I need to capture camera images from usb and use OPENCV APIs to process raw camera images and sink them to HDMI Display .
I could not find any OpenCV libraries in Edge AI SDK can you please help ?
This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
I need to capture camera images from usb and use OPENCV APIs to process raw camera images and sink them to HDMI Display .
I could not find any OpenCV libraries in Edge AI SDK can you please help ?
Hi Saurabh,
We have a Python, OpenCV based robotics demo that uses the SK-TDA4VM: https://github.com/TexasInstruments/edgeai-robotics-demos
Are you trying to use OpenCV with Python?
Regards,
Takuma
Hi Saurabh,
OpenCV is used within our Edge AI demo's post processing and there is a C++ example of that: https://git.ti.com/cgit/edgeai/edge_ai_apps/tree/apps_cpp/common/src/post_process_image_object_detect.cpp
OpenCV libraries should be available in the Edge AI SDK filesystem by default. Under /usr/lib could you run:
ls | grep -ir opencv
As a warning OpenCV currently runs solely on the A72 so APIs that require hardware accelerators like ISP and GPU may not run.
Edge AI SDK provides a few GStreamer plugins that offloads work to the hardware accelerator, and I would recommend looking at these: https://github.com/TexasInstruments/edgeai-gst-plugins/wiki/tiovxisp
Regards,
Takuma