CN116189067A

CN116189067A - Data processing performance determining method and device, electronic equipment and medium

Info

Publication number: CN116189067A
Application number: CN202111411327.4A
Authority: CN
Inventors: 张鹏国; 李玉天; 张田田
Original assignee: Zhejiang Uniview Technologies Co Ltd
Current assignee: Zhejiang Uniview Technologies Co Ltd
Priority date: 2021-11-25
Filing date: 2021-11-25
Publication date: 2023-05-30

Abstract

The embodiment of the application discloses a data processing performance determining method, a data processing performance determining device, electronic equipment and a medium. Wherein the method comprises the following steps: determining the target quantity of targets to be processed according to the candidate image data acquired by the candidate image acquirer; determining target image data from the candidate image data according to the target quantity; and sending the target image data to target equipment for processing, and determining the data processing performance of the target equipment according to a processing result. According to the technical scheme, the target image data acquired by the image acquisition device is sent to the target equipment for processing, so that the actual data processing performance of the target equipment is tested, the target equipment is scheduled to be used according to the actual data processing performance of the target equipment, the image data processing performance of the target equipment is fully utilized, and the image data processing performance of the target equipment is more matched with the actual use scene of the target equipment.

Description

Data processing performance determining method and device, electronic equipment and medium

Technical Field

The embodiment of the application relates to the technical field of data processing, in particular to a method, a device, a medium and equipment for determining data processing performance.

Background

With the comprehensive development of data processing technology, the application of using intelligent analysis equipment to process the image acquired by the image acquisition device is also becoming wider and wider. The image data processing performance of different intelligent analysis devices is different, and the processing methods of the image data may also be different. When the image data flow is large, the intelligent analysis device may have a situation that it cannot process all in time. When the image data has no flow, the resource waste of the intelligent analysis equipment exists, so that the preset image data processing performance of the intelligent analysis equipment is not matched with the actual use scene of the intelligent analysis equipment. In addition, the upgrade or modification of the device algorithm can also cause the change of the image data processing performance, and if the intelligent analysis device is scheduled according to the preset image data processing performance, the situation of insufficient algorithm or waste of calculation power can be caused.

At present, a fixed test video and a fixed image are used for testing the data processing performance of the equipment, the test result is too ideal, the test result is inaccurate, and the equipment can have the condition of wasting calculation force or insufficient calculation force in the actual use process.

Disclosure of Invention

The embodiment of the application provides a method, a device, a medium and equipment for determining data processing performance, which can accurately test the actual data processing performance of target equipment by sending target image data acquired by an image acquisition device to the target equipment for processing.

In a first aspect, an embodiment of the present application provides a method for determining data processing performance, where the method includes:

determining the target quantity of targets to be processed according to the candidate image data acquired by the candidate image acquirer;

determining target image data from the candidate image data according to the target quantity;

and sending the target image data to target equipment for processing, and determining the data processing performance of the target equipment according to a processing result.

In a second aspect, an embodiment of the present application provides a data processing performance determining apparatus, including:

the target number determining module is used for determining the number of targets to be processed according to the candidate image data acquired by the candidate image acquirer;

a target image data determining module, configured to determine target image data from the candidate image data according to the target number;

And the data processing performance determining module is used for sending the target image data to target equipment for processing and determining the data processing performance of the target equipment according to a processing result.

In a third aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a data processing performance determining method as described in embodiments of the present application.

In a fourth aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and capable of being executed by the processor, where the processor executes the computer program to implement a method for determining data processing performance according to an embodiment of the present application.

According to the technical scheme provided by the embodiment of the application, the target number of the targets to be processed is determined according to the candidate image data acquired by the candidate image acquirer; and determining target image data from the candidate image data according to the target quantity, so as to adaptively determine suitable target image data for testing the target equipment. And sending the target image data to target equipment for processing, and determining the data processing performance of the target equipment according to a processing result. And sending the target image data acquired by the image acquisition device to target equipment for processing so as to test the actual data processing performance of the target equipment, further scheduling the target equipment according to the actual data processing performance of the target equipment, and processing the image data acquired by the image acquisition device so as to fully utilize the processing performance of the target equipment and match with the actual use scene of the target equipment.

Drawings

FIG. 1 is a flow chart of a method for determining data processing performance provided by one embodiment of the present application;

FIG. 2 is a flow chart of a method for determining data processing performance provided in another embodiment of the present application;

FIG. 3 is a flow chart of a data processing performance determination method provided by yet another embodiment of the present application;

FIG. 4 is a first schematic illustration of candidate image data screening according to an embodiment of the present application;

FIG. 5a is a second schematic illustration of candidate image data screening according to an embodiment of the present application;

FIG. 5b is a third schematic illustration of candidate image data screening according to an embodiment of the present application;

FIG. 6a is a fourth schematic diagram of candidate image data screening according to an embodiment of the present application;

FIG. 6b is a fifth schematic illustration of candidate image data screening according to an embodiment of the present application;

FIG. 7 is a block diagram of a data processing performance determining apparatus provided in one embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The present application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present application are shown in the drawings.

Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts steps as a sequential process, many of the steps may be implemented in parallel, concurrently, or with other steps. Furthermore, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.

Fig. 1 is a flowchart of a data processing performance determining method according to an embodiment of the present application, where the embodiment of the present application may be applicable to a scenario of testing an image data processing performance of a device, where the method may be performed by a data processing performance determining apparatus according to the embodiment of the present application, where the apparatus may be implemented by software and/or hardware, and may be integrated into an electronic device. As shown in fig. 1, the data processing performance determining method includes:

s110, determining the target quantity of the targets to be processed according to the candidate image data acquired by the candidate image acquirer.

The candidate image collector can be a camera, a mobile phone camera or a monitoring camera and other devices with an image collecting function. The candidate image data is an image frame in a picture or video captured by the candidate image capture. The target to be processed may be a target determined according to an actual application. For example, in a traffic violation monitoring scenario, it is mainly required to monitor whether a vehicle has a violation, so the target to be processed is the vehicle. In the scenes of office buildings, residential areas and the like, whether the people entering and exiting are abnormal behaviors or not is mainly required to be monitored, and therefore the target to be processed is the person. In the candidate image data acquired by the candidate image acquirer, a target to be processed may exist or may not exist.

In the embodiment of the application, the candidate image data can be subjected to image recognition, and the targets existing in the candidate image data are determined. And carrying out image matching on preset image features of the targets to be processed and image features of targets in the candidate image data, wherein the targets in the candidate image data successfully matched are the targets to be processed, and further counting the number of the targets to be processed in the candidate image data.

Specifically, assuming that the number of candidate image collectors is 16, the targets to be processed are people, counting the number of people appearing in the candidate image data collected by each image collector, and recording the shooting time of each candidate image data. The resolution of the candidate image collectors can be determined in a polling mode, 16 candidate image collectors are classified according to the resolution of the candidate image collectors, target equipment suitable for the candidate image collectors is selected for each type of candidate image collectors, and candidate image data collected by the candidate image collectors are processed.

S120, determining target image data from the candidate image data according to the target quantity.

The target image collector is used for providing image data to perform data processing performance test on target equipment. The data processing performance of the target device can be embodied by the speed of processing the image data per unit time. For better and more reliable test data processing performance, a part of image data with target quantity meeting the requirement can be screened out from the candidate image data to serve as target image data. In the embodiment of the application, the target image data is image data determined according to practical application, and the target image data can be determined in various manners. For example, the candidate image data may be arranged in descending order according to the target number, and candidate image data arranged first or before a preset ranking may be selected as target image data; the preset threshold range may be set, and the candidate image data whose target number is within the preset threshold range may be set as the target image data. It is understood that not all candidate image data may be suitable as the target image data to test the target device, and there may or may not be a target to be processed in the candidate image data collected by the candidate image collector, and the number of targets included in each candidate image data may be different, so that candidate image data in which there is no target to be processed or in which the number of targets to be processed does not satisfy the requirement may be screened out.

Specifically, assuming that the object to be processed is a vehicle, counting the number of vehicles appearing in the candidate image data acquired by each image acquirer in one day, setting the preset threshold range of the number of vehicles to be more than or equal to 10000, traversing the number of vehicles in all the candidate image data, and determining the object image data in which the number of vehicles meets the preset threshold range.

S130, the target image data are sent to target equipment for processing, and the data processing performance of the target equipment is determined according to the processing result.

The target device is a device for processing image data acquired by the image acquisition device, such as a monitoring background server. For example, in a traffic violation monitoring scenario, the target device is a server of a command dispatch console in a monitoring command center; in an office building, residential area, etc., the target device is a server that monitors the machine room.

The processing result may be a processing speed of the target device for the target image data. Which can be represented with a time-consuming process of a certain amount of target image data according to the target device; or may be expressed in terms of the number of target devices processing target image data over a period of time. After the time of acquiring the target device to process a certain amount of target image data or the amount of target image data processed by the target device within a certain period of time, the data processing performance thereof may be evaluated according to the time period or the processing amount thereof in accordance with the pre-divided levels, such as: excellent, good, poor neutralization; the data processing performance of the target device may be better as the score is higher, wherein the score is higher as the time spent is shorter, the score is higher as the processing number is higher.

According to the data processing performance determining method provided by the embodiment of the application, the target number of the targets to be processed is determined according to the candidate image data acquired by the candidate image collector; determining target image data from the candidate image data according to the target quantity; and sending the target image data to target equipment for processing, and determining the data processing performance of the target equipment according to a processing result. The target image data acquired by the image acquisition device is sent to the target equipment for processing so as to test the actual data processing performance of the target equipment, so that the image data processing performance of the target equipment is fully utilized and is more matched with the actual use scene of the target equipment.

