Snapshot system performance analysis method, device and computer readable storage medium

Abstract

The application relates to the technical field of computer processing, and particularly provides a snapshot system performance analysis method and device and a computer readable storage medium, the method comprising the following steps: monitoring resource usage data and working state data of a snapshot system; judging whether the snapshot system has performance abnormity according to the resource usage data and the working state data; when the snapshot system has performance abnormity, reducing the camera channel number of the snapshot system, when the snapshot system does not have performance abnormity, increasing the camera channel number of the snapshot system, re-judging whether the snapshot system has performance abnormity until the camera channel number used by the snapshot system under the condition of no performance abnormity reaches the maximum; and generating a performance analysis report of the snapshot system according to the maximum camera channel number used by the snapshot system. According to the application, the camera channel number of the snapshot system reaches the maximum under the condition of no performance abnormity, and the performance analysis report can be accurately generated according to the maximum camera channel number at this time.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and specifically provides a method, apparatus, and computer-readable storage medium for analyzing the performance of a snapshot system. Background Technology

[0002] With the increasing popularity of AI (artificial intelligence) technology, the number of users of AI capture systems is growing exponentially, whether for cooperative or non-cooperative use, and the fields involved are becoming wider and wider, such as finance, security, intelligent transportation, stations, airports, communities, smart cities, etc. AI technology is making society more orderly, safer and more efficient.

[0003] Currently, there is a lack of methods for evaluating the performance of AI capture systems. This inability to assess the performance of AI capture systems in current deployment environments leads to improper configuration, impacting the working quality and efficiency of the AI ​​intelligent capture system. Therefore, a new technical solution is needed to effectively evaluate the performance of AI capture systems. Summary of the Invention

[0004] To overcome the above-mentioned deficiencies, the present invention is proposed to provide a method, apparatus, and computer-readable storage medium for performance analysis of capture systems, which solves or at least partially solves the problem of performance evaluation of capture systems.

[0005] In a first aspect, the present invention provides a performance analysis method for a snapshot system, the method comprising: monitoring resource usage data and working status data of the snapshot system, wherein the snapshot system uses multiple cameras to perform snapshot tasks; determining whether the snapshot system has performance abnormalities based on the resource usage data and the working status data; reducing the number of cameras in the snapshot system when performance abnormalities are found, and increasing the number of cameras in the snapshot system when performance abnormalities are not found, and re-determining whether the snapshot system has performance abnormalities, until the number of cameras used by the snapshot system reaches its maximum without performance abnormalities; and generating a performance analysis report of the snapshot system based on the maximum number of cameras used by the snapshot system.

[0006] Preferably, the aforementioned performance analysis method for the capture system, "determining whether the capture system has performance abnormalities", specifically includes: calculating the difference between the resource usage data and the preset resource usage threshold, and the difference between the working status data and the preset working status threshold, and determining whether the capture system has performance abnormalities based on the magnitude of the calculation results.

[0007] Preferably, in the aforementioned performance analysis method for the capture system, the step of "re-judging whether the capture system has performance abnormalities" includes: after increasing or decreasing the number of cameras in the capture system, re-judging whether the capture system has performance abnormalities after a preset stabilization time.

[0008] Preferably, the aforementioned performance analysis method for the capture system includes the step of "until the number of camera channels used by the capture system reaches its maximum without performance abnormalities" as follows: after the number of times the number of camera channels is alternately increased or decreased reaches a preset number, the number of camera channels of the capture system is no longer increased, and the number of camera channels at this time is taken as the maximum number of camera channels used by the capture system without performance abnormalities.

[0009] Preferably, in the aforementioned performance analysis method for the capture system, the step of "reducing the number of camera channels in the capture system" includes: reducing the number of camera channels in the capture system according to a preset granularity value; the step of "increasing the number of camera channels in the capture system" includes: increasing the number of camera channels in the capture system according to the granularity value.

[0010] Preferably, the aforementioned performance analysis method for the capture system further includes, before the step of "generating the performance analysis report of the capture system", the following: comparing the shooting effect of the capture system using the maximum number of cameras with the shooting effect of using a single camera, and performing the step of "generating the performance analysis report of the capture system" when the difference is less than a preset difference threshold.

[0011] Preferably, in the aforementioned performance analysis method for the capture system, the resource usage data includes CPU, GPU, and memory data used by the capture system; and the working status data includes the failure frame rate and frame drop rate of the capture system.

