Method and System for Estimating 3D Pose of Specular Objects

• US 20100296724A1
• Filed: 07/27/2009
• Published: 11/25/2010
• Est. Priority Date: 03/27/2009
• Status: Active Grant

• Current Assignee: Mitsubishi Electric Research Laboratories, Inc. (Mitsubishi Electric Corporation)
• Original Assignee: Mitsubishi Electric Research Laboratories, Inc. (Mitsubishi Electric Corporation)
• Inventors: Chang, Ju Yong, Thorton, Jay E., Veeraraghavan, Ashok N., Raskar, Ramesh N., Agrawal, Amit Kumar
• Granted Patent: US 8,437,537 B2
• Time in Patent Office: Days
• US Class Current: 382/154
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/75 involving models
• CPC Class Codes: G06V 20/647 by matching two-dimensional images to three-dimensional objects

Abstract

A method estimates a 3D pose of a 3D specular object in an environment. In a preprocessing step, a set of pairs of 2D reference images are generated using a 3D model of the object, and a set of poses of the object, wherein each pair of reference images is associated with one of the poses. Then, a pair of 2D input images are acquired of the object. A rough 3D pose of the object is estimated by comparing features in the pair of 2D input images and the features in each pair of 2D reference images using a rough cost function. The rough estimate is optionally refined using a fine cost function.

Claims

30-1. The method of claim 1, further comprising:

estimating a reflectance of the object in the input images while estimating the pose.

32-2. The method of claim 1, further comprising:

actively illuminating the surrounding with an illumination source

32-3. The method of claim 1, where the input images are acquired using polarization to estimate specular components.

33-4. The method of claim 1, further comprising:

illuminating the scene with different colors, and performing the method independently for each color.

38. An apparatus for estimating a 3D pose of a 3D object in an environment, wherein the object has a specular surface, comprising:

a rendering engine configured to render a set of pairs of 2D reference images using a 3D model of the object, and a set of poses of the object, wherein each pair of reference images is associated with one of the poses;

a camera configure to acquire a pair of 2D input images of the object; and

means, implemented in a processor, for estimating a 3D pose of the object by comparing features in the pair of 2D input images and the features in each pair of 2D reference images using a cost function matching the features.