Semantic segmentation of 3D point clouds - First steps towards intelligent 3D Models

[Guest]

Autonomous vehicles require digital maps to navigate safely, smart cities requires knowledge of urban features to be managed appropriately, and digital twins require physical assets to be recognised before they can simulate predictive models. All those applications require a detailed representation and understanding of the spatial environment. The ability to create intelligent 3D models of the real world is a critical enabler for the reduction in cost and programme of major design activities. For instance, Highways England is one of the pioneers in developing parametric design solutions for complex national infrastructure.

Working together with the Alan Turing Institute and the University of Oxford, Sensat opened up some of our data to look at collaborating and building on the last two years of working at the cutting edge of 3D computer vision as part of our mission to teach computers to understand the real world.

Great read if you have some time and as we continue to explore creating full digital models of existing assets - advancements in AI and data segmentation will allow us to truly create replicable models of real infrastructure, cities, and more.

 

https://www.turing.ac.uk/sites/default/files/2020-06/the_alan_turing_institute_data_study_group_final_report_-_sensat_0.pdf

the_alan_turing_institute_data_study_group_final_report_(Sensat).pdf