In this series' previous two blog posts, we provided an Introduction to 360-Degree Videos and Imaging and explored Existing Open Source for 360-Degree Projection. The existing open-source solutions did an excellent job of extracting images from the equirectangular format; however, each took a fair amount of time. One implementation could extract about 1 to 2 frames per second (FPS), and the other was close to 12 FPS. People debate about the best frame rate, which depends on the application to some degree. Your Eyes vs. Frame Rates: What You Can (and Can’t) See describes some key frame rates and some myths. Around 10 FPS, individual frames blend, and apparent motion begins. Movies often capture 24 FPS. Modern monitors typically refresh at 30 or 60 FPS. Thus, having the ability to extract faster than 30 or 60 FPS could be beneficial.
The third blog in the series, Execution Framework and Serial Code Optimizations, reports on new, open-source development, which creates a framework for consistently testing various algorithm implementations. The framework code includes the ability to time various parts of the code to calculate how many FPS each algorithm implementation produces.
The remainder of the blog describes two tools, Intel® VTune and Intel® Advisor and uses them to find code hotspots to focus optimization efforts on. Even though all implementations in this blog use serial programming techniques, the final implementation achieved 170 FPS versus the initial one that produced 1 FPS.
Next week's blog on this topic will explore parallel programming methods to see if the frame rate can be improved further. If you are interested in being notified when that is posted, subscribe to get the latest updates from the team.
We would like to hear from you! Let us know in the comments or discuss – what frame rate would be required for your use cases?
About the Intel Health and Life Sciences
Reach out to Intel's Health and Life Sciences team at health.lifesciences@intel.com or learn more about what we do at https://www.intel.com/health.
About the Authors
Doug Bogia received his Ph.D. in computer science from the University of Illinois, Urbana-Champaign, and works at Intel Corporation. He enjoys photography, woodworking, programming, and optimizing solutions to run as fast as possible on a given piece of hardware. Connect with him on LinkedIn https://www.linkedin.com/in/doug-bogia-4653696/ by mentioning this blog.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.