Our master student Jakob Mischek just finished his work on our tracking system which just got way better. Check out the video and his thesis (in German). The new system was made possible by an improved upstream process, the detection and decoding of the bee markers got better thanks to work done by Leon Sixt. See this post for more information!
Our team member Leon Sixt has developed a new image processing component for the decoding of bee markers. The method is based on convolutional neural networks, the current state of the art in computer vision. ConvNets are awesome, however, they need large amounts of labeled data. In our case, this would have meant to click not only the image location of a tag but also the bit configuration for many thousand tag instances. Leons new solution “RenderGAN” (paper in prep) was to train a special network that can learn to reproduce realistic tag images. He then trained a decoder network using only generated tag images – no human labeling necessary!
Fernando gave a talk on our BeesBook project at the 1st Biotech Convention in Hamburg!
The BeesBook team just published a new methods paper in Frontiers in Ecology and Evolution : “Automatic methods for long-term tracking and the detection and decoding of communication dances in honeybees”. Check it out!
Raúl Rojas frequently publishes articles on AI and robotics or science in general in Telepolis, a popular German online magazine. This time, he writes about the biology of the honeybee waggle dance! The article is a good start to understand why the bee dance is so impressive and unique in the animal world. Of course, BeesBook is mentioned as an example of current research.
We have successfully applied to The North-German Supercomputing Alliance (HLRN) for computing and storage resources. The HLRN grants more than half a million computing points (NPL) worth over a 100.000 €! We are very happy and look forward to using the Cray XC30 throughout the next 12 months! Thank you HLRN and Wolfgang Baumann for valuable advice!
We changed the design of the binary tags to a circular code. Look below!
Project “Beesbook” has been selected as Project of the Month by our colleagues at Hasso-Plattner-Institute in Potsdam. We have been granted access to high-end computing machines on which we will run computer vision algorithms that detect and decode special tags that are carried by all bees in the hive. Learn more