WO2023174346A1

WO2023174346A1 - Collision detection method, electronic device, and computer readable medium

Info

Publication number: WO2023174346A1
Application number: PCT/CN2023/081702
Authority: WO
Inventors: 刘旸; 刘芙蕾; 黄河
Original assignee: 中兴通讯股份有限公司
Priority date: 2022-03-16
Filing date: 2023-03-15
Publication date: 2023-09-21
Also published as: CN116805966A

Abstract

The present disclosure provides a collision detection method, comprising: determining a detection moment of at least one video frame in at least one conflict detection window, wherein the detection moment of the video frame comprises a start moment and an end moment of the video frame; according to the detection moment of the video frame, generating a set to be detected corresponding to the conflict detection window, wherein detection moments in said set are arranged in a time sequence; and performing collision detection on the video frame according to said set corresponding to the conflict detection window. The present disclosure further provides an electronic device and a computer readable medium.

Description

Collision detection method, electronic device, computer readable medium

Cross-references to related applications

This application claims priority to Chinese patent application CN 202210258184.6 titled "Collision detection method, electronic device, computer-readable medium" submitted on March 16, 2022, the entire content of which is incorporated herein by reference.

Technical field

The present disclosure relates to the field of communication technology, and specifically to a collision detection method, an electronic device, and a computer-readable medium.

Background technique

Video data packets are transmitted in frame units. Common frame types include I frames and P frames. The I frame constructs the image background and moving subjects, contains complete picture information, and has a low compression rate. It is the basis for P frame decoding. P frames rely on I frames for inter-frame prediction, difference transmission, and higher compression rates.

Since the amount of data in an I frame is much larger than that of a P frame, after passing through a bandwidth-limited transmission channel, the I frame will take up more transmission time, which may cause reception delays at the receiving end. If the transmission time of the I frame exceeds a certain threshold, it will cause video playback freeze at the receiving end.

I-frame collision has become an important factor affecting video user experience.

Contents of the invention

Embodiments of the present disclosure provide a collision detection method, an electronic device, and a computer-readable medium.

In a first aspect, an embodiment of the present disclosure provides a collision detection method, including: determining a detection time of at least one video frame in at least one conflict detection window, wherein the detection time of the video frame includes a starting time and an end of the video frame. time; generate a set to be detected corresponding to the conflict detection window according to the detection time of the video frame, wherein the detection times in the set to be detected are arranged in chronological order; according to the conflict detection window corresponding The set to be detected is used for collision detection of video frames.

In a second aspect, embodiments of the present disclosure provide an electronic device, including: one or more processors; a memory on which one or more programs are stored. When the one or more programs are processed by the one or more The processor executes, so that the one or more processors implement the collision detection method described in the first aspect of the embodiment of the present disclosure.

In a third aspect, an embodiment of the present disclosure provides a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the collision detection method described in the first aspect of the embodiment of the present disclosure is implemented.

Description of the drawings

Figure 1 is a flow chart of the collision detection method provided by the present disclosure;

Figure 2 is a block diagram of the electronic device provided by the present disclosure;

Figure 3 is a block diagram of a computer-readable medium provided by the present disclosure;

Figure 4 is a schematic diagram of collision detection provided by the present disclosure;

Figure 5 is another schematic diagram of collision detection provided by the present disclosure.

Detailed ways

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the collision detection method, electronic equipment, and computer-readable media provided by the present disclosure will be described in detail below in conjunction with the accompanying drawings.

Example embodiments will be described more fully below with reference to the accompanying drawings, which may, however, be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully understand the scope of the disclosure to those skilled in the art.

The embodiments of the present disclosure and the features in the embodiments may be combined with each other without conflict.

As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

The terminology used herein is used to describe particular embodiments only and is not intended to limit the disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well. formula, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and/or "made of" are used in this specification, the presence of stated features, integers, steps, operations, elements and/or components is specified but does not exclude the presence or Add one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be construed to have meanings consistent with their meanings in the context of the relevant art and the present disclosure, and will not be construed as having idealized or excessive formal meanings, Unless expressly so limited herein.

