Bitstream analysis method and device, storage medium and electronic device

Abstract

This invention provides a bitstream analysis method, apparatus, storage medium, and electronic device. The method includes: acquiring the raw bitstream reported by a target camera device accessing a server, wherein the server has an analysis function to analyze the raw bitstream, and the analysis function is configured in the server through an acquired configuration file, which is pre-acquired from camera devices that have historically accessed the server; determining, based on the capabilities of the target camera device, whether the target camera device has performed target analysis on target bitstreams included in the raw bitstream; extracting the target bitstream from the raw bitstream and performing target analysis on the target bitstream. This invention solves the problem of poor intelligent analysis capabilities of camera devices in related technologies, achieving the goal of enhancing the intelligent analysis capabilities of camera devices and improving the efficiency of intelligent analysis.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of video surveillance technology, and more specifically, to a bitstream analysis method, apparatus, storage medium, and electronic device. Background Technology

[0002] With the rapid development of the social economy, the security monitoring market has expanded dramatically, and the intelligent analysis functions and types supported by video surveillance cameras have gradually become more diverse. Although the number of cameras with high-end intelligent analysis functions on the market is growing rapidly, there are still a large number of cameras that do not support intelligent analysis functions or whose intelligent analysis functions are relatively outdated. However, replacing these cameras that do not support intelligent analysis functions or whose intelligent analysis functions are relatively outdated in real time is very time-consuming and labor-intensive.

[0003] In related technologies, when a business platform receives a video analysis task, it searches for smart cameras that meet the analysis criteria and sends the video analysis task to these cameras to fully utilize their redundant computing capabilities and improve video analysis efficiency. However, searching for smart cameras that meet the analysis criteria through the business platform takes time, and there may be a period of time during which no smart camera that meets the analysis criteria is found, resulting in low actual video analysis efficiency. In addition, when the business platform sends video analysis tasks to smart cameras that meet the analysis criteria, the video analysis tasks will increase the access forwarding bandwidth of the smart cameras, thereby affecting the original functions of the smart cameras.

[0004] There is currently no effective solution to the problem of poor intelligent analysis capabilities of camera equipment in related technologies. Summary of the Invention

[0005] This invention provides a bitstream analysis method, apparatus, storage medium, and electronic device to at least address the problem of poor intelligent analysis capabilities of camera devices in related technologies.

[0006] According to an embodiment of the present invention, a bitstream analysis method is provided, comprising: acquiring an original bitstream reported by a target camera device accessing the server, wherein the server has an analysis function for analyzing the original bitstream, and the analysis function is configured in the server through an acquired configuration file, the configuration file being pre-acquired from camera devices that have historically accessed the server; determining, based on the capabilities of the target camera device, that the target camera device has not performed target analysis on a target bitstream included in the original bitstream; extracting the target bitstream from the original bitstream, and performing the target analysis on the target bitstream.

[0007] In an exemplary embodiment, after obtaining the raw bitstream reported by the target camera device accessing the server, the method further includes: if it is determined that the target camera device is a device with analysis capabilities, obtaining target configuration information within the target camera device, wherein the target configuration information is used to configure the analysis capabilities supported by the target camera device; if it is determined based on the target configuration information that the target camera device has a first analysis capability, and the first analysis capability is not configured in the server, obtaining first configuration information for configuring the first analysis capability from the target configuration information; and configuring the first analysis capability in the server using the first configuration information.

[0008] In one exemplary embodiment, determining that the target analysis not performed by the target camera device on the target bitstream included in the original bitstream based on the capabilities of the target camera device includes at least one of the following: if it is determined that the target camera device is a device without analysis capabilities, determining the analysis that the server can perform as the target analysis; if it is determined that the target camera device is a device with analysis capabilities, determining the analysis capabilities of the target camera device, and by comparing the analysis capabilities of the target camera device with the analysis capabilities of the server, determining the functions included in the analysis capabilities of the server but not included in the analysis capabilities of the target camera device, and determining the analysis that can be performed by the functions as the target analysis.

[0009] In an exemplary embodiment, when it is determined that the target camera device is a device without analysis function, or when it is determined that the target camera device is a device with analysis function and no analysis result reported by the target camera device is received within a predetermined time period, extracting the target bitstream from the original bitstream and performing the target analysis on the target bitstream includes: determining the entire original bitstream as the target bitstream and performing the target analysis on the target bitstream.

[0010] In one exemplary embodiment, after performing the target analysis on the target bitstream, the method further includes: returning the target analysis result obtained after performing the target analysis to the target terminal.