[0012] In a second aspect, the present invention provides a performance analysis device for a capture system, the device comprising: a data monitoring module for monitoring resource usage data and working status data of the capture system, wherein the capture system uses multiple cameras to perform capture tasks; an anomaly judgment module for determining whether the capture system has performance anomalies based on the resource usage data and the working status data; a camera adjustment module for reducing the number of cameras in the capture system when performance anomalies are present, and increasing the number of cameras in the capture system when performance anomalies are not present, and re-judging whether the capture system has performance anomalies through the anomaly judgment module until the number of cameras used by the capture system reaches its maximum without performance anomalies; and an analysis report module for generating a performance analysis report of the capture system based on the maximum number of cameras used by the capture system.

[0013] In a third aspect, a control device is provided, comprising a processor and a storage device, the storage device being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to execute the performance analysis method of the capture system described in any of the above-described technical solutions.

[0014] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, the program codes being adapted to be loaded and run by a processor to perform the above-described performance analysis method for a capture system as described in any of the technical solutions above.

[0015] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0016] In the technical solution of this invention, after monitoring the resource usage data and working status data of the capture system, it can be determined whether there is an abnormal state in the capture system. If there is an abnormality, the number of cameras in the capture system is reduced; if there is no abnormality, the number of cameras in the capture system is increased. By increasing or decreasing the number of cameras, the capture system is gradually made to reach the maximum number of cameras without any performance abnormalities. That is, the situation in which the capture system performs at its maximum is accurately found. At this time, a performance analysis report of the capture system can be accurately generated based on the maximum number of cameras. Attached Figure Description

[0017] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Wherein:

[0018] Figure 1 This is a flowchart of a performance analysis method for a capture system according to an embodiment of the present invention;

[0019] Figure 2 This is a flowchart of a performance analysis method for a capture system according to an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram illustrating the working principle of a performance analysis method for a capture system according to an embodiment of the present invention. Detailed Implementation

[0021] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0022] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0023] like Figure 1 As shown, one embodiment of the present invention provides a method for performance analysis of a capture system, the method comprising:

[0024] Step S110: Monitor the resource usage data and working status data of the capture system. The capture system uses multiple cameras to perform capture tasks.

[0025] The capture system in this embodiment uses AI technology, i.e., an AI capture system. To successfully monitor the data from the capture system, some basic parameters need to be configured in advance to use the capture system as a data source. These parameters include RTSP (Real-Time Streaming Protocol) stream type, address, port, username, and password. These parameters can clearly identify which system is the data source, its type, and its login username and password.

[0026] Furthermore, the resource usage data in this embodiment includes CPU (Central Processing Unit), GPU (Graphics Processing Unit), and memory data used by the capture system, and the working status data in this embodiment includes the failure frame rate and frame drop rate of the capture system.

[0027] Step S120: Based on resource usage data and working status data, determine whether there is any performance abnormality in the capture system.

[0028] In this embodiment, abnormal performance situations include resources being completely used up (reflected by resource usage data) or resources being available but the algorithm being unable to support them (reflected by working status data). The former requires code optimization to reduce resource usage, while the latter requires in-depth analysis to determine whether the encoding / decoding has reached a bottleneck, whether there is a problem with the queue cache settings, whether the algorithm cannot handle the workload, or whether the algorithm is stuck.

[0029] Step S130: When the capture system has a performance abnormality, reduce the number of camera channels in the capture system; when the capture system does not have a performance abnormality, increase the number of camera channels in the capture system. Re-evaluate whether the capture system has a performance abnormality until the number of camera channels used by the capture system reaches the maximum when no performance abnormality occurs.

[0030] In this embodiment, a base number of cameras can be pre-set for the capture system as the initial number of cameras before performing system performance analysis. Reducing the number of cameras in the capture system decreases resource usage and makes it easier for the system to return to normal operation. Conversely, increasing the number of cameras increases resource usage and makes the system more prone to problems. Therefore, by adjusting the number of cameras, it is possible to gradually find the maximum number of cameras the capture system uses without experiencing performance anomalies. At this maximum number, the capture system performs at its best, and this maximum number of cameras is suitable as a basis for evaluating and analyzing the capture system's performance.

[0031] Step S140: Generate a performance analysis report for the capture system based on the maximum number of camera paths used by the capture system.