Referring to Figure 1, the present disclosure provides a collision detection method, including steps S1 to S3.

In step S1, the detection time of at least one video frame in at least one conflict detection window is determined, wherein the detection time of the video frame includes the start time and the end time of the video frame.

In step S2, a set to be detected corresponding to the conflict detection window is generated according to the detection time of the video frame, where the detection times in the set to be detected are arranged in chronological order.

In step S3, collision detection of video frames is performed according to the set to be detected corresponding to the conflict detection window.

The embodiment of the present disclosure places no special limit on the length of the conflict detection window. In some embodiments, the length of the conflict detection window can be set as needed.

The embodiment of the present disclosure does not impose special limitations on video frames. For example, a video frame can be an I frame or a P frame.

In the embodiment of the present disclosure, video frame collision means that several video frames overlap in transmission time. The embodiment of the present disclosure does not place a special limit on the number of video frames colliding at the same time. For example, the number of colliding video frames may be 1, indicating that no collision occurs; the number of colliding video frames may be 2 or more.

In the embodiment of the present disclosure, performing collision detection may include determining the combination of video frames in which the collision occurs, determining the time when the collision occurs, determining the probability of collision, determining the duty cycle, and determining the time of collision. of traffic. The embodiments of the present disclosure do not impose special limitations on this.

In the collision detection method provided by the embodiment of the present disclosure, the start time and end time of the video frame are determined, and the start time and end time of the video frame are formed into a set to be detected in chronological order, and then the video is performed based on the set to be detected. Frame collision detection can determine the time of collision, collision probability, duty cycle, traffic during collision, etc., which can serve as the basis for subsequent I-frame avoidance and help improve the video user experience.

In the embodiment of the present disclosure, when generating a set to be detected corresponding to the conflict detection window based on the detection time of the video frame, the following rules need to be met: In a conflict detection window, several video frames with only the end time and no start time will be generated. The starting time is set to the first time. The first time can be the starting time of the conflict detection window, or the starting time of any one of the several video frames, or it can be any time, as long as it ensures that there is only the end time. , the starting time of video frames without starting time can all be the same; in a conflict detection window, the ending time of several video frames with only starting time and no ending time is set as the second time, and the second time can be It is the end time of the conflict detection window, or it can be the end time of any one of the several video frames, or it can be any time, as long as the end time of several video frames with only the starting time and no end time is ensured to be the same. ; Put the end time on the boundary of the conflict detection window into the set to be detected corresponding to the previous conflict detection window, and put the starting time on the boundary of the conflict detection window into the set to be detected corresponding to the next conflict detection window.

The embodiment of the present disclosure does not place any special limitations on how to perform collision detection on video frames.

In some embodiments, performing collision detection of video frames based on the set to be detected corresponding to the conflict detection window (ie, step S3) includes: determining the number of frames in the conflict detection window based on the set to be detected corresponding to the conflict detection window. The number of n-stream collisions that occur, where n-stream collision means that the transmission periods of n video frames overlap in time, and n is an integer greater than or equal to 1.

In some embodiments, determining the number of n-flow collisions in the conflict detection window according to the set to be detected corresponding to the conflict detection window includes: according to the detection time in the set to be detected corresponding to the conflict detection window. In order, each target detection time is detected in turn to determine the number of n-flow collisions in the conflict detection window, where the target detection time is the detection time when the flag bit in the set to be detected is the first flag bit, The first flag indicates that the corresponding detection time has not been detected; wherein, the target Detection at the detection time includes: determining the number of n-flow collisions before the target detection time, n, based on the relationship between the target detection time and the previous detection time, and the flag bits of each detection time before the target detection time. is an integer greater than or equal to 1.

