Color gradation adjustment and identification system for front-end environment of intelligent automobile

By obtaining multiple data on the front-end environment of the smart car and customizing AI identification models, the problem that it is difficult for smart cars to identify whether images have been adjusted in color, and the reliability and stability of image identification in the front-end environment of the smart car are achieved.

CN118918054AActive Publication Date: 2024-11-08SUZHOU CHUANSHI BUILDING MATERIALS CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411154866.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-22
Publication Date
2024-11-08
Estimated Expiration
2044-08-22

AI Technical Summary

Technical Problem

It is difficult for existing smart car technology to clearly determine whether the acquisition component has turned on the color level adjustment process when acquiring front-end image frames, resulting in the inability to accurately identify whether the image has undergone color level adjustment process.

Method used

By obtaining the signal-to-noise ratio, maximum noise amplitude, number of noise types, number of targets present and percentage of maximum target area of ​​the field acquisition frame, and combining with the customized structure-designed AI identification model, multi-stage conversion components are used to perform convolutional neural networks through the use of multi-stage conversion components Multi-level conversion processing, filtering the type identification value of the color level adjustment processing type and the grayscale value of the standard pattern, to achieve intelligent identification of whether the image has undergone color level adjustment processing.

Benefits of technology

It provides reliable basic information and intelligent identification mechanism, ensuring the reliability and stability of intelligent identification results, and helping the image acquisition end to clarify the original content of the image.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a color gradation adjustment and identification system for a front-end environment of an intelligent automobile, and the system comprises an image capturing part which is fixed at the front end of the intelligent automobile, is used for carrying out the collection of a front-end image frame, and is used for obtaining and outputting a corresponding on-site collection frame; and the final-stage analysis mechanism is used for intelligently identifying whether the field acquisition frame is subjected to color gradation adjustment processing or not based on an AI identification model according to the picture data of each part of the field acquisition frame, the type identification value corresponding to the color gradation adjustment processing type and the gray value of each pixel point of the standard pattern processed by the color gradation adjustment processing type. According to the invention, based on various visual data of the field acquisition frame, the AI identification model with a customized structure design is adopted to intelligently identify whether the field acquisition frame is subjected to the color gradation adjustment processing type, so that the reliability and the stability of an intelligent identification result are ensured, and an image acquisition end is helped to clarify the original content of an image.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] The present invention relates to the field of intelligent automobiles, and in particular to a color scale adjustment and identification system for a front-end environment of an intelligent automobile. Background Art

[0002] Smart cars are cars that have advanced sensors (such as radars, cameras, etc.), controllers, actuators and other devices added to ordinary cars. Through the on-board environmental perception system and information terminals, they can exchange information with people, cars, roads, etc., so that cars have intelligent environmental perception capabilities, can automatically analyze the safety and danger status of car driving, and make the car reach the destination according to the wishes of people, and finally achieve the purpose of replacing people to operate. In general, smart cars are equipped with advanced sensing systems, decision-making systems, and execution systems, and use new technologies such as information communication, the Internet, big data, cloud computing, and artificial intelligence. They have partial or full automatic driving functions and are a new generation of cars that are gradually transformed from simple transportation tools to intelligent mobile spaces. Smart car technology is different from the generally referred to automatic driving technology. It refers to the automatic driving of cars using a variety of sensors and intelligent highway technology.

[0003] In the prior art, when a smart car uses its front-end to execute the front-end image frame acquisition action to obtain and output the corresponding on-site acquisition frame, even if it is known that the acquisition component that executes the acquisition action has an image processing function of color scale adjustment processing, it is still impossible to clearly determine at the acquisition end of the on-site acquisition frame whether the acquisition component has turned on the image processing function of color scale adjustment processing. It is difficult to identify whether the image has undergone color scale adjustment processing based on the image content. Summary of the invention

