Image processing method and device of row-park integrated camera multi-image signal processor

Abstract

The application relates to an image processing method and device of a multi-image signal processor of a driving and parking integrated camera, which comprises the following steps: collecting a current image of a vehicle through an image sensor of a camera; sending the current image to an image signal processor; collecting a current image parameter and optimizing the current image parameter by the image signal processor; processing the current image based on the optimized image parameter by the image signal processor, and calculating an image sensor parameter needing to be adjusted; feeding back the image sensor parameter needing to be adjusted to the image sensor to adjust the image sensor; and the image signal processor comprises a first image signal processor and a second image signal processor. The first image signal processor and the second image signal processor are arranged to respectively adjust image parameters of images meeting driving and parking algorithm requirements and images meeting human perception requirements, so as to meet image use requirements of different vehicles in current scenes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent vehicles, in particular to an image processing method and device of a multi-image signal processor of a parking and driving integrated camera. BACKGROUND

[0002] With the development of artificial intelligence, there appears an autonomous vehicle, which is an intelligent vehicle that realizes unmanned driving through a computer system. The autonomous vehicle relies on the cooperation of artificial intelligence, visual computing, radar, monitoring devices and a global positioning system, so that the computer system can control the vehicle to travel automatically and safely without human initiative.

[0003] Currently, the use scenarios of intelligent driving in the industry are divided into intelligent driving scenarios and intelligent parking scenarios. In the field of intelligent driving, there is a parking and driving integrated solution, that is, four high-resolution fisheye cameras are deployed around the vehicle. The camera takes into account driving and parking. The parking and driving integrated solution brings a lot of convenience to people during driving, and the acceptance of users is also getting higher and higher. The images collected by the parking and driving integrated camera are mainly applied to intelligent driving scenarios, intelligent parking scenarios and manual parking scenarios. However, different scenarios have different requirements for images. In the intelligent driving scenario and the intelligent parking scenario, the images are provided to the perception algorithm in the automatic driving system, and the human sense of the image does not need to be considered. In the manual parking scenario, the image is provided for people to see, and the algorithm requirement does not need to be considered. Specifically, the difference between the perception algorithm requirement and the manual perception requirement for image adjustment is reflected in the exposure time, shading correction, low-illumination image brightness, color saturation and ISP parameter synchronization. For the ISP parameter synchronization, the perception algorithm needs to independently adjust the ISP of each camera to achieve the optimal image effect of each camera, and the manual perception needs to keep the multiple ISP parameters consistent as much as possible to ensure the consistency of the image color / brightness.

[0004] Currently, the intelligent driving scenario, the intelligent parking scenario and the manual parking scenario have different requirements for image adjustment, which causes contradictions in the application of the parking and driving integrated camera. Specifically, in the prior art, an image signal processor is usually used to process the images collected by the camera. In the case of only meeting the algorithm requirement or only meeting the manual perception requirement, the image can be well adjusted. However, when the image needs to be recognized by the algorithm and needs to be seen by people at the same time, the image signal processor is difficult to meet the requirements at the same time, resulting in that the optimal image meeting different requirements cannot be obtained in different scenarios, and further affecting the safety of driving and parking. SUMMARY

[0005] To solve the problems in the background art, the present application provides an image processing method of a multi-image signal processor of a parking and driving integrated camera, which comprises the following steps:

[0006] acquiring a current image of the vehicle by an image sensor of a camera;

[0007] sending the current image to an image signal processor, the image signal processor acquiring current image parameters and optimizing the current image parameters;

[0008] the image signal processor processing the current image based on the optimized image parameters and calculating image sensor parameters that need to be adjusted, and feeding back the image sensor parameters that need to be adjusted to the image sensor to adjust the image sensor;

[0009] the image signal processor includes a first image signal processor and a second image signal processor, the first image signal processor obtains a first image after processing the current image, the first image is provided to a driving or parking algorithm, and / or the second image signal processor obtains a second image after processing the current image, the second image is provided to a panoramic monitoring system.

[0010] Further, the current image is simultaneously sent to the first image signal processor and the second image signal processor, wherein the first image signal processor and the second image signal processor adopt the same hardware channel to process the current image in time division multiplexing, and one of the first image signal processor and the second image signal processor obtains the image sensor parameters that need to be adjusted.

