gicLAB is undertaking a 2 month project for an AI in industry challenge
The Glasgow Intelligent Computing Lab (gicLAB) is undertaking the AIMDDE (AI-based Manufacturing Defect Detection at the Edge) research challenge (initially for two months but potentially extended to five), as part of the BonsAPPs EU’s Horizon 2020 project (https://bonsapps.eu/). The overall goal of the challenge is to produce AI models which can effectively detect defects in manufactured goods (e.g., rolled steel, or textiles), and deploy them in a constrained edge device (e.g., Nvidia AGX Xavier), such that their latency/performance would be viable in a real production environment. The team will leverage state-of-the-art image segmentation models, and the lab’s extensive expertise in Deep Neural Network compression and optimisation. Additionally, the challenge requires ensuring that training and deployment are encapsulated in reproducible artifacts. Dr José Cano Reyes is the project PI, and PhD student Perry Gibson is the technical lead.
This project has received funding from the European Union’s Horizon 2020 research and innovation programme within the framework of the BonsAPPs Project funded under grant agreement No 101015848