How to get the spatial information/relation between detected objects in the image?

[BojanAndonovski71]

Hi

I have images from the construction field and would like to detect objects such as: workers, vehicles, blocks, scaffolding, tools. A part of that would like to get spatial information/relation of the detected objects in the image. So, for example if have detected two objects in the construction field image let say worker and vehicle. So I would like to know how far are they from each other and also how far are they from the sensor. So to have some spacial information of the detected objects related to the environment and to each other

Any help , or information how would be possible to do that?

Thanks