IP Library › Granted Patent US 12,263,836
Granted Patent B2
US 12,263,836 · App. 18/500,174 · Granted Apr 1, 2025

Methods and systems for providing depth maps with confidence estimates

Inventors: Leaf Alden Jiang (Concord, MA); Carsten Louis Boers (Cambridge, MA)
Assignee: NODAR Inc.
B60W30/09G01S17/89G06T7/50G06T2207/10024G06T2207/10028
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 12,263,836
App. No.
18/500,174
Granted
Apr 1, 2025
Kind
B2
Abstract

An automated vehicle assistance system is provided for supervised or unsupervised vehicle movement. The system includes a control system and a first sensor system. The first sensor system may receive first image data of a scene and may output a first disparity map and a first confidence map based on the first image data. The control system may output a video stream based on the first disparity map and the first confidence map. The vehicle assistance system also may include a second sensor system that receives second image data of at least a portion of the scene that outputs a second confidence map based on second image data. The video stream may include super-frames, with each super-frame including a 2D image of the scene, a depth map corresponding to the 2D image, and a certainty map corresponding to the depth map.

Claims (46)

1. A system comprising:

a first sensor system configured to:

receive first image data of a scene captured by a pair of camera sensors,

calculate first disparity values and first confidence values from the first image data, and

output a first disparity map comprising the first disparity values, and output a first confidence map comprising the first confidence values; and

a machine control system configured to output a first control signal to a control unit of the machine to control the machine based on the first disparity map and the first confidence map, wherein controlling the machine based on the first disparity map and the first confidence map comprises determining whether to use the first disparity values or discard the first disparity values based on an assessment of the corresponding first confidence values.

2. The system of claim 1 , wherein the machine control system is further configured to output, to a display device of the machine, a video stream based on the first disparity map and the first confidence map.

3. The system of claim 1 , wherein:

the first image data comprises a plurality of pixels,

the first disparity map comprises a disparity value for each of the pixels, and

the first confidence map comprises a confidence value for each of the pixels.

4. The system of claim 1 , further comprising:

a second sensor system configured to receive second image data of at least a portion of the scene and to output a second confidence map based on the second image data,

wherein the machine control system is further configured to output a video stream as a sequence of super-frames, with each super-frame comprising information based on: the first disparity map, the first confidence map, and the second confidence map.

5. The system of claim 1 , wherein the machine control system is configured to output a plurality of control signals to a plurality of control units of the machine based on the first disparity map and the first confidence map.

6. The system of claim 4 , wherein:

the video stream comprises:

at least one super-frame comprising the first disparity map and the first confidence map, and

at least one super-frame comprising the first disparity map and the second confidence map.

7. The system of claim 4 , wherein the video stream comprises at least one super-frame comprising a portion of the first confidence map and a portion of the second confidence map.

8. The system of claim 4 , wherein:

the first image data comprises stereo-vision data, and

the second image data comprises lidar data.

9. The system of claim 1 , wherein the first sensor system comprises a confidence processor configured:

to generate a plurality of camera-based confidence maps based on the first image data,

to aggregate data from the plurality of camera-based confidence maps, and

to output the first confidence map based on the data aggregated from the plurality of camera-based confidence maps.

10. The system of claim 2 , wherein:

the video stream comprises a plurality of super-frames, and

each super-frame of the video stream comprises:

a first region corresponding to a two-dimensional (2D) image of the scene,

a second region corresponding to a depth map of the scene, and

a third region corresponding to a certainty map of the scene.

11. The system of claim 10 , wherein pixels of the 2D image of the scene, pixels of the depth map of the scene, and pixels of the certainty map of the scene are temporally and spatially matched.

12. The system of claim 2 , wherein the video stream comprises two-dimensional (2D) color images, with each 2D color image comprising a plurality of pixels, and with an alpha-channel transparency of each pixel being proportional to a confidence value for the pixel.

13. A non-transitory computer-readable storage medium storing code that, when executed by a computer processor, causes the computer processor to perform a method, wherein the method comprises:

the computer processor receiving first image data of a scene captured by a pair of camera sensors,

the computer processor calculating first disparity values and first confidence values from the first image data,

the computer processor generating a first disparity map comprising the first disparity values, and generating a first confidence map comprising the first confidence values, and

the computer processor outputting a first control signal to a control unit of a machine to control the machine based on the first disparity map and the first confidence map, wherein controlling the machine based on the first disparity map and the first confidence map comprises determining whether to use the first disparity values or discard the first disparity values based on an assessment of the corresponding first confidence values.

