by: AMD
The natural language processing (NLP) SmartVision application continuously detects keywords spoken by the user and showcases keyword-based dynamic switching between multiple vision tasks and/or changes the display properties.
Live audio capture from USB Microphone
Video capture from AR1335 camera sensor
Key Word Spotting (KWS) & Keyword based dynamic switching of vision tasks (Face detect / Object detect / Plate detect)
HDMI or DisplayPort out
Complete application including HW design
No, the application does not require any experience in FPGA design.
This application is free of charge from AMD.
The NLP-SmartVision application has been primarily designed and tested with onsemi’s AR1335 image sensor. You will have to update the design and application if adding another MIPI sensor.
The application should work with most USB microphones.
The NLP-SmartVision application will only work for the pre-defined 10 keywords. You can train the model with custom keywords and modify the application using the released app sources.
Certain AMD technologies may require third-party enablement or activation. Supported features may vary by operating system. Please confirm with system manufacturer for specific features. No technology or product can be completely secure.
