CN-122027904-A - Image parameter adjustment method and related device based on double lenses

CN122027904ACN 122027904 ACN122027904 ACN 122027904ACN-122027904-A

Abstract

The application provides a double-lens-based image parameter adjustment method and a related device, wherein a first image and a second image are respectively acquired through a first camera and a second camera, the first image and the second image are processed to obtain a first image parameter and a second image parameter, a tunnel state parameter is calculated on the basis of a tunnel detection model on the image parameter, an exposure convergence parameter of a preset automatic exposure algorithm is adjusted according to the tunnel state parameter to obtain a target automatic exposure algorithm, then the first image parameter and the second image parameter are respectively calculated on the basis of the target automatic exposure algorithm and the tunnel state parameter to obtain a first image exposure parameter and a second image exposure parameter, the first image exposure parameter and the second image exposure parameter are adjusted, a first target image and a second target image are generated according to the adjusted parameters, and the first target image and the second target image are displayed through a display terminal. Thus, the driving safety can be improved.

Inventors

Yan Nanjie
ZHOU DIFEI

Assignees

深圳市欧冶半导体有限公司

Dates

Publication Date: 20260512
Application Date: 20260408

Claims (10)

1. The image parameter adjustment method based on the double lenses is characterized by being applied to a processor in a streaming media rearview mirror system, wherein the streaming media rearview mirror system comprises a first camera, a second camera and a display terminal, a preset tunnel detection model is deployed on the processor, the first camera and the second camera are in communication connection with the processor, and the processor is connected with the display terminal, and the method comprises the following steps: Acquiring a first image through the first camera, and acquiring a second image through the second camera; Processing the first image to obtain a first image parameter, and processing the second image to obtain a second image parameter; Calculating the first image parameters and/or the second image parameters based on the tunnel detection model to obtain tunnel state parameters; adjusting exposure convergence parameters of a preset automatic exposure algorithm according to the tunnel state parameters to obtain a target automatic exposure algorithm; Calculating the first image parameter and the second image parameter based on the target automatic exposure algorithm and the tunnel state parameter respectively to obtain a first image exposure parameter and a second image exposure parameter; adjusting the first image parameters according to the first image exposure parameters to obtain first image adjustment parameters, and adjusting the second image parameters according to the second image exposure parameters to obtain second image adjustment parameters; Generating a first target image according to the first image adjustment parameter, and generating a second target image according to the second image adjustment parameter; and sending the first target image and the second target image to the display terminal so as to display the first target image and the second target image through the display terminal.
2. The method of claim 1, wherein the tunnel state parameters include a tunnel scene state, a tunnel portal distance parameter, and a tunnel field of view area change rate, and the adjusting exposure convergence parameters of a preset automatic exposure algorithm according to the tunnel state parameters to obtain the target automatic exposure algorithm comprises: determining exposure corresponding to a tunnel scene state based on a mapping relation between the preset tunnel scene state and preset exposure to obtain a first exposure, wherein the tunnel scene state comprises one of a tunnel entrance scene state, a tunnel exit scene state, a driving scene state in a tunnel and a driving scene state outside the tunnel; Determining an adjustment value of an exposure convergence parameter according to the first exposure, the tunnel portal distance parameter, the tunnel visual field area change rate and the first image parameter to obtain an exposure convergence adjustment value; and adjusting exposure convergence parameters in the automatic exposure algorithm according to the exposure convergence adjustment value to obtain the target automatic exposure algorithm.
3. The method of claim 2, wherein determining an adjustment value for an exposure convergence parameter based on the first exposure amount, the tunnel portal distance parameter, the tunnel field of view region change rate, and the first image parameter, comprises: Acquiring vehicle operation parameters of a target vehicle; extracting the exposure of a first camera of the target vehicle from the first image parameter to obtain a second exposure; determining a difference value between the first exposure amount and the second exposure amount to obtain an exposure amount difference value; determining exposure convergence pressing factors corresponding to the tunnel scene states based on the vehicle running parameters, the tunnel portal distance parameters and the tunnel visual field area change rate; Determining the direction parameter and the adjustment amplitude required to be adjusted for the exposure convergence parameter according to the exposure convergence urgent factor and the exposure difference value to obtain an adjustment direction parameter and an adjustment amplitude value; and calculating the adjustment direction parameter and the adjustment amplitude value to obtain the exposure convergence adjustment value.
