The dataset is constructed from the drone flight log messages extracted from publicly available drone image datasets provided by VTO Labs under the Drone Forensic Program. The entire process of building this dataset includes extraction, decryption, parsing, cleansing, unique filtering, annotation, splitting, and analysis. The resulting dataset is in CoNLL format, annotated using the IOB2 scheme with six entity types. The total number of log messages acquired from 12 DJI drone models is 1850. The data are split based on the drone models, resulting in 1412 messages for training and 438 messages for testing. The average length of log messages is 6.5 globally, 6.6 and 8.8 for the train and the test sets, respectively.

Original languageEnglish
Article number109179
JournalData in Brief
Publication statusPublished - Jun 2023


  • Digital forensics
  • Drone dataset
  • Drone entity recognition
  • Drone forensics
  • Infrastructure
  • NER dataset


Dive into the research topics of 'DroNER: Dataset for drone named entity recognition'. Together they form a unique fingerprint.

Cite this