Methods and Apparatus for Practical 3D Vision System

A method for specifying an area of interest in a 3D imaging system including a plurality of cameras that include at least first and second cameras wherein each camera has a field of view arranged along a camera distinct trajectory, the method comprising the steps of:

• presenting a part at a location within the fields of view of the cameras;
• using a laser device to sequentially and independently indicate on the part a plurality of points that define an area of interest;
• for each of the plurality of cameras, while indicating the points on the part, acquiring images of the part including the area of interest;
• using the points in multiple images for each camera to identify a field of interest in the field of view corresponding to the area of interest;
• and
• storing the field of interest in the field of view as a camera specific field of interest.

A system for training a three dimensional vision system to define camera specific fields of interest where an area of interest is indicated on a part, the system comprising:

• a plurality of cameras, each camera having a field of view and arranged along a camera distinct trajectory so that the area of interest is within the field of view of the camera, each camera for obtaining images of the part in the field of view of the camera;
• and
• a machine vision processor programmed to perform the steps of, for each camera:
• (i) receiving images;
• (ii) using at least one of the received images to identify a portion of the field of view of the camera used to generate the image that is associated with the area of interest as a field of interest;
• and
• (iii) storing the field of interest that is associated with the area of interest as a camera specific field of interest.