[0011] Further, the current image is simultaneously sent to the first image signal processor and the second image signal processor, wherein the first image signal processor and the second image signal processor adopt different hardware channels to process the current image, and the first image signal processor and / or the second image signal processor obtains the image sensor parameters that need to be adjusted.

[0012] Further, the image sensor parameters include first image sensor parameters and second image sensor parameters, the first image sensor parameters are controlled by the first image signal processor, and the second image sensor parameters are controlled by the second image signal processor; the image includes odd frame images and even frame images, the first image sensor parameters are image sensor parameters of the odd frame images, and the second image sensor parameters are image sensor parameters of the even frame images.

[0013] Further, when the current scene of the vehicle is switched to an intelligent driving scene or an intelligent parking scene, the second image signal processor is closed, the image is processed by the first image signal processor and the image sensor parameters that need to be adjusted are obtained;

[0014] When the current scene of the vehicle switches to the panoramic monitoring scene, the first image signal processor is closed, the image is processed by the second image signal processor, and the image sensor parameter that needs to be adjusted is obtained.

[0015] Further, when the current scene of the vehicle switches to the intelligent driving and panoramic monitoring scene or the intelligent parking and panoramic monitoring scene, the image is processed by the first image signal processor and the second image signal processor, and the first image signal processor obtains the image sensor parameter that needs to be adjusted.

[0016] Further, when the current scene of the vehicle switches to the intelligent driving and panoramic monitoring scene or the intelligent parking and panoramic monitoring scene, the image is processed by the first image signal processor and the second image signal processor, and the first image signal processor and the second image signal processor respectively obtain the image sensor parameter that needs to be adjusted.

[0017] Further, the image sensor parameter includes exposure time, exposure gain and white balance; and the image parameter includes color saturation and brightness.

[0018] A multi-image signal processor processing device for a driving and parking integrated camera, comprising:

[0019] An image sensor, configured to collect a current image of a vehicle and send the current image to an image signal processor;

[0020] An image signal processor, configured to collect a current image parameter and perform tuning, process the current image based on the tuned image parameter, and calculate an image sensor parameter that needs to be adjusted, and feed back the image sensor parameter that needs to be adjusted to the image sensor to adjust the image sensor.

[0021] The image signal processor comprises a first image signal processor and a second image signal processor, the first image signal processor is configured to process the current image to obtain a first image, and provide the first image to a driving / parking algorithm, and / or the second image signal processor is configured to process the current image to obtain a second image, and provide the second image to a panoramic monitoring system.

[0022] A vehicle comprising the multi-image signal processor processing device for a driving and parking integrated camera according to claim 9.

[0023] Compared with the prior art, the present application has the following beneficial effects:

[0024] The application adjusts the image parameters of the image meeting the driving / parking algorithm requirement and the image meeting the human perception requirement by setting the first image signal processor and the second image signal processor, so as to meet the image use requirement of different vehicles in the current scene; meanwhile, for the high frame rate image sensor, the image sensor parameters are further divided into odd frame image sensor parameters and even frame image sensor parameters, and are one-to-one corresponding to the first image signal processor and the second image signal processor, so that the image meeting the algorithm requirement and the image meeting the human perception requirement are independently adjusted, and the image meeting the algorithm requirement and the image meeting the human perception requirement can be output at the same time, so as to better meet the image use requirement of different vehicles in the current scene.

[0025] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and attained by the structure particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0027] Figure 1 A flowchart of an image processing method of a multi-image signal processor of a driving and parking integrated camera according to the present application is shown;

[0028] Figure 2 A flowchart of the first embodiment of the present application is shown;

[0029] Figure 3 A flowchart of the second embodiment of the present application is shown;

[0030] Figure 4 A structural diagram of an image processing device of a multi-image signal processor of a driving and parking integrated camera according to the present application is shown. DETAILED DESCRIPTION

[0031] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the drawings in the embodiments of the present application to clearly and completely explain the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0032] As Figure 1 shown, the present application provides an image processing method of a multi-image signal processor of a driving and parking integrated camera, specifically comprising the following steps:

[0033] acquiring a current image of the vehicle through an image sensor of the camera;

[0034] sending the current image to an image signal processor, the image signal processor acquiring current image parameters and optimizing the image parameters, the image signal processor processing the current image based on the optimized image parameters and calculating image sensor parameters that need to be adjusted, and feeding back the image sensor parameters that need to be adjusted to the image sensor to adjust the image sensor;

[0035] the image signal processor comprises a first image signal processor and a second image signal processor; the first image signal processor obtains a first image after processing the current image, the first image being provided to a driving or parking algorithm, and / or the second image signal processor obtains a second image after processing the current image, the second image being provided to a panoramic monitoring system.