14. The computer-readable storage medium of claim 13 , wherein the method further comprises:

the computer processor obtaining a second confidence map corresponding to second image data of at least a portion of the scene, and

the computer processor outputting a video stream as a sequence of super-frames, with each super-frame comprising information based on: the first disparity map, the first confidence map, and the second confidence map.

15. The computer-readable storage medium of claim 13 , wherein the method further comprises:

the computer processor outputting a plurality of control signals to a plurality of control units of the machine based on the first disparity map and the first confidence map.

16. The system of claim 1 , wherein the assessment of the corresponding first confidence values comprises determining whether the corresponding first confidence value is within an acceptable confidence threshold.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 10, 2024
From: JIANG, LEAF ALDEN; BOERS, CARSTEN LOUIS
To: NODAR INC.
Reel/Frame 067946/0507 →
Continuity (6)
Continuation 17887588 · Aug 15, 2022
Continuation 17559384 · Dec 22, 2021
Continuation In Part PCTUS2021012294 · Jan 6, 2021
Provisional Application 63229102 · Aug 4, 2021
Provisional Application 62964148 · Jan 22, 2020
Related Publication 20240326787A1 · Oct 3, 2024
References Cited (114)
US 6392688B1 · Barman et al. · 2002 [cited by applicant]
US 8208716B2 · Choi et al. · 2012 [cited by applicant]
US 8797387B2 · Huggett et al. · 2014 [cited by applicant]
US 8971634B2 · Barnum · 2015 [cited by applicant]
US 8981966B2 · Stein et al. · 2015 [cited by applicant]
US 9286680B1 · Jiang et al. · 2016 [cited by applicant]
US 9369689B1 · Tran et al. · 2016 [cited by applicant]
US 9509979B2 · Livyatan et al. · 2016 [cited by applicant]
US 9958964B2 · Wurster · 2018 [cited by examiner]
US 10097812B2 · Livyatan et al. · 2018 [cited by applicant]
US 10244228B2 · Millett · 2019 [cited by applicant]
US 10257489B2 · Nam · 2019 [cited by applicant]
US 10269257B1 · Gohl et al. · 2019 [cited by applicant]
US 10430959B2 · Chang et al. · 2019 [cited by applicant]
US 10567748B2 · Okouneva · 2020 [cited by applicant]
US 10591594B2 · Oyaizu et al. · 2020 [cited by applicant]
US 10965929B1 · Bellows · 2021 [cited by examiner]
US 11157751B2 · Kumano et al. · 2021 [cited by applicant]
US 11282234B2 · Jiang et al. · 2022 [cited by applicant]
US 11321875B2 · Jiang et al. · 2022 [cited by applicant]
US 11321876B2 · Jiang et al. · 2022 [cited by applicant]
US 11427193B2 · Jiang et al. · 2022 [cited by applicant]
US 11577748B1 · Wang et al. · 2023 [cited by applicant]
US 11782145B1 · Swierczynski et al. · 2023 [cited by applicant]
US 11834038B2 · Jiang et al. · 2023 [cited by applicant]
US 11983899B2 · Jiang et al. · 2024 [cited by applicant]
US 12043283B2 · Wang et al. · 2024 [cited by applicant]
US 20070070069A1 · Samarasekera et al. · 2007 [cited by applicant]
US 20070291125A1 · Marquet · 2007 [cited by applicant]
US 20100208034A1 · Chen · 2010 [cited by applicant]
US 20110025548A1 · Nickolaou · 2011 [cited by applicant]
US 20110050864A1 · Bond · 2011 [cited by applicant]
US 20120321172A1 · Jachalsky et al. · 2012 [cited by applicant]
US 20130063594A1 · Hwang et al. · 2013 [cited by applicant]
US 20130188018A1 · Stevens et al. · 2013 [cited by applicant]
US 20130329015A1 · Pulli et al. · 2013 [cited by applicant]
US 20150103147A1 · Ho et al. · 2015 [cited by applicant]
US 20160323560A1 · Jin et al. · 2016 [cited by applicant]
US 20160323561A1 · Jin et al. · 2016 [cited by applicant]
US 20170278014A1 · Lessmann et al. · 2017 [cited by applicant]
US 20170287169A1 · Garcia · 2017 [cited by applicant]
US 20170307759A1 · Pei et al. · 2017 [cited by applicant]