[0032] According to the technical solution of this embodiment, after monitoring the resource usage data and working status data of the capture system, it can be determined whether there is an abnormal state in the capture system. If there is an abnormality, the number of cameras in the capture system is reduced; if there is no abnormality, the number of cameras in the capture system is increased. By increasing or decreasing the number of cameras, the capture system can be gradually made to reach the maximum number of cameras without performance abnormalities. That is, the situation in which the capture system performs at its maximum is accurately found. At this time, a performance analysis report of the capture system can be accurately generated based on the maximum number of cameras.

[0033] like Figure 2 As shown, one embodiment of the present invention provides a method for performance analysis of a capture system, the method comprising:

[0034] Step S210: Monitor the resource usage data and working status data of the capture system. The capture system uses multiple cameras to perform capture tasks.

[0035] Furthermore, the resource usage data in this embodiment includes CPU, GPU, and memory data used by the capture system, and the working status data in this embodiment includes the failure frame rate (including the encoding / decoding failure frame rate and the capture algorithm processing failure frame rate) and the frame drop rate (including the encoding / decoding frame drop rate and the capture algorithm processing frame drop rate) of the capture system.

[0036] In this embodiment, two parts of monitoring are implemented. First, the resource usage of the AI ​​capture system is collected and stored in real time. Resource usage refers to CPU, GPU, and memory. If it is a single-machine deployment, only the resource usage data of that server is collected. If it is a cluster deployment, the resource usage data of all servers in the cluster needs to be collected in real time. Second, the status (i.e., working status) of the data processing inside the AI ​​capture system is collected and stored, such as decoding failed data frames, decoding lost frames, total decoding frames, encoding failed frames, encoding lost frames, total encoding frames, algorithm data processing failed frames, lost frames, and total algorithm processing frames.

[0037] Step S220: Calculate the difference between resource usage data and preset resource usage threshold, and the difference between working status data and preset working status threshold, and determine whether the capture system has performance abnormalities based on the calculation results.

[0038] The resource usage thresholds set in this embodiment are the limits that the AI ​​capture system considers to be reached when resource usage reaches a set value, which will trigger the reduction of the number of capture paths. The resource usage thresholds include CPU usage threshold, GPU memory usage threshold, GPU usage threshold, GPU encoding / decoding usage threshold, memory occupancy threshold, etc.

[0039] The working status thresholds set in this embodiment correspond to the monitored working status data and must include at least a failure frame rate threshold and a frame drop rate threshold. The failure frame rate threshold includes the encoding / decoding failure frame rate threshold and the capture algorithm processing failure frame rate threshold. Generally, for failure frame rates, it is necessary to analyze whether the error is due to a problem with the data source, a code compatibility issue, or a resource bottleneck. In this embodiment, this will trigger a reduction in the number of capture paths. The frame drop rate threshold includes the encoding / decoding frame drop rate threshold and the capture algorithm processing frame drop rate threshold. Generally, for frame drop rates, it is necessary to analyze whether the frame drop is due to a data problem, a code logic problem, or a resource bottleneck. In this embodiment, this will trigger a reduction in the number of capture paths.

[0040] Step S230: When the capture system has a performance abnormality, reduce the number of camera channels of the capture system according to a preset granularity value. When the capture system does not have a performance abnormality, increase the number of camera channels of the capture system according to the same granularity value. After increasing or decreasing the number of camera channels of the capture system, a preset stabilization time is required before re-evaluating whether the capture system has a performance abnormality. After the number of times the number of camera channels is alternately increased or decreased reaches a preset number, the number of camera channels of the capture system is no longer increased. The number of camera channels at this time is taken as the maximum number of camera channels used by the capture system when no performance abnormality occurs.

[0041] In this embodiment, a granularity value can be set as the unit step size for dynamically increasing or decreasing the number of cameras in the AI ​​capture system. For example, if it is set to 3, 3 cameras will be added if no performance abnormality occurs, and 3 cameras will be removed if a performance abnormality occurs.

[0042] In this embodiment, a stabilization period can be set. Increasing or decreasing the number of cameras will lead to the allocation and release of server resources. If performance anomalies are analyzed during this period, it will be inaccurate. Therefore, a stabilization period is set, and the performance anomaly analysis phase is re-entered based on new monitoring data after this period. In this embodiment, a single test time can also be set. After the above-mentioned stabilization period, performance anomaly analysis is performed. If this time is too long, it is a waste of time; if it is too short, it will not be accurate enough. It needs to be set based on experience.

[0043] In this embodiment, a swing count can also be set, that is, the number of alternating increases and decreases, indicating that the process of increasing or decreasing the number of camera paths is like a pendulum swinging back and forth, and the process continues for a set number of times.

