IP Library Granted Patent US 12,450,825
Granted Patent B2
US 12,450,825 · App. 18/303,911 · Granted Oct 21, 2025

Surround view system

Inventors: Doron Sabo (Tel-Aviv, IL); Aviad Cohen (Tel-Aviv, IL); Aya Wolf (Tel-Aviv, IL); Liran Azaria (Tel-Aviv, IL)
Assignee: SAMSUNG ELECTRONICS CO., LTD.
G06T15/205G06T5/50G06T5/70G06T7/50G06T7/80G06V10/56G06V10/761G06T2207/20221G06V2201/07
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 12,450,825
App. No.
18/303,911
Granted
Oct 21, 2025
Kind
B2
Abstract

Aspects of the method, apparatus, non-transitory computer readable medium, and system include estimating extrinsic camera parameters of a plurality of cameras based on detection of corners in a camera calibration arrangement by projecting an image of the detected corners onto an image plane of at least one of the plurality of cameras. The aspects further include incrementally tuning a location estimate for the detected corners based on pixels of the projected image, and adjusting the extrinsic camera parameters of the at least one of the plurality of cameras based on the tuned location estimate. The aspects further include generating a virtual image based on the pixels of the projected image mapped to a virtual image plane.

Claims (32)

1. A method of generating a virtual camera view, comprising:

receiving a plurality of adjoining images, wherein the plurality of adjoining images include pixels;

detecting one or more objects in each of the plurality of adjoining images;

receiving depth information for the pixels of the one or more detected objects;

analyzing a mismatch between each of the adjoining images;

prioritizing the image having a closer detected object based on the depth information;

forming a virtual image by merging the adjoining images together, wherein pixels of the prioritized image are used in an overlap region of the adjoining images; and

identifying a seam location between the adjoining images according to a path of minimal depth discrepancy between the adjoining views.

2. The method of claim 1 , further comprising:

assigning a weight to the pixels along the seam; and

blending the pixels along the seam based on the assigned weights.

3. The method of claim 2 , wherein:

the assigned weight is based on a distance of the pixel from an optical center of a camera obtaining the image.

4. The method of claim 3 , further comprising:

adjusting a position of the seam based on depth information for the pixels along the seam.

5. The method of claim 4 , further comprising:

applying color harmonization to the adjoining images along the seam.

6. A virtual image generation system, comprising:

a plurality of cameras positioned relative to an origin; and

one or more processors that receive a communication signal from the plurality of cameras,

wherein the virtual image generation system is configured to generate a virtual image from a plurality of adjoining images received from the plurality of cameras;

wherein each of the adjoining images include pixels, and wherein the virtual image is formed based on a mismatch between each of the adjoining images and prioritizing the adjoining image that has a closer object based on depth information, and merging the adjoining images together, wherein the pixels of the prioritized image are used in an overlap region of the adjoining images.

7. The virtual image generation system of claim 6 , wherein:

the virtual image generation system is further configured to identify a seam location between the adjoining images according to a path of minimal depth discrepancy between the adjoining images based on the depth information, wherein the adjoining images are merged along the seam.

8. The virtual image generation system of claim 7 , wherein:

the virtual image generation system is further configured to use pixels of the prioritized image in an overlap region of the adjoining images.

9. The virtual image generation system of claim 6 , further comprising:

a plurality of LiDAR sensors, wherein the virtual image generation system is further configured to receive a communication signal from each of the plurality of LiDAR sensors, and wherein the communication signal includes the depth information.

10. The virtual image generation system of claim 6 , further comprising:

a memory coupled to the one or more processors, wherein the depth information is stored in the memory with an associated image of the plurality of adjoining images.