[0011] In an exemplary embodiment, when the target camera device is determined to be a device with analysis capabilities, the method further includes: obtaining a first analysis result obtained and reported by the target camera device after analyzing the target bitstream; extracting the target bitstream from the original bitstream and performing the target analysis on the target bitstream includes: determining the bitstream received from the target camera device within a first predetermined time period before the time point when the target camera device reports the first analysis result to a second predetermined time period after the time point as the target bitstream; and performing the target analysis on the target bitstream.

[0012] In an exemplary embodiment, after performing the target analysis on the target bitstream, the method further includes: integrating the target analysis result obtained after performing the target analysis with the first analysis result to obtain an integrated analysis result; and returning the integrated analysis result to the target terminal.

[0013] According to another embodiment of the present invention, a bitstream analysis apparatus is provided, comprising: a first acquisition module, configured to acquire raw bitstreams reported by target camera devices accessing the server, wherein the server has an analysis function for analyzing the raw bitstreams, and the analysis function is configured in the server through an acquired configuration file, the configuration file being pre-acquired from camera devices that have historically accessed the server; a first determination module, configured to determine, based on the capabilities of the target camera device, that the target camera device has not performed target analysis on target bitstreams included in the raw bitstreams; and an analysis module, configured to extract the target bitstreams from the raw bitstreams and perform the target analysis on the target bitstreams.

[0014] According to yet another embodiment of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0015] According to yet another embodiment of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0016] This invention allows for the prior acquisition of configuration files from camera devices accessing historical servers. These configuration files are then used to configure corresponding analysis functions on the server. Even when the target camera device has not performed target analysis on the target bitstream included in the raw bitstream reported by the target camera device on the access server, the target bitstream is extracted from the raw bitstream and subjected to target analysis. This solves the problem of poor intelligent analysis capabilities of camera devices in related technologies, thereby enhancing the intelligent analysis capabilities of camera devices and improving their efficiency. Attached Figure Description

[0017] Figure 1 This is a hardware structure block diagram of a mobile terminal for a bitstream analysis method according to an embodiment of the present invention.

[0018] Figure 2 This is a flowchart of a code stream analysis method according to an embodiment of the present invention;

[0019] Figure 3 This is a flowchart of a camera intelligent analysis function enhancement scheme according to an embodiment of the present invention;

[0020] Figure 4 This is a flowchart of dynamic intelligent analysis of the bitstream according to an embodiment of the present invention;

[0021] Figure 5 This is a flowchart of multi-intelligent parallel analysis according to an embodiment of the present invention;

[0022] Figure 6 This is a flowchart illustrating the implementation of multi-intelligent parallel supplementation according to the present invention;

[0023] Figure 7 This is a structural block diagram of a stream analysis device according to an embodiment of the present invention. Detailed Implementation

[0024] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0026] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a bitstream analysis method according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0027] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the code stream analysis method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0028] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0029] This embodiment provides a bitstream analysis method. Figure 2 This is a flowchart of a bitstream analysis method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0030] Step S202: Obtain the raw bitstream reported by the target camera device accessing the server. The server has an analysis function to analyze the raw bitstream. The analysis function is configured in the server through an acquired configuration file, which is obtained in advance from camera devices that have historically accessed the server.

[0031] Step S204: Based on the capabilities of the target camera device, determine that the target camera device did not perform target analysis on the target bitstream included in the original bitstream;

[0032] Step S206: Extract the target bitstream from the original bitstream and perform the target analysis on the target bitstream.

[0033] The entity executing the above steps can be an intelligent device with bitstream analysis capabilities, such as an intelligent server, or an intelligent system or processor with bitstream analysis capabilities, or other processing devices or processing units with similar processing capabilities. The target camera device can be a device with camera and intelligent analysis functions.

[0034] In the above embodiments, configuration files can be obtained in advance from the camera devices of the historical access server, and then the corresponding analysis functions can be configured in the server using the configuration files. If it is determined that the target camera device has not performed target analysis on the target bitstream included in the original bitstream reported by the target camera device of the access server, the target bitstream is extracted from the original bitstream and target analysis is performed on the target bitstream. This solves the problem of poor intelligent analysis capability of camera devices in related technologies, achieves the purpose of enhancing the intelligent analysis capability of camera devices, and improves the intelligent analysis efficiency of camera devices.

