Pose (computer vision)

As a pose or spatial location of the combination of position and orientation of an object is referred to in the technical context.

Containment

According to DIN EN ISO 8373 ( industrial robots dictionary ) the pose is the combination of position and orientation in three-dimensional space. The position of a point mass in relation to a Cartesian coordinate system, therefore, is defined by the distances along the coordinate directions x, y, z you tense, then defines the orientation of this coordinate cross by the angular offset of its coordinate axes in this mass point a second Cartesian coordinate system on with respect to the corresponding axes of the base coordinate system. There are thus three additional angle necessary to describe the location of the new coordinate system based on the base coordinate system.

Determination of Pose

From the known positions of markers in space and in image, the pose of a camera can be determined. Conversely, it can be determined from markers attached to a robot, for example, the position of the end effector by means of a camera. This method is also used in the robot calibration used.

One way to specify the angle between the coordinate systems is by means of roll- pitch-yaw angle (also known as Roll- Pitch - Yaw ). In addition, there are several other conventions eg the Cardan and Euler angle or "rotary axis & angle".