In some embodiments, based on the relationship between the target detection moment and the previous detection moment, and the flag bits of each detection moment before the target detection moment, determining the number of n-flow collisions before the target detection moment includes: When the target detection time is the same as the previous detection time and the target detection time is the end time, set the flag bit of the target detection time and the flag bit of the start time corresponding to the target detection time. is the second flag bit, which indicates that the corresponding detection time has been detected; when the target detection time is different from the previous detection time, and the target detection time is the starting time, the previous detection time is In the case of the starting time, count the number i of starting times before the target detection time when the flag bit is the first flag bit, and add 1 to the first counter corresponding to the i-flow collision, where i is a positive integer; In the case that the target detection time is different from the previous detection time and the target detection time is the end time, count the number j of the start time whose flag bit is the first flag bit before the target detection time, Add 1 to the first counter corresponding to the collision of j stream, where j is a positive integer; set the flag bit of the target detection time and the flag bit of the starting time corresponding to the target detection time as the second flag bit .

For example, the set to be detected is represented by an array t, and each detection moment corresponds to an element in the array t; flag=0 represents the first flag bit, flag=1 represents the second flag bit; the length of the array t is N, k= 2...N, that is, starting from the second element, retrieve the value of flag=0 in the array;

In the case where t[k] is equal to t[k-1]:

If t[k] is the starting time (starttime), it will not be processed;

If t[k] is the end time (endtime), set the flag=1 of the starttime of the corresponding stream to t[k] and the flag=1 of the endtime;

When t[k] is not equal to t[k-1]:

If t[k] is starttime, if t[k-1] is endtime, it will not be processed; otherwise, the number of flows i with flag = 0 in the starttime before t[k] is counted, and the i flows are considered to have collided (i.e., occurred i stream collision), the corresponding first counter counter_i+1;

If t[k] is endtime, count the number j of flows with flag=0 in starttime before this value, and consider that the j flows collide (that is, j flow collision occurs), and the corresponding counter_j+1;

Set the flag=1 of the starttime and the flag=1 of the endtime of the corresponding stream in t[k].

In some embodiments, performing collision detection of video frames according to the set to be detected corresponding to the conflict detection window (ie, step S3) also includes: determining the occurrence of n-stream collisions based on the number of n-stream collisions in the conflict detection window. The combination of colliding video streams and the time period during which n streams collide, where n is an integer greater than or equal to 1.

In some embodiments, the first collision probability is calculated based on actual counting results.

Correspondingly, in some embodiments, performing collision detection of video frames according to the set to be detected corresponding to the conflict detection window (ie, step S3) also includes: determining based on the number of n-stream collisions occurring in the conflict detection window. A first collision probability, wherein the first collision probability represents the probability of n-flow collision occurring, and n is an integer greater than or equal to 1.

In some embodiments, determining the first collision probability according to the number of n-flow collisions occurring in the conflict detection window includes: in the case that the first counter corresponding to the n-flow collision is not cleared, according to the collision detection window corresponding of the set to be detected, determine the number of n-flow collisions in the conflict detection window, and obtain the total number of n-flow collisions, where n is an integer greater than or equal to 1; accumulate the value of the first counter to obtain the number of collisions. The total number of times; the first collision probability is calculated based on the total number of n-flow collisions and the total number of collisions.

For example, calculating the first collision probability can be expressed as the following formula:

Among them, _Pi represents the probability of i-flow collision, counter_i represents the number of i-flow collisions, and i is a positive integer.

In some embodiments, the second collision probability is calculated based on the event count results.

Correspondingly, in some embodiments, performing collision detection of video frames according to the set to be detected corresponding to the conflict detection window (ie, step S3) also includes: determining based on the number of n-stream collisions occurring in the conflict detection window. A second collision probability, wherein the second collision probability represents the probability that n flow collisions are the maximum number of flow collisions, and n is an integer greater than or equal to 1.

In some embodiments, according to the number of n-flow collisions occurring in the conflict detection window, Determining the second collision probability includes: for the conflict detection window, determine the maximum value of n according to the number of n-flow collisions in the conflict detection window to obtain the maximum number of flow collisions; and add the second counter corresponding to the maximum number of flow collisions Add 1; calculate the second collision probability according to the value of the second counter and the number of conflict detection windows.

