IP Library Granted Patent US 12,273,633
Granted Patent B2
US 12,273,633 · App. 17/793,034 · Granted Apr 8, 2025

Image processing method and sensor device for performing coloring processing on an image signal acquired using an array sensor

Inventors: Susumu Takatsuka (Tokyo, JP); Hiroki Tetsukawa (Tokyo, JP)
Assignee: SONY GROUP CORPORATION
H04N25/11G06T7/62G06T7/90G06V10/56G06V10/60G06T2207/10024G06V2201/07
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 12,273,633
App. No.
17/793,034
Granted
Apr 8, 2025
Kind
B2
Abstract

Object detection is performed for an image acquired by imaging using an array sensor in which a plurality of imaging elements are arranged one-dimensionally or two-dimensionally, some of the imaging elements are configured as color-filter-disposed pixels in which a color filter is disposed in an incident optical path, and color information acquisition points are formed by the color-filter-disposed pixels. Then, coloring processing in a pixel range of a detected object is performed by referring to color information acquired at the color information acquisition points corresponding to the inside of the pixel range of the detected object.

Claims (18)

1. An image processing method comprising:

performing object detection for an image acquired by imaging using an array sensor in which a plurality of imaging elements are arranged one-dimensionally or two-dimensionally, some of the imaging elements are configured as color-filter-disposed pixels in which a color filter is disposed in an incident optical path, and color information acquisition points are formed by the color-filter-disposed pixels; and

performing coloring processing in a pixel range of a detected object by referring to color information acquired at the color information acquisition points corresponding to the inside of the pixel range of the detected object,

wherein, in the coloring processing, coloring of the pixel range of the detected object is performed by setting candidate colors in the detected object using a color estimating process based on learning data from machine learning and selecting a candidate color on a basis of the color information acquired from the color information acquisition points.

2. A sensor device comprising:

an array sensor in which a plurality of imaging elements are arranged one-dimensionally or two-dimensionally, some of the imaging elements are configured as color-filter-disposed pixels in which a color filter is disposed in an incident optical path, and color information acquisition points are formed by the color-filter-disposed pixels; and

arithmetic operation circuitry configured to perform object detection for an image acquired by imaging using the array sensor and performing coloring processing in a pixel range of a detected object by referring to color information acquired at the color information acquisition points corresponding to the inside of the pixel range of the detected object,

wherein the arithmetic operation circuitry is configured to perform coloring processing of the pixel range of the detected object by setting candidate colors in the detected object using a color estimating process based on learning data from machine learning and selecting a candidate color on a basis of the color information acquired from the color information acquisition points.

3. The sensor device according to claim 2 , wherein the arithmetic operation circuitry is configured to generate a color layer on the basis of the candidate color selected on the basis of the color information acquired from the color information acquisition points and generate a color image by combining the color layer with a luminance information image acquired from the array sensor.

4. The sensor device according to claim 3 , wherein the arithmetic operation circuitry is configured to perform luminance correction of pixels corresponding to the color information acquisition points for the luminance information image acquired from the array sensor and combine the luminance information image and the color layer.

5. The sensor device according to claim 2 , wherein a total area of pixels not forming the color information acquisition points exceeds 25% of a total area of all the effective pixels on the array sensor.

6. The sensor device according to claim 2 , wherein the color information acquisition points are discretely disposed in the array sensor.

7. The sensor device according to claim 2 , wherein the color information acquisition points are disposed at constant intervals in the array sensor.

8. The sensor device according to claim 2 , wherein the color information acquisition points are disposed at non-constant intervals in the array sensor.

9. The sensor device according to claim 2 , wherein one unit of the color information acquisition points is configured using a plurality of adjacent pixels.

10. The sensor device according to claim 2 , wherein one unit of the color information acquisition points is configured using a plurality of adjacent pixels and includes an R pixel, a G pixel, and a B pixel.

11. The sensor device according to claim 2 , wherein one unit of the color information acquisition points is configured using a plurality of adjacent pixels and includes an R pixel, a G pixel, a B pixel, and a pixel of another color.