Fig. 2 is a flowchart of a method for determining data processing performance according to another embodiment of the present application, which is optimized based on the above embodiment. The concrete optimization is as follows: determining target image data from the candidate image data according to the target number, including: determining a target image collector from the candidate image collectors according to the number of targets in the candidate image data collected by the candidate image collectors; and determining target image data from the candidate image data acquired by the target image acquisition device according to the target quantity in the candidate image data acquired by the target image acquisition device and the theoretical processing quantity of the target equipment to be processed. As shown in fig. 2, the method in the embodiment of the application specifically includes the following steps:

S210, determining the number of targets to be processed according to the candidate image data acquired by the candidate image acquirer.

S220, determining a target image collector from the candidate image collectors according to the number of targets in the candidate image data collected by the candidate image collectors.

In the embodiment of the application, the target image collector can be determined from the candidate image collectors first, and then the target image data is determined from the candidate image data collected by the target image collector, so that the screening range is gradually narrowed for hierarchical screening.

For example, the candidate image collectors corresponding to the candidate image data with the target number greater than a certain threshold may be selected as the target image collectors according to the target number in the candidate image data collected by the candidate image collectors, so as to test the maximum performance that the target device can process. Alternatively, the candidate image collectors corresponding to the candidate image data with the target number larger than the lower limit of the number and smaller than the upper limit of the number may be used as the target image collectors to test the general performance of the target device.

In an embodiment of the present application, determining, from candidate image collectors, a target image collector according to the number of targets in candidate image data collected by the candidate image collector includes: determining the target quantity of targets to be processed in the candidate image data acquired by the candidate image acquirer in each time period; and determining a target image collector from the candidate image collectors according to the target quantity corresponding to each time period.

In order to quickly and conveniently determine the target image collectors meeting the conditions, different time periods can be divided for the same period, the target quantity in the candidate image data collected by different candidate image collectors in each time period is counted, and then the target image data is screened. The period and the time period may be preset according to practical situations, and the period may be set to 1 day as one period, and each hour in 1 day is set to one time period, and 2 time periods are included in 1 day. The respective periods and the respective time periods may be continuous or discontinuous, for example, 3 periods may be 1 month and 1 day, 1 month and 2 days, 1 month and 3 days, or 1 month and 1 day, 1 month and 3 days, and 1 month and 5 days, respectively. The respective time period in 1 day may be 0:00-1:00, 1:00-2:00, 2:00-3:00, or 0:30-1:30, 3:30-4:30, 6:30-7:30. The screening mode can also be based on a statistical method, the variance of the target number in the candidate image data of the candidate image data in the same time period in different periods is calculated, and the deviation degree and the stability of the target number in the candidate image data acquired by different candidate image collectors are analyzed.

In the embodiment of the present application, determining, from candidate image collectors, a target image collector according to the number of targets corresponding to each time period includes: traversing each time period corresponding to the same time period, and if the number of targets in the candidate image data in the traversed current time period is smaller than a preset number threshold value, determining the score of the candidate image collector in the current time period according to the duration of the current time period from the current time; determining the sum of the scores of the candidate image collectors in each time period as a count score, and determining the variance of the target quantity in the same time period; and determining a target image collector from the candidate image collectors according to the count scores and the variances.

The preset quantity threshold is determined according to experience or theoretical processing quantity of the target equipment to be processed. For example, for the same time period, a score of the candidate image collector is determined for each time period, the score being determined based on the number of targets in the candidate image data during the time period and/or the duration of the time period from the current time. For example, the determining the score of the candidate image collector in the period 2:00-3:00 of the 3 rd period may be determining the duration of the 3 rd period from the current time if the target number of the candidate image data in the 3 rd period is less than the preset number threshold value, and determining the score corresponding to the candidate image collector in the time period according to the duration. And if the target number of the candidate image data in the 3 rd period is greater than or equal to a preset number threshold value, determining that the score corresponding to the candidate image collector in the time period is 0. The determining of the score of the candidate image collector in the 3:00-4:00 of the 5 th period may be determining the duration of the 5 th period from the current moment if the target number of the candidate image data in the 5 th period is smaller than the preset number threshold, and determining the score corresponding to the candidate image collector in the time period according to the duration. And if the target number of the candidate image data in the 5 th period is greater than or equal to a preset number threshold, determining that the score corresponding to the time period of the candidate image collector in the time period is 0. For example, for time periods 2:00-3:00, the count score of the candidate image collector is the sum of the candidate image collector scores in time periods 2:00-3:00 of each cycle. Determining the variance of the number of targets in the same time period, for example, the number of targets in the candidate image data acquired by the candidate image acquirer in the time period 2:00-3:00 in the 1 st, 2 nd, 3 rd, 4 th and 5 th periods is 200, 340, 190, 330 and 430, and calculating the variances of 200, 340, 190, 330 and 430. And selecting a target image collector according to the count scores of the candidate image collectors in each time period and the variance of the target quantity.

In the embodiment of the present application, determining the score of the candidate image collector in the current time period according to the time from the current time period to the current time includes: and determining the score of the candidate image collector in the current time period corresponding to the duration according to the negative correlation relation between the preset duration and the score.