[0035] In an exemplary embodiment, after obtaining the raw bitstream reported by the target camera device accessing the server, the method further includes: if it is determined that the target camera device is a device with analysis capabilities, obtaining target configuration information within the target camera device, wherein the target configuration information is used to configure the analysis capabilities supported by the target camera device; if it is determined based on the target configuration information that the target camera device has a first analysis capability, and the first analysis capability is not configured in the server, obtaining first configuration information for configuring the first analysis capability from the target configuration information; and configuring the first analysis capability in the server using the first configuration information. In this embodiment, there can be multiple target camera devices, thereby acquiring target configuration information within multiple target camera devices. Then, if it is determined based on the multiple target configuration information that each target camera device possesses a corresponding first analysis function, and the server does not have a first analysis function corresponding to the multiple target camera devices configured, any one of the multiple first configuration information can be randomly used to configure the corresponding first analysis function on the server. If it is determined that the algorithms for the first analysis functions within the multiple target devices are different, first analysis functions under multiple algorithms can also be configured on the server. In this case, the configuration information within each target camera device can be used sequentially to configure the first analysis functions corresponding to various algorithms on the server. Furthermore, based on the priority or weight of the multiple target camera devices, the first configuration information of the target camera device with higher priority or greater weight can be used to configure the corresponding first analysis function on the server. It should be noted that the above-described application method of the first configuration information is only an exemplary embodiment, and the application method of the first configuration information is not limited to the above example.

[0036] In one exemplary embodiment, determining that the target analysis not performed by the target camera device on the target bitstream included in the original bitstream based on the capabilities of the target camera device includes at least one of the following: if it is determined that the target camera device is a device without analysis capabilities, determining the analysis that the server can perform as the target analysis; if it is determined that the target camera device is a device with analysis capabilities, determining the analysis capabilities of the target camera device, and by comparing the analysis capabilities of the target camera device with the analysis capabilities of the server, determining the functions included in the analysis capabilities of the server but not included in the analysis capabilities of the target camera device, and determining the analysis that can be performed by the functions as the target analysis. In this embodiment, the target camera device may or may not support intelligent analysis. The target camera device may possess multiple analysis functions. If the target camera device is determined to have analysis functions, its multiple analysis functions can be identified first, and then compared one by one with the analysis functions of the server. This quickly identifies functions included in the server's analysis functions but not included in the target camera device's analysis functions, and the analysis performed by these functions is determined as the target analysis. Furthermore, there may be multiple functions, so the required function can be selected from these multiple functions according to the actual application (or all multiple functions can be configured on the server to further enhance the server's analysis capabilities). The analysis performed by this function is then determined as the target analysis. It should also be noted that the required function can be adjusted according to the actual application, and the analysis performed by the adjusted function is then determined as the target analysis.

[0037] In an exemplary embodiment, when it is determined that the target camera device is a device without analysis capabilities, or when it is determined that the target camera device is a device with analysis capabilities but no analysis results reported by the target camera device are received within a predetermined time period, extracting the target bitstream from the original bitstream and performing the target analysis on the target bitstream includes: determining the entire original bitstream as the target bitstream and performing the target analysis on the target bitstream. In this embodiment, the predetermined time period can be a pre-set time period, such as 30 seconds, 50 seconds, 1 minute, etc. For example, when the predetermined time period is 50 seconds, when it is determined that the target camera device is a device without analysis capabilities, or when it is determined that the target camera device is a device with analysis capabilities but no analysis results reported by the target camera device are received within 50 seconds, in order to ensure the comprehensiveness of the analysis, the entire original bitstream can be determined as the target bitstream and the target bitstream can be subjected to target analysis. It should also be noted that the above example of the predetermined time period is only an exemplary embodiment, and the predetermined time period is not limited to the above example.

[0038] In the above embodiments, the analysis performed on the target bitstream can be of various types. Therefore, when analyzing the target bitstream, various types of analysis can be performed on the target bitstream in sequence. In order to save analysis time, multiple threads can be used to perform various types of analysis on the target bitstream simultaneously. In addition, the analysis with higher priority or greater weight can be performed on the target bitstream according to the priority or weight of the multiple types of analysis. It should be noted that the above examples of performing analysis functions are only exemplary embodiments and are not limited to the above examples.

[0039] In an exemplary embodiment, after performing the target analysis on the target bitstream, the method further includes: returning the target analysis results obtained after the target analysis to the target terminal. In this embodiment, the target analysis results obtained after the target analysis can be of multiple types. Therefore, before returning these multiple types of target analysis results to the target terminal, the target analysis results can be categorized according to their corresponding types, and the categorized target analysis results can be returned to the target terminal together. Alternatively, the categorized target analysis results can be returned to the target terminal sequentially according to different types. Furthermore, based on the priority or weight of the multiple types of target analysis results, the target analysis result with the highest priority or greatest weight can be returned to the target terminal. It should be noted that the above examples of target analysis results are only exemplary embodiments, and the target analysis results are not limited to the above examples.

