IP Library Granted Patent US 12,642,455
Granted Patent B2
US 12,642,455 · App. 18/907,879 · Granted Jun 2, 2026

Medical camera assembly comprising range camera and thermographic camera

Inventors: Hagen Kaiser (Munich, DE); Kajetan Berlinger (Munich, DE)
Assignee: BRAINLAB SE
A61B5/1128A61B5/0035A61B5/0064A61B5/0077A61B5/015A61B5/11A61B5/113A61B5/7292G01J5/00G06T7/0012G06T7/33G06T7/70A61B2576/00G01J2005/0077G01J5/48G06T2207/10028G06T2207/10048H04N2013/0081H04N13/239
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 12,642,455
App. No.
18/907,879
Granted
Jun 2, 2026
Kind
B2
Abstract

A camera assembly for use in medical tracking applications includes a range camera and a thermographic camera. The range camera is configured to acquire a first point cloud of at least a portion of an object at a first moment in time and a second point cloud of at least the portion of the object at a second moment in time. The thermographic camera is configured to acquire a first thermal image of at least the portion of the object at the first moment in time and a second thermal image of at least the portion of the object at the second moment in time. The assembly includes a processor configured to calculate a movement of at least the portion of the object between the first moment of time and the second moment of time based on the first point cloud and the second point cloud with additional information acquired from the first and second thermal images.

Claims (33)

1 . A camera assembly for use in medical tracking applications, comprising:

a range camera configured to acquire a first point cloud of at least a portion of an object at a first moment in time and a second point cloud of at least the portion of the object at a second moment in time;

a thermographic camera configured to acquire a first thermal image of at least the portion of the object at the first moment in time and a second thermal image of at least the portion of the object at the second moment in time; and

a processor configured to calculate a movement of at least the portion of the object between the first moment of time and the second moment of time based on the first point cloud and the second point cloud with additional information acquired from the first and second thermal images.

2 . The camera assembly of claim 1 , the processor is further configured to identify, based on the additional information acquired from the first and second thermal images, a first point in the first point cloud and a second point in the second point cloud, wherein the first point and the second point correspond to a same point on the object.

3 . The camera assembly of claim 2 , wherein the processor is further configured to identify a thermal feature in the first thermal image and the second thermal image.

4 . The camera assembly of claim 3 , wherein the thermal feature is at least one of a temperature, a thermal signature of an area surrounding the same point of the object, a temperature distribution, a descriptor of a value for a property of the same point of the object, or a descriptor over a period of time.

5 . The camera assembly of claim 2 , wherein the movement is calculated based on the first point and the second point.

6 . The camera assembly of claim 1 , wherein the processor is further configured to generate a first reduced point cloud and a second reduced point cloud respectively associated with the first point cloud and the second point cloud, wherein the first reduced point cloud and the second reduced point cloud have a point-to-point correspondence, and wherein the first reduced point cloud and the second reduced point cloud are generated based on the first and second thermal images.

7 . The camera assembly of claim 1 , wherein the range camera and the thermographic camera are in a fixed relative position to one another.

8 . The camera assembly of claim 1 , wherein the first point cloud is a collection of points in a first image captured by the range camera that includes respective locations of points in the first image relative to the range camera and the second point cloud is a collection of points in a second image captured by the range camera that includes respective locations of points in the second image relative to the range camera.

9 . The camera assembly of claim 1 , further comprising a common housing in which the range camera and the thermographic camera are arranged.

10 . The camera assembly of claim 1 , wherein the range camera is a stereo camera, a structured light 3D scanner, a time-of-flight camera or a laser scanner.

11 . The camera assembly of claim 1 , further comprising a storage unit which stores calibration information which represents a relative position between the range camera and the thermographic camera.

12 . The camera assembly of claim 1 , wherein the processor is further configured to:

identify a first point pair including a first point in the first thermal image and a second point in the second thermal image, wherein the first point and the second point correspond to a same point on a surface of the object; and

map points of the first point pair to the first point cloud and the second point cloud, respectively, to provide a second point pair, wherein points of the first point pair and points of the second point pair correspond to the same point on the surface of the object.

13 . The camera assembly of claim 12 , wherein the processor is further configured to calculate the movement of at least the portion of the object based on the second point pair.

14 . The camera assembly of claim 1 , wherein the processor is further configured to determine a point-to-point correspondence, of at least one point, between the first point cloud and the second point cloud based on the additional information from the first and second thermal images, wherein the movement is calculated based on the point-to-point correspondence.

15 . A method performed by a processor of a computer for tracking at least a part of a surface of an object, comprising the steps of:

acquiring, at the processor, at a first point in time, a first point cloud from a range camera and a first thermal image from a thermographic camera;

acquiring, at the processor, at a second point in time later than the first point in time, a second point cloud from the range camera and a second thermal image from the thermographic camera; and

calculating a movement of at least the part of the surface of the object between the first moment of time and the second moment of time based on the first point cloud and the second point cloud with additional information acquired from the first and second thermal images.

16 . The method of claim 15 , wherein calculating the movement involves calibration information which represents a relative position between the range camera and the thermographic camera.