For example, a negative correlation between the duration and the score may be preset, that is, the longer the duration, the smaller the score, the shorter the duration, the larger the score, and the specific correspondence may be determined according to the actual situation, for example, the score decreases by 1 every 5 minutes when the duration increases. And for a time period, if the target number in the candidate image data of the candidate image collector in the traversed current time period is lower than a preset number threshold value, screening the candidate image collector in the time period of the time period, and determining the score of the candidate image collector as a according to the duration of the current time period from the current moment. The closer the current time period is to the current time, namely the smaller the duration is, the larger the value of a is. The longer the current time period is from the current time, i.e. the longer the time length is, the smaller the value of a is. Specifically, as shown in table 1, for the IPC9 in the period 1, if the target number of candidate image data in the period 1 is not less than the preset number threshold, the corresponding score is 0, and in the period 2, if the target number of candidate image data in the IPC9 is less than the preset number threshold, the IPC9 is screened out, the period 2 is separated by 8 periods according to the duration of the current time, and if the duration is longer, the score of the period 2 is determined to be 2. In the period 8, if the target number of the candidate image data in the IPC9 is smaller than the preset number threshold, the IPC9 is screened out, the period 8 is separated by 2 periods according to the duration of the current time, and if the duration is shorter, the score of the period 8 is determined to be 8. And adding the scores corresponding to the periods of the same time period by the IPC9 to obtain the count score corresponding to the time period.

TABLE 1

IPC9	Time period 1	Time period 2	Time period 3	Time period 4	Time period 5	Time period 6
							Cycle 1	0	0	1	0	0	0
Cycle 2	2	0	2	0	0	0
							Cycle 3	3	0	3	0	0	3
Cycle 4	4	4	4	0	0	0
							Cycle 5	0	5	5	0	0	0
Period 6	6	6	6	6	0	0
							Period 7	7	0	0	0	0	0
Cycle 8	8	0	0	8	0	0
							Period 9	0	0	0	0	0	0
Cycle 10	10	0	0	10	0	0
							Count score	40	15	21	24	0	3

In an embodiment of the present application, determining a target image collector from the candidate image collectors according to the count score and the variance includes: carrying out weighted summation on the count value and the variance to obtain a score value of the candidate image collector; and taking the candidate image collector with the grading value smaller than the preset grading value as a target image collector.

It is understood that the count score can reflect the number of targets in the candidate image data center acquired by the candidate image acquirer in each time period of different periods, and the variance can reflect the stability of the number of targets in the candidate image data acquired by the candidate image acquirer in each time period of different periods. Wherein the greater the count score, the fewer the target number; the larger the variance, the lower its stability. Since the score value of the candidate image collector is obtained by weighted summation of the count value and the variance.

Specifically, the scoring value may be determined using the following formula:

Q＝B×x％+C×y％；

Wherein Q is the score value of the candidate image collector, B is the count value of the candidate image collector in a certain period, C is the variance of the target number of the target to be processed in the candidate image data collected in a certain period of different periods, x is the weighting coefficient of the count value, and y is the weighting coefficient of the variance.

S230, determining target image data from the candidate image data acquired by the target image acquisition device according to the target quantity in the candidate image data acquired by the target image acquisition device and the theoretical processing quantity of the target equipment to be processed.

Wherein the theoretical processing number of the target device is a pre-recorded processing performance parameter, which represents the theoretical processing performance of the target device. For example, the theoretical number of treatments of the target device is 100 pieces/second. In the embodiment of the application, the theoretical processing number of the target to be processed by the target device and the target number in the candidate image data acquired by the target image collector can be compared, and the image data with the target number being greater than or equal to the theoretical processing number is selected as target image data; the candidate image data of the target number which floats up and down within a certain preset number range based on the theoretical processing number may be selected as the target image data.

In this embodiment of the present application, according to the number of targets in the candidate image data acquired by the target image acquirer and the theoretical processing number of the target to be processed by the target device, determining target image data from the candidate image data acquired by the target image acquirer includes: according to the number of targets to be processed in the candidate image data acquired by the target image acquisition unit in each time period corresponding to the same time period, determining a time period average value of the number of targets in the same time period; calculating a unit average value in unit time in each time period according to the time period average value; and if the difference value between the unit average value and the theoretical processing number in the time period is larger than the first preset threshold value and smaller than the second preset threshold value, taking the candidate image data acquired by the target image acquisition device in the time period as target image data.

Wherein the time period average value may be a ratio of a sum of target numbers of targets to be processed within the same time period of each period to the number of time periods. Each time period can be divided into a plurality of unit time, and the unit average value is the ratio of the time period average value to the number of unit time in the time period. The unit average value may be the target number of the target to be processed in the candidate image data acquired by the target image acquirer per minute, or the target number of the target to be processed in the candidate image data acquired by the target image acquirer per second, which is not limited herein.

