Sachin Guruswamy

Hello @FPSychotic , > The camera_info topic is being published in rational_polinomial model which is not supported by ROS1 It is supported from Jade. [Here](http://docs.ros.org/en/melodic/api/sensor_msgs/html/distortion__models_8h.html) is the link to `distortion_model`...

Thanks for sharing. will look into those. > I know that modifications, that allow equidistant and rarional_polynomial but that is a feature for opencv and image_proc, in the same way...

I think you are not understanding my message. I am not saying we are not going to support the `plumb_bob`. I said we would provide a backward compatibility to `plumb_bob`...

Yes. that would send 4K. And color.yaml intrinsic needs to be scaled accordingly. But the necessity of the camera_info depends on your task

Here is the latency information for each resolution and camera. @Erol444 if you have more details can you share ?

Yes. you can use depthai-ros. For ex: `roslaunch depthai_examples stereo_node.launch monoResolution:=400p camera_model:=OAK-D-POE` from [here](https://github.com/luxonis/depthai-ros-examples/blob/main/depthai_examples/launch/stereo_node.launch)

I will modify the example to make that an argument.

Agreed. I think thats the way to go. But conversion to float32 mostly will happen on host-side instead of on-device in this case.

Let me know if [this](https://github.com/introlab/rtabmap/issues/742#issuecomment-1059600320) helps.

Thanks. Will check on our side and get back to you.