For example, calculating the second collision probability can be expressed as the following formula:

Among them, P _i,max represents the probability that the i-flow collision is the maximum number of flow collisions in the conflict detection window, counter_i_max represents the number of conflict detection windows corresponding to the i-flow collision being the maximum number of flow collisions in the conflict detection window, and the "total number of sampling times" is the conflict The total number of detection windows.

In some embodiments, performing collision detection of video frames according to the to-be-detected set corresponding to the conflict detection window (ie, step S3) also includes: calculating a duty cycle, where the duty cycle represents the total proportion of n-stream collisions. The proportion of time, n is an integer greater than or equal to 1.

In the embodiment of the present disclosure, the duty cycle is the ratio of the collision time of n streams to the total sampling time.

For example, the duty cycle is calculated as follows: 1 frame collision duty cycle = conflictPeriod_1/total time; 2 frame collision duty cycle = conflictPeriod_2/total time; and so on..., n frame collision duty cycle = conflictPeriod_n/total time.

Among them, conflictPeriod_n represents the collision time of n streams.

In some embodiments, performing collision detection of video frames according to the to-be-detected set corresponding to the conflict detection window (ie, step S3) also includes: calculating the traffic when n flow collisions occur, where n is greater than or equal to 1. integer.

For example, calculating the flow rate when n-flow collision occurs is as follows:

Calculate the traffic (kbps) of each video frame l where n-stream collision occurs: Among them, starttime(l) represents the starting time of video frame l, and endtime(l) represents the end time of video frame l;

Calculate the traffic (kbps) when n-flow collision occurs:

In some embodiments, determining the detection moment of at least one video frame in at least one conflict detection window (ie, step S1) includes: aggregating messages at a target aggregation level and determining the detection moment of the video frame, wherein, The above target aggregation levels include camera level, Either application level or cell level.

In some embodiments, determining the detection moment of at least one video frame in at least one conflict detection window (ie, step S1) includes: determining the detection moment of the video frame according to video frame level data.

Referring to Figure 2, the present disclosure also provides an electronic device, which includes: one or more processors 101; a memory 102 on which one or more programs are stored. When one or more programs are processed by one or more processors, Execute, causing one or more processors to implement any of the above collision detection methods.

In addition, the electronic device may also include one or more I/O interfaces 103, connected between the processor and the memory, and configured to implement information exchange between the processor and the memory.

The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU), etc.; the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically such as SDRAM). , DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); the I/O interface (read-write interface) 103 is connected between the processor 101 and the memory 102 to implement The processor 101 interacts with information of the memory 102, including but not limited to a data bus and the like.

In some embodiments, processor 101, memory 102, and I/O interface 103 are connected to each other and, in turn, to other components of the computing device via bus 104.

Referring to FIG. 3 , the present disclosure also provides a computer-readable medium on which a computer program is stored. When the program is executed by a processor, any one of the above collision detection methods is implemented.

In order to enable those skilled in the art to more clearly understand the technical solutions provided by the embodiments of the present disclosure, the technical solutions provided by the embodiments of the present disclosure are described in detail below through specific examples.

Example

This example uses the video frame as an I frame for illustration. This example does not impose special restrictions on application scenarios. For example, it can be a camera-level data flow aggregation scenario, an application-level APP data flow aggregation scenario, or a cell-level data flow aggregation scenario.

The data to be detected includes IP packet-level data contained in I frames in the video stream (this solution does not provide specific video stream service identification technology), including but not limited to: the arrival time of the IP packet, IP five-tuple information, Packet size information, etc.

The data to be detected includes video stream data at multiple aggregation levels, including but not limited to the following levels.

Camera level: Identify based on IP five-tuple, and perform collision detection on camera-level video IP packet flow.

APP level: Identified based on IP address (addr) and port number (port). Collision detection is performed after aggregating the video IP packet streams of the same APP.

Cell level: Identified based on NR CGI (Cell Global Identifier, cell global identifier). Collision detection is performed after aggregating video IP packet flows in the same cell.

