Search International and National Patent Collections

1. (WO2017039907) POINT-TO-POINT DISTANCE MEASUREMENTS IN 3D CAMERA IMAGES

Pub. No.:    WO/2017/039907    International Application No.:    PCT/US2016/044897
Publication Date: Fri Mar 10 00:59:59 CET 2017 International Filing Date: Sat Jul 30 01:59:59 CEST 2016
IPC: H04N 13/02
G06T 7/00
Applicants: INTEL CORPORATION
Inventors: SESHADRINATHAN, Kalpana
NESTARES, Oscar
MEHDIZADEH, Ali
STEIN, Max T.
WU, Yi
GRANGER, James
Title: POINT-TO-POINT DISTANCE MEASUREMENTS IN 3D CAMERA IMAGES
Abstract:
Systems and methods for determining point-to-point distances from 3D image data. In some embodiments, two measure points, for example specified by a user, represent endpoints on an object of interest within an image frame. Assuming all points lying between these endpoints also belong to the object of interest, additional 3D data associated with points that lie along a measurement line defined by the measure points may be leveraged to provide a robust distance measurement. In some embodiments, total least squares fitting is performed, for example through Robust Principal Component Analysis (RPCA) to identify linear structures within the set of the 3D coordinates on the measurement line. In some exemplary embodiments, the minimum covariance determinant (MCD) estimator of the covariance matrix of the data is computed for a highly robust estimate of multivariate location and multivariate scatter.