Information processing apparatus and device information derivation method

A device information derivation method comprising:

• acquiring an image captured by imaging a device that includes a plurality of markers;
• extracting N marker image coordinates in the captured image, N being an integer equal to or greater than three;
• and
• deriving position information and posture information of the device from the extracted N marker image coordinates and three-dimensional coordinates of N markers in a three-dimensional model of the device;
• the extracting N marker image coordinates including extracting, where selected N+A marker image coordinates have a predetermined positional relation, N marker image coordinates from among the N+A marker image coordinates, A being an integer equal to or greater than one,
• wherein the predetermined positional relation is such that a first line segment interconnecting a first marker image coordinate and a second marker image coordinate and a second line segment interconnecting the second marker image coordinate and a third marker image coordinate define a first obtuse angle therebetween, the second line segment and a third line segment interconnecting the third marker image coordinate and a fourth marker image coordinate define a second obtuse angle therebetween, and the first obtuse angle and the second obtuse angle are interior angles of a quadrangle defined by the first line segment, the second line segment, the third line segment, and a line segment that interconnects the fourth marker image coordinate and the first marker image coordinate.

A non-transitory computer readable medium having stored thereon a program for a computer, comprising:

• by a captured image acquisition unit, acquiring an image captured by imaging a device that includes a plurality of markers;
• by an extraction unit, extracting N marker image coordinates in the captured image, N being an integer equal to or greater than three;
• and
• by a position and posture derivation unit, deriving position information and posture information of the device from the extracted N marker image coordinates and three-dimensional coordinates of N markers in a three-dimensional model of the device;
• the extracting N marker image coordinates including extracting, where selected N+A marker image coordinates have a predetermined positional relation, N marker image coordinates from among the N+A marker image coordinates, A being an integer equal to or greater than one,
• wherein the predetermined positional relation is such that a first line segment interconnecting a first marker image coordinate and a second marker image coordinate and a second line segment interconnecting the second marker image coordinate and a third marker image coordinate define a first obtuse angle therebetween, the second line segment and a third line segment interconnecting the third marker image coordinate and a fourth marker image coordinate define a second obtuse angle therebetween, and the first obtuse angle and the second obtuse angle are interior angles of a quadrangle defined by the first line segment, the second line segment, the third line segment, and a line segment that interconnects the fourth marker image coordinate and the first marker image coordinate.

An information processing apparatus comprising:

• a captured image acquisition unit configured to acquire an image captured by imaging a device that includes a plurality of markers;
• an estimation processing unit configured to estimate position information and posture information of the device on a basis of a marker image coordinate in the captured image;
• wherein
• the estimation processing unit includes
• an extraction unit configured to extract N marker image coordinates in the captured image, N being an integer equal to or greater than three, and
• a position and posture derivation unit configured to derive the position information and the posture information of the device from the extracted N marker image coordinates and three-dimensional coordinates of N markers in a three-dimensional model of the device, and
• the extraction unit extracts, where selected N+A marker image coordinates have a predetermined positional relation, N marker image coordinates from among the N+A marker image coordinates, A being an integer equal to or greater than one;
• a candidate marker information retention unit configured to retain as candidate marker information a combination of at least N three-dimensional coordinates from among three-dimensional coordinates of N+A markers that satisfy a predetermined positional relation,
• wherein the position and posture derivation unit derives the position information and the posture information of the device using the N marker image coordinates extracted by the extraction unit and three-dimensional coordinates of N markers included in the candidate marker information;
• and
• a sensor data acquisition unit configured to acquire sensor data of a posture sensor of the device,
• wherein the position and posture derivation unit estimates a provisional posture of the device using the sensor data of the posture sensor of the device, and derives the position information and the posture information of the device using candidate marker information that satisfies, when the three-dimensional model is arranged so as to have the estimated provisional posture of the device, a predetermined criterion for the N marker image coordinates.