Optionally, the data to be detected may also include video frame-level data such as I frames and P frames calculated after preprocessing, including but not limited to: frame start time, frame end time, frame duration, frame type, IP quintuple information, frame size information, etc.

I-frame collision detection includes:

Set the conflict detection window (conflictWindow). The length of the conflict detection window can be set to any value as needed. Based on the current device local time, record the arrival time of the first IP data packet of the I frame of each video stream within the conflict detection window as the start time (starttime) of the I frame. Record the arrival time of the last IP data packet of the I frame as the end time of the I frame.

Set the flag bit flag for each I frame's starttime and endtime respectively and initialize it to 0. The purpose of this flag is to determine whether the current moment has been used to calculate the collision probability. When flag=0, it means that the time corresponding to the flag participates in the probability calculation; when flag=1, it means that the time corresponding to the flag does not participate in the collision probability calculation.

A set of I-frame collision counters counter_n (n=1, 2, 3...) is set for each conflict detection window, which is used to record the number of n I-frame collisions in the current window. counter_1 represents the number of times an I frame (ie, no collision) is recorded. Initialize all counters to 0.

For example, assume that the statistical results in a certain conflict detection window (assuming there are 5 video streaming services) are counter_2=2, counter_3=1, and other counters are all 0, that is, there are two two-frame collisions and one three-frame collision. Frame collision.

step 1:

Combine and sort the starttime and endtime of all flows within the conflict detection window, Generate the set t. If some flows within the conflict detection window only have endtime, the starttime of these flows will also be put into this set and set to the same value. The endtime on the boundary of the conflict detection window is put into the set of the previous conflict detection window, and the starttime on the boundary of the conflict detection window is put into the set of the next conflict detection window.

As shown in the example in Figure 4, there are a total of 6 I frames of the video stream in two adjacent conflict detection windows. The set t detected by conflict detection window 2 is:

t＝[4_starttime,5_starttime,4_endtime,5_endtime,6_start time,6_endtime];

It should be noted that in Figure 4, the I frame start time 4_starttime of stream 4 and the I frame start time 5_starttime of stream 5 can be set to the starting time of conflict detection window 2; they can also be set to 4_starttime of stream 4. The principle is 4_starttime The value of 5_starttime must be set to the same value, otherwise the number of collision frames will be overcounted.

Step 2:

Assume that the length of the combined sorted array t in step 1 is N, k=2...N, that is, the value of flag=0 in the array is retrieved starting from the second element.

In the case where t[k] is equal to t[k-1]:

If t[k] is the starting time (starttime), it will not be processed;

When t[k] is not equal to t[k-1]:

When a collision is detected, it is necessary to record the colliding flow combination (for example, a 4-flow collision records each flow number [3, 6, 10, 19]), and calculate the collision time period corresponding to each flow collision combination conflictPeroid= t[i]-t[i-1], unit millisecond (ms).

1) Calculate collision probability:

This example provides two methods for calculating collision probability: the method based on actual counts and the method based on event counts. The difference between the two methods is that the counting algorithm of the collision counter in the collision detection window is different. The method based on actual counting can record the number of all collision combinations that occur within the current conflict detection window; the method based on event counting is based on the previous counting method and filters out the events with the largest number of collisions within the conflict detection window. That is, what is considered based on the event counting method is that what needs to be resolved within a certain period of time is the event of the scene with the largest number of collision frames.

As shown in the example in Figure 5, there are a total of 6 video I frames in three adjacent conflict detection windows. Taking conflict detection window 1 as an example, in the current sudden detection window, the counting results output based on the actual count number are counter_1=1, counter_2=1, that is, one frame collision is recorded in the current sudden detection window ( i.e. no collision) and a two-frame collision. The method based on event counting only outputs the maximum number of collision flows counter_2=1 recorded in the current sudden detection window, that is, two frame collisions have occurred in the current sudden detection window.

a. The first collision probability based on the actual counting results:

After the detection of the current conflict window is completed, count the number of conflicts for each I frame, save the counter count result and accumulate it with the counter value corresponding to the next detection result, and finally count the total number of each counter.