It can be appreciated that, in order to avoid unreliable data processing performance determination caused by waste of resources in the early period and shortage of resources in the later period of the target device, a suitable time period needs to be selected for data processing capability test. The suitable time period should meet the following requirements: the difference value between the unit average value and the theoretical treatment quantity in the selected time period is larger than a first preset threshold value and smaller than a second preset threshold value. For example, the theoretical processing number of a certain target device is 100 pieces/second, and the difference between the unit average value and the theoretical processing number in a selected time period is more than 80 pieces/second and less than 120 pieces/second, so as to determine candidate image data of which the unit average value floats on the basis of the theoretical processing number as target image data, and test the processing capacity of the target device in the case of logarithmic floating in processing the data.

S240, the target image data are sent to target equipment for processing, and the data processing performance of the target equipment is determined according to the processing result.

According to the data processing performance determining method provided by the embodiment of the application, according to the number of targets in the candidate image data acquired by the candidate image acquirer, the target image acquirer is determined from the candidate image acquirer; and determining target image data from the candidate image data acquired by the target image acquisition device according to the target quantity in the candidate image data acquired by the target image acquisition device and the theoretical processing quantity of the target equipment to be processed. By adopting the scheme, the selection process of the target image data is optimized, the calculation amount of selecting the target image data is reduced, and meanwhile, the reliability and the applicability of the target image data are improved.

Fig. 3 is a flowchart of a data processing performance determining method according to another embodiment of the present application, which is optimized based on the above embodiments. The concrete optimization is as follows: before determining the target number of the target to be processed according to the candidate image data acquired by the candidate image acquirer, the method further comprises: dividing the acquisition time of the candidate image data into a preset number of time intervals; traversing each time interval, and removing the candidate image data acquired by the candidate image acquirer in the time interval if the target number of the targets to be processed in the candidate image data acquired by the candidate image acquirer in the time interval is smaller than the preset target number. As shown in fig. 3, the method in the embodiment of the application specifically includes the following steps:

s310, dividing the acquisition time of the candidate image data into a preset number of time intervals.

Wherein the acquisition time may consist of at least two periods, each period consisting of at least two time periods. For example, the acquisition time of a certain camera is 10 days, which is divided into 5 periods of 2 days each. Of course, the embodiment of the present application does not limit the dividing manner of the acquisition time.

S320, traversing each time interval, and if the number of targets to be processed in the candidate image data acquired by the candidate image acquirer in the time interval is smaller than the preset target number, removing the candidate image data acquired by the candidate image acquirer in the time interval.

In order to ensure that the target number of targets to be processed can meet the reliability of determining the processing performance of target equipment, candidate image data of which the target number does not meet the requirement needs to be screened out.

The time interval may be determined according to the actual situation, where the preset target number corresponds to the size of the time interval, for example, if the time interval is longer, the preset target number may set a larger value, and if the time interval is shorter, the preset target number may set a smaller value.

Specifically, the time interval may be set to be daily, and the preset target number is Q1, so as to count the target number of the target to be processed in the candidate image data collected by the candidate image collector within each day, and if the target number is smaller than Q1, the candidate image data is removed. Further, the time interval can be set to be the target number Q2 per hour, Q2< Q1 is preset, the target number of the targets to be processed in the candidate image data acquired by the candidate image acquisition unit per hour is counted, and if the target number is smaller than Q2, the candidate image data is removed. Further, the time interval may be set to be every minute, the preset target number is Q3, Q3< Q2, the target number of the target to be processed in the candidate image data collected by the candidate image collector in every minute is counted, and if the target number is smaller than Q3, the candidate image data is removed. Similarly, the partition time interval may be further refined to further screen candidate image data. In the embodiment of the present application, as long as there is a time interval, if the number of targets to be processed in the candidate image data collected by the candidate image collector in the time interval is smaller than the preset target number, all the candidate image data collected by the candidate image collector is removed, and the candidate image collector is not analyzed continuously.

S330, determining the number of targets to be processed according to the candidate image data acquired by the candidate image acquirer.

S340, determining target image data from the candidate image data according to the target quantity.

S350, the target image data are sent to target equipment for processing, and the data processing performance of the target equipment is determined according to the processing result.

According to the data processing performance determining method provided by the embodiment of the application, the acquisition time of the candidate image data is divided into a preset number of time intervals; traversing each time interval, and removing the candidate image data acquired by the candidate image acquirer in the time interval if the target number of the targets to be processed in the candidate image data acquired by the candidate image acquirer in the time interval is smaller than the preset target number. The calculation amount can be reduced, candidate image data meeting the requirements can be rapidly screened out, and the data processing performance is determined.

The present application provides a preferred embodiment, taking a camera as an example for illustration, the method includes:

the first step: traversing the candidate cameras, recording the resolution of each candidate camera, classifying the candidate cameras according to the resolution, and counting the number of targets to be processed, which are acquired by each time slice of the candidate cameras.

Table 2 is a statistical table of the target number in the data processing performance determining method provided in the embodiment of the present application. As shown in table 2, there are 10 candidate cameras in total, and the naming mode is "ipc+x", where X is the sequence number of the candidate cameras, and the table is the number of targets in candidate image data acquired by 10 candidate cameras in 10 time slices in a certain period.

