Image processing method and system based on intelligent calculation and data exchange

Abstract

The invention provides an image processing method and system based on intelligent calculation and data exchange, and the method comprises the steps: S1, collecting an image data signal, preprocessing the image data signal, and obtaining image data; s2, processing the image data to obtain a processing result; s3, searching and identifying the task area according to the processing result, judging whether a threat target exists or not, if so, identifying the threat target, tracking the threat target, and reporting the level of the threat target; if not, not processing; and distributing and transmitting image data according to the processing result. According to the invention, multi-core data processing, image preprocessing and data exchange technologies are adopted, so that the data exchange of the whole system is more flexible, the real-time performance is strong, and the network transmission function is stronger.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent computing technology, and in particular, relates to an image processing method and system based on intelligent computing and data exchange, and more particularly, to an image processing system technology based on intelligent computing and data exchange. Background Art

[0002] Traditional image processing modules generally use a single-core structure, perform simple data processing, and have relatively independent functions, and are unable to perform intelligent computing on data. When an external processor requires different image data, it is impossible to assign tasks to the data, and data cannot be exchanged between different processors. In addition, due to the limitations of traditional image processing modules, when fast remote data exchange and transmission is required, the module cannot meet the requirements.

[0003] In the real-time data image processing system, the real-time and reliability requirements for the system data processing are very high. Not only is the image data required to be processed in real time, but the image data also needs to be assigned tasks. The image data processing module has the ability to quickly exchange remotely, which requires the system to have strong real-time, variability and reliability.

[0004] Therefore, how to realize multi-tasking and fast remote data exchange and transmission in the relatively functionally independent system of general image signal processing has become a research direction.

[0005] Patent document CN105578012A discloses a high-performance embedded camera system based on a general-purpose CPU of the X86 platform. The solution includes: a front-end sensor module, an FPGA information acquisition module, and an X86 architecture information main processing module; the front-end sensor module transmits the collected image data to the FPGA information acquisition module; the FPGA information acquisition module converts and processes the image data and sends it to the X86 architecture information main processing module for information processing; the X86 architecture information main processing module extracts preset demand information after information processing and transmits it to the data receiving end. The solution proposes a high-performance embedded camera system based on a general-purpose CPU of the X86 platform, which uses the general-purpose CPU of the x86 architecture as a platform for high-definition information processing, instead of a dedicated embedded digital DSP chip, thereby reducing the difficulty of system development, reducing the product development cycle, and reducing the requirements for professionals. However, the solution does not solve the technical problems of low system flexibility, poor real-time performance, and poor network transmission function.

[0006] This problem needs to be solved urgently. Summary of the invention

[0007] In view of the defects in the prior art, the object of the present invention is to provide an image processing method and system based on intelligent computing and data exchange.

[0008] According to the present invention, an image processing method based on intelligent computing and data exchange includes:

[0009] Step S1: collecting image data signals, preprocessing the image data signals, and obtaining image data;

[0010] Step S2: Processing the image data to obtain a processing result;

[0011] Step S3: Based on the processing result, search and identify the task area to determine whether there is a threat target. If the result is yes, identify the threat target, track the threat target, and report the level of the threat target; if the result is no, do not process it; based on the processing result, allocate and transmit the image data.

[0012] Preferably, in the step S1, the image data signal is pre-processed, that is, the image data signal is input into the FPGA chip XC7K325T through the Cameralink chip for image processing; the image processing includes image coding and image enhancement.

[0013] Preferably, the step S2 includes:

[0014] Step S2.1: feature extracting the image data to obtain a data processing result;

[0015] Step S2.2: forwarding the data processing result, and then interacting with the outside to obtain the processing result;

[0016] The data processing result includes a feature quantity;

[0017] In the step S3, the data in the database are compared with the feature value to obtain a comparison result, and then the task area is searched and identified according to the comparison result;

[0018] The determination of whether there is a threat target is to determine whether the comparison value between the characteristic quantity and the data in the database is greater than a predetermined threshold. If yes, it is listed as a threat target and the optoelectronic device is commanded to track it; if no, no processing is performed.

[0019] Preferably, in the step S3, the level of the threat target is divided based on the comparison value;

[0020] The threat targets include low threat targets and high threat targets;

[0021] The contrast value corresponding to the low threat target is lower than the contrast value corresponding to the high threat target.

[0022] According to the present invention, an image processing system based on intelligent computing and data exchange is provided, comprising:

[0023] Instructing the image processing unit to collect image data signals, pre-process the image data signals, and obtain image data;

[0024] Instructing the image processing unit to process the image data to obtain a processing result;

[0025] The signal processing unit is instructed to search and identify the task area according to the processing result to determine whether there is a threat target. If the result is yes, the threat target is identified, tracked, and the level of the threat target is reported; if the result is no, no processing is performed; and according to the processing result, image data is allocated and transmitted.

[0026] Preferably, in the image processing unit, the image data signal is pre-processed, that is, the image data signal is input into the FPGA chip XC7K325T through the Cameralink chip for image processing; the image processing includes image encoding and image enhancement.

[0027] Preferably, the image processing unit includes:

[0028] The first image processing subunit is used to extract features from the image data and obtain a data processing result;

[0029] The second image processing subunit is used to forward the data processing result, and then to perform external interactive processing to obtain the processing result;

[0030] The data processing result includes a feature quantity;

[0031] In the signal processing unit, the data in the database are compared with the feature quantity to obtain a comparison result, and then the task area is searched and identified according to the comparison result;

[0032] The determination of whether there is a threat target is to determine whether the comparison value between the characteristic quantity and the data in the database is greater than a predetermined threshold. If yes, it is listed as a threat target and the optoelectronic device is commanded to track it; if no, no processing is performed.

[0033] Preferably, in the signal processing unit, the level of the threat target is divided based on the comparison value;

[0034] The threat targets include low threat targets and high threat targets;

[0035] The contrast value corresponding to the low threat target is lower than the contrast value corresponding to the high threat target.

[0036] According to a computer-readable storage medium storing a computer program provided by the present invention, when the computer program is executed by a processor, the steps of the image processing method based on intelligent computing and data exchange are implemented.

[0037] An electronic device provided according to the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the image processing method based on intelligent computing and data exchange are implemented.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. The present invention adopts a high-performance CPU chip and an image preprocessing core chip XC7K325T as the core, and cooperates with PCIE switching and Ethernet switching circuits to combine into a universal intelligent image processing and switching method.

[0040] 2. The present invention adopts multi-core data processing, image preprocessing and data exchange methods, making the data exchange of the entire system more flexible, real-time and the network transmission function more powerful.

[0041] 3. The present invention distributes tasks to image data, and the image data processing module has the capability of remote and rapid exchange, and has strong variability and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0043] Figure 1 A schematic diagram of the hardware structure provided by the present invention;

[0044] Figure 2 A schematic diagram of the data flow provided by the present invention;

[0045] The figure shows:

[0046] Signal processing unit 1 Image processing module 7

[0047] Image processing unit 2 Image acquisition module 8

[0048] Data exchange unit 3 First data exchange module 9

[0049] Ethernet switching unit 4 Second data switching module 10

[0050] First data processing module 5

[0051] Second data processing module 6 DETAILED DESCRIPTION

[0052] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0053] According to the present invention, an image processing system based on intelligent computing and data exchange is provided, comprising: a CPU, namely a data signal processing unit, an FPGA, namely an image processing unit, a PCIE, namely a switching unit, and an Ethernet switching unit.

[0054] A data signal processing device, comprising: a CPU core chip RK3399 and a CPU core chip RK1808;

[0055] Image processing unit, including: XC7K325T chip, Cameralink chip;

[0056] The data interaction unit includes: a PEX8619 chip, a BCM5396 chip and an 88E1111 chip.

[0057] As a preferred solution, the data processing core chips RK3399 and RK1808 are used to process and forward the received image data. The image signal preprocessing is implemented by the FPGA chip XC7K325T. The data transmission and interactive processing core chips are implemented by PEX8619 and BCM5396. The image signal is input to the FPGA for processing through the Cameralink chip.

[0058] As a preferred solution, the operating system and file system applications mainly run on RK3399 and RK1808, and the FPGA contains corresponding IP cores such as PCIE, image processing and Ethernet.

[0059] According to the present invention, an image processing method based on intelligent computing and data exchange includes:

[0060] Step S1: collecting image data signals, preprocessing the image data signals, and obtaining image data;

[0061] Step S2: Processing the image data to obtain a processing result;

[0062] Step S3: Based on the processing result, search and identify the task area to determine whether there is a threat target. If the result is yes, identify the threat target, track the threat target, and report the level of the threat target; if the result is no, do not process it; based on the processing result, allocate and transmit the image data.

[0063] In the step S1, the image data signal is preprocessed, specifically referring to: the image acquisition module inputs the image information to the FPGA chip XC7K325T through the Cameralink chip for image processing, including image enhancement and image encoding.

[0064] In the step S2, processing the image data specifically refers to the following operations: the first data processing module RK3399 performs feature extraction and image recognition on the received encoded and pre-processed image data, and the second data processing module RK1808 is used to forward the received image data and perform external interactive processing through the Ethernet switching unit BCM5396.

[0065] In the step S3, the task area is searched and identified according to the processing result, which is specifically achieved as follows: the feature quantity is compared with the database data according to the feature extraction of the target in the image data.

[0066] Identifying threat targets and tracking them is specifically achieved by extracting features of the target from image data and comparing the features with the database data. If the comparison result, i.e., the comparison value, is greater than a predetermined threshold, it is listed as a threat target and fed back to the optoelectronic device for tracking.

[0067] The levels of threat targets are specifically divided as follows: based on the comparison results and the threshold classification, the levels of threat targets are divided into: low threat targets and high threat targets.

[0068] In other words, the levels of the threat targets are divided based on the comparison values; the threat targets include low threat targets and high threat targets; and the comparison values ​​corresponding to the low threat targets are lower than the comparison values ​​corresponding to the high threat targets.

[0069] The steps of allocating and transmitting image data are specifically implemented as follows: if the target is a threat target or receives a data forwarding instruction, the second data processing module RK1808 transmits the processed image data to the outside through the Ethernet switching unit BCM5396, aiming to re-extract the target characteristics of the data sample to update the target sample database.

[0070] According to the present invention, an image processing system based on intelligent computing and data exchange combines the advantages of CPU, FPGA and PCIE Switch, including: signal processing unit, image processing unit, data exchange unit, Ethernet switching unit. It forms a multi-core structure of image preprocessing, image processing, image transmission, etc., with independent functions. It overcomes the shortcomings of the previous image processing system, such as single function, low flexibility, no remote fast exchange capability, poor real-time performance, and difficulty in updating the database system.

[0071] The signal processing unit is connected to the data exchange unit; the data exchange unit is connected to the image processing unit; and the data exchange unit is connected to the Ethernet switching unit.

[0072] Specifically, the signal processing unit implements image data processing, mainly completing target recognition and target tracking.

[0073] The signal processing unit includes: a first data processing module and a second data processing module.

[0074] Specifically, the image processing unit implements image data preprocessing, and includes: an image processing module and an image acquisition module.

[0075] Specifically, the data exchange unit realizes the transmission and interaction of image data, and includes: a first data exchange module and a second data exchange module.

[0076] Specifically, according to the image processing system based on intelligent computing and data exchange provided by the present invention, the first data processing module adopts the data processing core chip RK3399 to process the received image data, the second data processing module adopts RK1808 to forward the received image data, the image processing module is implemented by the FPGA chip XC7K325T, the image acquisition module inputs the image to the FPGA for processing through the Cameralink chip, the data interaction unit adopts the chip PEX8619 to transmit data, and the Ethernet switching unit adopts the chip BCM5396 for interaction processing.

[0077] Specifically, the operating system and file system applications run on RK3399 and RK1808, and the FPGA contains corresponding IP cores such as PCIE, image processing and Ethernet.

[0078] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0079] Figure 1 The schematic diagram of the hardware structure of an image processing system based on intelligent computing and data exchange technology.

[0080] In this embodiment, Figure 1 As shown, according to the present invention, an image processing system based on intelligent computing and data exchange is provided, which includes a CPU data signal processing unit, an FPGA image processing unit, a PCIE switching unit, and an Ethernet switching unit, which includes data transmission methods, interconnection relationships, interface methods, and configuration relationships.

[0081] Among them, the data processing core chip RK3399 and chip RK1808 are used to process and forward the received image data. The image signal preprocessing is implemented by the FPGA chip XC7K325T. The data transmission and interactive processing core chips are implemented by PEX8619 and BCM5396. The image signal is input to the FPGA for processing through the Cameralink chip.

[0082] Figure 2 This is a data flow chart of an image processing system technology based on intelligent computing and data exchange. Photoelectric identification and tracking and automatic search and alert are the main tasks, and manual remote control is an auxiliary task.

[0083] The basic process is automatic search and identification, information reporting, or guidance into tracking and identification mode.

[0084] In the absence of an alert, the optoelectronic search system will first automatically search the defense area of ​​the position, track the target after it is found, and identify the target, rank the threats, and report them to the system;

[0085] When there is an alarm, the optoelectronic equipment receives the situation information and adjusts the optoelectronic equipment to track and identify the target according to the threat level, and then determines the threat level of the target again and reports it to the system.

[0086] The operating system and file system applications mainly run on the RK3399 chip and the RK1808 chip. The FPGA contains the corresponding IP cores such as PCIE, image processing and Ethernet.

[0087] The system mainly provides video and data interfaces, and provides a hardware platform for image acquisition, preprocessing, and recognition, and cooperates with software to achieve image recognition and tracking requirements. The main functional modules are as follows: power supply, FPGA chip, RK3399 chip, RK1808 chip, PEX8619 chip, BCM5396 chip and image input processing module.

[0088] The present invention also provides an image processing system based on intelligent computing and data exchange. The image processing system based on intelligent computing and data exchange can be realized by executing the process steps of the image processing method based on intelligent computing and data exchange, that is, those skilled in the art can understand the image processing method based on intelligent computing and data exchange as a preferred implementation of the image processing system based on intelligent computing and data exchange.

[0089] According to the present invention, an image processing system based on intelligent computing and data exchange is provided, comprising:

[0090] Instructing the image processing unit to collect image data signals, pre-process the image data signals, and obtain image data;

[0091] Instructing the image processing unit to process the image data to obtain a processing result;

[0092] The signal processing unit is instructed to search and identify the task area according to the processing result to determine whether there is a threat target. If the result is yes, the threat target is identified, tracked, and the level of the threat target is reported; if the result is no, no processing is performed; and according to the processing result, image data is allocated and transmitted.

[0093] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0094] In the description of the present application, it should be understood that the terms "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0095] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. An image processing method based on intelligent computing and data exchange, characterized in that: include: Step S1: collecting image data signals, preprocessing the image data signals, and obtaining image data; Step S2: Processing the image data to obtain a processing result; Step S3: searching and identifying the task area according to the processing result to determine whether there is a threat target. If yes, identifying the threat target, tracking the threat target, and reporting the level of the threat target; If the result is no, no processing is performed; according to the processing result, the image data is allocated and transmitted.

2. The image processing method based on intelligent computing and data exchange according to claim 1, characterized in that: In the step S1, the image data signal is pre-processed, that is, the image data signal is input into the FPGA chip XC7K325T through the Cameralink chip for image processing; the image processing includes image coding and image enhancement.

3. The image processing method based on intelligent computing and data exchange according to claim 1, characterized in that: In the step S2, it includes: Step S2.1: feature extracting the image data to obtain a data processing result; Step S2.2: forwarding the data processing result, and then interacting with the outside world to obtain the processing result; The data processing result includes a feature quantity; In the step S3, the data in the database are compared with the feature value to obtain a comparison result, and then the task area is searched and identified according to the comparison result; The determination of whether there is a threat target is to determine whether the comparison value between the characteristic quantity and the data in the database is greater than a predetermined threshold. If yes, it is listed as a threat target and the optoelectronic device is commanded to track it; if no, no processing is performed.

4. The image processing method based on intelligent computing and data exchange according to claim 3 is characterized in that: In the step S3, the level of the threat target is divided based on the comparison value; The threat targets include low threat targets and high threat targets; The contrast value corresponding to the low threat target is lower than the contrast value corresponding to the high threat target.

5. An image processing system based on intelligent computing and data exchange, characterized in that: include: Instructing the image processing unit to collect image data signals, pre-process the image data signals, and obtain image data; Instructing the image processing unit to process the image data to obtain a processing result; Instruct the signal processing unit to search and identify the task area according to the processing result, and determine whether there is a threat target. If yes, identify the threat target, track the threat target, and report the level of the threat target; If the result is no, no processing is performed; according to the processing result, the image data is allocated and transmitted.

6. The image processing system based on intelligent computing and data exchange according to claim 5, characterized in that: In the image processing unit, the image data signal is pre-processed, that is, the image data signal is input into the FPGA chip XC7K325T through the Cameralink chip for image processing; the image processing includes image coding and image enhancement.

7. The image processing system based on intelligent computing and data exchange according to claim 5, characterized in that: The image processing unit includes: The first image processing subunit is used to extract features from the image data and obtain a data processing result; The second image processing subunit is used to forward the data processing result, and then to perform external interactive processing to obtain the processing result; The data processing result includes a feature quantity; In the signal processing unit, the data in the database are compared with the feature quantity to obtain a comparison result, and then the task area is searched and identified according to the comparison result; The determination of whether there is a threat target is to determine whether the comparison value between the characteristic quantity and the data in the database is greater than a predetermined threshold. If yes, it is listed as a threat target and the optoelectronic device is commanded to track it; if no, no processing is performed.

8. The image processing system based on intelligent computing and data exchange according to claim 7, characterized in that: In the signal processing unit, the level of the threat target is divided based on the comparison value; The threat targets include low threat targets and high threat targets; The contrast value corresponding to the low threat target is lower than the contrast value corresponding to the high threat target.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the image processing method based on intelligent computing and data exchange described in any one of claims 1 to 4 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by a processor, the steps of the image processing method based on intelligent computing and data exchange described in any one of claims 1 to 4 are implemented.

Images