Abstract

Training Semantic Segmentation for DRIVE PX

The level of accuracy needed for urban driving is different than highway driving due to the density of different objects in a given scene. Using CamVid dataset, this mini course will go through all the steps required to do semantic segmentation given the computation capabilities of DRIVE PX. You’ll learn how to:....


Speakers: Oliver Knieps, Jan Jamaszyk
Type:

DLI Instructor-Led Training 

Date: Thursday - October 18, 2018 03:30 PM - 05:30 PM
Location: Halls C4&C5
Topic: Autonomous Vehicle Technologies
Industry: Automotive / Transportation

 

The level of accuracy needed for urban driving is different than highway driving due to the density of different objects in a given scene. Using CamVid dataset, this mini course will go through all the steps required to do semantic segmentation given the computation capabilities of DRIVE PX. You’ll learn how to: convert an existing network into a fully convolutional network, explore different design choices to fit into the computation budget, and train a semantic segmentation neural network. Upon completion, you’ll be able to use create and train a fully convolutional network for semantic segmentation tasks in self-driving cars. Prerequisites: Fundamentals of Deep Learning for Computer Vision or equivalent background/experience