[0036] Specifically, the image parameters of the acquired current image of the vehicle are images of the surroundings of the vehicle in the current scene, and the current vehicle current scene includes an intelligent driving scene, an intelligent driving and panoramic monitoring scene, a panoramic monitoring scene, an intelligent parking scene, and an intelligent parking and panoramic monitoring scene. Among them, the intelligent driving scene and the intelligent parking scene rely on program algorithm to control the driving and parking of the vehicle, so the images collected in the above two scenes only need to meet the needs of the perception algorithm; the panoramic monitoring scene relies on human control for parking, so the images collected in this scene only need to meet the needs of human perception; the intelligent driving and panoramic monitoring scene and the intelligent parking and panoramic monitoring scene also rely on program algorithm to control the driving and parking of the vehicle, and at the same time need to provide the driving and parking situation for the driver to view, that is, the program algorithm mainly controls the vehicle, and human assistance is auxiliary, so the images collected in the above two scenes need to meet the needs of the perception algorithm and human perception.

[0037] Specifically, in the embodiment of the present application, an image sensor is used to collect an image of the surroundings of the vehicle in the current scene of the vehicle, the image sensor outputs the current image to an image signal processor, the image signal processor adjusts the current image parameters according to the optimal image parameters sent by the main controller, and processes the image based on the adjusted image parameters; at the same time, the image signal processor calculates the parameters needed to be set to the image sensor according to the adjusted image parameters, and controls and adjusts the parameters of the image sensor, so as to make the current output image and the next frame of image output in the scene meet the requirements of the algorithm and / or human perception. The parameters of the image sensor include but are not limited to exposure time, exposure gain and white balance, and the parameters of the image sensor take effect at the image sensor end; the image parameters include brightness, color saturation, noise reduction, etc., and the optimal image parameters are the image parameters corresponding to the current scene of the vehicle and meeting the requirements of the algorithm or human perception.

[0038] It should be understood that, although Figure 1 the steps in the schematic diagram are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, Figure 1 at least part of the steps in the schematic diagram can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0039] As Figure 2 shown in the first embodiment of the present application, the current image is sent to the first image signal processor and the second image signal processor at the same time, wherein the first image signal processor and the second image signal processor use the same hardware channel to process the current image in time division multiplexing, and one of the first image signal processor and the second image signal processor obtains the image sensor parameters that need to be adjusted.

[0040] Specifically, the image sensor parameters are only one set, and the first image signal processor and the second image signal processor are configured with the same set of image sensor parameters. When the first image signal processor and the second image signal processor process images by using the same hardware channel, different requirements for image adjustment based on different current vehicle scenes, so when the current vehicle scene is switched, the image signal processor that controls the image sensor parameters needs to be specified to adjust the image sensor. The switching of the current vehicle scene is triggered by human, that is, the driver controls the vehicle to start the intelligent driving, intelligent parking or panoramic monitoring system. At the same time of triggering the scene switching by human, the main controller obtains the scene switching information, and according to the scene switching information, the best image parameters corresponding to the scene stored in the internal storage are sent to the image signal processor, and the current image is processed by the image signal processor.

[0041] Further, when the current vehicle scene is intelligent driving or intelligent parking, the first image signal processor is turned on, and the second image signal processor is turned off. At this time, the image is processed by the first image signal processor and the image sensor parameters that need to be adjusted are obtained. When the current vehicle scene is intelligent driving, the first image signal processor switches to the driving image parameters, and the driving image parameters are used as the best image parameters in the current vehicle scene to optimize the current image parameters. The current image is processed based on the optimized image parameters; when the current vehicle scene is intelligent parking, the first image signal processor switches to the intelligent parking image parameters, and the intelligent parking image parameters are used as the best image parameters in the current vehicle scene. The current image parameters are optimized based on the best image parameters corresponding to the current vehicle scene, and the current image is processed based on the optimized image parameters to obtain the first image. The first image is provided to the driving / parking algorithm to meet the requirements of the perception algorithm. At the same time, the first image signal processor calculates the image sensor parameters that need to be adjusted based on the optimized image parameters, and feeds back the image sensor parameters to the image sensor for adjustment, so that the next frame of image collected by the image sensor meets the requirements of the perception algorithm.

