MOTION ESTIMATING DEVICE

• US 20100027847A1
• Filed: 06/22/2009
• Published: 02/04/2010
• Est. Priority Date: 06/23/2008
• Status: Active Grant

• Current Assignee: Swiss Federal Institute of Technology, Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Swiss Federal Institute of Technology, Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: Kitahama, Kenichi, Gool, Luc Van, Leibe, Bastian, Ess, Andreas, Schindler, Konrad, Funayama, Ryuji
• Granted Patent: US 8,213,684 B2
• Time in Patent Office: Days
• US Class Current: 382/107
• CPC Class Codes: G06T 7/215 Motion-based segmentation
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments

Abstract

A motion estimating device first detects mobile objects Oi and Oi′ in continuous image frames T and T′, and acquires image areas Ri and Ri′ corresponding to the mobile objects Oi and Oi′. Then, the motion estimating device removes the image areas Ri and Ri′ corresponding to the mobile objects Oi and Oi′ in the image frames T and T′, extracts corresponding point pairs Pj of feature points between the image frames T and T′ from the image areas having removed the image areas Ri and Ri′, and carries out the motion estimation of the autonomous mobile machine between the image frames T and T′ on the basis of the positional relationship of the corresponding point pairs Pj of feature points.

Claims

1. A motion estimating device that captures images of an ambient environment of an autonomous mobile machine by using an imaging device, and estimates the motion state of the autonomous mobile machine on the basis of a change in the respective captured images of the ambient environment, the motion estimating device comprising:

an image area removing section detecting mobile objects which exist in the respective captured images of the ambient environment, and removing image areas corresponding to the mobile objects;

a corresponding feature point extracting section extracting corresponding feature points from the respective captured images having removed the image areas corresponding to the mobile objects; and

a first estimating section estimating the motion state of the autonomous mobile machine on the basis of the positional relationship between the corresponding feature points of the respective captured images.

2. The motion estimating device according to claim 1, further comprising:

a determining section determining whether or not the number of corresponding feature points is larger than a predetermined value,

wherein, when the determining section determines that the number of corresponding feature points is larger than the predetermined value, the first estimating section estimates the motion state of the autonomous mobile machine on the basis of the positional relationship between the corresponding feature points of the respective captured images.

3. The motion estimating device according to claim 2, further comprising:

a second estimating section estimating the motion state of the autonomous mobile machine on the basis of the previous positions of the autonomous mobile machine when the determining section determines that the number of corresponding feature points is not larger than the predetermined value.

4. The motion estimating device according to claim 2, further comprising:

a position detecting section acquiring the position of the mobile object with respect to the imaging device;

a speed detecting section acquiring the speed of the mobile object;

a temporary estimating section estimating the temporary motion state of the autonomous mobile machine on the basis of the previous positions of the autonomous mobile machine when the determining section determines that the number of corresponding feature points is not larger than the predetermined value; and

a second estimating section estimating the motion state of the autonomous mobile machine on the basis of the position of the mobile object with respect to the imaging device, the speed of the mobile object, and the temporary motion state of the autonomous mobile machine.