TABLE 2

	At 0 time	1 time	2 hours	At 3 hours	At 4 hours	At 5 hours	At 6 hours	At 7 hours	At 8 hours	At 9 hours	At 10 hours
												IPC1	326	734	995	793	390	264	689	549	463	724	918
IPC2	906	76	735	14	495	518	995	627	31	306	320
												IPC3	797	814	589	637	353	10	174	392	114	5	930
IPC4	489	388	998	599	530	240	299	491	391	967	753
												IPC5	198	143	698	432	526	140	365	394	741	729	920
IPC6	385	345	779	784	811	276	238	40	563	258	3
												IPC7	283	2	85	330	648	970	474	574	330	582	152
IPC8	107	956	884	429	277	842	485	449	326	781	387
												IPC9	262	477	453	263	937	370	529	913	197	798	103
IPC10	344	753	326	496	551	990	915	112	400	394	452

And a second step of: the target number of targets to be processed in the candidate image data acquired by the candidate camera every day is counted, and a first preset target number is set, for example, the first preset target number is 12000. And if the target number of the targets to be processed is smaller than the first preset target number, removing the candidate image data acquired by the candidate cameras in the time interval.

Fig. 4 is a first schematic diagram of candidate image data screening according to an embodiment of the present application. As shown in fig. 4, the first preset target number is set to 12000, and thus candidate image data of which the target number of targets to be processed is less than 12000 is removed.

And a third step of: the number of targets to be processed in the candidate image data in different time segments within each day, such as five time segments of night, early peak, daytime, late peak, and evening, in the candidate camera is counted, and the second preset target number may be set to 2000. And if the target number of the targets to be processed is smaller than the second preset target number, removing the candidate image data acquired by the candidate cameras in the time interval.

Fig. 5a is a second schematic diagram of candidate image data screening according to an embodiment of the present application, and fig. 5b is a third schematic diagram of candidate image data screening according to an embodiment of the present application. As shown in fig. 5a and 5b, fig. 5a is the target number of targets to be processed in the candidate image data of each time segment of the IPC1, and fig. 5b is the target number of targets to be processed in the candidate image data of each time segment of the IPC 4. The second preset target number is set to 2000, so that candidate image data of IPC1 having a target number of targets to be processed smaller than 2000 are removed.

Fourth step: the target number of targets to be processed in the candidate image data in the time segment thinned in the candidate camera is counted, and the third preset target number can be set to 800. The refined time segment may be every hour. And if the target number of the targets to be processed is smaller than the third preset target number, removing the candidate image data acquired by the candidate cameras in the time interval.

Fig. 6a is a fourth schematic diagram of candidate image data screening according to an embodiment of the present application, and fig. 6b is a fifth schematic diagram of candidate image data screening according to an embodiment of the present application. As shown in fig. 6a and 6b, fig. 6a is the target number of targets to be processed in the candidate image data per hour of the IPC4, and fig. 6b is the target number of targets to be processed in the candidate image data per hour of the IPC 9. The third preset target number is set to 800, so that candidate image data of which the target number of targets to be processed is less than 800 is removed. With respect to fig. 6a, if the target number of IPC4 at 0, 17, 19, 20, 21, 22 and 24 times does not reach 800, the candidate image data of IPC4 in the above period is removed, and only the candidate image data at 18 and 23 are retained. Fifth step: and traversing each time period corresponding to the same time period, and if the number of targets in the candidate image data in the traversed current time period is smaller than a preset number threshold value, determining the score of the candidate image collector in the current time period according to the duration of the current time period from the current time.

As shown in table 1, the values of the 6 time slices of IPC9 in the first 10 cycles are calculated, and the time period is, for example, cycle 1 to cycle 10 in table 2. The calculation rule is as follows: according to the screening method from the second step to the fourth step, if the candidate image data in the same time slice in different periods is removed, the score of the IPC9 in the time slice is added with a, wherein the value of a is larger as the time slice is closer. And accumulating and summing the scores of each time slice to obtain a count score.

Sixth step: the scores of the time periods are summed to obtain a count score for each time slice corresponding to the candidate camera, as shown in table 1.

Seventh step: and traversing each historical time period before the current time period, and determining the variance B of the target number of each time slice of the target camera.

The variance B can be determined using the following formula:

where x is the target number in the candidate image data for each time slice, 1, 2, 3, …, n is the cycle sequence number, and n is the cycle number.

Eighth step: carrying out weighted summation on the count score C and the variance B to obtain a score value Q of the candidate camera; and sorting in a descending order according to the scoring value Q, and taking the candidate cameras with the scoring value smaller than a preset scoring value as target cameras.

The score value Q may be determined using the following formula:

Q＝B×x+C×y；

table 3 is a schematic diagram of the scoring values in the data processing performance determining method provided in the embodiment of the present application. As shown in table 3, the score Q of each time slice of IPC4, IPC14, and IPC19 was calculated by setting x to 50% and y to 50%; and performing ascending order according to the grading value Q, and setting the preset grading value to be 5, and selecting the IPC14 and the IPC19 as target cameras.