[0040] In an exemplary embodiment, when the target camera device is determined to be a device with analysis capabilities, the method further includes: obtaining a first analysis result obtained and reported by the target camera device after analyzing the target bitstream; extracting the target bitstream from the original bitstream and performing the target analysis on the target bitstream includes: determining the bitstream received from the target camera device within a first predetermined time period before the time point when the target camera device reports the first analysis result to a second predetermined time period after the time point as the target bitstream; and performing the target analysis on the target bitstream. In this embodiment, to avoid analyzing bitstreams without analytical value, which would lead to increased bitstream analysis latency, wasted bitstream analysis resources, and reduced bitstream analysis efficiency, only the bitstreams received from the target camera device within a first predetermined time period before the time point when the target camera device reports the first analysis result, and within a second predetermined time period after the time point, can be analyzed. Furthermore, both the first and second predetermined time periods are preset time periods. The first predetermined time period can be set to 30 seconds, 40 seconds, 50 seconds, etc., before the time point when the target camera device reports the first analysis result, and the second predetermined time period can be set to the time point when the target camera device reports the first analysis result. The first predetermined time period is 30 seconds, 40 seconds, 50 seconds, etc., after the time point of the analysis result. For example, when the first predetermined time period is 30 seconds before the time point when the target camera device reports the first analysis result, and the second predetermined time period is 30 seconds after the time point when the target camera device reports the first analysis result, the bitstream received from the target camera device within 30 seconds before the time point when the target camera device reports the first analysis result to 30 seconds after the time point is determined as the target bitstream. It should also be noted that the above-mentioned first predetermined time period and the above-mentioned second predetermined time period are only exemplary embodiments, and the first predetermined time period and the second predetermined time period are not limited to the above examples.

[0041] In an exemplary embodiment, after performing the target analysis on the target bitstream, the method further includes: integrating the target analysis result obtained after the target analysis with the first analysis result to obtain an integrated analysis result; and returning the integrated analysis result to the target terminal. In this embodiment, integrating the target analysis result obtained after the target analysis with the first analysis result can further fully utilize the target analysis result obtained after the target analysis and the first analysis result reported by the target camera device, thereby effectively improving the accuracy of the intelligent analysis result of the target camera device.

[0042] Obviously, the embodiments described above are only some embodiments of the present invention, and not all embodiments.

[0043] The present invention will be described in detail below with reference to specific embodiments:

[0044] Figure 3 This is a flowchart of a camera intelligent analysis function enhancement scheme according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0045] S302, Begin;

[0046] S304, The camera connects to the intelligent server and obtains client information of the connected camera (corresponding to the aforementioned target camera device);

[0047] S306 makes the first judgment by obtaining camera capabilities to determine whether the current camera supports intelligence;

[0048] S308, if the first judgment result is negative, the intelligent server will perform dynamic intelligent analysis on the camera access bitstream.

[0049] S310, End;

[0050] S312, if the first judgment result is yes, then obtain the camera's supported intelligence and current intelligence configuration information (corresponding to the target configuration information mentioned above);

[0051] S314, perform a second judgment to determine whether the camera supports "Multi-Smart";

[0052] S316, If the second judgment result is negative, the intelligent server will use the "multi-intelligence" in the server to perform multi-intelligence parallel analysis, and after the multi-intelligence parallel analysis, step S310 will be executed.

[0053] S318, if the second judgment result is yes, the intelligent server can perform multi-intelligence parallel analysis by combining the current camera's own "multi-intelligence", and then execute step S310 after the multi-intelligence parallel analysis.

[0054] Finally, after integrating the results of dynamic intelligent analysis of the bitstream, the results of parallel analysis of camera "multi-intelligence" and the results of parallel analysis of server multi-intelligence, the intelligent analysis results (corresponding to the target analysis results) are returned to the client accessing the camera (corresponding to the target terminal mentioned above).

[0055] It should also be noted that the intelligent server internally includes an intelligent integrated system containing distributed storage devices, intelligent boxes, etc., and externally it can provide intelligent media such as intelligent stream analysis and multi-intelligent parallel analysis by connecting to cameras.

[0056] The following describes the main contents of this specific embodiment:

[0057] 1. Dynamic intelligent analysis of bitstream

[0058] After the camera connects to the intelligent server, the server obtains the camera's capabilities to determine whether the camera supports intelligence. When the camera does not support intelligence, the intelligent server performs dynamic intelligent analysis on the bitstream connected to the camera. Figure 4 This is a flowchart of dynamic intelligent analysis of the bitstream according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps:

[0059] S402, Begin;

[0060] S404, obtain the camera access bitstream;

[0061] The S406 intelligent server uses type detection intelligence (e.g., intelligent motion detection) to perform intelligent analysis on the current bitstream (corresponding to the target analysis mentioned above);

[0062] S408, If a person is detected in the current bitstream, the intelligent server will perform intelligent analysis (person) on the current bitstream. That is, through intelligent detection algorithms for people such as face detection, human body detection and human behavior detection, the intelligent server will perform intelligent analysis on the people appearing in the camera access bitstream (corresponding to the above target analysis).

