Seattle, WA
December 10–13, 2018
Click Here for More Information & Registration
View Venue Map
Tuesday, December 11 • 10:50am - 11:25am
Real-time Vision Processing on Kubernetes: Working with Data Locality - Yisui Hu, Google

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Kubernetes as a general purpose cloud native application platform simplifies the operation of applications. Data processing is one of the common of applications that benefit from the power of Kubernetes. However attempting real-time computer vision processing on Kubernetes isn't that straightforward, as the maximum processing time for a single frame is expected to be less than 30ms to reach 30fps or no more than 60ms (15fps, start being laggy). This presentation demonstrates the actual issues, feature gaps encountered and workarounds applied running a real-time vision pipeline on Kubernetes from the presenter's hobby robotics project. The pipeline involves a few image pre-processing tasks, a ML model (SSD mobilenet) for object detection and depth estimation with a single camera. The biggest challenge is how to distribute the tasks across nodes with data locality in consideration.

avatar for Yisui Hu

Yisui Hu

Software Engineer, Google
Yisui Hu is a Software Engineer currently working on Kubernetes Engine at Google. He has over 14 years industry experience focused on software engineering across multiple areas, including operating systems, networking, embedded systems, cloud infrastructure, etc.

Tuesday December 11, 2018 10:50am - 11:25am