active vision

Terms from Artificial Intelligence: humans at the heart of algorithms

The glossary is being gradually proof checked, but currently has many typos and misspellings.

Active vision is when the camera or camera platform changes its orientation or position in order to better recogonise or interpret an object or scene. For example, you might look at an object from several angles, or even peek around the corner of a building. In some cases a similar effect can be achieved by manipulating the object itself if it is held in a robotic hand, or is on a moving platform.

Used in Chap. 12: page 161; Chap. 15: pages 232, 234, 235