Camera delay statistical method and device, equipment and medium

Abstract

The invention discloses a delay statistical method and device of a camera, equipment and a medium. The method comprises the following steps: controlling a to-be-detected camera to carry out picture acquisition on a timer screen to obtain an acquired image frame, and determining a counter timestamp according to the acquired image frame; when the to-be-detected camera processes the acquired image frame, acquiring an acquisition timestamp of the acquired image frame and a candidate process timestamp of the acquired image frame; determining whether the acquisition timestamp is accurate or not according to the acquisition delay expectation of the acquisition timestamp and the timer timestamp; if yes, determining a target delay statistical result according to the target timestamp; wherein the target timestamp is the candidate flow timestamp and the collection timestamp, or is the candidate flow timestamp. According to the invention, the acquisition delay expectation is verified, so that the accuracy of the acquisition timestamp is ensured, the problem that the acquisition timestamp is deviated and counterfeited is solved, and the accuracy of judgment on the delay performance of the camera is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cameras, and in particular to a method, device, equipment and medium for counting delays of cameras. Background Art

[0002] Currently, cameras are widely used in the surveillance industry for real-time regional monitoring. In order to improve the real-time performance of the surveillance images, the surveillance industry has strict low-index requirements for the delay parameters of the cameras put into use.

[0003] The acquisition delay accounts for a large proportion of the delay parameters. The acquisition delay is affected by the acquisition timestamp. In order to meet the low delay index requirements, some manufacturers will shift the acquisition timestamp backward, making the acquired acquisition delay smaller than the actual delay, resulting in the acquired acquisition delay not being able to truly reflect the delay performance of the camera. In addition, the delay of other processes in the subsequent process is also determined based on the acquisition timestamp. Therefore, an inaccurate acquisition timestamp will also cause inaccurate delays in other processes, affecting the judgment of the camera performance. Summary of the invention

[0004] The present invention provides a camera delay statistics method, device, equipment and medium to solve the problem of inaccurate camera delay statistics.

[0005] According to one aspect of the present invention, a method for counting delay of a camera is provided, wherein the method comprises:

[0006] Control the camera to be detected to collect images of the timer screen to obtain a collected image frame, and determine the counter timestamp according to the collected image frame;

[0007] When the camera to be detected processes the acquired image frame, acquiring an acquisition timestamp of the acquired image frame and a candidate process timestamp of the acquired image frame;

[0008] Determining whether the acquisition timestamp is accurate according to the acquisition timestamp and the expected acquisition delay of the timer timestamp;

[0009] If so, determine the target delay statistics result according to the target timestamp; wherein the target timestamp is the candidate process timestamp and the acquisition timestamp, or is the candidate process timestamp.

[0010] According to another aspect of the present invention, a delay statistics device for a camera is provided, characterized in that it comprises:

[0011] The image acquisition module is used to control the camera to be detected to acquire images of the timer screen to obtain acquired image frames, and determine the counter timestamp according to the acquired image frames;

[0012] A timestamp acquisition module, used for acquiring an acquisition timestamp of the acquired image frame and a candidate process timestamp of the acquired image frame when the camera to be detected processes the acquired image frame;

[0013] A collection timestamp verification module, used to determine whether the collection timestamp is accurate based on the collection timestamp and the collection delay expectation of the timer timestamp;

[0014] The delay statistics module is used to determine the target delay statistics result according to the target timestamp if the acquisition timestamp is accurate; wherein the target timestamp is the candidate process timestamp and the acquisition timestamp, or is the candidate process timestamp.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the delay statistics method for a camera described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the delay statistics method for a camera described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention verifies the expected acquisition delay to ensure the accuracy of the acquisition timestamp, solves the problem that the acquisition timestamp may be offset and falsified, and improves the accuracy of the camera delay performance judgment.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flowchart of a method for counting delay of a camera provided according to the first embodiment of the present invention;

[0024] Figure 2 is a schematic diagram of a first acquisition time axis of a camera provided by an embodiment of the present invention;

