TY - GEN
T1 - Invariance--A new framework for vision
AU - Forsyth, David
AU - Mundy, Joseph L.
AU - Zisserman, Andrew
AU - Brown, Christopher M.
PY - 1990
Y1 - 1990
N2 - It is shown that curved planar objects have shape descriptors that are unaffected by the position, orientation and intrinsic parameters of the camera. These shape descriptors can be used to index quickly and efficiently into a large model base of curved planar objects, because their value is independent of pose and unaffected by perspective. Thus, recognition can proceed independent of calculating pose. Object curves are represented using conics, attached with a fitting technique that commutes with projection. This means that the pose of an object can be determined by backprojecting known conics. The authors show examples of recognition and pose determination using real image data.
AB - It is shown that curved planar objects have shape descriptors that are unaffected by the position, orientation and intrinsic parameters of the camera. These shape descriptors can be used to index quickly and efficiently into a large model base of curved planar objects, because their value is independent of pose and unaffected by perspective. Thus, recognition can proceed independent of calculating pose. Object curves are represented using conics, attached with a fitting technique that commutes with projection. This means that the pose of an object can be determined by backprojecting known conics. The authors show examples of recognition and pose determination using real image data.
UR - http://www.scopus.com/inward/record.url?scp=0025575572&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0025575572&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0025575572
SN - 0818620579
T3 - Proc 3 Int Conf Comput Vision
SP - 598
EP - 605
BT - Proc 3 Int Conf Comput Vision
PB - Publ by IEEE
T2 - Proceedings 3rd International Conference on Computer Vision
Y2 - 4 December 1990 through 7 December 1990
ER -