1

I'm using the object detection algorithm YOLOv3 in combination with a Raspberry Pi 3B+ equipped with an IP camera in order to recognize objects in real time. In case of the detection of desired items some kind of note/message is supposed to be displayed within my Smart Home Platform (openHAB) at the same time.

However, I'm currently struggling with the transfer of detected objects to other places. My code so far enables me just to see a livestream on my desktop from the Raspberry Pi with the from YOLO detected objects marked in it.

Does anyone have experience in the extraction of detected objects from a livestream and subsequent use of the detected objects in other applications?

So far I tried to save the detected objects to a JSON file which worked for single images but I don't know how to code this for the livestream. Is there another option to directly forward the detections in some way?

Simon Kieweg
  • 11
  • 1
  • The code to update your openhab using json your be on the rpi, not the desktop. However, as this is a slow synch operation (posting the json to the openhab) you will need to do it in another thread/process asynchronously, probably using a queue. Another, perhaps easier option, would be to save things into a NAS or direcotry on the openhab using smb and have a process on the openhab look in this directory and update your system' – Moshel Aug 22 '19 at 09:50

0 Answers0