[0025] Figure 3 is a schematic diagram of a second acquisition time axis of a camera provided in an embodiment of the present invention;

[0026] Figure 4 It is a structural schematic diagram of a delay statistics device for a camera provided according to Embodiment 3 of the present invention;

[0027] Figure 5 It is a structural schematic diagram of an electronic device for implementing the delay statistics method of a camera according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "candidate", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1A flowchart of a method for counting delays of a camera is provided for the first embodiment of the present invention. This embodiment is applicable to the case of counting delays of various processes of a camera. The method can be executed by a delay counting device of a camera. The delay counting device of the camera can be implemented in the form of hardware and / or software. The delay counting device of the camera can be configured in a camera or server with computing and communication capabilities. Figure 1 As shown, the method includes:

[0032] S110, controlling the camera to be detected to collect images of the timer screen to obtain collected image frames, and determining the counter timestamp according to the collected image frames.

[0033] In order to accurately obtain the exact timestamp of the camera to be detected at the acquisition moment, this embodiment adopts the method of aiming the camera to be detected at the timer screen for image acquisition, and the timer screen and the camera should be synchronized at the millisecond level to avoid introducing too many influencing errors in the subsequent delay calculation.

[0034] Optionally, in this embodiment, the timer timestamp displayed on the timer screen is used as the absolute timestamp of the collection moment. Since the time displayed on the timer screen cannot be displayed in milliseconds, in order to reduce the error between the timer timestamp and the absolute timestamp, the timer screen uses a millisecond timer screen with a high frame rate refresh.

[0035] Specifically, based on the millisecond-level synchronization of the timer screen, camera and decoding end, the camera to be detected is controlled to capture the image of the timer screen, the decoding end decodes the received image frame and performs text recognition, and the time on the timer screen is extracted from the text recognition result of the captured image frame as the timer timestamp.

[0036] S120 . When the camera to be detected processes the captured image frame, obtain a capture timestamp of the captured image frame and a candidate process timestamp of the captured image frame.

[0037] When the camera to be detected transmits the acquired image frames, a series of process processing is required, such as encoding process, packaging process, sending process and decoding process at the decoding end. Optionally, the candidate process includes encoding, packaging, sending and / or decoding.

[0038] Specifically, after the camera is aimed at the timer screen for image acquisition, after the acquisition module in the camera obtains a complete frame of acquisition image, the corresponding acquisition completion timestamp is recorded as the acquisition timestamp. And according to the requirements of delay statistics, the completion time corresponding to the subsequent process is recorded, that is, the candidate process timestamp.

[0039] S130: Determine whether the collection timestamp is accurate according to the collection timestamp and the collection delay expectation of the timer timestamp.

[0040] Since the collection timestamp may be offset and falsified by the manufacturer, in order to ensure the accuracy of the collection timestamp and the accuracy of the candidate delay statistics, multiple groups of collection delays are obtained, and the accuracy of the collection timestamp is judged based on the collection delay expectations of the multiple groups of collection delays.

[0041] Specifically, according to the historical statistical results of acquisition delay, the acquisition delay expectation is accurate when the preset conditions are met. Therefore, by counting the acquisition timestamps and timer timestamps corresponding to multiple groups of cameras to be detected, multiple groups of acquisition delays are determined according to the difference between the timer timestamp and the acquisition timestamp, and then according to whether the acquisition delay expectations determined by the multiple groups of acquisition delays meet the preset conditions, it is determined whether the acquisition timestamp of the camera to be detected is accurate. Optionally, the preset conditions are related to the inherent parameters of the camera to be detected.

[0042] In a feasible embodiment, the acquisition frame interval parameter of the camera to be detected is an integer multiple of the shutter time parameter, and the shutter time parameter is smaller than the screen refresh interval parameter of the timer screen;

[0043] Accordingly, determining whether the acquisition timestamp is accurate based on the acquisition delay expectation of the acquisition timestamp and the timer timestamp includes:

[0044] The acquisition delay distribution information and the acquisition delay expectation are determined according to the acquisition timestamp and the timer timestamp; if the acquisition delay distribution information conforms to the normal distribution, and the acquisition delay expectation is greater than 0 and less than the screen refresh interval parameter, the acquisition timestamp is determined to be accurate.

