There are deep cnn models for doing joint recognition detection at around 60fps (at 300x300) at reasonable accuracy 75%.
This is arguably the most expensIve part of the pipeline, but we sHould have atleast two more architectures out by NVDA/AMD before any product comes out.
This is arguably the most expensIve part of the pipeline, but we sHould have atleast two more architectures out by NVDA/AMD before any product comes out.