17 . The method of claim 15 , wherein calculating the movement involves matching, by the processor, at least a subset of the first point cloud and at least a subset of the second point cloud, the subsets of the point clouds comprising points respectively corresponding to same points on the surface of the object.

18 . The method of claim 17 , wherein matching the subsets of the point clouds utilizes the additional information acquired from the first and the second thermal images.

19 . The method of claim 15 , further comprising:

identifying a first point pair including a first point in the first thermal image and a second point in the second thermal image, wherein the first point and the second point correspond to a same point on the surface of the object; and

mapping points of the first point pair to the first point cloud and the second point cloud, respectively, to provide a second point pair, wherein points of the first point pair and points of the second point pair correspond to the same point on the surface of the object.

20 . A non-transitory computer-readable program storage medium storing a program which, when running on a computer, causes the computer to perform the steps of:

acquiring, at the computer, at a first point in time, a first point cloud from a range camera and a first thermal image from a thermographic camera;

acquiring, at the computer, at a second point in time later than the first point in time, a second point cloud from the range camera and a second thermal image from the thermographic camera; and

calculating a movement of at least a part of a surface of an object between the first moment of time and the second moment of time based on the first point cloud and the second point cloud with additional information acquired from the first and second thermal images.

Assignments (2)
CHANGE OF NAME Recorded Feb 24, 2026
From: BRAINLAB AG
To: BRAINLAB SE
Reel/Frame 073875/0224 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 7, 2024
From: KAISER, HAGEN; BERLINGER, KAJETAN
To: BRAINLAB AG
Reel/Frame 068813/0111 →
Priority Claims (2)
WO PCT/EP2014/076287 · Dec 2, 2014 · international
WO PCT/EP2015/059171 · Apr 28, 2015 · international
Continuity (4)
Continuation 18139478 · Apr 26, 2023
Continuation 16953803 · Nov 20, 2020
Continuation 15308962
Related Publication 20250241559A1 · Jul 31, 2025
References Cited (31)
US 6754370B1 · Hall-Holt · 2004 [cited by examiner]
US 7519210B2 · Hirsch · 2009 [cited by applicant]
US 7734077B2 · Hirsch et al. · 2010 [cited by applicant]
US 10874331B2 · Kaiser · 2020 [cited by examiner]
US 11666250B2 · Kaiser · 2023 [cited by examiner]
US 12138043B2 · Kaiser · 2024 [cited by examiner]
US 20020173723A1 · Lewis · 2002 [cited by applicant]
US 20040023612A1 · Kriesel · 2004 [cited by applicant]
US 20070247517A1 · Zhang · 2007 [cited by applicant]
US 20100135550A1 · Arnon · 2010 [cited by applicant]
US 20100172567A1 · Prokoski · 2010 [cited by examiner]
US 20100284591A1 · Arnon et al. · 2010 [cited by applicant]
US 20110021944A1 · Arnon · 2011 [cited by examiner]
US 20110118608A1 · Lindner et al. · 2011 [cited by applicant]
US 20120078113A1 · Whitestone et al. · 2012 [cited by applicant]
US 20120226152A1 · Porikli · 2012 [cited by applicant]
US 20120289850A1 · Xu · 2012 [cited by examiner]
US 20120307046A1 · Lundberg · 2012 [cited by applicant]
US 20160006951A1 · Moghadam · 2016 [cited by applicant]
EP 2779624A1 · 2014 [cited by applicant]
GB 2418495B · 2010 [cited by applicant]
WO 2014127431A1 · 2014 [cited by applicant]
WO 2016086976A1 · 2016 [cited by applicant]
Skala, Karolj, et al. “4D thermal imaging system for medical applications.” Periodicum biologorum 113.4 (2011): 407-416. (Year: 2011). [cited by examiner]
Bilodeau, Guillaume-Alexandre, et al. “Body temperature estimation of a moving subject from thermographic images.” Machine Vision and Applications 23.2 (2012): 299-311. (Year: 2012). [cited by examiner]
Weinmann, Martin, et al. “Thermal 3D mapping for object detection in dynamic scenes.” ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2 (2014): 53-60. (Year: 2014). [cited by examiner]
International Search Report for PCT/EP2015/059542, Date of Mailing Aug. 12, 2015, pp. 1-6. [cited by applicant]
Written Opinion of the International Searching Authority for PCT/EP2015/059542, pp. 1-11. [cited by applicant]
M. Calonder et al., “BRIEF: Computing a Local Binary Descriptor Very Fast”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, issue No. 07, Jul. 2012, pp. 1281 to 1298. [cited by applicant]
C.Lu et al., “Fast and Globally Convergent Pose Estimation from Video Images” published in IEEE Transactions on Patent Analysis and Machine Intelligence, vol. 22, No. 6, Jun. 2000, pp. 610 to 622. [cited by applicant]
M. Calonder et al., “BRIEF: Computing a Local Binary Descriptor Very Fast”, Computer Vision Laboratory, I&C Faculty, pp. 1-29, Lausanne, Switzerland. [cited by applicant]