Pose (computer vision)

From Wikipedia, the free encyclopedia

The introduction to this article provides insufficient context for those unfamiliar with the subject matter.
Please help improve the introduction to meet Wikipedia's layout standards. You can discuss the issue on the talk page.

In computer vision and in robotics, pose refers to the 3D position and orientation of a specific object relative to some coordinate frame, depicted in an image or set of images. It can also be applied to the orientation of a living being or parts of a living being, e.g., head or hands.

The pose can be described by means of a rotation transformation which brings the object from a reference pose to the observed pose. This rotation transformation can be represented in different ways, e.g., as a rotation matrix or a quaternion.

In some applications, pose may refer to the complete transformation, also including translation, of an object from a reference pose to its observed pose. In this case a transformation on homogeneous coordinates can be used.

If a vision based system should be able to manipulate the object, e.g., pick it up, pose estimation is a necessary task to be solved by the system. This can be done in different ways depending on the image sensor configuration, and choice of methodology.