Harnessing computer vision and collaboration to transform manufacturing quality assurance
Our internal Phoenix Contact project group is pioneering AI technology by using Computer Vision to analyze beekeeping hand movements, aiming to identify crucial process actions and enhance workflow efficiency.
Through video capture and collaboration with beekeepers, they are training an AI model to recognize these gestures, with the ultimate goal of applying this technology to improve quality control in assembly processes.
Learn more details about the project
Our Phoenix Contact project group is making remarkable strides in the realm of AI technology with their latest initiative centered around the recognition of beekeeping handles. Leveraging the power of Computer Vision, a prominent field within the realm of Artificial Intelligence (AI), they are delving into the intricate world of hand movement analysis.
The essence of the project lies in the ability to analyze and understand the nuances of hand gestures within the context of beekeeping. By deploying advanced Computer Vision techniques, they aim to identify and group distinct hand actions, creating clusters that provide insight into significant process actions. This, in turn, enables them to map and subsequently monitor the flow of these intricate processes, thereby enhancing efficiency and precision.
Beekeeping handles have become a fascinating testing ground for their exploration into hand recognition technology. Through capturing hand movements on video and collaborating closely with beekeepers to document process steps, they are training an AI model to discern and comprehend these subtle yet crucial gestures.
The broader goal of the project is to extend this technology to real-world applications within the production environment. Their focus area is within assembly stations, where various components are brought together to craft the final product. With the implementation of Computer Vision, they are striving to enhance quality control by verifying whether all necessary components have been integrated accurately into the end product. This innovation has the potential to revolutionize the way we ensure quality and accuracy in manufacturing processes.
While they are in the early stages of their project, the promise of this AI technology is already becoming evident. The team is actively working on integrating visual elements such as heatmaps and hand recognition examples into our project. Although challenges remain, particularly in the complex task of clustering and detection, we are motivated by the potential impact of our work.
Four questions to the team
We are curious to get to know the people behind the ideas. Who are the members of the team?
Dennis Reetz and Lennart Bömelburg
Aside from developing smart technologies for bees, what else do you do in your spare time?
Dennis: Developing smart technologies for my home.
And besides working at Phoenix Contact Electronics, I am also doing my master degree in Business Information System with the major in Data Science. So there is not a lot of spare time left but I am into hiking, bouldering and running.
Lennart: Next to my work at Phoenix Contact Electronics I am also doing my bachelor degree in applied computer science with the focus on Data Science. On some weekends of the year I travel around europe with an motorsport team, helping them on the race weekends preparing the cars.
How did you come up with this idea and what was your motivation behind it?
We talked with Iris, the project manager of the Beehyve at the Hannover Messe. We have a similar use case in our production in Bad Pyrmont where we also want to use predictive analytics for hand tracking. That’s why we thought the Beehyve project would fit perfectly to train our skills and collect some experience.
Bees are remarkable animals, but which bee fact surprised or impressed you the most?
We are very impressed about how the bees every time perfectly build their honeycombs and also how they are communicating by coding the information into a dance.