US 20170358092A1 · Bliebel et al. · 2017 [cited by applicant]
US 20180007345A1 · Bougnoux · 2018 [cited by applicant]
US 20180176543A1 · Wan · 2018 [cited by applicant]
US 20180222499A1 · Gomes et al. · 2018 [cited by applicant]
US 20190087186A1 · Endo · 2019 [cited by applicant]
US 20190158813A1 · Rowell et al. · 2019 [cited by applicant]
US 20190204427A1 · Abari et al. · 2019 [cited by applicant]
US 20190208181A1 · Rowell · 2019 [cited by examiner]
US 20190220989A1 · Harmsen · 2019 [cited by examiner]
US 20190289282A1 · Briggs et al. · 2019 [cited by applicant]
US 20190295282A1 · Smolyanskiy et al. · 2019 [cited by applicant]
US 20190304164A1 · Zhang · 2019 [cited by examiner]
US 20200064483A1 · Li · 2020 [cited by examiner]
US 20200077073A1 · Nash et al. · 2020 [cited by applicant]
US 20200177870A1 · Tadi et al. · 2020 [cited by applicant]
US 20200346581A1 · Lawson et al. · 2020 [cited by applicant]
US 20200409376A1 · Ebrahimi Afrouzi · 2020 [cited by examiner]
US 20210003683A1 · Chen et al. · 2021 [cited by applicant]
US 20210327092A1 · Jiang · 2021 [cited by examiner]
US 20210350576A1 · Jiang et al. · 2021 [cited by applicant]
US 20210352259A1 · Jiang et al. · 2021 [cited by applicant]
US 20220111839A1 · Jiang · 2022 [cited by examiner]
US 20230005184A1 · Jiang et al. · 2023 [cited by applicant]
US 20230076036A1 · Jiang et al. · 2023 [cited by applicant]
US 20230356743A1 · Wang et al. · 2023 [cited by applicant]
US 20240183963A1 · Swierczynski et al. · 2024 [cited by applicant]
US 20240242382A1 · Jiang et al. · 2024 [cited by applicant]
DE 102012009577A1 · 2012 [cited by applicant]
EP 1457384A1 · 2004 [cited by applicant]
JP 2003269917A · 2003 [cited by applicant]
JP 2008022125A · 2008 [cited by applicant]
JP 2008509619A · 2008 [cited by applicant]
JP 2015136056A · 2015 [cited by applicant]
JP 2015158749A · 2015 [cited by applicant]
JP 2016048839A · 2016 [cited by applicant]
JP 2017057058A · 2017 [cited by applicant]
KR 1020090031998A · 2009 [cited by applicant]
WO WO2015015542A1 · 2015 [cited by applicant]
WO WO2017057058A1 · 2017 [cited by applicant]
WO WO2017209015A1 · 2017 [cited by applicant]
WO WO2018196001A1 · 2018 [cited by applicant]
WO WO2019155719A1 · 2019 [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2021/064856, mailed May 5, 2022. [cited by applicant]
International Preliminary Report on Patentability for International Application No. PCT/US2021/064856, mailed Jul. 20, 2023. [cited by applicant]
Achanta et al., SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence. May 2, 20129;34(11):2274-82. [cited by applicant]
Ashigahara, How close has computer vision come to human vision? Difficulties and practical approaches to avoid them. Vision Systems for robots and their applications. Journal of the Institute of Image Information and Te… [cited by applicant]
Badino et al., Free space computation using stochastic occupancy grids and dynamic programming. Workshop on Dynamical Vision, ICCV, Rio de Janeiro, Brazil. Oct. 20, 2007;20:73. [cited by applicant]
Cholakkal et al., LiDAR-Stereo Camera Fusion for Accurate Depth Estimation. 2020 AEIT International Conference of Electrical and Electronic Technologies for Automotive (Aeit Automotive). Nov. 18, 2020:1-6. [cited by applicant]
Dai et al., A Review of 3D Object Detection for Autonomous Driving of Electric Vehicles. World Electric Vehicle Journal. Sep. 2021;12(3):139. [cited by applicant]
Fan et al., Real-time stereo vision-based lane detection system. Measurement Science and Technology. May 24, 2018;29(7):074005. [cited by applicant]
Feng et al., Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges. IEEE Transactions on Intelligent Transportation Systems. Feb. 17, 2020;22(3):1341-60. [cited by applicant]
