KR950013189A - How to control the auto white balance (AWB) of your camcorder - Google Patents

How to control the auto white balance (AWB) of your camcorder Download PDF

Info

Publication number
KR950013189A
KR950013189A KR1019930020880A KR930020880A KR950013189A KR 950013189 A KR950013189 A KR 950013189A KR 1019930020880 A KR1019930020880 A KR 1019930020880A KR 930020880 A KR930020880 A KR 930020880A KR 950013189 A KR950013189 A KR 950013189A
Authority
KR
South Korea
Prior art keywords
awb
neural network
network controller
camcorder
microprocessor
Prior art date
Application number
KR1019930020880A
Other languages
Korean (ko)
Other versions
KR970006549B1 (en
Inventor
유재근
Original Assignee
배순훈
대우전자 주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 배순훈, 대우전자 주식회사 filed Critical 배순훈
Priority to KR1019930020880A priority Critical patent/KR970006549B1/en
Publication of KR950013189A publication Critical patent/KR950013189A/en
Application granted granted Critical
Publication of KR970006549B1 publication Critical patent/KR970006549B1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Processing Of Color Television Signals (AREA)
  • Color Television Image Signal Generators (AREA)

Abstract

본 발명은 신경회로망을 이용하여 정확한 AWB(auto white balance) 동작을 구현할 수 있는 캠코더의 AWB 제어방법에 관한 것으로, 캠코더의 AWB 제어방법은 캠코더 AWB 처리 시스템의 렌즈부로 부터 입사되는 영상신호의 R, G, B, Y 신호, 아이리스, 셔터 속도 상태값 마이크로프로세서에 의하여, R, B 이득을 조정하는 단계와, 마이크로프로세서에 입력된 영상신호를 신경회로망 제어기에 의해 학습하고, R, B 이득값을 산출하는 단계와, 신경회로망 제어기의 학습기능을 이용하여 AWB 동작을 수행하는 단계에 의해 AWB 제어과정이 수행됨으로서, AWB의 정밀도가 증진될 뿐 아니라 학습되지 않은 새로운 환경에서도 AWB 동작을 수행할 수 있도록 한 것이다.The present invention relates to an AWB control method of a camcorder capable of implementing accurate AWB (auto white balance) operation using a neural network, wherein the AWB control method of a camcorder is R, of an image signal incident from a lens unit of a camcorder AWB processing system. G, B, Y signal, iris, shutter speed state value microprocessor, adjusting the R, B gain, the image signal input to the microprocessor is learned by the neural network controller, and the R, B gain value The AWB control process is performed by the step of calculating and performing the AWB operation using the learning function of the neural network controller, so that not only the accuracy of the AWB is improved but also the AWB operation can be performed even in a new unlearned environment. It is.

Description

캠코더의 오토 화이트 밸런스(AWB) 제어방법How to control the auto white balance (AWB) of your camcorder

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음Since this is an open matter, no full text was included.

제3도는 본 발명에 따라, 신경회로망의 기준 입출력 데이타 획득 방법을 도시한 개략적인 블럭도.3 is a schematic block diagram showing a method for acquiring reference input / output data of a neural network according to the present invention.

제4도는 본 발명에 따라, 신경회로망 제어기에 의한 학습 과정을 도시한 개략적인 블럭도.4 is a schematic block diagram illustrating a learning process by a neural network controller, in accordance with the present invention.

제5도는 본 발명에 따라, 신경회로망 제어기에 의한 출력(실제 AWB 동작 수행) 과정을 도시한 개략적인 블럭도.5 is a schematic block diagram illustrating a process of performing an output (performing an actual AWB operation) by a neural network controller, in accordance with the present invention.

제6도는 본 발명에 따라, 신경회로망의 제어기에 의한 AWB 학습과정 및 출력의 흐름도.6 is a flow chart of AWB learning process and output by a controller of a neural network, in accordance with the present invention.

제7도는 본 발명에 따라, 신경회로망 제어기에 의한 AWB 학습과정의 시스템을 도시한 도면.7 is a neural network, in accordance with the present invention. A diagram of a system of AWB learning process by a controller.

제8도는 본 발명에 따라, 신경회로망 제어기에 의한 AWB 시스템을 도시한 도면.8 is a neural network according to the present invention. AWB system by controller.

Claims (4)

