Method and system for scanning an object using an rgb-d sensor

Patent metadata

Field	Value
Publication number	US-2017287162-A1
Application number	US-201415506991-A
Country	US
Kind code	A1
Filing date	Aug 29, 2014
Priority date	Aug 29, 2014
Publication date	Oct 5, 2017
Grant date	—

Abstract

A method and system for scanning an object using an RGB-D sensor, the method includes: a plurality of elementary scans of the object using an RGB-D sensor and visual odometry, each elementary scan delivering a plurality of key frames associated with a pose of the sensor with respect to the object, and each elementary scan being associated with a position of the object; for each elementary scan, elaborating a three-dimensional model of the object using the plurality of key frames and poses of the scan; merging each three-dimensional model into a merged three-dimensional model of the object.

First claim

1 - 13 . (canceled)

14 : A method for scanning an object comprising:
a plurality of elementary scans of the object using an RGB-D sensor and visual odometry, each elementary scan delivering a plurality of key frames associated with a pose of the sensor with respect to the object, and each elementary scan being associated with a position of the object, the position of the object being different between two different elementary scans; for each elementary scan, elaborating a three-dimensional model of the object using the plurality of key frames and poses of the scan; merging each three-dimensional model into a merged three-dimensional model of the object.

15 : The method according to claim 14 , further comprising for each elementary scan a rotation of the object or a rotation of the sensor around the object, the object being in the position associated with the elementary scan.

16 : The method according to claim 15 , wherein loop closure is detected after a revolution of the object or a revolution of the sensor around the object.

17 : The method according to claim 16 , wherein a pose graph optimization is carried out on the poses of each elementary scan after detecting loop closure.

18 : The method according to claim 14 , wherein the elaborating the three-dimensional model for each elementary scan is made using a variational technique using colored signed distance fields and an approximate L 1 minimization.

19 : The method according to claim 14 , wherein the elaborating the merged three-dimensional model of the object comprises a determination of the transformations that transforms each three-dimensional model into an initial three-dimensional model, the determination of the transformations comprising an alignment of each three-dimensional model into the initial three-dimensional model using an approximate L 1 norm.

20 : The method according to claim 14 , further comprising using the marching cube algorithm on the merged three-dimensional model of the object to obtain a three-dimensional mesh of the object.

21 : The method according to claim 14 , wherein positions of the object during at least two elementary scans are different and display different portions of the object to the sensor.

22 : The method according to claim 14 , further comprising a segmentation of each key frame to separate the object from the background on the key frame.

23 : A system for scanning an object, comprising:
an RGB-D sensor configured to be directed towards the object; means for scanning the object in a position using the RGB-D sensor and visual odometry, delivering a plurality of key frames associated with a pose of the sensor with respect to the object; means for elaborating a three-dimensional model of the object using a plurality of key frames and poses of a of a scan of the object; means for merging a plurality of three-dimensional models into a merged three-dimensional model of the object.

24 : The system according to claim 23 , further comprising means for rotating the object or rotating the sensor around the object.

25 : The system according to claim 24 , further comprising means for detecting loop closure after a revolution of the object or a revolution of the sensor around the object.

26 : The system according to claim 25 , further comprising means for carrying out a pose-graph optimization on the poses of each elementary scan after detecting loop closure.

Assignees

• Toyota Motor Europe
• Univ Muenchen Tech

Inventors

• Wasik Zbigniew
• Kehl Wadim
• Navab Nassir

Classifications

• G06T2200/04

  involving 3D image data · CPC title

• G06T7/73 Primary

  using feature-based methods · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06T7/579

  from motion · CPC title

• G06T2207/20072

  Graph-based image processing · CPC title