Hopefully this one doesn't sound absurd. I would like to know is there a way to find a dimension of an object, or nearest, finding the pixel coordinate of the recognized object (say a box..) and estimating size of a box by using Tensorflow (or openVino) etc.
I had this idea and was researching (search in Google etc), finding resource before dive deeper into it. I plan to use depth camera so finding distance between camera and object is no issue.
Do guide me.
There is a series of RealSense cameras from Intel that can give depth information.You will able to obtain the dimension and pixel coordinate of an object. Check out the following page to learn more regarding RealSense camera technology that might suitable for your application. https://www.intelrealsense.com/which-device-is-right-for-you/