SENSORO and Graphcore partner for safer, greener towns and cities
SENSORO a provider of smart sensor and beacon technology has chosen Graphcore systems to deliver the AI compute behind its latest environmental and safety monitoring systems. Graphcore IPUs will power a range of SENSORO solutions, designed to help towns and cities become safer, greener places to live.
Smart sensors are emerging as an essential tool in the management of modern, urban environments as they transition to more sustainable forms of energy and transportation, while also dealing with the effects of climate change.
Fire, flood and fishing
SENSORO will initially use Graphcore IPU compute for:
- Smart fire protection:Â The rapid growth in the use of electric bicycles has also seen an increase in e-bike charging fires. SENSORO’s monitoring system can alert building managers to the arrival of an e-bike at their premises, allowing them to assist with safe charging procedure and facilities.
- Emergency flood prevention:Â Graphcore is working with SENSORO to develop early warning systems based on monitoring of urban flood risk areas, enabling better disaster preparedness and emergency response.
- Smart ecological governance: Illegal river fishing breaks the ecological chain and destroys the integrity of the ecosystem. SENSORO systems are able to recognise different fishing scenarios, such as electric fishing and net fishing, providing accurate information on illegal fishing activity.
Computing foundation
SENSORO founder and CEO Tony Zhao welcomed our partnership, saying, “Graphcore’s IPU system provides an efficient and easy-to-use computing platform for the urban ESG solution jointly created by both parties, and solves the computing power bottleneck that we have faced for a long time. We will be continuing to work with Graphcore, and using the IPU to deliver positive change in more aspects of people’s lives.”
YOLO
One of the main AI models used by SENSORO, running on Graphcore IPUs, is YOLO. YOLO (You Only Look Once) is a highly effective convolutional neural network for real-time object detection. Since the release of the first version in 2015, it has undergone a number of refinements to improve speed and accuracy.
SENSORO found that the IPU’s fine-grained and highly parallel compute capabilities lent themselves to the parallelisation required to get the most out of YOLO. When running inference on high resolution images (1920x1080px), SENSORO saw a 4X performance gain, compared to the GPU-based inference solution they had been using previously.
Comment on this article below or via Twitter @IoTGN