TABLE 3 Table 3

Time slice 1	Average flow value	Count value	Variance of	Q value	Ordering of
						IPC14	100	6	2	4	1
IPC19	110	5	4	4.5	2
						IPC9	120	10	3	6.5	3
….

Ninth step: according to the number of targets to be processed in the candidate image data acquired by the target camera in each time period corresponding to the same time period, determining a time period average value A1 of the number of targets in the same time period; calculating a unit average value A2 in unit time in each time period according to the time period average value A1; and if the difference value between the unit average value A2 and the theoretical processing quantity A in the time period is larger than the first preset threshold value and smaller than the second preset threshold value, taking the candidate image data acquired by the target camera in the time period as target image data.

The first preset threshold and the second preset threshold may be set according to actual situations, for example, the first preset threshold may be set to 0, and the second preset threshold may be set to 20, that is, the difference between the unit average value and the theoretical processing number is greater than 0 and less than 20. Assuming that the theoretical processing number is 100 pieces/second, if there is candidate image data whose unit average value is between 80 and 100 or between 100 and 120, the candidate image data is taken as target image data.

Specifically, the value requirement of the unit average value of the selected target image data can be determined according to the theoretical processing quantity. For example, if the theoretical processing number is a, the unit average value may be set to have a value of a (1+d%), a (1-d%), where d% may be determined according to the actual situation, for example, may be determined to be 10%. Assuming that a is 100 pieces/second, if the unit average value of the target number in the candidate image data in a certain period is 100 (1+10%), the candidate image data in the certain period is taken as target image data, and if the unit average value of the target number in the candidate image data in the certain period is 100 (1-10%), the candidate image data in the certain period is taken as target image data.

Tenth step: and sending the target image data to target equipment for processing, and determining the data processing performance of the target equipment according to a processing result.

Specifically, the actual processing speed of the target device may be calculated, for example, the number of objects to be processed per second, i.e., a/second is counted, and if a/second is smaller than 100/second, it is determined that the actual processing performance of the target device is lower than the pre-recorded performance, so that the number of target devices may be appropriately increased to meet the requirement of processing the image data. If a/s is greater than 100/s, the number of target devices can be appropriately reduced to save processing resources while satisfying processing of image data. If a/s is equal to 100/s, the number of target devices is not processed.

Fig. 7 is a block diagram of a data processing performance determining apparatus according to an embodiment of the present application, where the apparatus may perform the data processing performance determining method according to any embodiment of the present application, and the apparatus has functional modules and beneficial effects corresponding to the performing method. As shown in fig. 7, the apparatus may include:

a target number determining module 710, configured to determine a target number of the target to be processed according to the candidate image data acquired by the candidate image acquirer;

a target image data determining module 720, configured to determine target image data from the candidate image data according to the target number;

and the data processing performance determining module 730 is configured to send the target image data to a target device for processing, and determine the data processing performance of the target device according to the processing result.

Further, the target image data determining module 720 includes:

the target image collector determining submodule is used for determining the target image collector from the candidate image collectors according to the number of targets in the candidate image data collected by the candidate image collectors;

and the target image data determining sub-module is used for determining target image data from the candidate image data acquired by the target image acquisition device according to the target quantity in the candidate image data acquired by the target image acquisition device and the theoretical processing quantity of the target equipment to be processed.

Further, the target image collector determines a sub-module comprising:

the target number determining unit is used for determining the target number of the targets to be processed in the candidate image data acquired by the candidate image acquirer in each time period in different time periods;

and the target image collector determining unit is used for determining the target image collector from the candidate image collectors according to the target quantity corresponding to each time period.

Further, the target image collector determining unit includes:

the score determining subunit is used for traversing each time period corresponding to the same time period, and determining the score of the candidate image collector in the current time period according to the duration of the current time period from the current time if the number of targets in the candidate image data in the traversed current time period is smaller than a preset number threshold;

the variance determining subunit is used for determining the sum of the scores of the candidate image collectors in each time period as a count score and determining the variance of the target quantity in the same time period;

and the target image collector determining subunit is used for determining a target image collector from the candidate image collectors according to the count scores and the variances.

Further, the score determining subunit is specifically configured to:

and determining the score of the candidate image collector in the current time period corresponding to the duration according to the negative correlation relation between the preset duration and the score.

Further, the target image collector determines the subunit, specifically for:

carrying out weighted summation on the count value and the variance to obtain a score value of the candidate image collector;

and taking the candidate image collector with the grading value smaller than the preset grading value as a target image collector.

Further, the target image data determination submodule includes:

the time period average value determining unit is used for determining the time period average value of the target number in the same time period according to the target number of the target to be processed in the candidate image data acquired by the target image acquirer in each time period corresponding to the same time period;

a unit average value determining unit for calculating a unit average value in a unit time in each time period according to the time period average value;

and the target image data determining unit is used for taking the candidate image data acquired by the target image acquisition unit in the time period as target image data if the difference value between the unit average value and the theoretical processing quantity in the time period is larger than a first preset threshold value and smaller than a second preset threshold value.

The product can execute the enhancement method of the thermal imaging image provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method.

