Talking Autonomy: Explaining KineticFlow - Ghost's Visual Perception Neural Network скачать в хорошем качестве

Talking Autonomy: Explaining KineticFlow - Ghost's Visual Perception Neural Network

Ghost Autonomy co-founder and CTO Volkmar Uhlig introduces KineticFlow, Ghost's core vision-based AI algorithm for autonomous vehicle perception. Traditional approaches to computer vision have either leveraged a series of mono cameras at multiple fields of view, or have used two stereo cameras to detect disparity like the human eyes. Mono camera approaches utilize image recognition and object classification to aid in inference of distance and motion, but suffer from challenges associated with mis-recognized objects, poor low-light performance, and reliability. Stereo approaches can measure distance more directly through disparity, but face challenges with long-distance perception. KineticFlow represents a new approach that fuses both mono and stereo algorithms into a single neural network, providing the distance (depth), velocity, and direction of motion of an object, on a per-pixel basis. In this video, Volkmar covers the key functions and benefits of KineticFlow and explains why it was designed to serve as the foundational vision algorithm for the Ghost Autonomy Engine. 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 Autonomy Engine on the web: https://www.ghostautonomy.com/platform KineticFlow vision neural network: https://www.ghostautonomy.com/kinetic... Follow Ghost on Twitter:   / ghostautonomy   Follow Ghost on LinkedIn:   / ghostautonomy   #selfdriving #AI #autonomous #GhostAutonomy #computervision