Calculating the first collision probability can be expressed as the following formula:

b. Second collision probability based on event counting results:

After the current conflict window detection is completed, only the event with the largest number of collision frames (i.e., the largest n value among non-zero values in counter_n) is recorded, and the corresponding event counter (i.e., the second counter) count_n+1; each conflict detection After the window detection is completed, the counter of each actual count number of I frame collisions (ie, the first counter) is cleared to 0.

Calculating the second collision probability can be expressed as the following formula:

Among them, P _i,max represents the probability that the i-flow collision is the maximum number of flow collisions in the conflict detection window, and counter_i_max represents the probability that the i-flow collision is the maximum number of flow collision pairs in the conflict detection window. The corresponding number of conflict detection windows, "total sampling times" is the total number of conflict detection windows.

2) Calculate the duty cycle:

After the detection of the current conflict window is completed, count the number of conflicts for each I frame, save the counter count results and accumulate them with the counter values corresponding to the next detection results, and finally count the total number of each counter.

After the detection is completed, the time of all types of I frame collisions is obtained, and the total time is calculated. The total time is the sum of the times for all types of I-frame collisions. The I frame collision duty cycle is calculated as follows: 1 frame collision duty cycle = conflictPeriod_1/total time; 2 frame collision duty cycle = conflictPeriod_2/total time; and so on..., n frame collision duty cycle = conflictPeriod_n/total time .

Among them, conflictPeriod_n represents the collision time of n streams.

3) Calculate the flow rate when n-flow collision occurs:

Calculate the traffic (kbps) when n-flow collision occurs:

Those of ordinary skill in the art can understand that all or some steps, systems, and functional modules/units in the devices disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may consist of several physical components. Components execute cooperatively. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit . Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As is known to those of ordinary skill in the art, the term computer storage media includes volatile and nonvolatile media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. removable, removable and non-removable media. computer storage media Including but not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disk (DVD) or other optical disk storage, magnetic cassettes, tapes, magnetic disk storage or other magnetic storage devices, or may be used for storage Any other medium on which the information is desired and can be accessed by the computer. Additionally, it is known to those of ordinary skill in the art that communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media .

Example embodiments have been disclosed herein, and although specific terms are employed, they are used and should be interpreted in a general illustrative sense only and not for purpose of limitation. In some instances, it will be apparent to those skilled in the art that features, characteristics and/or elements described in connection with a particular embodiment may be used alone, or may be used in conjunction with other embodiments, unless expressly stated otherwise. Features and/or components used in combination. Accordingly, it will be understood by those skilled in the art that various changes in form and details may be made without departing from the scope of the present disclosure as set forth in the appended claims.

Claims

A collision detection method including:

Determine a detection time of at least one video frame in at least one conflict detection window, wherein the detection time of the video frame includes a start time and an end time of the video frame;

Generate a set to be detected corresponding to the conflict detection window according to the detection time of the video frame, wherein the detection times in the set to be detected are arranged in chronological order;

Collision detection of video frames is performed according to the set to be detected corresponding to the conflict detection window.
The collision detection method according to claim 1, wherein performing collision detection of video frames according to the to-be-detected set corresponding to the conflict detection window includes:

Determine the number of n-flow collisions in the conflict detection window according to the set to be detected corresponding to the conflict detection window,

Wherein, n-stream collision means that the transmission periods of n video frames overlap in time, and n is an integer greater than or equal to 1.
The collision detection method according to claim 2, wherein determining the number of n-flow collisions in the conflict detection window according to the set to be detected corresponding to the conflict detection window includes:

According to the order of each detection time in the set to be detected corresponding to the conflict detection window, the target detection time is detected sequentially to determine the number of n-flow collisions in the conflict detection window, where the target detection time is The flag bit in the set to be detected is the detection time of the first flag bit, and the first flag bit indicates that the corresponding detection time is not detected;

Wherein, detecting the target detection moment includes:

