IP Library Granted Patent US 12,461,535
Granted Patent B2
US 12,461,535 · App. 17/349,178 · Granted Nov 4, 2025

Positioning apparatus capable of measuring position of moving body using image capturing apparatus

Inventor: Takumi Kojima (Osaka, JP)
Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
G05D1/0274G06T7/74G06V10/44G06V10/457G06V10/462G06V20/56G06V20/588G06V40/10G06T2207/30196G06T2207/30204G06T2207/30252
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,461,535
App. No.
17/349,178
Granted
Nov 4, 2025
Kind
B2
Abstract

A first calculator calculates relative position and attitude of a vehicle based on images captured by an image capturing apparatus on the vehicle. A second calculator extracts one marker from a captured image, calculates absolute position and attitude of the vehicle based on a position and an attitude of the one extracted marker, and calculates an angle of a direction of the vehicle 1 with respect to a normal line to a plane of the one marker 4 based on a position and an attitude of the vehicle 1 in a marker coordinate system. A corrector generates a corrected position and attitude, not using the absolute position and attitude calculated based on the marker for which the angle is not larger than a first threshold, but using the absolute position and attitude calculated based on the marker for which the angle is larger than the first threshold.

Claims (67)

1 . A moving body comprising:

a camera that is mounted on the moving body and captures a plurality of images;

a storage apparatus; and

a circuit,

wherein the storage apparatus stores information on identifiers, positions, and attitudes of a plurality of markers disposed at predetermined positions and visually distinguishable from each other, and information on a map containing a passageway for the moving body,

wherein the circuit performs:

calculating a first position and a first attitude of the moving body indicating a relative position and a relative attitude of the moving body with respect to a reference position and a reference attitude, based on the plurality of images captured by the camera, using Simultaneous Localization and Mapping (SLAM);

extracting one of the plurality of markers from an image captured by the camera, calculating a second position and a second attitude of the moving body indicating a position and an attitude of the moving body in the map, based on a position and an attitude of the one extracted marker, and calculating an angle of a direction of the camera with respect to a normal line to a plane of the one marker, based on a position and an attitude of the moving body in a marker coordinate system with an origin at the one marker; and

correcting the first position and the first attitude based on the second position and the second attitude to generate a third position and a third attitude of the moving body,

wherein the circuit further determines, based on the calculated angle, whether or not to correct the first position and the first attitude based on the second position and the second attitude, such that:

when the calculated angle is not larger than a first threshold, the circuit does not correct the first position and the first attitude based on the second position and the second attitude, and generates the first position and the first attitude as the third position and the third attitude; and

when the calculated angle is larger than a first threshold, the circuit corrects the first position and the first attitude based on the second position and the second attitude to generate the third position and the third attitude, and

wherein the circuit further performs recording a trajectory of the moving body.

2 . The moving body of claim 1 ,

wherein the circuit further counts a number of images from which a marker having a same identifier is extracted, among a plurality of images consecutively captured by the camera, and

wherein, when the marker having the same identifier does not appear over the number of images equal to a second threshold, the circuit does not correct the first position and the first attitude based on the second position and the second attitude, and generates the first position and the first attitude as the third position and the third attitude, and when the marker having the same identifier appears over the number of images equal to or more than the second threshold, the circuit corrects the first position and the first attitude based on the second position and the second attitude to generate the third position and the third attitude.

3 . The moving body of claim 1 ,

wherein the circuit further calculates a position and an attitude of the moving body in each of a plurality of marker coordinate systems with origins at a plurality of markers having a same identifier and extracted from a plurality of images consecutively captured by the camera, and

wherein, when coordinates of the moving body in the marker coordinate systems do not have a same sign over a number of images equal to a third threshold, the circuit does not correct the first position and the first attitude based on the second position and the second attitude, and generates the first position and the first attitude as the third position and the third attitude, when coordinates of the moving body in the marker coordinate systems have a same sign over a number of images equal to or more than the third threshold, the circuit corrects the first position and the first attitude based on the second position and the second attitude to generate the third position and the third attitude.

4 . The moving body of claim 1 ,

wherein the circuit further calculates a size of the marker in the image captured by the camera, and

wherein, when the marker has the size equal to or smaller than a fourth threshold, the circuit does not correct the first position and the first attitude based on the second position and the second attitude, and generates the first position and the first attitude as the third position and the third attitude, when the marker has the size larger than the fourth threshold, the circuit corrects the first position and the first attitude based on the second position and the second attitude to generate the third position and the third attitude.

