In this episode of Process This, Shyam Jagannathan, the architect of TI's Processor SDK Linux for Edge AI, will dig deep into the software development kit and explain how the SDK enables a modular interplay of multiple open-source components such as GStreamer, OpenVx, OpenCV and Deep Learning Runtime such as TFLite, ONNX and Neo-AI DLR. This makes edge AI application development as easy as it can be with programming in Python or C++ while still taking advantage of hardware accelerators for vision processing and AI functions.
- SDK architecture overview
- The Interplay of Gstreamer and OpenVx
- gStreamer plugin designs
- How to bring in a new sensor
- Complete application development