According to the relationship between the target detection time and the previous detection time, and the flag bits of each detection time before the target detection time, the number of n-flow collisions that occur before the target detection time is determined.
The collision detection method according to claim 3, wherein according to the target The relationship between the detection time and the previous detection time, as well as the flag bits of each detection time before the target detection time, determining the number of n-flow collisions before the target detection time includes:

When the target detection time is the same as the previous detection time and the target detection time is the end time, set the flag bit of the target detection time and the flag bit of the start time corresponding to the target detection time. is a second flag bit, which indicates that the corresponding detection time has been detected;

When the target detection time is different from the previous detection time, and the target detection time is the starting time and the previous detection time is the starting time, the flag bit before the target detection time is counted as the first The number i of the starting moment of the flag bit increases the first counter corresponding to the collision of i stream by 1, where i is a positive integer;

In the case that the target detection time is different from the previous detection time and the target detection time is the end time, count the number j of the start time whose flag bit is the first flag bit before the target detection time, Add 1 to the first counter corresponding to the collision of stream j, where j is a positive integer;

The flag bit of the target detection time and the flag bit of the starting time corresponding to the target detection time are set as the second flag bit.
The collision detection method according to any one of claims 2 to 4, wherein performing collision detection of video frames based on the to-be-detected set corresponding to the conflict detection window further includes:

According to the number of times n-stream collisions occur in the conflict detection window, the combination of video streams in which n-stream collisions occur and the time period in which n-stream collisions occur are determined.
The collision detection method according to any one of claims 2 to 4, wherein performing collision detection of video frames based on the to-be-detected set corresponding to the conflict detection window further includes:

A first collision probability is determined according to the number of times n-flow collisions occur in the conflict detection window, where the first collision probability represents the probability of n-flow collisions occurring.
The collision detection method according to claim 6, wherein determining the first collision probability according to the number of n-flow collisions occurring in the conflict detection window includes:

When the first counter corresponding to the n-flow collision is not cleared, determine the number of n-flow collisions in the conflict detection window according to the set to be detected corresponding to the conflict detection window, and obtain the total number of n-flow collisions. ;

Accumulate the value of the first counter to obtain the total number of collisions;

The first collision probability is calculated based on the total number of n-flow collisions and the total number of collisions.
The collision detection method according to any one of claims 2 to 4, wherein performing collision detection of video frames based on the to-be-detected set corresponding to the conflict detection window further includes:

The second collision probability is determined according to the number of n-flow collisions occurring in the conflict detection window, where the second collision probability represents the probability that the n-flow collision is the maximum number of flow collisions.
The collision detection method according to claim 8, wherein determining the second collision probability according to the number of n-flow collisions occurring in the conflict detection window includes:

For the conflict detection window, determine the maximum value of n according to the number of n flow collisions in the conflict detection window, and obtain the maximum number of flow collisions;

Add 1 to the second counter corresponding to the maximum number of flow collisions;

The second collision probability is calculated according to the value of the second counter and the number of collision detection windows.
The collision detection method according to any one of claims 2 to 4, wherein performing collision detection of video frames based on the to-be-detected set corresponding to the conflict detection window further includes:

A duty cycle is calculated, wherein the duty cycle represents the proportion of n-flow collisions to the total time.
The collision detection method according to any one of claims 2 to 4, wherein the collision detection of video frames is performed based on the set to be detected corresponding to the conflict detection window. include:

Calculate the flow rate when n-flow collision occurs.
The collision detection method according to any one of claims 1 to 11, wherein determining the detection moment of at least one video frame in at least one conflict detection window includes:

The messages at a target aggregation level are aggregated to determine the detection time of the video frame, where the target aggregation level includes any one of a camera level, an application level, and a cell level.
The collision detection method according to any one of claims 1 to 11, wherein determining the detection moment of at least one video frame in at least one conflict detection window includes:

According to the data at the video frame level, the detection moment of the video frame is determined.
An electronic device including:

one or more processors;

A memory having one or more programs stored thereon. When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 13. The collision detection method described in the item.
A computer-readable medium on which a computer program is stored. When the program is executed by a processor, the collision detection method according to any one of claims 1 to 13 is implemented.