Published June 9, 2025 | Version v0
Image Open

Labeled Dataset for Detecting Fanning Behavior of Honeybees at the Hive Entrance

Creators

  • 1. ROR icon Vilnius Gediminas Technical University

Description

The dataset was compiled from video recordings of hive landing boards at a local apiary in the Vilnius district during the 2023 beekeeping season. A stationary camera, positioned approximately 30 cm above the landing boards, recorded footage at 1920×1080 resolution and 30 frames per second. To ensure environmental diversity, recordings were taken under both sunny and cloudy conditions. Individual frames were extracted from the videos for annotation. The dataset consists of high-resolution images from four beehives, each housing a colony exhibiting fanning behavior, and captures a variety of environmental settings and insect activity. In total, 18,000 frames were extracted—equivalent to approximately 10 minutes of continuous video—with 15,111 frames containing visible fanning bees. Across these frames, 57,597 individual instances of fanning behavior were annotated. 84% of the images contain fanning behavior, while 16% do not.

Record ID Images Fanning frames Fanning bees Time Usage
20230609c  2900  2585  4699  1 min 37 s  train
20230711a aaa aaaa  8800  6914  23357  4 min 53 s  train
20230711b  3600  2912  9824  2 min  val
20230711cc  2700  2700  19717 1 min 30 s train
Sum:  18000  15111  57597  10 min  80% train / 20% val

 If you are using this dataset in your research, please cite my recent articles listed below.

Files

dataset-rgb.zip

Files (17.3 GB)

Name Size Download all
md5:d955adbbf48f4369b178090a42b9966e
17.3 GB Preview Download

Additional details

References

  • Sledevič, T. (2025). Evaluation of Single-Shot Object Detection Models for Identifying Fanning Behavior in Honeybees at the Hive Entrance. Agriculture, 15(15), 1609. https://doi.org/10.3390/agriculture15151609
  • Sledevič T, Serackis A, Matuzevičius D, Plonis D, Vdoviak G. (2025) Visual recognition of honeybee behavior patterns at the hive entrance. PLOS ONE 20(2): e0318401. https://doi.org/10.1371/journal.pone.0318401
  • Vdoviak, G., Sledevič, T., Serackis, A., Plonis, D., Matuzevičius, D., & Abromavičius, V. (2025). Evaluation of Deep Learning Models for Insects Detection at the Hive Entrance for a Bee Behavior Recognition System. Agriculture, 15(10), 1019. https://doi.org/10.3390/agriculture15101019
  • Sledevič, T., Serackis, A., Matuzevičius, D., Plonis, D., & Andriukaitis, D. (2024). Keypoint-Based Bee Orientation Estimation and Ramp Detection at the Hive Entrance for Bee Behavior Identification System. Agriculture, 14(11), 1890. https://doi.org/10.3390/agriculture14111890
  • Sledevič, T., Serackis, A., & Plonis, D. (2022). FPGA Implementation of a Convolutional Neural Network and Its Application for Pollen Detection upon Entrance to the Beehive. Agriculture, 12(11), 1849. https://doi.org/10.3390/agriculture12111849
  • Sledevič, T. (2025). Evaluation of Single-Shot Object Detection Models for Identifying Fanning Behavior in Honeybees at the Hive Entrance. Agriculture, 15(15), 1609. https://doi.org/10.3390/agriculture15151609