Reconstruction of Three-Dimensional Trajectories of Honeybees Flying in High-Density Aerial Environments
Mahadeeswara, M. Y.; Srinivasan, M. V.
Show abstract
So far, relatively few studies have investigated the flight of insects moving in experimental conditions approximating natural scenes. This is mainly because of the technical difficulties involved in detecting and tracking individual insects in three dimensions in outdoor scenarios, as well as matching views of corresponding insects in stereo images for trajectory reconstruction (the so-called Correspondence Problem). In this study, we describe the methods we have developed to track and unambiguously reconstruct the trajectories and body orientations of a large number of bees flying in close proximity in a bee cloud, using just two high-speed video cameras configured as a stereo pair in a semi-outdoor setting. Using these methods, two separate bee clouds were filmed and the data were analysed to reconstruct the three-dimensional trajectories, including the head and tail positions, of a total of 382 bees. This dataset should enable future analysis of the movement characteristics of bees flying in a dense environment, as well as uncover potential strategies for mid-air collision avoidance.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Tracking individual honeybees among wildflower clusters with computer vision-facilitated pollinator monitoring 97%
- Utilizing CNNs for classification and uncertainty quantification for 15 families of European fly pollinators 94%
- Precise automatic classification of 46 different pollen types with convolutional neural networks 94%
Similar papers in this journal
- An Assistive Computer Vision Tool to Automatically Detect Changes in Fish Behavior In Response to Ambient Odor 94%
- Computer vision and deep learning automates nocturnal rainforest ant tracking to provide insight into behavior and disease risk 93%
- WormSwin: Instance segmentation of C. elegans using vision transformer 92%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.