[0042] Further, when the current vehicle current scene is in manual parking, the first image signal processor is closed, and the second image signal processor is opened. At this time, the image is processed by the second image signal processor, and the image sensor parameter that needs to be adjusted is obtained. Based on the current vehicle current scene being manual parking, the second image signal processor switches to the panoramic monitoring image parameter, and the panoramic monitoring image parameter is taken as the best image parameter under the current vehicle current scene. The current image parameter is adjusted to the best image parameter level, and then the current image is processed to obtain a second image. The second image is provided to the panoramic monitoring system to meet the needs of human perception. At the same time, the second image signal processor calculates the image sensor parameter that needs to be adjusted according to the adjusted image parameter, and feeds back the image sensor parameter to the image sensor for adjustment, so that the image collected by the image sensor in the next frame meets the needs of human perception.

[0043] Further, when the current vehicle current scene is in intelligent driving and panoramic monitoring scene or intelligent parking and panoramic monitoring scene, the first image signal processor and the second image signal processor are both opened to process the image. Coupling occurs between the first image signal processor and the second image signal processor in the image sensor configuration, that is, only one image signal processor can be used to obtain the image sensor parameter that needs to be adjusted. When the first image signal processor needs to be started, the first image signal processor is taken as the main one, that is, the image that meets the needs of the perception algorithm is given priority. Therefore, when the current vehicle current scene is in intelligent driving and panoramic monitoring scene or intelligent parking and panoramic monitoring scene, the image sensor parameter that needs to be adjusted is obtained by the first image signal processor. Based on the current vehicle current scene being intelligent driving and panoramic monitoring scene, the first image signal processor switches to the driving image parameter, and the second image signal processor switches to the panoramic monitoring image parameter. Based on the current vehicle current scene being intelligent parking and panoramic monitoring scene, the first image signal processor switches to the intelligent parking image parameter, and the second image signal processor switches to the panoramic monitoring image parameter, and the intelligent parking image parameter is taken as the best image parameter under the current vehicle current scene. In the above two vehicle scenes, the first image signal processor and the second image signal processor both adjust the current image parameter according to the best image parameter corresponding to the current vehicle current scene. Based on the adjusted image parameter, the current image is processed. The first image signal processor processes the image to obtain a first image, which is provided to the driving / parking algorithm to meet the needs of the perception algorithm. At the same time, the second image signal processor processes the image to obtain a second image, which is provided to the panoramic monitoring system. Based on the above vehicle scene, the driving or parking is controlled by the intelligent driving system. The image collected by the image sensor finally needs to be provided to the driving / parking algorithm, so the image parameter that meets the needs of the algorithm is given priority. Therefore, at this time, the image sensor parameter is controlled by the first image signal processor, so that the image collected by the image sensor in the next frame meets the needs of the algorithm.

[0044] As Figure 3 shown in the second embodiment of the present application, the current image is sent to the first image signal processor and the second image signal processor simultaneously, wherein the first image signal processor and the second image signal processor process the current image by using different hardware paths, and the first image signal processor and / or the second image signal processor obtain the image sensor parameter that needs to be adjusted.

[0045] Further, the image sensor parameter includes the first image sensor parameter and the second image sensor parameter, the first image sensor parameter is controlled by the first image signal processor, and the second image sensor parameter is controlled by the second image signal processor; the image includes the odd frame image and the even frame image, the first image sensor parameter is the image sensor parameter of the odd frame image, and the second image sensor parameter is the image sensor parameter of the even frame image. For the high frame rate image sensor, for example, 60fps, the image sensor sends the odd frame image to the first image signal processor and sends the even frame image to the second image signal processor, and the first image signal processor and the second image signal processor process the image with half of the total frame rate, that is, 30fps.

[0046] Further, when the current vehicle is in the intelligent driving or intelligent parking scene, the first image signal processor is turned on, and the second image signal processor is turned off, at this time, the first image signal processor controls the processing of the odd frame current image and obtains the odd frame image sensor parameter that needs to be adjusted, and the specific implementation manner is the same as that in the intelligent driving or intelligent parking scene in the first embodiment.