[0045] Specifically, the process of determining the preset conditions corresponding to the collection delay expectation is as follows:

[0046] Set the actual real time to T, which is linear and continuous. However, due to the influence of the screen refresh rate, the time displayed on the timer screen cannot be continuously refreshed at the millisecond level, and can only be updated with the screen refresh frequency. Set the screen refresh interval parameter to the constant G0, in milliseconds. Assuming that the time of the first refresh of the timer screen is X0, the display time Y on the timer screen corresponding to any real time T is: Y = X0 + (T-X0) / / G0 * G0 + △ Ts; where / / represents integer division, and △ Ts is the system random error generated by each refresh cycle. For example, for example: the time X0 of the first refresh of the timer screen is 105ms, and the screen refresh frequency is 50Hz, then the screen refresh interval parameter is 20ms; the time displayed on the timer screen will be refreshed at intervals of about 20ms: {105ms ± △ Ts, 125ms ± △ Ts, 145ms ± △ Ts...}.

[0047] The speed at which the camera collects images will be affected by the shutter time. The shutter time parameter of the camera is set to a constant G1, that is, the camera needs to go through a constant G1 from the beginning of collecting a frame of image to the completion of collection; in addition, since the collection time is discrete, the collection interval between every two frames of image is related to the camera frame rate, and the collection frame interval parameter is set to a constant G2. Assuming that the collection starts at time S, the corresponding collection timestamp is Xn, that is, the collection timestamp is Xn∈{S+0*G2+G1+△Tc, S+1*G2+G1+△Tc, S+2*G2+G1+△Tc,...,S+(n-1)*G2+G1+△Tc}; where △Tc is the system random error of each collection.

[0048] Substituting the acquisition timestamp Xn into the real time T, the timer screen display timestamp Y(n) acquired on each frame of the camera, that is, the timer timestamp should be:

[0049] Y(n)=X0+(T-X0) / / G0*G0+ΔTs;

[0050] =X0+(S+(n-1)*G2+G1+ΔTc-X0) / / G0*G0+ΔTs.

[0051] Wherein, the acquisition delay is equal to the acquisition timestamp minus the timer timestamp: Xn-Y(n)=S+(n-1)*G2+G1+△Tc-(X0+(S+(n-1)*G2+G1+△Tc-X0) / / G0*G0+△Ts)

[0052] To simplify the calculation process: take X0 as 0, that is, refresh the counter from 0 seconds; take S as the time of the first collection; then Xn-Y(n)=S+(n-1)*G2+G1+△Tc-(S+(n-1)*G2+G1+△Tc) / / G0*G0-△Ts.

[0053] Further, to determine the satisfaction rule of the acquisition delay, it is determined that when G2 is set to an integer multiple of G1, (S + (n - 1)*G2 + G1 + △Tc) / / G0 * G0 = S + (n - 1)*G2 + G1 + △Tc; further, it is set that G1 < G0, that is, the shutter time parameter is less than the screen refresh interval parameter, then it is determined according to the formula of Xn - Y(n):

[0054] When S + G1 < G0, the first acquisition time axis schematic diagram of the camera is as Figure 2 shown, then:

[0055] n = 1; X1 - Y(1) = S + G1 + △Tc - △Ts;

[0056] n = 2; X2 - Y(2) = S + G1 + △Tc - △Ts;...

[0057] Therefore, the acquisition delay Xn - Y(n) = S + G1 + △Tc - △Ts.

[0058] When S + G1 > G0, the second acquisition time axis schematic diagram of the camera is as Figure 3 shown, then:

[0059] When n = 1; X1 - Y(1) = S + G1 – G0 + △Tc - △Ts;

[0060] When n = 2; X2 - Y(2) = S + G1 – G0 + △Tc - △Ts;...