[0004] In order to solve the technical problems in the prior art, the present invention provides a color scale adjustment identification system for a front-end environment of an intelligent automobile. By obtaining the signal-to-noise ratio, maximum noise amplitude, number of noise types, number of existing targets and percentage of maximum target area of ​​a field acquisition frame, and outputting them as each piece of picture data of the field acquisition frame, reliable basic information is provided for intelligent identification of whether the field acquisition frame has been subjected to the color scale adjustment processing type. An AI identification model with a customized structure design is also adopted to provide an intelligent identification mechanism for intelligent identification of whether the field acquisition frame has been subjected to the color scale adjustment processing type. The customized structure is manifested in the introduction of a multi-level conversion component for performing multi-level conversion processing on a convolutional neural network to obtain an AI identification model. Each level of conversion processing performed on the convolutional neural network is each learning operation performed on the convolutional neural network. The multiple basic information screened for intelligent identification of whether the field acquisition frame has been subjected to the color scale adjustment processing also includes a type identification value corresponding to the color scale adjustment processing type and a grayscale value of each pixel of a standard pattern that has only been processed by the color scale adjustment processing type. The standard pattern has the same resolution as the field acquisition frame and corresponds to the image capture environment of the same front end of the intelligent automobile, thereby ensuring the reliability and stability of the intelligent identification result.

[0005] According to the present invention, a color scale adjustment and identification system for a front-end environment of an intelligent vehicle is provided, the system comprising: A multi-level conversion component, used for performing multi-level conversion processing on the convolutional neural network to obtain an AI identification model, wherein performing multi-level conversion processing on the convolutional neural network to obtain the AI ​​identification model includes: each level of conversion processing performed on the convolutional neural network is each learning operation performed on the convolutional neural network; An image capture component is fixed at the front end of the smart car to perform the front end image frame acquisition action, and is used to acquire and output the corresponding on-site acquisition frame; A primary analysis mechanism, connected to the image capture component, is used to obtain the signal-to-noise ratio, maximum noise amplitude, number of noise types, number of existing targets and percentage of maximum target area of ​​the field acquisition frame, and output it as each copy of the picture data of the field acquisition frame; A secondary parsing mechanism is used to extract a type identification value corresponding to a color scale adjustment processing type, wherein the type identification value is a binary coded value corresponding to a type name of the color scale adjustment processing type; The final analysis mechanism is connected to the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively, and is used to intelligently identify whether the scene acquisition frame has been processed by the color scale adjustment based on the AI ​​identification model according to each piece of picture data of the scene acquisition frame, the type identification value corresponding to the color scale adjustment processing type, and the grayscale value of each pixel point of the standard pattern that has only been processed by the color scale adjustment processing type; A real-time reminder mechanism, connected to the final analysis mechanism, for performing a real-time display operation on the intelligent identification result of the AI ​​identification model; Among them, based on the AI ​​identification model, according to each picture data of the scene acquisition frame, the type identification value corresponding to the color scale adjustment processing type and the grayscale value of each pixel point of the standard pattern that has only been processed by the color scale adjustment processing type, intelligently identify whether the scene acquisition frame has been processed by the color scale adjustment processing type, including: the standard pattern has the same resolution as the scene acquisition frame and corresponds to the same image capture environment of the front end of the smart car.

[0006] It can be seen that the present invention has at least the following three important inventive concepts: Firstly: the signal-to-noise ratio, maximum noise amplitude, number of noise types, number of existing targets and percentage of the maximum target area of ​​the scene acquisition frame are obtained and output as the data of each image of the scene acquisition frame, so as to provide reliable basic information for intelligent identification of whether the scene acquisition frame has been processed by color gradation adjustment; Secondly: an AI identification model with a customized structure design is used to provide an intelligent identification mechanism for intelligent identification of whether the scene acquisition frame has been processed by the color level adjustment type. Its customized structure is manifested in the introduction of a multi-level conversion component for performing multi-level conversion processing on the convolutional neural network to obtain an AI identification model. Each level of conversion processing performed on the convolutional neural network is each learning operation performed on the convolutional neural network. Again: the multiple basic information for intelligent identification of whether the on-site acquisition frame has undergone color scale adjustment processing also includes the type identification value corresponding to the color scale adjustment processing type and the grayscale value of each pixel of the standard pattern that has only been processed by the color scale adjustment processing type. The standard pattern has the same resolution as the on-site acquisition frame and corresponds to the image capture environment of the same smart car front end, thereby ensuring the reliability and stability of the intelligent identification results. DETAILED DESCRIPTION

[0007] The following is a detailed description of an embodiment of the color scale adjustment and identification system for a front-end environment of a smart car according to the present invention.