[0063] S410, if a vehicle is detected in the current bitstream, the intelligent server will perform intelligent analysis (vehicle) on the current bitstream. That is, through intelligent detection algorithms for vehicles such as license plate detection, motor vehicle / non-motor vehicle detection and vehicle behavior detection, the intelligent server performs intelligent analysis on the vehicles appearing in the camera access bitstream (corresponding to the above target analysis).

[0064] S412, If other types of objects besides people and vehicles are detected in the current bitstream, the intelligent server will perform intelligent analysis (other) on the current bitstream. That is, through intelligent detection algorithms such as object type detection and object behavior detection, the intelligent server will perform intelligent analysis on the types of objects besides people and vehicles appearing in the camera access bitstream (corresponding to the above target analysis).

[0065] S414 integrates and reports the analysis results, that is, it integrates the intelligent analysis results of intelligent analysis (human), intelligent analysis (vehicle), and intelligent analysis (other) and reports them to the client connected to the camera.

[0066] S416, End.

[0067] 2. Multi-Intelligent Parallel Analysis

[0068] After the camera is connected to the intelligent server, the server determines whether the camera supports intelligence by acquiring the camera's capabilities. If the camera supports intelligence, the intelligent server will perform multi-intelligence parallel analysis by combining the camera's supported intelligence and the current intelligence configuration information.

[0069] Figure 5This is a flowchart of multi-intelligent parallel analysis according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps:

[0070] S502, Begin;

[0071] S504, obtains information about the intelligence supported by the camera and the current intelligence.

[0072] After the S506 receives the camera's bitstream, the intelligent server then obtains the intelligent information supported by the camera and the current intelligent information (corresponding to the above configuration file, which includes, but is not limited to, capability information, configuration information, etc.).

[0073] S508 performs the first judgment to determine whether the camera supports "Multi-Smart";

[0074] S510, if the first judgment result is negative, obtain the current intelligent configuration (corresponding to the target configuration information);

[0075] The server performs parallel analysis of "multi-intelligence" capabilities. When the camera does not support "multi-intelligence" capabilities, it first obtains the current intelligence configuration of the camera. Then, the intelligence server configures one or more "intelligent copy cameras" with different algorithm information within the server and provides multi-intelligence parallel analysis capabilities to the "intelligent copy cameras" (i.e., configures multi-intelligence parallel analysis capabilities for the "intelligent copy cameras").

[0076] S512, an intelligent system configured with multiple algorithms;

[0077] S514 performs a second judgment to determine whether the current camera has intelligent reporting capabilities;

[0078] S516, If the second judgment result is yes, the intelligent analysis result (result analysis) reported by the multi-intelligent analysis camera;

[0079] If the current camera reports intelligent analysis results, the intelligent server will use the "Algorithm Copy Camera" and "Intelligent Copy Camera" with different types of intelligence configurations than the current camera to perform parallel intelligent analysis on the images or related bitstreams reported by the camera to supplement the information that the current camera's intelligence cannot detect; otherwise, it will directly analyze the camera's access bitstream.

[0080] S518, multi-intelligent analysis of the bitstream accessed by the camera (process analysis). If the result of the second judgment above is negative, proceed directly to this step;

[0081] If the current camera reports an intelligent analysis result (corresponding to the first analysis result mentioned above), the intelligent server will use the "Algorithm Copy Camera" and the "Intelligent Copy Camera" (which have different intelligent configurations than the current camera) to perform parallel intelligent analysis on the bitstream (corresponding to the target bitstream) within the range before and after the time point when the camera reported the result (corresponding to the first predetermined time period before the time point when the target camera reported the first analysis result to the second predetermined time period after the time point). If the current camera does not report an intelligent analysis result, the intelligent server will use all the intelligent cameras in the "Algorithm Copy Camera" and the "Intelligent Copy Camera" to perform parallel intelligent analysis on the bitstreams accessed by the camera at the same time (i.e., analyze all bitstreams).

[0082] When the intelligent analysis results are not reported due to reasons such as problems with the camera algorithm, camera anomalies, or missed reports, multi-functional analysis will be performed directly on all accessed bitstreams after a certain period of time.

[0083] S520 integrates intelligent analysis results;

[0084] The system integrates the intelligent analysis results (result analysis) reported by multiple intelligent analysis cameras and the intelligent analysis results of the access bitstream (process detection) from multiple intelligent analysis cameras, and reports them to the client connected to the cameras.

