Subfield of
Artificial intelligence where the idea is to get a
computer to "understand" a scene. Frequent goals include:
- Detect, segment, locate and recognize certain objects in images, like (e.g.) human faces
- Tracking an object through an image sequence
- Mapping a scene to a three-dimensional model of the scene, so that (e.g.) a robot could navigate within the scene
- Estimating the three-dimensional poses of humans and their limbs
A very difficult task, but one with a small number of commercial successes.
Interestingly, [biological vision]? (cats have been extensively studied) seems to have lots of "hardware" assist, that is, special "circuitry" to find lines, etc. However, most computer vision has been done strictly with software.