The embodiment of the application provides electronic equipment. Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 8, an embodiment of the present application provides an electronic device 800, which includes: one or more processors 820; a storage 810 for storing one or more programs that, when executed by the one or more processors 820, cause the one or more processors 820 to implement a data processing performance determination method provided by an embodiment of the present application, the method comprising:

Of course, those skilled in the art will appreciate that processor 820 may also implement aspects of the data processing performance determination method provided in any embodiment of the present application.

The electronic device 800 shown in fig. 8 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present application.

As shown in fig. 8, the electronic device 800 includes a processor 820, a storage device 810, an input device 830, and an output device 840; the number of processors 820 in the electronic device may be one or more, one processor 820 being taken as an example in fig. 8; the processor 820, the memory device 810, the input device 830, and the output device 840 in the electronic device may be connected by a bus or other means, as exemplified in fig. 8 by the bus 850.

The storage device 810 is a computer readable storage medium, and may be used to store a software program, a computer executable program, and a module unit, such as program instructions corresponding to the data processing performance determining method in the embodiment of the present application.

The storage device 810 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for functions; the storage data area may store data created according to the use of the terminal, etc. In addition, storage 810 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, storage 810 may further include memory located remotely from processor 1020, which may be connected via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 830 may be used to receive input numeric, character information, or voice information, and to generate key signal inputs related to user settings and function control of the electronic device. Output device 840 may include an electronic device such as a display screen, speaker, etc.

The data processing performance determining device, the electronic device and the medium provided in the foregoing embodiments may execute the data processing performance determining method provided in any embodiment of the present application, and have the corresponding functional modules and beneficial effects of executing the method. Technical details not described in detail in the above embodiments may be found in the data processing performance determining method provided in any embodiment of the present application.

The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a data processing performance determining method as provided by all the inventive embodiments of the present application:

Any combination of one or more computer readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations of the present application may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

Note that the above is only a preferred embodiment of the present application and the technical principle applied. Those skilled in the art will appreciate that the present application is not limited to the particular embodiments described herein, but is capable of numerous obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the present application. Therefore, while the present application has been described in connection with the above embodiments, the present application is not limited to the above embodiments, but may include many other equivalent embodiments without departing from the spirit of the present application, the scope of which is defined by the scope of the appended claims.

Claims

1. A method of determining data processing performance, the method comprising:

2. The method of claim 1, wherein determining target image data from the candidate image data based on the target number comprises:

determining a target image collector from the candidate image collectors according to the number of targets in the candidate image data collected by the candidate image collectors;

and determining target image data from the candidate image data acquired by the target image acquisition device according to the target quantity in the candidate image data acquired by the target image acquisition device and the theoretical processing quantity of the target equipment to be processed.

3. The method of claim 2, wherein determining the target image collector from the candidate image collectors based on the number of targets in the candidate image data collected by the candidate image collectors comprises:

Determining the target quantity of targets to be processed in the candidate image data acquired by the candidate image acquirer in each time period;

and determining a target image collector from the candidate image collectors according to the target quantity corresponding to each time period.

4. A method according to claim 3, wherein determining the target image collector from the candidate image collectors based on the number of targets corresponding to each time period comprises:

traversing each time period corresponding to the same time period, and if the number of targets in the candidate image data in the traversed current time period is smaller than a preset number threshold value, determining the score of the candidate image collector in the current time period according to the duration of the current time period from the current time;

determining the sum of the scores of the candidate image collectors in each time period as a count score, and determining the variance of the target quantity in the same time period;

and determining a target image collector from the candidate image collectors according to the count scores and the variances.

5. The method of claim 4, wherein determining the score of the candidate image collector for the current time period based on the time of the current time period from the current time instant comprises:

6. The method of claim 5, wherein determining a target image collector from the candidate image collectors based on the count score and the variance comprises:

7. A method according to claim 3, wherein determining target image data from the candidate image data acquired by the target image acquisition unit based on the number of targets in the candidate image data acquired by the target image acquisition unit and the theoretical number of targets to be processed by the target device, comprises:

according to the number of targets to be processed in the candidate image data acquired by the target image acquisition unit in each time period corresponding to the same time period, determining a time period average value of the number of targets in the same time period;

Calculating a unit average value in unit time in each time period according to the time period average value;

and if the difference value between the unit average value and the theoretical processing number in the time period is larger than the first preset threshold value and smaller than the second preset threshold value, taking the candidate image data acquired by the target image acquisition device in the time period as target image data.

8. The method of claim 1, wherein prior to determining the number of objects to be processed from the candidate image data acquired by the candidate image collector, the method further comprises:

dividing the acquisition time of the candidate image data into a preset number of time intervals;

traversing each time interval, and removing the candidate image data acquired by the candidate image acquirer in the time interval if the target number of the targets to be processed in the candidate image data acquired by the candidate image acquirer in the time interval is smaller than the preset target number.

9. A data processing performance determining apparatus, the apparatus comprising:

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the data processing performance determination method of any of claims 1-8 when the computer program is executed by the processor.

11. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the data processing performance determination method according to any one of claims 1 to 8.