[0047] Further, when the current vehicle is in the manual parking scene, the first image signal processor is turned off, and the second image signal processor is turned on, at this time, the second image signal processor processes the even frame current image and obtains the even frame image sensor parameter that needs to be adjusted, and the specific implementation manner is the same as that in the manual parking scene in the first embodiment.

[0048] Further, when the current scene of the current vehicle is in the intelligent driving and panoramic monitoring scene or the intelligent parking and panoramic monitoring scene, the first image signal processor and the second image signal processor are both started to process the current image, at this time, the first image signal processor optimizes and processes the first image of the odd frame of the current image, and the second image signal processor optimizes and processes the second image of the even frame of the current image. At this time, the first image signal processor and the second image signal processor are respectively configured with image sensor parameters, and when the current scene of the current vehicle is in the intelligent driving and panoramic monitoring scene or the intelligent parking and panoramic monitoring scene, the image sensor parameters are independently controlled by the first image signal processor and the second image signal processor. When the current scene of the current vehicle is in the intelligent driving and panoramic monitoring scene, the first image signal processor switches to the driving image parameters, adjusts the current image parameters according to the driving image parameters, and processes the image to obtain the first image provided to the driving / parking algorithm, and at the same time, the first image signal processor calculates the image sensor parameters of the odd frame of the image that need to be adjusted according to the optimized image parameters of the odd frame of the image, and feeds back the image sensor parameters of the odd frame of the image to the image sensor for adjustment, so that the image collected by the image sensor of the odd frame meets the requirement of the perception algorithm; the second image signal processor switches to the panoramic monitoring image parameters, adjusts the current image parameters according to the panoramic monitoring image parameters, and processes the image to obtain the second image provided to the panoramic monitoring system, and at the same time, the second image signal processor calculates the image sensor parameters of the even frame of the image that need to be adjusted according to the optimized image parameters of the even frame of the image, and feeds back the image sensor parameters of the even frame of the image to the image sensor for adjustment, so that the image collected by the image sensor of the even frame meets the requirement of human perception.

[0049] In the embodiment, the image output by the image sensor is divided into odd frame and even frame, wherein the odd frame image and the even frame image correspond to the first image signal processor and the second image signal processor respectively, the first image signal processor controls the odd frame image sensor parameters, and the second image signal processor controls the even frame image sensor parameters. Through the above technical solution, the first image signal processor and the second image signal processor can control the image sensor parameters without interfering with each other, that is, by setting two image signal processors and two sets of image sensor parameters, the independent adjustment of the image parameters meeting the requirements of the driving / parking algorithm and meeting the requirements of human perception can be realized, so that in the intelligent driving and panoramic monitoring scene or the intelligent parking and panoramic monitoring scene, the image meeting the algorithm requirement and the image meeting the human perception requirement can be output at the same time.

[0050] As shown in Figure 4 , the present application provides a kind of image processing device of multi-image signal processor of line parking integrated camera, comprising:

[0051] an image sensor configured to capture a current image of the vehicle and send the current image to an image signal processor;

[0052] an image signal processor configured to capture current image parameters and perform tuning, process the current image based on the tuned image parameters, and calculate image sensor parameters that need to be adjusted, and feed the image sensor parameters back to the image sensor to adjust the image sensor;

[0053] The image signal processor comprises a first image signal processor configured to process images to obtain a first image and provide the first image to a driving or parking algorithm, and / or a second image signal processor configured to process images to obtain a second image and provide the second image to a surround monitoring system.

[0054] The application also provides a vehicle comprising the image processing device of the integrated driving and parking camera multi-image signal processor as described above.

[0055] The application also provides a computer readable storage medium having a computer program stored thereon, which is executed by a processor to implement the image processing method of the integrated driving and parking camera multi-image signal processor as described above.

[0056] The computer readable medium described above in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be, for example and without limitation, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program used by or in connection with an instruction execution system, apparatus or device. In the present disclosure, the computer readable signal medium can include a computer readable program code propagated in or on a carrier wave, in baseband or as part of a carrier wave. Such a propagated computer readable signal medium can take many forms, including but not limited to, electro-magnetic, optical or any suitable combination thereof. Computer readable signal medium can be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. Program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to, wire, cable, RF, etc., or any suitable combination of the foregoing.

