I’m working on a computer vision project where I need to estimate the real size of an object from an image. To achieve this, I understand that knowing the working distance (the distance between the camera and the object) is crucial. However, I’m struggling with how to accurately determine this working distance.

I have tried reading about various methods, such as using triangle similarity, intrinsic camera parameters, and even using stereo vision or depth cameras. However, I’m particularly interested in a method that uses the camera’s intrinsic parameters for a single camera setup.
I have the following information:
FOV dimensions
Sensor size
Focal length
Pixel size
Image size (in pixels)
Object size (in pixels)
I’m expecting to be able to calculate the working distance accurately with the given information and then use this distance to estimate the real size of the object in the image.