[0044] In this embodiment, after periodically reading the monitored data, the existing data is analyzed in real time to obtain a phased result indicating whether the capture system has performance abnormalities. Based on the phased result, the number of camera channels is added or deleted. The analysis is then performed in a loop until the performance abnormality analysis ends.

[0045] In one specific implementation of this embodiment, the key indicators and control logic used by the AI ​​capture system are defined using mathematical formulas as follows:

[0046] a. Q-weight list:

[0047] Q = {q1, q2, q3…q} n}

[0048] Where q n This represents the proportion of a certain indicator (including resource usage data and working status data) in the logical judgment. For example, the contribution of the algorithm's failed frame rate (a type of working status data) to the overall index of the camera's operation. Where n=9 represents 9 metrics, namely CPU utilization, GPU utilization, GPU memory, GPU encoding / decoding rate, memory utilization, encoding / decoding failure frame rate, encoding / decoding lost frame rate, algorithm processing lost frame rate, and algorithm processing failure frame rate.

[0049] b. T-threshold list:

[0050] T = {t1, t2, t3, ..., t} n}, n=9 as explained above, means there are 9 threshold indicators, and all thresholds have default values.

[0051] c、C i-Comprehensive index of the i-th camera's performance:

[0052] The index list K = {k1, k2, k3, ..., k} n K is divided into resource-related indicators (i.e., resource usage data) and algorithm processing indicators (i.e., working status data). Resource indicator K z =Average usage / Total usage * 100%, algorithm-related frame metric K f = Number of failed (or lost) frames / Total number of frames to be processed * 100%.

[0053] d. Dr - The camera with the highest overall performance index:

[0054] Dr=Max{C1, C2, C3,...,C i}, i = Num (i represents the total number of cameras currently added). If Dr > 0, it is considered to be a performance abnormality (meaning the algorithm drops frames, resources are fully loaded, etc.), and the number of cameras needs to be reduced. The AI ​​capture system that is the bottleneck of the resource location (i.e., the performance abnormality) will send a deletion command to it. If Dr <= 0, it means that all cameras are running normally, and it also means that there are still resources left (no performance abnormality). Cameras can continue to be added, and they will be added to the AI ​​capture system with the most sufficient resources through the load balancing gateway.

[0055] Step S240: Compare the shooting effect of the capture system using the maximum number of cameras with the shooting effect of a single camera with the shooting effect of a single camera.

[0056] In this embodiment, for the AI ​​capture system at its maximum performance, the single-channel capture effect and the capture effect of each channel under the maximum number of channels are compared. For example, the total number of targets captured and the effect of each captured image under the single-channel condition are compared with the total number of captures and the effect of each captured image under the maximum performance number of channels. This is to further supplement and verify the maximum number of camera channels obtained in the previous analysis. The difference between the single-channel effect and the effect of the maximum performance number of channels is used to confirm whether the above analysis result is the true maximum supported number of channels. If the difference is not large, it indicates that the calculated maximum number of camera channels is correct. If the difference is large, it means that the capture system is not sufficient to support the operation of the maximum number of cameras. In this case, a performance analysis report cannot be generated, and the maximum number of camera channels needs to be reduced until the difference between the single-channel camera capture effect and the capture effect of each channel is less than a set value.

[0057] Step S250: When the difference is less than a preset difference threshold, generate a performance analysis report of the capture system based on the maximum number of camera paths used by the capture system.

[0058] In this embodiment, the maximum number of camera channels supported by the AI ​​capture system has been calculated in the existing equipment resources or deployed cluster environment. Based on this conclusion, combined with intermediate data, tables, and graphs, such as the system resource time curve used for monitoring, the processing process of the capture system, the data from multiple iterations of swing data, and the comparison data from the verification stage, the conclusion is supported by data, forming a reliable and credible evaluation and analysis report.

[0059] The overall structure of the technical solution in this embodiment is as follows: Figure 3 As shown, the capture system is connected to the network through a load balancer (gateway). Each capture system can connect to multiple cameras. In this embodiment, the resource indicators (resource usage data) such as GPU, CPU, and memory of the capture system, as well as the algorithm indicators (working status data) fed back during operation, are collected and stored, and then subjected to multi-dimensional aggregation analysis. The capture system is repeatedly judged to determine whether there are performance abnormalities and the number of cameras is increased or decreased accordingly until the maximum number of cameras supported by the capture system is calculated. The capture effect of multiple cameras is compared with the capture effect of a single camera according to the maximum number of cameras to see if it is the actual number of cameras supported. Finally, an analysis and evaluation report is generated. The report can also reflect the intermediate process data of this evaluation as well as the final results and conclusions.