[0085] S522, End;

[0086] S524, if the first judgment result is yes, obtain the intelligent algorithm information supported by the camera;

[0087] If the camera supports complementary detection types (e.g., face detection and vehicle detection) or supplementary detection types (e.g., face detection and face comparison), then the camera is considered to support "multi-intelligence" (that is, if the camera's intelligences are not mutually exclusive, the camera itself can achieve multi-intelligence parallel functions with multiple intelligence detection types and multiple complementary intelligences in the same scene); otherwise, the camera is considered not to support "multi-intelligence".

[0088] When the camera supports "multi-intelligence", it first obtains the algorithm information (algorithm model, algorithm version, etc.) of the intelligence supported by the camera. Then, the intelligence server builds an "algorithm copy camera" with the same algorithm information as the camera and provides multi-intelligence parallel analysis function for the "algorithm copy camera".

[0089] S526, Configure the camera algorithm intelligently; after configuration is complete, proceed to step S514.

[0090] It should also be noted that, Figure 6 This is a flowchart of a multi-intelligent parallel supplement implemented according to the present invention, such as... Figure 6 As shown, intelligent analysis can be supplemented in the following ways (see appendix). Figure 6 The direction of the middle arrow indicates the direction of supplementary intelligent analysis:

[0091] For scope-based intelligent analysis (e.g., dynamic detection), additional type-discriminating intelligent analysis can be added;

[0092] For type-discriminating intelligent analysis (e.g., intelligent dynamic detection), additional type detection intelligent analysis can be added;

[0093] For intelligent analysis of type detection, additional intelligent analysis of type comparison and intelligent analysis of type behavior detection can be provided.

[0094] For intelligent analysis of type detection (e.g., face detection, human body detection, license plate detection, motor vehicle detection, non-motor vehicle detection), additional intelligent analysis of type comparison can be added.

[0095] For intelligent analysis of type detection (e.g., face detection, human body detection, license plate detection, motor vehicle detection), intelligent analysis of type behavior detection can be added as an additional feature;

[0096] For intelligent analysis of type detection (e.g., face detection, human body detection, license plate detection, motor vehicle detection, non-motor vehicle detection), intelligent analysis of type comparison (e.g., face comparison, human body comparison, license plate comparison, motor vehicle comparison, non-motor vehicle comparison), and intelligent analysis of type behavior detection (e.g., human behavior detection, vehicle behavior detection), additional intelligent analysis of type detection statistics can be added. For intelligent analysis of type detection statistics (e.g., people statistics, vehicle statistics), more advanced intelligent analysis can be added. Figure 6 (Not shown in the image).

[0097] As can be seen from the foregoing embodiments, by dynamically analyzing the bitstream, intelligence is provided to cameras that do not support intelligence. Combined with multi-intelligence parallel analysis, the problem of not being able to perform multi-intelligence analysis on the monitoring screen at the same time due to the mutual exclusion of camera intelligence is solved. This achieves the goal of enhancing the camera's intelligent analysis function, which can save the cost of replacing large-scale cameras that do not support intelligence, and also save the cost of increasing the number of intelligent cameras to achieve multi-intelligence parallel analysis of the monitoring screen. In addition, the embodiments of the present invention also achieve the following objectives:

[0098] An enhanced solution for camera intelligent analysis is proposed. This solution provides dynamic intelligent analysis of the bitstream for cameras that do not support intelligence through an intelligent server, and then performs multi-intelligent parallel analysis on the monitoring video of intelligent cameras at the same time.

[0099] This strategy implements a dynamic intelligent analysis strategy for bitstreams. It determines whether the current camera supports intelligence by acquiring camera capabilities, and then combines the dynamic intelligent analysis of bitstream detection type to analyze the monitoring footage of cameras that do not support intelligence. This provides cameras with simple and fast intelligent analysis functions.

[0100] A multi-intelligence parallel analysis strategy is implemented. This strategy determines whether a camera supports "multi-intelligence" by acquiring the intelligence supported by the camera and the current intelligence information. Then, it combines the "algorithm copy camera" of the camera's "multi-intelligence" parallel analysis and the "intelligent copy camera" of the server's "multi-intelligence" parallel analysis to perform multi-intelligence parallel analysis on the camera's reported intelligence analysis results (result analysis) and the camera's access bitstream (process analysis). This can not only solve the problem of data omission caused by camera intelligence mutual exclusion, but also fully explore the intelligence information in the camera's reported intelligence analysis results and access bitstream, thereby improving the accuracy of the camera's intelligence analysis results.

[0101] A multi-intelligence parallel supplementation strategy is implemented. This strategy supplements the type-distinguishing intelligence with the range-based intelligence, the type-distinguishing intelligence with the type detection intelligence, the type detection intelligence with the type comparison intelligence, the type detection intelligence with the type behavior detection intelligence, and the type detection intelligence, type comparison intelligence, and type behavior detection intelligence with the type detection statistics intelligence. The type detection statistics intelligence can supplement more advanced intelligence.

