Deploying computer vision-based solutions in very remote locations (such as those often found in mining and oil drilling) introduces unique challenges. For example, it is typically impractical to test solutions in the real operating environment—or to replicate the environment to enable testing during development. Further complicating matters, these remote locations typically lack network connectivity, making it impossible to monitor deployed systems. In this talk, we present specific practical techniques for overcoming these challenges. We cover 3D modelling, the use of GANs for data generation, testing set-ups and specialized software techniques. We will also discuss methods for accelerating software adaptation to resolve issues when systems are deployed.
Developing Edge Computer Vision Solutions for Applications with Extreme Limitations on Real-World Testing
Session Speakers
-
Alexander Belugin
Computer Vision Product Manager, NEDRA
For the last three years, Alexander Belugin has focused on computer vision products for the mining, metals and oil and gas industries, including industrial safety and monitoring of mining vehicles. In previous roles, he worked in an education start-up and spent 10 years in project and product management in business-to-business applications. At Yandex, the #4 search engine in the world, Alexander brought machine learning technology to the retail, oil and gas, and metals industries, and won a 2018 Best AI Project in Manufacturing Award. Alexander graduated from Bauman University in Moscow.