캠코더 AWB(auto white balance) 처리 시스템에서 렌즈부로부터 입사되는 영상신호의 R, G, B 신호 및 아이리스, 셔터 속도 상태값을 마이크로 프로세서를 통해 영상신호 값을 조절하는 캠코더의 AWB 제어 방법에 있어서, 상기 방법은 : 렌즈부로부터 상기 R, G, B, Y 신호, 아이리스(iris) 및 셔터 속도(shutter speed)신호에 따른 모든 영상 데이타를 상기 마이크로 프로세서에 입력하여 R, B 이득을 조정하는 단계와; 상기 마이크로 프로세서에 입력된 상기 영상신호를 신경회로망 제어기에 의해 학습하고 상기 R, B 이득값을 산출하는 단계와; 상기 신경회로망 제어기의 학습 기능을 이용하여 상기 AWB 동작을 수행하는 단계를 포함하는 방법.In the camcorder AWB control method of controlling the video signal value of the R, G, B signal and the iris and shutter speed state of the video signal incident from the lens unit in the camcorder AWB (auto white balance) processing system through a microprocessor, The method comprises: inputting all image data according to the R, G, B, Y signals, iris and shutter speed signals from a lens unit to the microprocessor to adjust R and B gains; ; Learning the image signal input to the microprocessor by a neural network controller and calculating the R and B gain values; Performing the AWB operation using a learning function of the neural network controller. 제1항에 잇어서, 상기 학습단계는, 상기 마이크로 프로세서로부터 입력된 모든 경우의 상기 R, G, B, Y 신호 및 아이리스 값을 신경회로망 제어기로 기준 입력 데이타를 입력하는 단계와, 상기 조정된 R, B 이득을 상기 신경회로망 제어기의 기준 출력으로 입력하는 단계와, 상기 신경회로망 제어기의 가중치를 초기화하는 단계와, 학습 데이타를 설정하여 역전파(back propagation) 알고리즘으로 수행하는 단계로 더욱 이루어진 캠코더의 AWB 제어방법.The method according to claim 1, wherein the learning step comprises inputting reference input data to the neural network controller using the R, G, B, Y signals and iris values in all cases input from the microprocessor, and the adjusted R. Inputting a B gain as a reference output of the neural network controller, initializing weights of the neural network controller, and setting learning data to perform a back propagation algorithm. AWB control method. 제2항에 있어서, 상기 역전파 알고리즘을 수행하여 기준 오차값 이내로 수렴하는 단계를 더욱 포함하는 캠코더의 AWB 제어방법.The method of claim 2, further comprising converging within a reference error value by performing the backpropagation algorithm. 제1항 또는 제2항에 있어서, 상기 AWB 수행 단계는, 상기 역전파 알고리즘 수행단계에 이어서 화면의 상기 R, G, B, Y 신호 및 아이리스, 셔터 속도 상태값을 학습 완료된 신경회로망 제어기에 입력하는 단계와, 상기 신경회로망 제어기에 의해 상기 R, B 이득을 출력하는 단계를 포함하는 캠코더의 AWB 제어방법.The method of claim 1, wherein the performing of the AWB comprises: inputting the R, G, B, Y signals, the iris, and the shutter speed state values of the screen to the learned neural network controller following the performing the backpropagation algorithm. And outputting the R and B gains by the neural network controller. ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: The disclosure is based on the initial application.
KR1019930020880A 1993-10-08 1993-10-08 Control method for automatic white balance (awb) of camcorder KR970006549B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1019930020880A KR970006549B1 (en) 1993-10-08 1993-10-08 Control method for automatic white balance (awb) of camcorder

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019930020880A KR970006549B1 (en) 1993-10-08 1993-10-08 Control method for automatic white balance (awb) of camcorder

Publications (2)

Publication Number Publication Date
KR950013189A true KR950013189A (en) 1995-05-17
KR970006549B1 KR970006549B1 (en) 1997-04-29

Family

ID=19365510

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019930020880A KR970006549B1 (en) 1993-10-08 1993-10-08 Control method for automatic white balance (awb) of camcorder

Country Status (1)

Country Link
KR (1) KR970006549B1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113518210A (en) * 2020-04-10 2021-10-19 华为技术有限公司 Method and device for automatic white balance of image

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113518210A (en) * 2020-04-10 2021-10-19 华为技术有限公司 Method and device for automatic white balance of image
CN113518210B (en) * 2020-04-10 2024-05-24 华为技术有限公司 Method and device for automatic white balance of image

Also Published As

Publication number Publication date
KR970006549B1 (en) 1997-04-29

Similar Documents

Publication Publication Date Title
US5258848A (en) Exposure controller of a video camera
KR880008675A (en) White balance adjuster for color video cameras
KR910019460A (en) White balance adjustment device which automatically performs white balance adjustment based on the color information signal obtained from the imaging element
KR950010529A (en) Imager
JPH0797830B2 (en) Black level correction circuit for video camera
US8411163B2 (en) Auto exposure controlling device and method
KR950013189A (en) How to control the auto white balance (AWB) of your camcorder
JPH03291073A (en) Video camera
JP2954883B2 (en) Method and apparatus for adjusting iris by changing luminance of input signal
KR950013188A (en) How to control the auto white balance (AWB) of your camcorder
JPH05344414A (en) Video camera
JP2002300468A (en) Imaging device and method for controlling the same
KR950004914A (en) Brightness control circuit in the viewfinder of the camcorder
JP2630683B2 (en) White balance adjustment device
JP2879569B2 (en) Imaging device
KR970019384A (en) Automatic camera adjustment mode and method of camcorder
JPH08163576A (en) Iris controller for surface sequential color camera
JPH0614256A (en) Exposure controller
JP2625688B2 (en) Aperture control device
JPH10210347A (en) Ae control signal processor
JPS5952361A (en) Arithmetic system for picture signal processing
JPH04273226A (en) Conversion adapter device of interchangeable lens system
KR970003036B1 (en) System against over-response of an iris
JPH05316416A (en) Lens diaphragm control system
JPH04104242A (en) Gain adjustment circuit for automatic exposure

Legal Events

Date Code Title Description
A201 Request for examination
G160 Decision to publish patent application
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
LAPS Lapse due to unpaid annual fee