4. A method according to any one of claims 1-3, wherein said adjusting said first image parameters according to said first image exposure parameters to obtain first image adjustment parameters comprises: extracting parameters for exposure control from the first image exposure parameters to obtain first exposure control parameters; Determining parameters for controlling exposure of the first image in the first image parameters to obtain second exposure control parameters; Determining a difference value between the first exposure control parameter and the second exposure control parameter to obtain an exposure control parameter difference value; And determining an image adjustment parameter required for the first image according to the exposure control parameter difference value to obtain the first image adjustment parameter.
5. The method of claim 4, wherein determining the required image adjustment parameters for the first image based on the exposure control parameter difference value, the first image adjustment parameters comprising: Determining local tone mapping intensity and dynamic range compression intensity corresponding to the first image; Determining a brightness deviation value of the first image according to the exposure control parameter difference value, wherein the brightness deviation value is used for representing the brightness unbalance degree of the exposure state in the first image; Determining a local tone mapping adjustment interval of the first image according to the brightness deviation value to obtain a local tone mapping adjustment interval; Determining an adjustment interval of the dynamic range compression parameter of the first image according to the exposure control parameter difference value to obtain a dynamic range compression adjustment interval; calculating based on the local tone mapping intensity and the local tone mapping adjustment interval to obtain a target local tone mapping intensity, and calculating based on the dynamic range compression adjustment interval and the dynamic range compression intensity to obtain a target dynamic range compression intensity; And carrying out continuity constraint calculation on the first image based on a preset adjustment model, the target local tone mapping intensity and the target dynamic range compression intensity to obtain the first image adjustment parameter.
6. A method according to any of claims 1-3, wherein said generating a first target image from said first image adjustment parameters comprises: extracting a local tone mapping control parameter and a dynamic range compression control parameter corresponding to a first image from a first image adjustment parameter; Performing local brightness mapping processing on the first image according to the local tone mapping control parameters to obtain a brightness mapping image; Carrying out dynamic range compression processing on the brightness mapping image according to the dynamic range compression control parameters to obtain a dynamic compressed image; and carrying out inter-frame constraint processing on the dynamic compressed image to obtain the first target image.
7. The method of claim 6, wherein said performing inter-frame constraint processing on said dynamic compressed image to obtain said first target image comprises: determining a current frame image according to the dynamic compressed image, and a historical frame image corresponding to the current frame image; determining a brightness change value between the current frame image and the historical frame image to obtain a brightness change amplitude; And when the brightness change amplitude is larger than a preset brightness amplitude, processing the dynamic compressed image through a preset inter-frame constraint algorithm to obtain the first target image.
8. The image parameter adjusting device based on the double lenses is characterized by being applied to a processor in a streaming media rearview mirror system, wherein the streaming media rearview mirror system comprises a first camera, a second camera and a display terminal, a preset tunnel detection model is deployed on the processor, the first camera and the second camera are in communication connection with the processor, and the processor is connected with the display terminal, and the device comprises: the acquisition unit acquires a first image through the first camera and acquires a second image through the second camera; The system comprises a first image, a processing unit, a tunnel detection model, a target automatic exposure algorithm, a first image parameter processing unit, a second image parameter processing unit, a tunnel state parameter calculating unit, a target automatic exposure algorithm and a first image parameter processing unit, wherein the first image is processed to obtain the first image parameter; The control unit is used for adjusting the first image parameters according to the first image exposure parameters to obtain first image adjustment parameters, adjusting the second image parameters according to the second image exposure parameters to obtain second image adjustment parameters, generating a first target image according to the first image adjustment parameters, and generating a second target image according to the second image adjustment parameters; and the output unit is used for sending the first target image and the second target image to the display terminal so as to display the first target image and the second target image through the display terminal.
9. An electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method of any of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of any of claims 1-7.

