Talking Autonomy: Map-less Driving - Understanding Lanes and Scenes

Ghost Autonomy model engineer Arun Narayanaswamy explains how Ghost uses mono vision to understand lanes and the overall driving scene with a dedicated lane understanding neural network.

Lanes are mission-critical for driving - not just to understand where to position the car in real-time, but to understand if that object perceived 100s of meters down the road is in our lane, and how/if to react to it? But understanding lanes with vision is hard - there are many situations where lane markers are occluded by other cars, poorly painted, or just plain missing...and lane markers look different in every country, at different times of day, in different weather conditions, etc, etc. Arun walks through how Ghost trains its lane marker neural network to provide an accurate understanding of the lanes and overall scene in all these conditions.

Thank you for watching Talking Autonomy, a series of short tech talks that explain the key elements of our work at Ghost. Subscribe and stay tuned for new episodes as we continue exploring the core technologies behind the Ghost Autonomy Engine and sharing insights from the founders, engineers, designers, mathematicians, and even the policy-makers who are responsible for bringing Ghost’s self-driving technology to the roads.

Connect with Ghost and learn more:
Ghost's Talking Autonomy video series: https://www.ghostautonomy.com/video-s...
Ghost Autonomy Engine on the web: https://www.ghostautonomy.com/platform
Follow Ghost on Twitter:   / ghostautonomy  
Follow Ghost on LinkedIn:   / ghostautonomy  

#selfdriving #AI #autonomous #GhostAutonomy #computervision