5 . The moving body of claim 1 ,

wherein the circuit further calculates a distance from the moving body to the marker based on the image captured by the camera, and

wherein, when the distance from the moving body to the marker is equal to or more than a fifth threshold, the circuit does not correct the first position and the first attitude based on the second position and the second attitude, and generates the first position and the first attitude as the third position and the third attitude, when the distance from the moving body to the marker is less than the fifth threshold, the circuit corrects the first position and the first attitude based on the second position and the second attitude to generate the third position and the third attitude.

6 . The moving body of claim 1 ,

wherein the circuit further obtains sensor data generated by one or more sensors mounted on the moving body, and combines data of the third position and the third attitude, with the sensor data.

7 . The moving body of claim 6 ,

wherein the circuit obtains sensor data including at least one of an acceleration and an angular velocity of the moving body.

8 . The moving body of claim 6 ,

wherein the circuit obtains sensor data including a weight of cargo carried by the moving body.

9 . The moving body of claim 6 ,

wherein the circuit further recognizes a predetermined target object from an image captured by the camera, and

wherein the circuit combines the data of the third position and the third attitude, with information on the recognized target object.

10 . The moving body of claim 9 ,

wherein the circuit recognizes a person.

11 . The moving body of claim 9 ,

wherein the circuit recognizes specific cargo learned in advance.

12 . The moving body of claim 1 ,

wherein the circuit generates the third position and the third attitude, based on the first position and the first attitude, and based on the second position and the second attitude calculated from the image identical to the image from which the first position and the first attitude are calculated.

13 . The moving body of claim 1 ,

wherein the moving body is a vehicle.

14 . The moving body of claim 1 ,

wherein the circuit further performs determining whether or not the one marker is reliable, and

the circuit determines that that the one marker is not reliable when the calculated angle is not larger than a first threshold.

15 . A moving body monitoring system comprising

a moving body;

a camera that captures a plurality of images;

a storage apparatus; and

a server apparatus comprising a circuit,

wherein the storage apparatus stores information on identifiers, positions, and attitudes of a plurality of markers disposed at predetermined positions and visually distinguishable from each other, and information on a map containing a passageway for the moving body,

wherein the circuit performs:

calculating a first position and a first attitude of the moving body indicating a relative position and a relative attitude of the moving body with respect to a reference position and a reference attitude, based on the plurality of images captured by the camera, using Simultaneous Localization and Mapping (SLAM);

extracting one of the plurality of markers from an image captured by the camera, calculating a second position and a second attitude of the moving body indicating a position and an attitude of the moving body in the map, based on a position and an attitude of the one extracted marker, and calculating an angle of a direction of the camera with respect to a normal line to a plane of the one marker, based on a position and an attitude of the moving body in a marker coordinate system with an origin at the one marker; and

correcting the first position and the first attitude based on the second position and the second attitude to generate a third position and a third attitude of the moving body,

wherein the circuit further determines, based on the calculated angle, whether or not to correct the first position and the first attitude based on the second position and the second attitude, such that:

when the calculated angle is not larger than a first threshold, the circuit does not correct the first position and the first attitude based on the second position and the second attitude, and generates the first position and the first attitude as the third position and the third attitude; and

when the calculated angle is larger than a first threshold, the circuit corrects the first position and the first attitude based on the second position and the second attitude to generate the third position and the third attitude, and

wherein the circuit further performs recording a trajectory of the moving body.

16 . A computer-implemented method for automatically generating a trajectory of a moving body, the method comprising:

receiving information on identifiers, positions, and attitudes of a plurality of markers disposed at predetermined positions and visually distinguishable from each other, and information on a map containing a passageway for the moving body,

calculating a first position and a first attitude of the moving body indicating a relative position and a relative attitude of the moving body with respect to a reference position and a reference attitude, based on the plurality of images captured by a camera, using Simultaneous Localization and Mapping (SLAM);

extracting one of the plurality of markers from an image captured by the camera, calculating a second position and a second attitude of the moving body indicating a position and an attitude of the moving body in the map, based on a position and an attitude of the one extracted marker, and calculating an angle of a direction of the camera with respect to a normal line to a plane of the one marker, based on a position and an attitude of the moving body in a marker coordinate system with an origin at the one marker;

correcting the first position and the first attitude based on the second position and the second attitude to generate a third position and a third attitude of the moving body,

wherein the method further comprises determining, based on the calculated angle, whether or not to correct the first position and the first attitude based on the second position and the second attitude, such that:

when the calculated angle is not larger than a first threshold, the first position and the first attitude are not corrected based on the second position and the second attitude, and the first position and the first attitude are generated as the third position and the third attitude; and

when the calculated angle is larger than a first threshold, the first position and the first attitude are corrected based on the second position and the second attitude to generate the third position and the third attitude, and; wherein the method further comprises recording a trajectory of the moving body.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 1, 2021
From: KOJIMA, TAKUMI
To: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
Reel/Frame 057986/0464 →
Priority Claims (1)
JP 2018-247829 · Dec 28, 2018 · national
Continuity (2)
Continuation PCTJP2019046185 · Nov 26, 2019
Related Publication 20210312661A1 · Oct 7, 2021
References Cited (30)
US 8196835B2 · Emanuel · 2012 [cited by examiner]
US 10268924B2 · Gu · 2019 [cited by examiner]
US 20060184013A1 · Emanuel · 2006 [cited by examiner]
US 20150213617A1 · Kim et al. · 2015 [cited by applicant]
US 20160364912A1 · Cho et al. · 2016 [cited by applicant]
US 20190039473A1 · Takehara et al. · 2019 [cited by applicant]
US 20190072975A1 · Choi · 2019 [cited by applicant]
EP 1870856 · 2007 [cited by applicant]
EP 3308911 · 2018 [cited by applicant]
JP 2003281676 · 2003 [cited by applicant]
JP 2011219229 · 2011 [cited by applicant]
JP 201248643 · 2012 [cited by applicant]
JP 2013235351 · 2013 [cited by applicant]
JP 2017139941 · 2017 [cited by applicant]
JP 3308911 · 2018 [cited by applicant]
WO 2018179960 · 2018 [cited by applicant]
Herman, Edwin, and Gilbert Strang. “Calculus Volume 3.” (2016). pp 177-178. https://openstax.org/details/books/calculus-volumr-3/. (Year: 2016). [cited by examiner]
Glibin, E. S., et al. “Method of Mobile Robot Indoor Navigation by Artificial Landmarks with Use of Computer Vision.” Journal of Physics: Conference Series, vol. 1015, No. 3, May 2018, p. 032171. Institute of Physics, h… [cited by examiner]
Khude, P. S., and S. S. Pawar. “Object Detection, Tracking and Counting Using Enhanced BMA on Static Background Videos.” 2013 IEEE International Conference on Computational Intelligence and Computing Research, 2013, pp.… [cited by examiner]
Liu, Yanling, and Zhenhua Liu. “An Optimized Method for Dynamic Measurement of Truck Loading Capacity.” 2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE), IEEE, 2018, pp. 120-124. … [cited by examiner]
Charalampous, Konstantinos, et al. “Robot Navigation in Large-Scale Social Maps: An Action Recognition Approach.” Expert Systems with Applications, vol. 66, Dec. 2016, pp. 261-273. DOI.org (Crossref), https://doi.org/10… [cited by examiner]
Frintrop, Simone, and Patric Jensfelt. “Attentional landmarks and active gaze control for visual SLAM.” IEEE Transactions on Robotics 24.5 (2008): 1054-1065. (Year: 2008). [cited by examiner]
Lamberti, Fabrizio, et al. “Mixed marker-based/marker-less visual odometry system for mobile robots.” International Journal of Advanced Robotic Systems 10.5 (2013): 260. (Year: 2013). [cited by examiner]
Herman, Edwin, and Gilbert Strang. “Calculus Volume 3.” (2016). pp 177-178. https://openstax.org/details/books/calculus-volume-3/. (Year: 2016). [cited by examiner]
Neunert, Michael, Michael Bloesch, and Jonas Buchli. “An open source, fiducial based, visual-inertial motion capture system.” 2016 19th International Conference on Information Fusion (FUSION). IEEE, 2016. (Year: 2016). [cited by examiner]
International Search Report issued Feb. 18, 2020 in International (PCT) Application No. PCT/JP2019/046185. [cited by applicant]
R. Mur-Artal et al., “ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras”, IEEE Transactions on Robotics, vol. 33, Issue: 5, Oct. 2016. [cited by applicant]
English Translation of International Preliminary Report on Patentability issued Jul. 1, 2021 International (PCT) Application No. PCT/JP2019/046185. [cited by applicant]
Partial Supplementary European Search Report issued Jan. 27, 2022 in corresponding International (PCT) Patent Application No. 19903677.3. [cited by applicant]
Extended European Search Report issued Apr. 29, 2022 in corresponding European Patent Application No. 19903677.3. [cited by applicant]