[0008] According to the first embodiment of the present invention, the color scale adjustment and identification system for the front-end environment of an intelligent vehicle includes: A multi-level conversion component, used for performing multi-level conversion processing on the convolutional neural network to obtain an AI identification model, wherein performing multi-level conversion processing on the convolutional neural network to obtain the AI ​​identification model includes: each level of conversion processing performed on the convolutional neural network is each learning operation performed on the convolutional neural network; Specifically, performing multi-level conversion processing on the convolutional neural network to obtain the AI ​​identification model includes: each level of conversion processing performed on the convolutional neural network for each learning operation performed on the convolutional neural network includes: selecting a numerical simulation mode to implement simulation and testing of a data processing process for each learning operation performed on the convolutional neural network; An image capture component is fixed at the front end of the smart car to perform the front end image frame acquisition action, and is used to acquire and output the corresponding on-site acquisition frame; A primary analysis mechanism, connected to the image capture component, is used to obtain the signal-to-noise ratio, maximum noise amplitude, number of noise types, number of existing targets and percentage of maximum target area of ​​the field acquisition frame, and output it as each copy of the picture data of the field acquisition frame; A secondary parsing mechanism is used to extract a type identification value corresponding to a color scale adjustment processing type, wherein the type identification value is a binary coded value corresponding to a type name of the color scale adjustment processing type; The final analysis mechanism is connected to the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively, and is used to intelligently identify whether the scene acquisition frame has been processed by the color scale adjustment based on the AI ​​identification model according to each piece of picture data of the scene acquisition frame, the type identification value corresponding to the color scale adjustment processing type, and the grayscale value of each pixel point of the standard pattern that has only been processed by the color scale adjustment processing type; A real-time reminder mechanism, connected to the final analysis mechanism, for performing a real-time display operation on the intelligent identification result of the AI ​​identification model; Among them, based on the AI ​​identification model, intelligently identifying whether the scene acquisition frame has been processed by the color scale adjustment according to each piece of picture data of the scene acquisition frame, the type identification value corresponding to the color scale adjustment processing type, and the grayscale value of each pixel point of the standard pattern that has only been processed by the color scale adjustment processing type includes: the standard pattern has the same resolution as the scene acquisition frame and corresponds to the same image capture environment of the front end of the smart car; And wherein, based on the AI ​​identification model, intelligently identifying whether the scene acquisition frame has undergone color scale adjustment processing according to each picture data of the scene acquisition frame, the type identification value corresponding to the color scale adjustment processing type, and the grayscale value of each pixel point of the standard pattern that has only been processed by the color scale adjustment processing type also includes: using different identification data to separately indicate whether the scene acquisition frame has undergone color scale adjustment processing.

[0009] Different from the first embodiment of the present invention, the color scale adjustment and identification system for the front-end environment of an intelligent vehicle according to the second embodiment of the present invention may further include the following components: a current detection device, arranged near the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism, and the secondary analysis mechanism and connected to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism, and the secondary analysis mechanism, respectively; Among them, the current detection device is arranged in the vicinity of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism and is respectively connected to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism, including: the current detection device is used to respectively realize the on-site measurement of the current of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism.

[0010] Different from the first embodiment of the present invention, the color scale adjustment and identification system for the front-end environment of an intelligent vehicle according to the third embodiment of the present invention may further include the following components: a bandwidth detection device, arranged near the final analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism and connected to the final analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively; Among them, the bandwidth detection device is arranged in the vicinity of the final analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism and is respectively connected to the final analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism, including: the bandwidth detection device is used to realize on-site measurement of the current bandwidth of the final analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively.

[0011] Next, the specific structure of the color scale adjustment and identification system for the front-end environment of a smart car of the present invention will be further described.

[0012] In the color scale adjustment identification system for a front-end environment of an intelligent vehicle according to any embodiment of the present invention: A field programmable gate array is used to perform image data processing on the output data of the final-stage parsing mechanism, the multi-stage conversion component, the primary parsing mechanism and the secondary parsing mechanism to obtain output processing data corresponding to the final-stage parsing mechanism, the multi-stage conversion component, the primary parsing mechanism and the secondary parsing mechanism respectively.

[0013] In the color scale adjustment identification system for a front-end environment of an intelligent vehicle according to any embodiment of the present invention: Using a field programmable gate array to perform image data processing on the output data of the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism to obtain the output processing data corresponding to the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism respectively includes: performing statistical sorting filtering on the output data of the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism to obtain the output processing data corresponding to the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism respectively.

[0014] In the color scale adjustment identification system for a front-end environment of an intelligent vehicle according to any embodiment of the present invention: Using a field programmable gate array to perform image data processing on the output data of the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism to obtain the output processing data corresponding to the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism respectively includes: performing gradient sharpening filtering on the output data of the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism to obtain the output processing data corresponding to the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism respectively.

[0015] In the color scale adjustment identification system for a front-end environment of an intelligent vehicle according to any embodiment of the present invention: Using a field programmable gate array to perform image data processing on the output data of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism to obtain the output processing data corresponding to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively includes: performing Butterworth low-pass filtering on the output data of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism to obtain the output processing data corresponding to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively.

[0016] And in a color scale adjustment identification system for a front-end environment of a smart car according to any embodiment of the present invention: A field programmable gate array is used to perform image data processing on the output data of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism to obtain the output processing data corresponding to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively, including: performing Gaussian high-pass filtering on the output data of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism to obtain the output processing data corresponding to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively.

[0017] In addition, in the color scale adjustment identification system for the front-end environment of a smart car, the final analysis mechanism is respectively connected to the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism, and is used to intelligently identify whether the field acquisition frame has undergone color scale adjustment processing based on the AI ​​identification model according to each piece of picture data of the field acquisition frame, the type identification value corresponding to the color scale adjustment processing type, and the grayscale value of each pixel point of the standard pattern that has only been processed by the color scale adjustment processing type, including: selecting a numerical simulation method to realize simulation and testing of the AI ​​identification model.

[0018] The color scale adjustment identification system for the front-end environment of a smart car of the present invention is used to address the technical problem in the prior art that it is impossible to accurately identify whether an image has been processed with color scale adjustment by analyzing the image content. An AI identification model with a customized structure is used based on various visualization data of the on-site acquisition frame to intelligently identify whether the on-site acquisition frame has been processed with color scale adjustment, thereby ensuring the reliability and stability of the intelligent identification results, helping the image acquisition end to clarify the original content of the image, and thus solving the above technical problem.

[0019] While the invention has been particularly shown and described with reference to exemplary embodiments, it will be understood by those skilled in the art that various changes in form and details may be made without departing from the spirit and scope of the invention as defined in the following claims.

Claims

1. A color scale adjustment and identification system for the front-end environment of intelligent vehicles, It is characterized in that The system comprises: A multi-level conversion component, used for performing multi-level conversion processing on the convolutional neural network to obtain an AI identification model, wherein performing multi-level conversion processing on the convolutional neural network to obtain the AI ​​identification model includes: each level of conversion processing performed on the convolutional neural network is each learning operation performed on the convolutional neural network; An image capture component is fixed at the front end of the smart car to perform the front end image frame acquisition action, and is used to acquire and output the corresponding on-site acquisition frame; A primary analysis mechanism, connected to the image capture component, is used to obtain the signal-to-noise ratio, maximum noise amplitude, number of noise types, number of existing targets and percentage of maximum target area of ​​the field acquisition frame, and output it as each copy of the picture data of the field acquisition frame; A secondary parsing mechanism is used to extract a type identification value corresponding to a color scale adjustment processing type, wherein the type identification value is a binary coded value corresponding to a type name of the color scale adjustment processing type; The final analysis mechanism is connected to the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively, and is used to intelligently identify whether the scene acquisition frame has been processed by the color scale adjustment based on the AI ​​identification model according to each piece of picture data of the scene acquisition frame, the type identification value corresponding to the color scale adjustment processing type, and the grayscale value of each pixel point of the standard pattern that has only been processed by the color scale adjustment processing type; A real-time reminder mechanism, connected to the final analysis mechanism, for performing a real-time display operation on the intelligent identification result of the AI ​​identification model; Among them, based on the AI ​​identification model, according to each picture data of the scene acquisition frame, the type identification value corresponding to the color scale adjustment processing type and the grayscale value of each pixel point of the standard pattern that has only been processed by the color scale adjustment processing type, intelligently identify whether the scene acquisition frame has been processed by the color scale adjustment processing type, including: the standard pattern has the same resolution as the scene acquisition frame and corresponds to the same image capture environment of the front end of the smart car.