12. The sensor device according to claim 2 , wherein one unit of the color information acquisition points is configured using one pixel, and the color information acquisition points are discretely disposed in the array sensor.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 15, 2022
From: TAKATSUKA, SUSUMU; TETSUKAWA, HIROKI
To: SONY GROUP CORPORATION
Reel/Frame 060513/0724 →
Priority Claims (1)
JP 2020-025952 · Feb 19, 2020 · national
Continuity (1)
Related Publication 20230037953A1 · Feb 9, 2023
References Cited (37)
US 10122951B2 · Takado · 2018 [cited by examiner]
US 11605153B1 · Price · 2023 [cited by examiner]
US 20070076269A1 · Kido · 2007 [cited by applicant]
US 20070159542A1 · Luo · 2007 [cited by examiner]
US 20080316326A1 · Wada · 2008 [cited by applicant]
US 20090285476A1 · Choe · 2009 [cited by applicant]
US 20110058064A1 · Hatano · 2011 [cited by applicant]
US 20130027560A1 · Seger · 2013 [cited by examiner]
US 20140125838A1 · Mackey · 2014 [cited by applicant]
US 20180007324A1 · Chen · 2018 [cited by applicant]
US 20180089532A1 · Xu · 2018 [cited by applicant]
US 20180188427A1 · Brueckner · 2018 [cited by applicant]
CN 101233763A · 2008 [cited by applicant]
CN 101783354A · 2010 [cited by applicant]
CN 102870405A · 2013 [cited by applicant]
CN 103533262A · 2014 [cited by applicant]
CN 103650487A · 2014 [cited by applicant]
CN 204697179U · 2015 [cited by applicant]
CN 106210572A · 2016 [cited by applicant]
CN 108695351A · 2018 [cited by applicant]
CN 109819136A · 2019 [cited by applicant]
CN 208970511U · 2019 [cited by applicant]
JP 2011199798A · 2011 [cited by applicant]
JP 2013524664A · 2013 [cited by applicant]
JP 2014515587A · 2014 [cited by applicant]
JP 2014161022A · 2014 [cited by applicant]
JP 201550494A · 2015 [cited by applicant]
JP 2015106791A · 2015 [cited by applicant]
JP 2018537742A · 2018 [cited by applicant]
JP 2019122045A · 2019 [cited by applicant]
WO WO2015074915A1 · 2015 [cited by applicant]
International Search Report and Written Opinion mailed on Mar. 16, 2021, received for PCT Application PCT/JP2020/048890, filed on Dec. 25, 2020, 9 pages including English Translation. [cited by applicant]
Chakrabarti, Ayan, et al, “Rethinking Color Cameras”, 2014 IEEE International Conference Oncomputational Photography (ICCP), IEEE, May 2, 2014 (May 2, 2014), pp. 1-8. [cited by applicant]
Chen, Ying, et al, “Image colourisation using linear neighbourhood propagation and weighted smoothing”, IET Image Processing, IET, vol. 11, No. 5, May 1, 2017 (May 1, 2017), pp. 285-291. [cited by applicant]
Luo, Gang, “A novel color filter array with 75% transparent elements”, Proceedings of SPIE, vol. 6502, Feb. 15, 2007 (Feb. 15, 2007), pp. 1-8, XP093015632, ISSN: 0277-786X, DOI : 10.1117/12.702950. [cited by applicant]
Sharif, S. M. A., et al., “Deep color reconstruction for a sparse color sensor”, Optics Express, vo1. 27, No. 17, Aug. 5, 2019 (Aug. 5, 2019), pp. 23661-23681, XP055832582,DOI: 10.1364/0E.27.023661. [cited by applicant]
Richard Zhang et al. , “Real-time user-guided image colorization with learned deep priors” , ACM Transactions on Graphics , Jul. 20, 2017, vol. 36 , No. 4 , p. 1-11. [cited by applicant]