Hello,
I need to get fish-eye video with real-time face blur filter(grayscale, 10FPS), that will be synchroninized with sensor signal (heart rate and pressure channel via BLE) on Raspberry Pi 4 with OpenCV/Python.
I was thinking about OAK 1 to perform the face blur on the MyriadX and stream the modified video to the RPi. Do you think it is a good idea?
The issues are stream latency, fish eye lens.. There must be some good similar project somewhere..
I will be thankful for any help.

  • erik replied to this.

    Hello MichalO,
    that could work, though you will need to create a custom CV model (tutorial here) to take frame + face bounding box to blur the face. Blurring itself is simple (tutorial), but blurring based on bounding box could be challenging. Another option would be to blur frames on the host with openCV, which would be easier (and there are tons of tutorials as well). What kind of low-latency do you require? There will be a few 100ms, since face detection (NN inference) by itself takes 100ms. Regarding the fish-eye lens, I am unsure if ArduCam provides color camera replacement (for OAK-1), but you could attach an external lens (eg this).
    Thanks, Erik

    Hello again MichalO , I have just submitted a code that achieves face blurring here.

      25 days later

      erik
      hello Erik,

      Thank you so much. Unfortunatelly, the link to github is not working (404 - Page not found).
      Could this be somehow overcome?

      Sincerely

      Michal

      • erik replied to this.