caa a22 4500 469036257 CHVBK 20180323132756.0 cr unu---uuuuu 170328e19920401xx s 000 0 eng 10.1007/BF00126395 doi (NATIONALLICENCE)springer-10.1007/BF00126395 Gennery Donald Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Drive, 91109, Pasadena, CA aut Visual tracking of known three-dimensional objects [Elektronische Daten] [Donald Gennery] A method is described of visually tracking a known three-dimensional object as it moves with six degrees of freedom. The method uses the predicted position of known features on the object to find the features in images from one or more cameras, measures the position of the features in the images, and uses these measurements to update the estimates of position, orientation, linear velocity, and angular velocity of the object model. The features usually used are brightness edges that correspond to markings or the edges of solid objects, although point features can be used. The solution for object position and orientation is a weighted least-squares adjustment that includes filtering over time, which reduces the effects of errors, allows extrapolation over times of missing data, and allows the use of stereo information from multiple-camera images that are not coincident in time. The filtering action is derived so as to be optimum if the acceleration is random. (Alternatively, random torque can be assumed for rotation.) The filter is equivalent to a Kalman filter, but for efficiency it is formulated differently in order to take advantage of the dimensionality of the observations and the state vector which occur in this problem. The method can track accurately with arbitrarily large angular velocities, as long as the angular acceleration (or torque) is small. Results are presented showing the successful tracking of partially obscured objects with clutter. Kluwer Academic Publishers, 1992 International Journal of Computer Vision Kluwer Academic Publishers 7/3(1992-04-01), 243-270 0920-5691 7:3<243 1992 7 11263 https://doi.org/10.1007/BF00126395 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00126395 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Gennery Donald Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Drive, 91109, Pasadena, CA aut NATIONALLICENCE 773 0- International Journal of Computer Vision Kluwer Academic Publishers 7/3(1992-04-01), 243-270 0920-5691 7:3<243 1992 7 11263 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer