Simulation verification test system for edge intelligent information generation

Abstract

The invention belongs to the technical field of signal generation and edge intelligent processing, and particularly relates to a simulation verification test system for edge intelligent information generation. The system comprises a signal generation module used for generating a video signal in a CameraLink format as edge intelligent information according to a preset image resolution, color depth and a signal modulation function, and outputting the video signal to an edge intelligent platform to be tested; the signal conversion module is used for carrying out acquisition and format conversion on the video signal in the CameraLink format; the signal analysis module is used for analyzing the collected video signals, calculating key evaluation indexes, generating a test report and performing alarm processing when the signals are abnormal; and the control and configuration module is used for providing an interface, receiving configuration parameters input by a user and monitoring a test process.

Description

Technical Field

[0001] The present invention belongs to the technical field of signal generation and edge intelligent processing, and specifically relates to a simulation verification test system for edge intelligent information generation. Background Art

[0002] With the rapid development of aerospace technology, the number of deep space exploration missions is increasing, which puts higher requirements on the accuracy and real-time performance of target detection. As an emerging computing model, edge intelligence technology effectively reduces data transmission delay and improves processing efficiency by sinking computing tasks to network edge devices. It is particularly suitable for scenarios with limited resources and high communication delays in deep space exploration. However, in practical applications, the development and verification of edge intelligence algorithms face many challenges, mainly including:

[0003] Difficulty in obtaining real data: The deep space environment is complex and changeable, and target characteristics are diverse. It is almost impossible to obtain real data covering all possible situations.

[0004] The experimental environment is complex to build: Deep space exploration systems usually involve multiple subsystems working together, and simulating real environments for algorithm verification is costly and technically difficult.

[0005] Insufficient algorithm verification: Due to data and environmental limitations, algorithms are often not fully verified before actual deployment, increasing the risk of system failure.

[0006] Therefore, it is particularly important to design a test system that can simulate deep space environments, generate diverse video signals, and support efficient verification of edge intelligence algorithms. Summary of the invention

[0007] The present invention provides a simulation verification test system for edge intelligent information generation, which aims to solve the problems of insufficient algorithm verification and inaccurate data processing capability evaluation caused by limitations such as difficulty in obtaining real data and complex experimental environment construction during edge computing platform development and algorithm verification.

[0008] The technical solution for implementing the present invention is as follows:

[0009] The embodiment of the present application provides a simulation verification test system for edge intelligent information generation, including a signal generation module, a signal conversion module, a signal analysis module, and a control and configuration module, wherein:

[0010] A signal generation module is used to generate a video signal in CameraLink format as edge intelligence information according to a preset image resolution, color depth, and signal modulation function, and output it to the edge intelligence platform to be tested;

[0011] A signal conversion module, used for collecting and converting the video signal in the CameraLink format;

[0012] The signal analysis module is used to analyze the collected video signals and calculate key evaluation indicators, generate test reports, and perform alarm processing when the signal is abnormal;

[0013] The control and configuration module is used to provide an interface, receive configuration parameters input by the user, and monitor the test process.

[0014] Furthermore, the specific process of the signal generation module of the present invention generating the video signal in the CameraLink format is as follows:

[0015] Assume that the image data matrix is ​​I, where I(i,j,k) represents the pixel value of the i-th row, j-th column, and k-th color channel, then the image data generation can be expressed as:

[0016] I(i,j,k)=G(i,j,k;M,N,D)

[0017] Among them, G is the image data generation function, and M, N, and D are the resolution and color depth of the image respectively.

[0018] Assuming the signal modulation function in the time domain is f(t), each pixel value in the image data matrix can be expressed as:

[0019] I'(i,j,k,t)=I(i,j,k)*f(t)

[0020] Among them, I'(i,j,k,t) represents the pixel value of the i-th row, j-th column, and k-th color channel at time t.

[0021] Furthermore, the signal modulation function f(t) of the present invention is a sine wave function:

[0022] f(t)=A*sin(ωt+φ)+C

[0023] Among them, A is the amplitude, ω is the angular frequency, φ is the initial phase, and C is the DC component.

[0024] Furthermore, the signal conversion module of the present invention includes two CameraLink video input modules and a protocol conversion module based on FPGA;

[0025] The two-channel CameraLink video input module adopts SDR26 interface packaging and receives two-channel CameraLink format video signals at the same time;

[0026] The FPGA-based protocol conversion module is used to convert two-channel Cameralink video signals into MIPI CSI-2 signals and send them to the RK3588 edge computing platform main control board to achieve signal acquisition.

[0027] Furthermore, the signal analysis module of the present invention pre-processes the video signal and then performs signal analysis; the signal analysis includes: signal quality analysis and transmission performance analysis.

[0028] Furthermore, the signal quality analysis of the present invention: performs quality assessment on the preprocessed image signal, calculates the signal-to-noise ratio, assesses the contrast and resolution of the image by an edge detection method, and generates a signal quality assessment report based on the assessment results;

[0029] Furthermore, the transmission performance analysis described in the present invention: analyzes the transmission rate, transmission delay and bit error rate of the image signal, and generates a transmission performance evaluation report based on the analysis results.

[0030] Furthermore, the signal analysis module of the present invention generates visualization of the analysis results and transmits the visualization results to the control and configuration module for display.

[0031] Beneficial effects:

[0032] First, the system integrates functional modules such as signal generation, signal conversion, and signal analysis. Through flexible parameter configuration, it can generate a variety of complex CameraLink video signals to meet the verification requirements of deep space target detection algorithms in different scenarios. At the same time, the system has the ability to evaluate signal quality and test the processing capabilities of edge intelligent platforms, providing a scientific basis for algorithm optimization and platform selection.

[0033] Second, the software system of the present invention simplifies the operation process and improves the test efficiency by integrating the CameraLink signal generation and acquisition test functions. At the same time, the system has the characteristics of high configurability, real-time and automated testing, which can meet the testing needs of different users. In addition, the system also supports remote monitoring and management, which is convenient for users to conduct remote testing and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 is a schematic diagram of the system of the present invention;

[0036] Figure 2 This is the overall design diagram of the multi-interface video input board;

[0037] Figure 3 This is a schematic diagram of the CameraLink interface conversion;

[0038] Figure 4 For the DS90CR288 receiver. DETAILED DESCRIPTION

[0039] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0040] It should be noted that the following embodiments and features in the embodiments may be combined with each other in the absence of conflict; and, based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making any creative work are within the scope of protection of the present disclosure.

[0041] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0042] The embodiment of the present application provides a simulation verification test system for edge intelligent information generation, such as Figure 1 As shown, it includes a signal generation module, a signal conversion module, a signal analysis module and a control and configuration module, wherein

[0043] A signal generation module is used to generate a video signal in CameraLink format according to a preset image resolution, color depth and signal modulation function, and output it to the device under test;

[0044] A signal conversion module, used for collecting and converting the video signal in the CameraLink format;

[0045] The signal analysis module is used to analyze the collected video signals and calculate key evaluation indicators, generate test reports, and perform alarm processing when the signal is abnormal;

[0046] The control and configuration module is used to provide an interface, receive configuration parameters input by the user, and monitor the test process.

[0047] The following is a detailed description of each module in the embodiment of the present application:

[0048] Signal generation module: responsible for generating a video signal in CameraLink format according to preset parameters. This module supports custom resolution, frame rate, color depth and other parameters, as well as simulating different lighting conditions, noise levels and other environmental factors to generate a variety of test signals. The generation process is as follows:

[0049] Let the image data matrix be I, where I(i,j,k) represents the pixel value of the i-th row, j-th column, and k-th color channel. Then the image data generation can be expressed as:

[0050] I(i,j,k)=G(i,j,k;M,N,D)

[0051] Among them, G is the image data generation function, and M, N, and D are the resolution and color depth of the image respectively.

[0052] Assuming the signal modulation function in the time domain is f(t), each pixel value in the image data matrix can be expressed as:

[0053] I'(i,j,k,t)=I(i,j,k)*f(t)

[0054] Where I'(i,j,k,t) represents the pixel value of the i-th row, j-th column, and k-th color channel at time t. In order to simulate the change of lighting conditions, a sine wave function can be selected as f(t):

[0055] f(t)=A*sin(ωt+φ)+C

[0056] Among them, A is the amplitude, ω is the angular frequency, φ is the initial phase, and C is the DC component. By adjusting these parameters, video signals under different lighting conditions can be simulated.

[0057] The CameraLink protocol specifies the transmission format of the video signal, including the structure of the data frame, the generation of the checksum, etc. In the signal generation module, according to the CameraLink protocol specification, the image data matrix is ​​encoded into a signal format that meets the protocol requirements. This process can be expressed as:

[0058] S=E(I')

[0059] Among them, S is the encoded CameraLink signal, E is the CameraLink encoding function, and I' is the image data matrix after time domain signal modulation.

[0060] Signal conversion module: The video input of the RK3588 edge computing platform main control board is two MIPI channels. Therefore, the video signal generated by the signal generation module passes through the signal conversion module, converts the two-channel Cameralink video signal into MIPI CSI-2 signal and sends it to the RK3588 edge computing platform main control board.

[0061] The signal conversion module of this embodiment includes two CameraLink video input modules and an FPGA-based protocol conversion module;

[0062] like Figure 2-3 As shown, the two-channel CameraLink video input module adopts the SDR26 interface package and receives two-channel CameraLink video signals at the same time; the FPGA-based protocol conversion module virtualizes the CameraLink interface conversion protocol into the RK3588 standard MIPI input RK3588 edge computing platform main control board, thereby realizing RK3588's acquisition of CameraLink video streams.

[0063] Since RK3588 does not support the Camera Link interface, it is necessary to convert the Camera Link interface into a communication interface that RK3588 can receive. The video input interface of RK3588 is mainly MIPI D-PHY, so the MIPI D-PHY interface is selected to access RK3588.

[0064] like Figure 4 As shown, the Camera Link is converted into 3.3V parallel port data through the TI DS90CR288 receiver and input into the FPGA, and the parallel port data is converted into the MIPI D-PHY TX interface and transmitted to the MIPI D-PHY CSI RX of RK3588 for processing.

[0065] Signal analysis module: First, the received image signal data is preprocessed. The preprocessing steps include denoising, standardization and other operations to eliminate the impact of noise and outliers on subsequent analysis.

[0066] Signal quality analysis: Evaluate the quality of the pre-processed image signal. Calculate indicators such as the signal-to-noise ratio (SNR). At the same time, evaluate the contrast and resolution of the image through edge detection methods. Generate a signal quality evaluation report based on the evaluation results.

[0067] Transmission performance analysis: Analyze transmission performance indicators such as transmission rate, transmission delay, and bit error rate of image signals. Evaluate transmission delay by calculating the timestamp difference of data packets, and use CRC check method to detect bit error rate. Generate a transmission performance evaluation report based on the analysis results.

[0068] Data visualization: The analysis results are visualized in the form of charts, curves, etc., so that users can intuitively understand the signal quality and transmission performance. At the same time, an interactive interface is provided to allow users to customize the data charts of different indicators.

[0069] The test method is as follows:

[0070] CRC (Cyclic Redundancy Check): The CRC check formula can be expressed as:

[0071] CRC = remainder / divisor

[0072] (1) Select a generating polynomial (divisor), which is usually represented by a binary number. For example, the generating polynomial of CRC-32 is 0x04C11DB7.

[0073] (2) The data to be checked (message) and a certain number of zeros are concatenated together to make its length the same as the generating polynomial. Remainder is the remainder obtained by dividing the data to be checked by the divisor (generating polynomial).

[0074] For example, assuming that the data to be checked is 101101 and the generator polynomial is 1101, the concatenated data is 101101000. The concatenated data is divided by the generator polynomial, and the remainder obtained is 010, which is the CRC check value.

[0075] Complete data comparison:

[0076] During the CameraLink data transmission process, the receiving end needs to verify the integrity of the received data. Assuming that the received data is (D_{text{recv}}) and the data generated by the signal generation module is (D_{text{send}}), the complete data comparison can be expressed as:

[0077] [D_{text{recv}}=D_{\text{send}}]

[0078] If (D_{text{recv}}!=D_{text{send}}), it means that there is an error in the data transmission process.

[0079] Receiving speed calculation:

[0080] The receiving speed of CameraLink can be obtained by calculating the amount of data received per unit time. Assuming that the amount of data received is N bits and the receiving time is T seconds, the receiving speed V can be expressed as: V = N\T, where the unit of V is bits / s.

[0081] Calculation of time difference between two frames

[0082] The inter-frame difference method is a method to obtain the difference in receiving time by performing a difference operation on two frames with the same timestamp. Assuming that the times of the two frames are t_1 and t_2 respectively, the time difference Deltat between the two frames can be expressed as:

[0083] Delta t=t_2-t_1

[0084] In CameraLink data transmission, the time difference between two frames can be calculated by recording the reception time of two adjacent frames of data.

[0085] In this embodiment, the signal analysis module generates visualization of the analysis results and transmits the visualization results to the control and configuration module for display.

[0086] Control and configuration module: Provides a user interface that allows users to configure test parameters such as signal type, environmental simulation parameters, etc. as needed, and monitor the test process.

[0087] The following is a detailed description of the use of this system:

[0088] ①System initialization

[0089] When starting the test software system, the system is initialized first, including loading necessary library files, configuring system parameters, checking the connection status of hardware devices, etc. After the initialization is completed, the system will enter the standby state, waiting for the user to start the test process.

[0090] ②Parameter setting

[0091] The user sets the test parameters through the test control module. These parameters include signal type (such as grayscale image, color image, etc.), transmission rate, resolution, test duration, etc. Users can set these parameters according to specific needs to meet different test scenarios.

[0092] ③Signal generation

[0093] According to the test parameters set by the user, the signal generation module starts to generate the corresponding Cameralink video image signal. This module uses the internal high-precision signal generator hardware to output the image signal according to the Cameralink interface standard. The generated signal will be transmitted to the device under test through the Cameralink interface.

[0094] ④Signal acquisition

[0095] The signal conversion module receives the video image signal from the signal generation module through the Cameralink interface. The collector uses high-speed, low-noise acquisition technology to ensure the quality of the acquired image signal. The acquired data will be transmitted to the result analysis module for further processing.

[0096] ⑤Results analysis

[0097] Data preprocessing: The signal analysis module first preprocesses the received video image signal data. The preprocessing steps include denoising, standardization and other operations to eliminate the impact of noise and outliers on subsequent analysis.

[0098] Signal quality analysis: Evaluate the quality of the pre-processed video image signal. Calculate indicators such as the signal-to-noise ratio (SNR). At the same time, evaluate the contrast and resolution of the image through edge detection methods. Generate a signal quality evaluation report based on the evaluation results.

[0099] Transmission performance analysis: Analyze the transmission performance indicators of video image signals, such as transmission rate, transmission delay, and bit error rate. Evaluate the transmission delay by calculating the timestamp difference of the data packets, and use the CRC check method to detect the bit error rate. Generate a transmission performance evaluation report based on the analysis results.

[0100] Data visualization: The analysis results are visualized in the form of charts, curves, etc., so that users can intuitively understand the signal quality and transmission performance. At the same time, an interactive interface is provided to allow users to customize the data charts of different indicators.

[0101] ⑥Report generation and output

[0102] Based on the results of signal quality evaluation and transmission performance analysis, the result analysis module automatically generates a detailed test report. The report contains statistical data and evaluation results of key indicators such as signal quality and transmission performance. The report is output in the form of PDF, Word documents, etc. to meet the different needs of users. Users can evaluate and make decisions on the equipment under test based on the content of the report.

[0103] ⑦Test end and cleanup

[0104] After the test is completed, the system enters the test end state. At this time, the system will automatically shut down the signal generation module and signal conversion module and release related resources. At the same time, the system will also save the test data and report for subsequent analysis and reference.

[0105] ⑧Exception handling

[0106] During the test, if an abnormal situation occurs (such as equipment failure, signal interruption, etc.), the system will automatically enter the abnormality handling process. The abnormality handling process includes recording error information, sending alarm notifications, trying to resume the test or stop the test, etc., to ensure the reliability and stability of the test.

[0107] The edge intelligent information processing simulation verification test system proposed in this invention realizes the comprehensive verification of deep space target detection algorithm by integrating CameraLink signal generation, signal conversion, signal analysis and other functional modules. This system not only improves the efficiency and comprehensiveness of algorithm verification, reduces experimental costs, but also provides a scientific basis for algorithm optimization. In addition, the system has good versatility and flexibility, can adapt to the testing requirements of different edge intelligent platforms, and provides strong support for the development and application of edge intelligent technology.

[0108] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A simulation verification test system for edge intelligent information generation, characterized in that: It includes a signal generation module, a signal conversion module, a signal analysis module, and a control and configuration module, among which: A signal generation module is used to generate a video signal in CameraLink format as edge intelligence information according to a preset image resolution, color depth, and signal modulation function, and output it to the edge intelligence platform to be tested; A signal conversion module, used for collecting and converting the video signal in the CameraLink format; The signal analysis module is used to analyze the collected video signals and calculate key evaluation indicators, generate test reports, and perform alarm processing when the signal is abnormal; The control and configuration module is used to provide an interface, receive configuration parameters input by the user, and monitor the test process.

2. The simulation verification test system for edge intelligence information generation according to claim 1, characterized in that: The specific process of the signal generation module generating a video signal in CameraLink format is as follows: Assume that the image data matrix is ​​I, where I(i,j,k) represents the pixel value of the i-th row, j-th column, and k-th color channel, then the image data generation can be expressed as: I(i,j,k)=G(i,j,k;M,N,D) Among them, G is the image data generation function, and M, N, and D are the resolution and color depth of the image respectively. Assuming the signal modulation function in the time domain is f(t), each pixel value in the image data matrix can be expressed as: I'(i,j,k,t)=I(i,j,k)*f(t) Among them, I'(i,j,k,t) represents the pixel value of the i-th row, j-th column, and k-th color channel at time t.

3. The simulation verification test system for edge intelligence information generation according to claim 2, characterized in that: The signal modulation function f(t) is a sine wave function: f(t)=A*sin(ωt+φ)+C Among them, A is the amplitude, ω is the angular frequency, φ is the initial phase, and C is the DC component.

4. The simulation verification test system for edge intelligence information generation according to claim 1, characterized in that: The signal conversion module includes two CameraLink video input modules and an FPGA-based protocol conversion module; The two-channel CameraLink video input module adopts SDR26 interface packaging and receives two-channel CameraLink format video signals at the same time; The FPGA-based protocol conversion module is used to convert two-channel Cameralink video signals into MIPICSI-2 signals and send them to the RK3588 edge computing platform main control board to realize signal acquisition.

5. The simulation verification test system for edge intelligence information generation according to claim 1, characterized in that: The signal analysis module pre-processes the video signal and then performs signal analysis; the signal analysis includes: signal quality analysis and transmission performance analysis.

6. The simulation verification test system for edge intelligence information generation according to claim 5, characterized in that: The signal quality analysis: performs quality assessment on the pre-processed image signal, calculates the signal-to-noise ratio, assesses the contrast and resolution of the image through an edge detection method, and generates a signal quality assessment report based on the assessment results.

7. The simulation verification test system for edge intelligence information generation according to claim 5, characterized in that: The transmission performance analysis: analyzes the transmission rate, transmission delay and bit error rate of the image signal, and generates a transmission performance evaluation report based on the analysis results.

8. The simulation verification test system for edge intelligence information generation according to claim 5, characterized in that: The signal analysis module generates visualization of the analysis results and transmits the visualization results to the control and configuration module for display.

9. The simulation verification test system for edge intelligence information generation according to claim 1, characterized in that: During the test process, if an abnormal situation occurs, the system will automatically enter the exception handling process, which includes recording error information, sending alarm notifications, attempting to resume the test, or stopping the test operation.

10. The simulation verification test system for edge intelligence information generation according to claim 1, characterized in that: After the test is completed, the system enters the test end state, automatically shuts down the signal generation module and the signal conversion module, and releases related resources to save the test data and reports.

Images