• Hero Sanborn Map

    The Sanborn Map Company, Inc.

    Sanborn 3D HD Maps for Autonomous Driving: Santa Clara

    Santa Clara County, California, United States

Project Summary

Project
Major auto manufacturers have already released, or are soon to release self-driving cars, and for the vehicles to operate safely, purpose-built, accurate, and highly detailed map-based data sets are essential. To fill this need, Sanborn’s Advanced Technology Group used its proprietary HD Mapping technology to develop standardized, high-precision 3D base maps of the Silicon Valley area, and surrounding locations, via multi-camera aerial oblique images. Sanborn needed to create a 3D reality mesh and overlay the models with Sanborn HD maps.

Solution
Bentley’s ContextCapture application enabled Sanborn to create 3D engineering-ready reality meshes of the urban environment through Sanborn’s aerial imagery without needing to utilize 3D modelers to create a model of each building, which could have taken up to six months. The software created the 3D reality meshes swiftly and accurately, saving Sanborn investment costs and providing its automotive partners real-world context they can rely on when making design decisions. The combined, precise information was made available to Sanborn’s automotive partners in many formats and across desktop and mobile devices.


Outcome
The real-world 3D data captured in a 3D reality mesh, overlaid with Sanborn HD maps for the Santa Clara area, is being used by automotive partners to simulate their autonomous driving solutions, showcase how their cars will handle different driving scenarios, and help them make informed decisions. Sanborn estimates that without Bentley software, the creation of such detailed 3D models would have required a team of three 3D modelers working continuously for six months at a cost of USD 100,000. This cost and timeframe would have precluded the entire project.

Software
ContextCapture enabled the quick and high-quality modeling of 3D reality meshes, which form the basis for Sanborn’s HD maps. Using automation, the application eliminated the need to manually model each building and empowered Sanborn’s team to create the 3D mesh quickly and affordably. Descartes was used to for editing to clean up the mesh for complex buildings. Bentley software also provided a way to share information with partners easily and consistently.

 

Project Playbook: ContextCapture Center, Descartes

Outcome/Facts
  • ContextCapture’s automated processes allowed for detailed 3D reality meshes to be created quickly, saving six months of time and USD 100,000 in project costs.
  • High-precision road feature data about painted lines, signs, signals, and parking spaces make up the data included in the 3D models that formed the basis for Sanborn HD maps.
  • The information in the maps is being used by auto manufacturers to create realistic, autonomous driving simulations.
  • Bentley software provided a way to share information with automotive partners easily and consistently.
Quote:
  • “Self-driving cars are no longer a futuristic idea. Major auto manufacturers have already released, or are soon to release, self-driving features that give the car some ability to drive itself. Through the 3D mesh generated using Bentley ContextCapture Center software, Sanborn’s Advanced Technology group has been able to showcase the quality of the HD map data, including true-ground-absolute accuracy than those found in current conventional resources, to its partner automotive firms. The automation of the production of 3D models of city-sized projects by ContextCapture Center made the project much faster than previously possible.”

    Sharad V. Oberoi, Ph.D. Director of IT & Software Engineering Sanborn Map Company