility, benchmarking, and further research on automated infrastructure inspection.
  
  The total size of the ZIP file is 25.4 GB.
• Content Notes:
  This item is made available under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) license https://creativecommons.org/licenses/by/4.0/. Use the following citation: Tsegaye, N. T. (2026). Annotated bridge inspection imagery and videos from AI-powered defect detection in Kansas bridges (Version v1.1) [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.23482965, Training Code: https://doi.org/10.5281/zenodo.17488232; Deployment Code: https://doi.org/10.5281/zenodo.17488363.
  
  Tsegaye, N. T. (2026). Curated Dataset and Inference Results for AI-Based Bridge Defect Detection Using Images and Videos [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.19268973
• Format:
  ZIP
• Funding:
  69A3552341015 SMARTFY22N1P1G24
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/88076/dot_88076_DS1.zip
• File Type:
  [ZIP - 89.84 MB]
• Collection(s):
  Artificial Intelligence Deployment Center of Excellence (AI COE) ; SMART Program
• Main Document Checksum:
  urn:sha-512:fedd4c06c04b3e21efd3f5a89ead1db3984996f32c239bd91dced90914fdf0b942368934a4781424d175c126cc9ca171d3c5fce3cc5e57954762c0b380aa8908