[0102] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0103] This embodiment also provides a bitstream analysis device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0104] Figure 7 This is a structural block diagram of a bitstream analysis device according to an embodiment of the present invention, such as... Figure 7 As shown, the device includes:

[0105] The first acquisition module 72 is used to acquire the raw bitstream reported by the target camera device that accesses the server. The server has an analysis function to analyze the raw bitstream. The analysis function is configured in the server through an acquired configuration file, which is obtained in advance from camera devices that have historically accessed the server.

[0106] The first determining module 74 is used to determine, based on the capabilities of the target camera device, that the target camera device has not performed target analysis on the target bitstream included in the original bitstream;

[0107] Analysis module 76 is used to extract the target bitstream from the original bitstream and perform the target analysis on the target bitstream.

[0108] In one exemplary embodiment, the above-described apparatus further includes:

[0109] The second acquisition module is used to acquire target configuration information within the target camera device after acquiring the raw bitstream reported by the target camera device connected to the server, and if it is determined that the target camera device is a device with analysis function. The target configuration information is used to configure the analysis function supported by the target camera device.

[0110] The second determining module is used to obtain first configuration information for configuring the first analysis function from the target configuration information when it is determined based on the target configuration information that the target camera device has a first analysis function and the first analysis function is not configured in the server.

[0111] A configuration module is used to configure the first analysis function within the server using the first configuration information.

[0112] In one exemplary embodiment, the first determining module 74 is further configured to determine, based on at least one of the capabilities of the target camera device, that the target camera device did not perform target analysis on the target bitstream included in the original bitstream:

[0113] If it is determined that the target camera device is a device without analysis capabilities, the analysis that the server can perform is determined as the target analysis;

[0114] If the target camera device is determined to be a device with analysis capabilities, the analysis capabilities of the target camera device are determined, and by comparing the analysis capabilities of the target camera device with the analysis capabilities of the server, the functions included in the analysis capabilities of the server but not included in the analysis capabilities of the target camera device are determined, and the analysis that the function can perform is determined as the target analysis.

[0115] In one exemplary embodiment, the analysis module 76 further includes:

[0116] The determination submodule is used to determine the entire original bitstream as the target bitstream and perform the target analysis on the target bitstream when it is determined that the target camera device is a device without analysis function, or when it is determined that the target camera device is a device with analysis function and no analysis result reported by the target camera device is received within a predetermined time period.

[0117] In one exemplary embodiment, the above-described apparatus further includes:

[0118] The first return module is used to return the target analysis result obtained after performing the target analysis on the target bitstream to the target terminal.

[0119] In an exemplary embodiment, the above-described apparatus is further configured to, when it is determined that the target camera device is a device with analysis capabilities, acquire a first analysis result obtained and reported by the target camera device after analyzing the target bitstream; the analysis module 76 is further configured to extract the target bitstream from the original bitstream in the following manner, and perform the target analysis on the target bitstream: determine the bitstream received from the target camera device within a first predetermined time period before the time point when the target camera device reports the first analysis result to a second predetermined time period after the time point as the target bitstream; and perform the target analysis on the target bitstream.

[0120] In one exemplary embodiment, the above-described apparatus further includes:

[0121] An integration module. This module is used to integrate the target analysis results obtained after performing the target analysis on the target bitstream with the first analysis result to obtain an integrated analysis result.

[0122] The second return module is used to return the integrated analysis results to the target terminal.

[0123] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0124] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0125] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0126] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0127] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0128] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0129] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0130] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A bitstream analysis method, characterized in that, Applied in servers, including: After the target camera device connects to the server, the client information of the target camera device is obtained to determine whether the target camera device supports intelligence. Obtain the raw bitstream reported by the target camera device; If the target camera device supports intelligence, the intelligence supported by the target camera device and the target configuration information within the target camera device are obtained. If the target camera device can achieve complementarity of multiple detection types or supplementation of the same detection type in the same frame, it is determined that the target camera device supports multiple intelligences. If the target camera device does not support intelligence, intelligent analysis is performed directly on the original bitstream. If the target camera device supports the multiple intelligences, obtain the algorithm information of the intelligences supported by the target camera device, build an algorithm copy camera with the same intelligence environment as the target camera device in the server, and provide the algorithm copy camera with the multiple intelligence parallel analysis function; if the target camera device does not support the multiple intelligences, obtain the current intelligence configuration of the target camera device, build one or more intelligent copy cameras with different algorithm information in the server, and provide the intelligent copy camera with the multiple intelligence parallel analysis function. When the target camera device reports the first analysis result, the algorithm is used to copy the camera and the smart copy camera, which are of different types from the current smart configuration of the target camera device. The target bitstream within a first predetermined time period before the time point of reporting the first analysis result and within a second predetermined time period after the time point is analyzed to obtain the target analysis result. The target analysis result is integrated with the first analysis result to obtain the integrated analysis result, and the integrated analysis result is returned to the target terminal. The server is equipped with an analysis function to analyze the original bitstream. The analysis function is configured in the server using a configuration file obtained in advance from camera devices that have historically accessed the server. The target configuration information is used to configure the analysis functions supported by the target camera device. The multi-intelligent parallel analysis function is used to achieve multiple intelligent complementarities. The intelligent complementarity includes intelligent analysis for range, supplementary intelligent analysis for type differentiation, and intelligent analysis for type differentiation, supplementary intelligent analysis for type detection. The target analysis includes the multi-intelligent parallel analysis function, and the target device is a client that accesses the target camera device.