11. The virtual image generation system of claim 10 , further comprising:

the virtual image generation system is further configured to utilize a three-dimensional model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 20, 2023
From: SABO, DORON; COHEN, AVIAD; WOLF, AYA; AZARIA, LIRAN
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 063389/0830 →
Continuity (1)
Related Publication 20240355041A1 · Oct 24, 2024
References Cited (41)
US 9386302B2 · Zeng et al. · 2016 [cited by applicant]
US 9866752B2 · Zhang et al. · 2018 [cited by applicant]
US 9892493B2 · Pekkucuksen et al. · 2018 [cited by applicant]
US 9978146B2 · Hedi et al. · 2018 [cited by applicant]
US 10085011B2 · Lin et al. · 2018 [cited by applicant]
US 10102610B2 · Forutanpour et al. · 2018 [cited by applicant]
US 10136055B2 · Lei et al. · 2018 [cited by applicant]
US 10235775B2 · Singh et al. · 2019 [cited by applicant]
US 10425638B2 · Yu et al. · 2019 [cited by applicant]
US 10621767B2 · Forutanpour et al. · 2020 [cited by applicant]
US 11303806B2 · Appia et al. · 2022 [cited by applicant]
US 11350073B2 · Fan et al. · 2022 [cited by applicant]
US 11380016B2 · Su · 2022 [cited by applicant]
US 20120287232A1 · Natroshvili et al. · 2012 [cited by applicant]
US 20160042515A1 · Sorgi et al. · 2016 [cited by applicant]
US 20170127045A1 · Lin et al. · 2017 [cited by applicant]
US 20180007263A1 · Vandrotti · 2018 [cited by examiner]
US 20190058870A1 · Rowell et al. · 2019 [cited by applicant]
US 20200314435A1 · Tourapis · 2020 [cited by examiner]
US 20210142497A1 · Pugh · 2021 [cited by examiner]
US 20220030212A1 · Aggarwal et al. · 2022 [cited by applicant]
US 20220118907A1 · Onishi et al. · 2022 [cited by applicant]
US 20230316635A1 · Jiang · 2023 [cited by examiner]
EP 2983131 · 2016 [cited by applicant]
EP 3362982 · 2018 [cited by applicant]
WO 2017065883 · 2017 [cited by applicant]
Chen, X., Yu, M., & Song, Y. (2022). Optimized seam-driven image stitching method based on scene depth information. Electronics 11(12), 1876. [cited by examiner]
Fu M, Liang H, Zhu C, Dong Z, Sun R, Yue Y, Yang Y. Image stitching techniques applied to plane or 3-D models: a review. IEEE Sensors Journal. Mar. 8, 2023;23(8):8060-79. [cited by examiner]
Lin, K., Jiang, N., Cheong, L. F., Do, M., & Lu, J. (2016). Seagull: Seam-guided local alignment for parallax-tolerant image stitching. In Computer Vision—ECCV 2016: 14th European Conference, Amsterdam, The Netherlands,… [cited by examiner]
Dosovitskiy, et al., “CARLA: An Open Urban Driving Simulator”, in Proceedings of the 1st Annual Conference on Robot Learning, arXiv preprint arXiv:1711.03938v1 [cs.LG] Nov. 10, 2017, pp. 1-16. [cited by applicant]
Harris, et al., “A Combined Corner and Edge Detector”, In Alvey Vision Conference, 1988, pp. 147-152. [cited by applicant]
Zhao, et al., “Monocular Depth Estimation Based on Deep Learning: An Overview”, In Science China Technological Sciences, vol. 63, Jun. 10, 2020, pp. 1-16. [cited by applicant]
Lin, et al., “Adaptive as-Natural-as-Possible Image Stitching”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1155-1163. [cited by applicant]
Zhang, et al., “Parallax-Tolerant Image Stitching”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 23, 2014, pp. 3262-3269. [cited by applicant]
Baek, et al., “Thin-Plate Spline-based Adaptive 3D Surround View”, In IEEE Intelligent Vehicles Symposium (IV), Jun. 2019, pp. 586-593. [cited by applicant]
Zaragoza, et al., “As-Projective-as-Possible Image Stitching with Moving DLT”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2013, pp. 2339-2346. [cited by applicant]
Garcia, “3D Reconstruction for Optimal Representation of Surroundings in Automotive HMIs, Based on Fisheye Multi-Camera Systems”, In ResearchGate, Jan. 2015, 183 pages. [cited by applicant]
Lee, et al., “Warping Residual Based Image Stitching for Large Parallax”, In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020, pp. 8198-8206. [cited by applicant]
Saputra, et al., “Visual SLAM and Structure from Motion in Dynamic Environments: A Survey”, In ACM Computing Surveys (CSUR), vol. 51, No. 2, Article 37, Feb. 2018, 36 pages. [cited by applicant]
Xiong, et al., “Color Matching of Image Sequences with Combined Gamma and Linear Corrections”, In ACM, Oct. 25-29, 2010, 10 pages. [cited by applicant]
Wang, et al., “Image Quality Assessment: From Error Visibility to Structural Similarity”, In IEEE Transactions on Image Processing, vol. 13, No. 4, Apr. 2004, pp. 600-612. [cited by applicant]