2. The color scale adjustment and identification system for the front-end environment of an intelligent vehicle as claimed in claim 1, Features: Based on the AI ​​identification model, intelligently identifying whether the field acquisition frame has undergone color scale adjustment processing according to the picture data of each part of the field acquisition frame, the type identification value corresponding to the color scale adjustment processing type, and the grayscale value of each pixel point of the standard pattern that has only been processed by the color scale adjustment processing type also includes: using different identification data to separately indicate whether the field acquisition frame has undergone color scale adjustment processing.

3. The color scale adjustment and identification system for the front-end environment of an intelligent vehicle as claimed in claim 2, It is characterized in that The system further comprises: a current detection device, arranged near the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism, and the secondary analysis mechanism and connected to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism, and the secondary analysis mechanism, respectively; Among them, the current detection device is arranged in the vicinity of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism and is respectively connected to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism, including: the current detection device is used to respectively realize the on-site measurement of the current of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism.

4. The color scale adjustment and identification system for the front-end environment of an intelligent vehicle as claimed in claim 2, It is characterized in that The system further comprises: a bandwidth detection device, arranged near the final analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism and connected to the final analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively; Among them, the bandwidth detection device is arranged in the vicinity of the final analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism and is respectively connected to the final analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism, including: the bandwidth detection device is used to realize on-site measurement of the current bandwidth of the final analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively.

5. The color scale adjustment and identification system for the front-end environment of an intelligent vehicle as claimed in any one of claims 2 to 4, Features: A field programmable gate array is used to perform image data processing on the output data of the final-stage parsing mechanism, the multi-stage conversion component, the primary parsing mechanism and the secondary parsing mechanism to obtain output processing data corresponding to the final-stage parsing mechanism, the multi-stage conversion component, the primary parsing mechanism and the secondary parsing mechanism respectively.

6. The color scale adjustment and identification system for the front-end environment of an intelligent vehicle as claimed in claim 5, Features: Using a field programmable gate array to perform image data processing on the output data of the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism to obtain the output processing data corresponding to the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism respectively includes: performing statistical sorting filtering on the output data of the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism to obtain the output processing data corresponding to the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism respectively.

7. The color scale adjustment and identification system for the front-end environment of an intelligent vehicle as claimed in claim 5, Features: Using a field programmable gate array to perform image data processing on the output data of the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism to obtain the output processing data corresponding to the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism respectively includes: performing gradient sharpening filtering on the output data of the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism to obtain the output processing data corresponding to the final-level parsing mechanism, the multi-level conversion component, the primary parsing mechanism and the secondary parsing mechanism respectively.

8. The color scale adjustment and identification system for the front-end environment of an intelligent vehicle as claimed in claim 5, Features: Using a field programmable gate array to perform image data processing on the output data of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism to obtain the output processing data corresponding to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively includes: performing Butterworth low-pass filtering on the output data of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism to obtain the output processing data corresponding to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively.

9. The color scale adjustment and identification system for the front-end environment of an intelligent vehicle as claimed in claim 5, Features: A field programmable gate array is used to perform image data processing on the output data of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism to obtain the output processing data corresponding to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively, including: performing Gaussian high-pass filtering on the output data of the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism to obtain the output processing data corresponding to the final-stage analysis mechanism, the multi-stage conversion component, the primary analysis mechanism and the secondary analysis mechanism respectively.

Citation Information

Patent Citations

  • Field information recognition feedback system

    CN110310515A

  • Image processing method and device, electronic equipment and storage medium

    CN111563517A

  • Image correction method and device and computer storage medium

    CN116071254A

  • Image processing apparatus, image processing method, and program

    JP2010003244A

  • Display device and control method of the same

    JP2014179875A