2. The method according to claim 1, characterized in that, After obtaining the raw bitstream reported by the target camera device connected to the server, the method further includes: If it is determined that the target camera device is a device with analysis capabilities, the target configuration information is obtained; If, based on the target configuration information, it is determined that the target camera device has a first analysis function, and the first analysis function is not configured in the server, first configuration information for configuring the first analysis function is obtained from the target configuration information. The first analysis function is configured within the server using the first configuration information.

3. The method according to claim 1, characterized in that, Determining, based on the capabilities of the target camera device, that the target camera device did not perform target analysis on the target bitstream included in the original bitstream includes at least one of the following: If it is determined that the target camera device is a device without analysis capabilities, the analysis that the server can perform is determined as the target analysis; If the target camera device is determined to be a device with analysis capabilities, the analysis capabilities of the target camera device are determined, and by comparing the analysis capabilities of the target camera device with the analysis capabilities of the server, the functions included in the analysis capabilities of the server but not included in the analysis capabilities of the target camera device are determined, and the analysis that the function can perform is determined as the target analysis.

4. The method according to claim 3, characterized in that, If it is determined that the target camera device is a device without analysis capabilities, or if it is determined that the target camera device is a device with analysis capabilities but no analysis results are received from the target camera device within a predetermined time period, the target bitstream is extracted from the original bitstream, and the target analysis is performed on the target bitstream, including: The entire original bitstream is identified as the target bitstream, and the target bitstream is subjected to the target analysis.

5. The method according to claim 4, characterized in that, After performing the target analysis on the target bitstream, the method further includes: The target analysis results obtained after performing the target analysis are returned to the target terminal.

6. A stream analysis device, characterized in that, Applied in servers, including: The device is also used to: after the target camera device connects to the server, obtain the client information of the target camera device and determine whether the target camera device supports intelligence; The first acquisition module is used to acquire the raw bitstream reported by the target camera device; The device is further configured to: when the target camera device supports intelligence, acquire the intelligence supported by the target camera device and the target configuration information within the target camera device; if the target camera device can achieve complementarity of multiple detection types or supplementation of the same detection type in the same frame, determine that the target camera device supports multiple intelligences; when the target camera device does not support intelligence, directly perform intelligent analysis on the original bitstream; The device is further configured to: when the target camera device supports the multiple intelligences, acquire the algorithm information of the intelligences supported by the target camera device, build an algorithm copy camera with the same intelligence environment as the target camera device in the server, and provide the algorithm copy camera with the multiple intelligences parallel analysis function; when the target camera device does not support the multiple intelligences, acquire the current intelligence configuration of the target camera device, build one or more intelligent copy cameras with different algorithm information in the server, and provide the intelligent copy camera with the multiple intelligences parallel analysis function; The device is further configured to: when the target camera device reports a first analysis result, use the algorithm to copy the camera and the smart copy camera, which are of a different type of intelligence than the current smart configuration of the target camera device, to perform the target analysis on the target bitstream within a first predetermined time period before the time point when the first analysis result was reported, and to a second predetermined time period after the time point, to obtain the target analysis result; integrate the target analysis result with the first analysis result to obtain an integrated analysis result; and return the integrated analysis result to the target terminal. The server is equipped with an analysis function to analyze the original bitstream. The analysis function is configured in the server using a configuration file obtained in advance from camera devices that have historically accessed the server. The target configuration information is used to configure the analysis functions supported by the target camera device. The multi-intelligent parallel analysis function is used to achieve multiple intelligent complementarities. The intelligent complementarity includes intelligent analysis for range, supplementary intelligent analysis for type differentiation, and intelligent analysis for type differentiation, supplementary intelligent analysis for type detection. The target analysis includes the multi-intelligent parallel analysis function, and the target device is a client that accesses the target camera device.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 1 to 5.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 5.

Images