[0061] Therefore, the acquisition delay Xn - Y(n) = S + G1 – G0 + △Tc - △Ts.

[0062] From the acquisition delays obtained in the above two cases, it can be seen that the parameters involved in the acquisition delay are all constants, so the acquisition delay is also a constant, that is, the acquisition delay satisfies the normal distribution, and according to the formula, it can be known that the expected value of the acquisition delay is greater than 0 and less than G0. Correspondingly, it is determined that the preset condition is to satisfy the normal distribution, and the acquisition delay expectation is greater than 0 and less than G0.

[0063] Specifically, according to the determination process of the above preset conditions, when judging whether the acquisition timestamp is accurate according to the preset conditions, it is necessary to set the acquisition frame interval parameter of the camera to be detected as an integer multiple of the shutter time parameter, and the shutter time parameter is less than the screen refresh interval parameter of the timer screen. On this basis, multiple groups of acquisition delays are obtained, and the acquisition delay expectation is determined according to the acquisition delays. If it is determined that the acquisition delay distribution information conforms to the normal distribution according to multiple groups of acquisition delays, and the acquisition delay expectation is greater than 0 and less than the screen refresh interval parameter, then it is determined that the acquisition timestamp is accurate.

[0064] Exemplarily, when the acquisition timestamp is offset and falsified, there are two situations: a fixed offset backward and a random offset backward. When the acquisition timestamp is offset backward, the acquisition delay expectation is calculated to be always greater than G0, so the verification of the acquisition timestamp is inaccurate; further, in order to avoid the situation where the acquisition delay expectation is always greater than G0 when the acquisition timestamp is offset and falsified, the acquisition timestamp is randomly offset backward, but because it is a random offset, the acquisition delay distribution will not conform to the normal distribution, so the verification of the acquisition timestamp is inaccurate. In summary, through the above preset conditions, it can be determined whether the acquisition timestamp is accurate through the acquisition delay distribution and the acquisition delay expectation.

[0065] S140: If the acquisition timestamp is accurate, determine the target delay statistics result according to the target timestamp; wherein the target timestamp is the candidate process timestamp and the acquisition timestamp, or is the candidate process timestamp.

[0066] If the acquisition timestamp is inaccurate, it is necessary to calibrate the internal parameters of the camera to be detected, and then perform delay statistics until the acquisition timestamp is verified to be accurate. If the acquisition timestamp is accurate, the delay statistics result can be determined based on the difference in the corresponding process timestamps.

[0067] In one possible embodiment, the candidate flow timestamp includes an encoding flow timestamp;

[0068] Accordingly, the target delay statistics are determined according to the target timestamp, including:

[0069] The encoding delay statistics are obtained based on the encoding process timestamp and the acquisition timestamp.

[0070] The encoding process refers to the encoding action performed by the camera before transmitting the captured image frame. For example, the captured image frame is encoded into H.264 format for transmission. The timestamp when the encoding module in the camera completes encoding of each captured image frame is determined as the encoding process timestamp. For example, the encoding process timestamp is recorded after each frame completes the corresponding encoding format.

[0071] Specifically, when determining the coding delay statistics corresponding to the coding process, the coding delay is determined according to the coding process timestamp and the acquisition timestamp, and the coding delay statistics are determined according to multiple groups of coding delays. The coding delay statistics include coding delay distribution information. In a feasible embodiment, the coding delay statistics include coding delay expectations and coding delay variances. Specifically, the coding delay expectations and coding delay variances are determined according to multiple groups of coding delays.

[0072] In a feasible embodiment, the candidate flow timestamps include a packet flow timestamp and a decoding flow timestamp;

[0073] Accordingly, the target delay statistics are determined according to the target timestamp, including:

[0074] The network transmission delay statistics are obtained based on the packet process timestamp and the decoding process timestamp.

[0075] Among them, the packetization process refers to the action of the camera to package the encoded image frames. After the image frames are packaged, the camera will send the packaged image frames to the decoding end; the decoding process refers to the receiving and decoding action of the receiving module of the decoding end on the packaged image frames transmitted by the camera.

