Open Udayaprasad opened 3 years ago
Hi Uday @Udayaprasad,
My project architecture has many cameras sending images to a few hub computers that analyze those images. The imageZMQ package is just an image transport tool. It suits my own project perfectly, but there are several questions that might help you decide if imageZMQ will scale well for you.
Here are my thoughts:
I have an overview of my Yin Yang Ranch project that uses imageZMQ in this GitHub repo: I also gave a 30 minute PyCon 2020 presentation about it. (Here is the slide deck for that if you want the outline without the talk itself).
Here are some other lessons I have learned as I scaled to larger numbers of cameras using imageZMQ. This comes from a post I made on a message board about ways to set up a network of cameras using imageZMQ. Some of it may be helpful to you; some of it is a restatement of the above ideas:
Feel free to ask follow on questions in this thread and I’ll do my best to answer them. Also, please share your learnings as you build out your own system. If you find something better than imageZMQ for scaling to 200 cameras, please comment in this thread and let me (and the other imageZMQ users) know. All of us are always iterating to newer and faster tools.
Jeff
Thank you for the detailed explanation, @jeffbass.
1) We would like to keep 15 fps for each camera (compressed to 416X416), also we are using RTSP protocol to get the camera feeds. Each camera is running its own thread. 2) PUB/SUB model will be better for us because we need to transfer each model's predictions to other models for better reusability (Attached example diagram).
I will sure keep this open and provide my findings as and when I am successful with the whole integration
Hi @jeffbass,
We are working on one of the video surveillance project, where we need to process 200+ camera feeds to multiple computer vision algorithms. This project looks great, but can you suggest the best way to scale the ZMQ setup?
Thank, Uday