[0057] The computer readable medium described above can be included in the electronic device described above; or can exist separately from the electronic device, and can be accessed via the electronic device.

[0058] Computer program code for carrying out operations of the present disclosure can be written in any one or combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0059] Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood that modifications can be made to the foregoing embodiments, or additional implementations can be implemented, without departing from the spirit and scope of the inventive subject matter. Accordingly, the present application is not limited to the implementations described herein, but is intended to be defined by the claims set forth below, and equivalents thereof.

Claims

1. An image processing method of a multi-image signal processor of a camera for both driving and parking, characterized by, The method comprises the following steps: acquiring a current image of the vehicle by an image sensor of a camera; sending the current image to an image signal processor, which acquires current image parameters and optimizes the current image parameters; the image signal processor processes the current image based on the optimized image parameters and calculates image sensor parameters that need to be adjusted, and feeds back the image sensor parameters that need to be adjusted to the image sensor to adjust the image sensor; the image signal processor comprises a first image signal processor and a second image signal processor, the first image signal processor obtains a first image after processing the current image, and the first image is provided to a driving or parking algorithm, and / or the second image signal processor obtains a second image after processing the current image, and the second image is provided to a panoramic monitoring system; the current image is sent to the first image signal processor and the second image signal processor at the same time, wherein the first image signal processor and the second image signal processor process the current image by different hardware channels, and the first image signal processor and / or the second image signal processor obtain the image sensor parameters that need to be adjusted; the image sensor parameters comprise first image sensor parameters and second image sensor parameters, the first image sensor parameters are controlled by the first image signal processor, and the second image sensor parameters are controlled by the second image signal processor; the image comprises odd frame images and even frame images, the first image sensor parameters are image sensor parameters of the odd frame images, and the second image sensor parameters are image sensor parameters of the even frame images.

2. The image processing method of claim 1, wherein, when the current scene of the vehicle is switched to an intelligent driving scene or an intelligent parking scene, the second image signal processor is closed, the image is processed by the first image signal processor, and the image sensor parameters that need to be adjusted are obtained; when the current scene of the vehicle is switched to a panoramic monitoring scene, the first image signal processor is closed, the image is processed by the second image signal processor, and the image sensor parameters that need to be adjusted are obtained.

3. The image processing method of claim 1, wherein, when the current scene of the vehicle is switched to an intelligent driving and panoramic monitoring scene or an intelligent parking and panoramic monitoring scene, the image is processed by the first image signal processor and the second image signal processor, and the first image signal processor and the second image signal processor respectively obtain the image sensor parameters that need to be adjusted.

4. The image processing method of claim 1, wherein, The image sensor parameters comprise exposure time, exposure gain and white balance; and the image parameters comprise color saturation and brightness.

5. A kind of camera multi-image signal processor processing device of row and berth integration, it is characterized in that, The method comprises the following steps: an image sensor is used to acquire a current image of the vehicle and send the current image to an image signal processor; the image signal processor is used to acquire current image parameters and optimize the current image parameters, process the current image based on the optimized image parameters, calculate image sensor parameters that need to be adjusted, and feed back the image sensor parameters that need to be adjusted to the image sensor to adjust the image sensor; The image signal processor comprises a first image signal processor and a second image signal processor, the first image signal processor is used for processing a current image to obtain a first image, and providing the first image to a driving / parking algorithm, and / or the second image signal processor is used for processing the current image to obtain a second image, and providing the second image to a panoramic monitoring system; The current image is sent to the first image signal processor and the second image signal processor simultaneously, wherein the first image signal processor and the second image signal processor process the current image by using different hardware channels, and the first image signal processor and / or the second image signal processor obtains an image sensor parameter that needs to be adjusted; The image sensor parameter comprises a first image sensor parameter and a second image sensor parameter, the first image sensor parameter is controlled by the first image signal processor, and the second image sensor parameter is controlled by the second image signal processor; the image comprises an odd frame image and an even frame image, the first image sensor parameter is an image sensor parameter of the odd frame image, and the second image sensor parameter is an image sensor parameter of the even frame image.

6. A vehicle characterized by comprising: The application further discloses a driving / parking integrated camera multi-image signal processor processing device comprising the device as claimed in claim 5.

Images