We held our next tinyML Talks webcast. Jens Wilhelmsson from Chalmers University of Technology in Gothenburg presented The Turbinator: A Contact-less Turbidity Sensor utilizing Laser, Camera and Low Power Neural Network Processing on April 27, 2023.
This talk presents a recently patented sensor for measuring turbidity in water. The sensor works by photographing laser light scattering in the water and processes the images using a multi-input, multi-output neural network running on an efficient low-power processor (Greenwaves Technologies GAP). Thanks to the low energy consumption, the sensor can be put in a stormwater well for several years while communicating through NB-IoT. The neural network’s regression head processes the captured images by combining the distance to the surface with the photographed image, resulting in two outputs: the predicted turbidity and an error indicator to determine the similarity of the photographed image to the data it has been trained on. A significant challenge faced during the development of the sensor was obtaining training data with accurate ground truth information and conditions that closely resembled real-world scenarios, as data collected in stormwater wells is often not well-distributed and therefore also not suitable for training. Additionally, quantizing the neural network model to reduce memory usage while maintaining accuracy is a challenge.
Jens Wilhelmsson M.Sc. in Complex Adaptive Systems from Chalmers University of Technology in Gothenburg, Sweden. Since 2019, he is working at IVL Swedish Environmental Research Institute with applying machine learning within different environmental research projects. His main interests are computer vision, image processing and related sensor development.
Watch on YouTube:
Download presentation slides:
Feel free to ask your questions on this thread and keep the conversation going!