[0076] Specifically, when determining the network transmission delay statistics corresponding to the network transmission process, the network transmission delay is determined according to the difference between the decoding process timestamp and the packet process timestamp, and the network transmission delay statistics are determined according to multiple groups of network transmission delays. The network transmission delay statistics include network transmission delay distribution information. In a feasible embodiment, the network transmission delay statistics include network transmission delay expectation and network transmission delay variance. Specifically, the network transmission delay expectation and network transmission delay variance are determined according to multiple groups of network transmission delays.

[0077] In a feasible embodiment, after determining the target delay statistical result according to the target timestamp, the method further includes:

[0078] Determine the accuracy of the target delay statistics results based on the normal distribution verification results of the target delay;

[0079] Determine the target process performance evaluation results based on the delay expectation;

[0080] The target process stability evaluation result is determined based on the delay variance.

[0081] Among them, the target delay includes acquisition delay, encoding delay and network transmission delay, the delay expectation includes acquisition delay expectation, encoding delay expectation and network transmission delay expectation, and the delay variance includes acquisition delay variance, encoding delay variance and network transmission delay variance.

[0082] Specifically, the accuracy of the corresponding delay statistics can be determined according to the acquisition delay, encoding delay and network transmission delay. Exemplarily, if the encoding delay does not satisfy the normal distribution, it is determined that there is an error in the encoding delay statistics, that is, there is an error in the encoding process timestamp. The performance evaluation results of the corresponding process can be determined according to the acquisition delay expectation, encoding delay expectation and network transmission delay expectation. Exemplarily, the lower the acquisition delay expectation, the better the camera acquisition performance; the lower the encoding delay expectation, the better the device encoding and ISP performance; the lower the network transmission delay expectation, the better the camera network card performance. The stability evaluation results of the corresponding process can be determined according to the acquisition delay variance, encoding delay variance and network transmission delay variance. Exemplarily, the lower the acquisition delay variance, the better the camera acquisition stability; the lower the encoding delay variance, the better the device encoding and ISP stability; the lower the network transmission delay variance, the better the camera network card stability.

[0083] The technical solution of the embodiment of the present invention verifies the expected acquisition delay to ensure the accuracy of the acquisition timestamp, solves the problem that the acquisition timestamp may be offset and falsified, and improves the accuracy of the camera delay performance judgment.

[0084] Embodiment 2

[0085] This embodiment provides another method for counting the delay of a camera, and this embodiment is a preferred example of the above embodiment. The method includes:

[0086] First, the timer screen, camera, and decoder are synchronized at the millisecond level.

[0087] Set the acquisition frame interval parameter of the camera to be detected to an integer multiple of the shutter time parameter, and the shutter time parameter is smaller than the screen refresh interval parameter of the timer screen. Control the camera to aim at the timer screen to collect the picture, and record the absolute timestamp of the current collected picture as TimeStamp_Original.

[0088] The camera acquisition module records the acquisition timestamp TimeStamp_VI when each frame of image is acquired. Exemplarily, the acquisition timestamp is usually recorded when the acquisition module obtains the complete first frame of RAW data.

[0089] The camera encoding module records the encoding process timestamp TimeStamp_Encode of each frame after the encoding is completed. For example, the encoding process timestamp is usually recorded after each frame completes the corresponding encoding format such as H.264.

[0090] The camera packaging module records the packet process timestamp TimeStamp_PACKET of each frame after the packaging is completed. For example, it is usually recorded after the packet operation is completed for each frame, such as RTP packet.

[0091] The camera sending module adds all the above timestamps (TimeStamp_VI, TimeStamp_Encode, TimeStamp_PACKET) to the transmission data SEI and sends it out with each frame of data.

[0092] The receiving module at the decoding end records the decoding process timestamp TimeStamp_Recv of each frame received.

[0093] The decoding end performs text recognition after decoding each frame and extracts the timer time TimeStamp_Original from the image screen.

