Digital Assistance for Quality Assurance - Augmenting Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects

Explore a 23-minute conference talk from the 2019 ACM International Conference on Interactive Surfaces and Spaces that presents a digital assistance approach for applied metrology on near-symmetrical objects. Discover how deep learning techniques can be used to augment workspaces and improve quality assurance processes in manufacturing. Learn about a two-step approach for locating, orienting, and disambiguating objects based on their shape and small visual features. Gain insights into the challenges of measuring and documenting near-symmetrical products like LEGO bricks, and how situated visual measurement guides can support workers in this task. Examine the application and comparison of different deep learning approaches in the context of this use case, and understand the potential impact on improving accuracy and efficiency in quality control processes.