Deep Learning for Pollen Sac Detection and Measurement on Honeybee Monitoring Video

@INPROCEEDINGS{8961011,
  author={C. {Yang} and J. {Collins}},
  booktitle={2019 International Conference on Image and Vision Computing New Zealand (IVCNZ)}, 
  title={Deep Learning for Pollen Sac Detection and Measurement on Honeybee Monitoring Video}, 
  year={2019},
  volume={},
  number={},
  pages={1-6},
  abstract={This paper introduces a new model which applies deep learning techniques to pollen sac detection and measurement on honeybee monitoring video. The outcome of this model is a measurement of the number of pollen sacs being brought to the beehive, so that beekeepers will not need to open beehives frequently to check food storage. The pollen sacs are detected on individual bee images which are collected using a bee detection model on the entire video frame. The pollen detection model is built using a deep convolutional neural network. The architecture is Faster RCNN with VGG-16 core network. The network is trained to detect pollen sacs so the individual bee images are identified as either pollen or nonpollen bee images. This pollen sac detection model is then combined with a bee tracking model, so that each flying bee tracked on successive video frames is identified as carrying pollen or not. Finally, the number of pollen-carrying bees can be counted. The experimental results show that the measurement error of this model is 7%. The deep learning model improves the results from the conventional image processing method, which produced 33% measurement error.},
  keywords={biology computing;convolutional neural nets;learning (artificial intelligence);object detection;object tracking;video signal processing;zoology;faster RCNN;measurement error;deep learning;pollen-carrying bees;video frames;flying bee;bee tracking model;nonpollen bee images;VGG-16 core network;deep convolutional neural network;pollen detection model;bee detection model;beehive;pollen sac detection;honeybee monitoring video;bee detection;pollen measurement;deep learning},
  doi={10.1109/IVCNZ48456.2019.8961011},
  ISSN={2151-2205},
  month={Dec},}