[0060] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0061] Furthermore, the present invention also provides a control device. In one embodiment of the control device according to the present invention, the control device includes a processor and a storage device. The storage device can be configured to store a program for executing the performance analysis method of the capture system described in the above-described method embodiments. The processor can be configured to execute the program in the storage device, which includes, but is not limited to, the program for executing the performance analysis method of the capture system described in the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. This control device can be a control device device comprising various electronic devices.

[0062] Furthermore, the present invention also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program for executing the capture system performance analysis method of the above-described method embodiments. This program can be loaded and run by a processor to implement the above-described capture system performance analysis method. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0063] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, hardware, or a combination of software and hardware. Therefore, the number of modules shown in the figures is merely illustrative.

[0064] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of the present invention; therefore, the technical solutions after splitting or combining will fall within the protection scope of the present invention.

[0065] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for performance analysis of a snapshot system, characterized in that, include: The system monitors resource usage data and operational status data of the capture system, which uses multiple cameras to perform capture tasks. Based on the resource usage data and the working status data, determine whether the capture system has any performance abnormalities; When the capture system has a performance abnormality, reduce the number of camera channels of the capture system; when the capture system does not have a performance abnormality, increase the number of camera channels of the capture system, and re-evaluate whether the capture system has a performance abnormality until the number of camera channels used by the capture system reaches the maximum without a performance abnormality. Based on the maximum number of cameras used by the capture system, a performance analysis report of the capture system is generated; The capture system is an AI capture system, and the working status data includes the failure frame rate and frame loss rate of the capture system.

2. The performance analysis method for the capture system according to claim 1, characterized in that, "Determining whether the capture system has performance abnormalities" specifically includes: Calculate the difference between the resource usage data and the preset resource usage threshold, and the difference between the working status data and the preset working status threshold. Based on the magnitude of the calculation results, determine whether the capture system has performance abnormalities.

3. The performance analysis method for the capture system according to claim 1, characterized in that, The steps for "reassessing whether the capture system has performance abnormalities" include: After increasing or decreasing the number of cameras in the capture system, a preset stabilization time is allowed before reassessing whether the capture system has any performance abnormalities.

4. The performance analysis method for the capture system according to claim 1, characterized in that, The step of "until the number of camera channels used by the capture system reaches its maximum without performance abnormalities" includes: After the number of times the number of camera channels is alternately increased or decreased reaches a preset number, the number of camera channels in the capture system will no longer be increased. The current number of camera channels will be used as the maximum number of camera channels that the capture system can use without any performance abnormalities.

5. The performance analysis method for the capture system according to claim 1, characterized in that, The steps of "reducing the number of camera channels in the capture system" include: The number of cameras in the capture system is reduced according to a preset granularity value; The steps for "increasing the number of camera channels in the capture system" include: The number of camera channels in the capture system is increased according to the stated granularity value.

6. The performance analysis method for the capture system according to claim 1, characterized in that, Before the step of "generating the performance analysis report of the capture system", the following steps are also included: Compare the shooting effect of the capture system using the maximum number of cameras with the shooting effect using a single camera. If the difference is less than a preset difference threshold, execute the step of "generating a performance analysis report of the capture system".

7. The performance analysis method for the capture system according to claim 1, characterized in that, The resource usage data includes the CPU, GPU, and memory data used by the capture system.

8. A performance analysis device for a snapshot system, characterized in that, include: The data monitoring module monitors the resource usage data and working status data of the capture system, which uses multiple cameras to perform capture tasks. The anomaly detection module determines whether the capture system has performance anomalies based on the resource usage data and the working status data. The camera adjustment module reduces the number of cameras in the capture system when there is a performance abnormality, and increases the number of cameras in the capture system when there is no performance abnormality. The abnormality judgment module re-judges whether there is a performance abnormality in the capture system until the number of cameras used by the capture system reaches the maximum when no performance abnormality occurs. The analysis report module generates a performance analysis report for the capture system based on the maximum number of camera channels used by the capture system. The capture system is an AI capture system, and the working status data includes the failure frame rate and frame drop rate of the capture system.

9. A control device, comprising a processor and a storage device, said storage device being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the capture system performance analysis method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the capture system performance analysis method according to any one of claims 1 to 7.

Images