Guindel et al., Automatic extrinsic calibration for lidar-stereo vehicle sensor setups. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). Oct. 16, 2017:1-6. [cited by applicant]
Hamid et al., Stereo matching algorithm based on deep learning: A survey. Journal of King Saud University: Computer and Information Sciences. Aug. 28, 2020:1-11. [cited by applicant]
Hinzmann et al., Flexible stereo: Constrained, non-rigid, wide-baseline stereo vision for fixed-wing aerial platforms. 2018 IEEE International Conference on Robotics and Automation (ICRA) May 21, 2018:2550-7. [cited by applicant]
Hirschmüller et al., Evaluation of cost functions for stereo matching. 2007 IEEE Conference on Computer Vision and Pattern Recognition. Jun. 17, 2007:1-8. [cited by applicant]
Hirschmüller, Stereo processing by semiglobal matching and mutual information. IEEE Transactions on Pattern Analysis and Machine Intelligence. Dec. 18, 2007;30(2):328-41. [cited by applicant]
Hsu et al., Online Recalibration of a Camera and Lidar System. 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Oct. 7, 2018:4053-8. [cited by applicant]
Hu et al., A quantitative evaluation of confidence measures for stereo vision. IEEE Transactions on Pattern Analysis and Machine Intelligence. Jan. 31, 2012;34(11):2121-33. [cited by applicant]
John et al., Automatic calibration and registration of lidar and stereo camera without calibration objects. 2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES). Nov. 5, 2015:231-7. [cited by applicant]
Kakegawa et al., Road surface segmentation based on vertically local disparity histogram for stereo camera. International Journal of Intelligent Transportation Systems Research. May 2018;16(2):90-7. [cited by applicant]
Longuet-Higgins, A computer algorithm for reconstructing a scene from two projections. Nature. Sep. 1981;293(5828):133-5. [cited by applicant]
Nelder et al., A simplex method for function minimization. The Computer Journal. Jan. 1, 1965;7(4):308-13. [cited by applicant]
Poggi et al., On the confidence of stereo matching in a deep-learning era: a quantitative evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence. Apr. 2, 2021:1-8. [cited by applicant]
Rajaraman et al., Fully automatic, unified stereo camera and LiDAR-camera calibration. Automatic Target Recognition XXXI. Apr. 12, 2021;11729:270-277. [cited by applicant]
Rhemann et al., Fast cost-volume filtering for visual correspondence and beyond. CVPR '11: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Jun. 2011:3017-24. [cited by applicant]
Rosero et al., Calibration and multi-sensor fusion for on-road obstacle detection. 2017 Latin American Robotics Symposium (LARS) and 2017 Brazilian Symposium on Robotics (SBR). Nov. 8, 2017:1-6. [cited by applicant]
Sarika et al., Census filtering based stereomatching under varying radiometric conditions. Procedia Computer Science. Jan. 1, 2015;58:315-20. [cited by applicant]
Woo et al., Localization for autonomous driving. Handbook of Position Location: Theory, Practice, and Advances, Second Edition. Mar. 23, 2018:1051-87. [cited by applicant]
Zabih et al., Non-parametric local transforms for computing visual correspondence. European Conference on Computer Vision May 2, 1994:151-158. [cited by applicant]
Zhang et al., A robust and rapid camera calibration method by one captured image. IEEE Transactions on Instrumentation and Measurement. Dec. 17, 2018;68(10):4112-21. [cited by applicant]
Extended European Search Report for European Application No. 21918078.3, dated Oct. 22, 2024. [cited by applicant]
Kemsaram et al. A stereo perception framework for autonomous vehicles. In2020 IEEE 91st vehicular technology conference (VTC2020-Spring) May 25, 2020:(pp. 1-6). [cited by applicant]