A pixel encodes color, not distance
Every pixel in a photo stores brightness and color, essentially what wavelength of light hit that spot on the sensor. What it does not store is how far away the surface was that reflected that light. This is not a limitation of any particular camera, it is a fundamental consequence of how cameras work: a lens projects the 3D world down onto a flat 2D sensor, and that projection collapses one whole dimension, distance along the camera's viewing axis, into a single point on the image plane. Once that projection happens, the depth information is gone unless something else recovers it.
This is why a toy car held a foot from the camera and a real car parked fifty meters away can produce nearly identical-looking images. If both happen to fill the same portion of the frame at the same apparent size, the raw pixels alone give a vision system no reliable way to tell them apart. A detector trained in the earlier courses in this track could confidently say 'car' for both, and it would be right about the category and completely uninformed about the distance, because category and distance are answered by different kinds of information.