[0094] The acquisition delay distribution information and the expected acquisition delay are determined based on the acquisition timestamp TimeStamp_VI and the timer timestamp TimeStamp_Original. If the acquisition delay distribution information conforms to the normal distribution and the expected acquisition delay is greater than 0 and less than the screen refresh interval parameter, the acquisition timestamp is determined to be authentic and valid to prevent tampering with the acquisition timestamp.

[0095] The encoding process timestamp minus the acquisition timestamp gets the encoding delay (TimeStamp_Encode-TimeStamp_VI). The encoding delay is a key data reflecting the device encoding and ISP performance.

[0096] The decoding process timestamp minus the packet process timestamp gets the network transmission delay (TimeStamp_Recv-TimeStamp_Encode). The network transmission delay reflects the performance of the device network card.

[0097] Furthermore, the normal distribution of coding delay and network transmission delay can be verified to verify the accuracy of coding delay and network transmission delay. Then, the coding delay expectation and coding delay variance, as well as the network transmission delay expectation and network transmission delay variance are obtained based on coding delay and network transmission; the performance of the corresponding process is evaluated by expectation, and the stability of the corresponding process is evaluated by variance.

[0098] This embodiment can realize the delay statistics of the entire process of acquisition, encoding, packaging, and transmission performed by the camera during monitoring, thereby improving the efficiency of delay statistics; and by performing delay statistics through constraint conditions, the delay data can be converged to a normal distribution to ensure the reliability of the acquisition timestamp; and the expectation and variance analysis of the delay results of each process link can be performed to obtain the evaluation results of performance and stability.

[0099] Embodiment 3

[0100] Figure 4 This is a schematic diagram of the structure of a camera delay statistics device provided by the third embodiment of the present invention. Figure 4 As shown, the device comprises:

[0101] The image acquisition module 410 is used to control the camera to be detected to acquire images of the timer screen to obtain acquired image frames, and determine the counter timestamp according to the acquired image frames;

[0102] A timestamp acquisition module 420, configured to acquire an acquisition timestamp of the acquired image frame and a candidate process timestamp of the acquired image frame when the camera to be detected processes the acquired image frame;

[0103] A collection timestamp verification module 430, configured to determine whether the collection timestamp is accurate based on the collection timestamp and the collection delay expectation of the timer timestamp;

[0104] The delay statistics module 440 is used to determine a target delay statistics result according to a target timestamp if the acquisition timestamp is accurate; wherein the target timestamp is the candidate process timestamp and the acquisition timestamp, or is the candidate process timestamp.

[0105] Optionally, the acquisition frame interval parameter of the camera to be detected is an integer multiple of a shutter time parameter, and the shutter time parameter is smaller than a screen refresh interval parameter of the timer screen;

[0106] Correspondingly, the acquisition timestamp verification module is specifically used for:

[0107] Determine acquisition delay distribution information and acquisition delay expectation according to the acquisition timestamp and the timer timestamp;

[0108] If the acquisition delay distribution information conforms to a normal distribution, and the acquisition delay expectation is greater than 0 and less than the screen refresh interval parameter, it is determined that the acquisition timestamp is accurate.

[0109] Optionally, the candidate process timestamp includes an encoding process timestamp;

[0110] Correspondingly, the delay statistics module is specifically used for:

[0111] The coding delay statistics result is obtained according to the coding process timestamp and the acquisition timestamp.

[0112] Optionally, the coding delay statistics include coding delay expectation and coding delay variance.

[0113] Optionally, the candidate process timestamps include a packetization process timestamp and a decoding process timestamp;

[0114] Correspondingly, the delay statistics module is specifically used for:

[0115] The network transmission delay statistics result is obtained according to the packet process timestamp and the decoding process timestamp.

[0116] Optionally, the network transmission delay statistics include network transmission delay expectation and network transmission delay variance.

[0117] Optionally, the device further comprises a performance evaluation module, which is used to, after determining the target delay statistical result according to the target timestamp,

[0118] Determine the accuracy of the target delay statistical result according to the normal distribution verification result of the target delay;

[0119] Determine the target process performance evaluation results based on the delay expectation;

[0120] The target process stability evaluation result is determined based on the delay variance.

