University of Minnesota
Software Engineering Center

You are here

Safely Driven: How Trimble is Applying Deep Learning and Pragmatic Practices to Help Make the Roads Safer for Everyone

Date of Presentation: 
Wednesday, January 16, 2019
Deep learning certainly has roots in the autonomous vehicle space. However, most trucking companies have a substantial investment in existing class 8 semi-trailer trucks that are not going to be replaced with self-driving trucks overnight. Trimble Transportation Mobility (TTM) is using deep learning technologies, in conjunction with other advanced analytic techniques and state of the art DevOps approaches to help ensure the safe operation of trucking fleets. While it may be premature for many trucking fleets to embrace autonomous vehicles, TTM has made it possible for those same companies to leverage deep learning as a way to reduce costs and improve safety. This talk will cover how TTM has used deep learning models along with specific DevOps techniques to filter video content taken from forward facing cameras in semi-trucks. The TTM Smart Review system has been running "in production" since October 2018 as part of the Trimble PeopleNet Fleet Manager - Video Intelligence platform. The system processes over 400 hours of video per month.