Description

Image parameter adjustment method and related device based on double lenses Technical Field The present application relates to the field of image processing technologies, and in particular, to a method and an apparatus for adjusting image parameters based on dual lenses. Background At present, a vehicle-mounted streaming media rearview mirror system is gradually an important component of intelligent driving and driving safety and is used for providing a driver with real-time images of front and rear views in the driving process of a vehicle. However, in an actual environment, various scenes with a high dynamic range are often encountered in the running process of the vehicle, especially when entering and exiting the tunnel in daytime, the brightness difference between the inside and the outside of the tunnel is significant, the brightness of the external environment is higher, the brightness of the inside of the tunnel is lower, and the running speed of the vehicle is higher, so that the image acquisition and the display face a larger exposure control challenge. Specifically, when a vehicle enters the tunnel from outside the tunnel, images acquired by front and rear cameras in the streaming media rearview mirror system often appear obvious excessively dark phenomenon and can gradually converge to normal brightness after a certain time, and when the vehicle exits the tunnel from inside the tunnel, automatic exposure adjustment is not completed until the external environment brightness suddenly rises, so that the images are excessively exposed in a short time, and the accurate judgment of a driver on the road environment is further affected. Therefore, when a vehicle enters and exits a tunnel, how to improve the visual definition and driving safety of the driver is needed to be solved. Disclosure of Invention The embodiment of the application provides an image parameter adjusting method and a related device based on double lenses, wherein when a front view mirror and a rear view mirror are arranged on a vehicle driving recorder, the front view mirror senses the state and the distance of a tunnel in advance and outputs the state and the distance to an image signal processor of a rear view lens when the vehicle driving recorder enters the tunnel, so as to adjust an image convergence parameter and a local tone matching parameter, prevent an image from being too bright, avoid the image from being excessively exposed, and further improve the visual definition and driving safety of a driver. In a first aspect, an embodiment of the present application provides a method for adjusting image parameters based on dual lenses, where the method is applied to a processor in a streaming rearview mirror system, where the streaming rearview mirror system includes a first camera, a second camera, and a display terminal, the processor is deployed with a preset tunnel detection model, the first camera, the second camera are in communication connection with the processor, and the processor is connected with the display terminal, and the method includes: Acquiring a first image through the first camera, and acquiring a second image through the second camera; Processing the first image to obtain a first image parameter, and processing the second image to obtain a second image parameter; Calculating the first image parameters and/or the second image parameters based on the tunnel detection model to obtain tunnel state parameters; adjusting exposure convergence parameters of a preset automatic exposure algorithm according to the tunnel state parameters to obtain a target automatic exposure algorithm; Calculating the first image parameter and the second image parameter based on the target automatic exposure algorithm and the tunnel state parameter respectively to obtain a first image exposure parameter and a second image exposure parameter; adjusting the first image parameters according to the first image exposure parameters to obtain first image adjustment parameters, and adjusting the second image parameters according to the second image exposure parameters to obtain second image adjustment parameters; Generating a first target image according to the first image adjustment parameter, and generating a second target image according to the second image adjustment parameter; and sending the first target image and the second target image to the display terminal so as to display the first target image and the second target image through the display terminal. In a second aspect, an embodiment of the present application provides a dual-lens-based image parameter adjustment device, which is applied to a processor in a streaming rearview mirror system, where the streaming rearview mirror system includes a first camera, a second camera and a display terminal, the processor is deployed with a preset tunnel detection model, the first camera, the second camera are in communication connection with the processor, and the processor is connected with