[0121] The delay statistics device for a camera provided in an embodiment of the present invention can execute the delay statistics method for a camera provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0122] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations and do not violate public order and good morals.

[0123] Embodiment 4

[0124] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0125] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0126] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0127] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0128] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for time-delay statistics of a camera.

[0129] In some embodiments, the method of delay statistics of the camera can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the delay statistics of the camera described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the delay statistics of the camera in any other appropriate manner (for example, by means of firmware).

[0130] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific reference products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0131] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0132] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0133] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0134] The systems and techniques described herein may be implemented in a computing system that includes a backend component (e.g., as a data server), or a computing system that includes a switch component (e.g., an application server), or a computing system that includes a frontend component (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, switch components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0135] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0136] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0137] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A camera delay statistics method, characterized in that: The method includes: Control the camera to be detected to collect images of the timer screen to obtain a collected image frame, and determine the counter timestamp according to the collected image frame; When the camera to be detected processes the acquired image frame, acquiring an acquisition timestamp of the acquired image frame and a candidate process timestamp of the acquired image frame; Determining whether the acquisition timestamp is accurate according to the acquisition timestamp and the expected acquisition delay of the timer timestamp; If so, determine the target delay statistics result according to the target timestamp; wherein the target timestamp is the candidate process timestamp and the acquisition timestamp, or is the candidate process timestamp.

2. The method according to claim 1, characterized in that in, The acquisition frame interval parameter of the camera to be detected is an integer multiple of the shutter time parameter, and the shutter time parameter is smaller than the screen refresh interval parameter of the timer screen; Correspondingly, determining whether the acquisition timestamp is accurate according to the acquisition timestamp and the expected acquisition delay of the timer timestamp includes: Determine acquisition delay distribution information and acquisition delay expectation according to the acquisition timestamp and the timer timestamp; If the acquisition delay distribution information conforms to a normal distribution, and the acquisition delay expectation is greater than 0 and less than the screen refresh interval parameter, it is determined that the acquisition timestamp is accurate.

3. The method according to claim 1, characterized in that The candidate flow timestamp includes an encoding flow timestamp; Accordingly, the target delay statistics are determined according to the target timestamp, including: The coding delay statistics result is obtained according to the coding process timestamp and the acquisition timestamp.

4. The method according to claim 3, characterized in that The coding delay statistics include coding delay expectation and coding delay variance.

5. The method according to claim 1, characterized in that The candidate process timestamps include a packet process timestamp and a decoding process timestamp; Accordingly, the target delay statistics are determined according to the target timestamp, including: The network transmission delay statistics result is obtained according to the packet process timestamp and the decoding process timestamp.

6. The method according to claim 5, characterized in that The network transmission delay statistical result includes the network transmission delay expectation and the network transmission delay variance.

7. The method according to claim 4 or 6, characterized in that: After determining the target delay statistical result according to the target timestamp, the method further includes: Determine the accuracy of the target delay statistical result according to the normal distribution verification result of the target delay; Determine the target process performance evaluation results based on the delay expectation; The target process stability evaluation result is determined based on the delay variance.

8. A camera delay statistics device, characterized in that: include: The image acquisition module is used to control the camera to be detected to acquire images of the timer screen to obtain acquired image frames, and determine the counter timestamp according to the acquired image frames; A timestamp acquisition module, used for acquiring an acquisition timestamp of the acquired image frame and a candidate process timestamp of the acquired image frame when the camera to be detected processes the acquired image frame; A collection timestamp verification module, used to determine whether the collection timestamp is accurate based on the collection timestamp and the collection delay expectation of the timer timestamp; The delay statistics module is used to determine the target delay statistics result according to the target timestamp if the acquisition timestamp is accurate; wherein the target timestamp is the candidate process timestamp and the acquisition timestamp, or is the candidate process timestamp.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the time-delay statistics method for a camera according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the delay statistics method for a camera according to any one of claims 1 to 7 when executed.

Images