Security monitoring video transmission method, device, equipment and computer readable medium

Abstract

The embodiments of the present disclosure disclose a security monitoring video sending method, device, equipment and computer-readable medium. A specific implementation of the method includes: collecting a security monitoring video frame set; performing video frame parsing processing on the security monitoring video frame set; performing feature extraction processing on the moving object image corresponding to each moving object information in the moving object information set; performing clustering processing on each moving object feature information obtained; determining the moving object identification corresponding to each moving object feature information cluster in each moving object feature information cluster; determining each object identification that meets the preset identification screening condition in each moving object identification as each person identification; generating monitoring content structured description information; storing the background reference frame and the moving object information set in a preset shared database; and sending the monitoring content structured description information to the video viewing terminal. This implementation reduces the waste of network bandwidth resources.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a security monitoring video sending method, device, equipment, and computer-readable medium. Background Art

[0002] Traditional security monitoring systems usually use security monitoring videos to record monitoring images. Security monitoring video transmission is a technology for sending monitoring images of security monitoring videos. At present, when sending security monitoring videos to viewing terminals (e.g., mobile phones) to convey the monitoring images of security monitoring videos, the commonly used method is: compressing the security monitoring videos and sending them to the viewing terminals, and the viewing terminals decompress the compressed videos to obtain restored monitoring videos.

[0003] However, when the above method is used to send security surveillance videos, the following technical problems often occur:

[0004] First, the security surveillance video is compressed and sent to the viewing end, and the viewing end decompresses the compressed video to obtain the surveillance restoration video. As people's requirements for video clarity become more and more stringent, video resolution continues to increase. Even if the security surveillance video is compressed, the amount of compressed surveillance data obtained is still large, and the network resource occupancy rate is still large, which leads to a waste of network bandwidth resources.

[0005] Continuing, in the process of adopting technical solutions to solve the above-mentioned technical problem 1, the following technical problems often occur: before generating the structured description information of the monitoring content, it is necessary to parse the security monitoring video frame set to obtain the moving object information in each security monitoring video frame. When performing the parsing process, the conventional solution is generally: parse the security monitoring video frame set by the frame difference method to obtain the moving object information in each security monitoring video frame. However, the above conventional solution parses the security monitoring video frame set by the frame difference method to obtain the moving object information in each security monitoring video frame, and still has the following problems:

[0006] Second, when the frame difference method is used to detect moving objects with similar colors or larger moving objects in adjacent frames, holes may occur in the detection process (that is, all pixels of the moving object cannot be fully detected). The frame difference method is used to parse the security monitoring video frame set, resulting in low accuracy of the moving object information obtained, which in turn leads to low accuracy of the structured description information of the monitoring content, resulting in a large degree of distortion in the security monitoring video restored based on the structured description information of the monitoring content.

[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0008] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0009] Some embodiments of the present disclosure propose a security monitoring video sending method, device, electronic device and computer-readable medium to solve one or more of the technical problems mentioned in the above background technology section.

[0010] In a first aspect, some embodiments of the present disclosure provide a method for sending a security monitoring video, the method comprising: acquiring a security monitoring video frame set; performing video frame parsing processing on the security monitoring video frame set to obtain a background reference frame and a moving object information group set, wherein a moving object information group in the moving object information group set corresponds to a security monitoring video frame in the security monitoring video frame set; performing feature extraction processing on a moving object image corresponding to each moving object information in the moving object information group set to obtain moving object feature information corresponding to the moving object information; performing clustering processing on each moving object feature information obtained to obtain each moving object feature information cluster; determining the corresponding moving object feature information of each moving object feature information cluster in the moving object feature information cluster. The corresponding moving object identification is obtained to obtain each moving object identification; each object identification that meets the preset identification screening condition among the above-mentioned moving object identifications is determined as each person identification; based on the above-mentioned each person identification, the above-mentioned each moving object feature information cluster and the above-mentioned moving object information set, the monitoring content structured description information is generated, wherein the above-mentioned monitoring content structured description information includes archived person structured description information and unfamiliar mobile object structured description information; the above-mentioned background reference frame and the above-mentioned moving object information set corresponding to the above-mentioned monitoring content structured description information are stored in a preset shared database; the above-mentioned monitoring content structured description information is sent to the video viewing end, so that the above-mentioned video viewing end can generate a restored monitoring video corresponding to the above-mentioned monitoring content structured description information.

[0011] In a second aspect, some embodiments of the present disclosure provide a security monitoring video sending device, the device comprising: an acquisition unit, configured to acquire a security monitoring video frame set; a parsing processing unit, configured to perform video frame parsing processing on the security monitoring video frame set to obtain a background reference frame and a moving object information group set, wherein a moving object information group in the moving object information group set corresponds to a security monitoring video frame in the security monitoring video frame set; a feature extraction unit, configured to perform feature extraction processing on a moving object image corresponding to each moving object information in the moving object information group set to obtain moving object feature information corresponding to the moving object information; a clustering processing unit, configured to perform clustering processing on each moving object feature information obtained to obtain each moving object feature information cluster; a first determination unit, configured to determine each moving object in each moving object feature information cluster. The moving object identification corresponding to the body feature information cluster is obtained to obtain each moving object identification; the second determining unit is configured to determine each object identification that meets the preset identification screening condition among the above-mentioned moving object identifications as each person identification; the generating unit is configured to generate monitoring content structured description information based on the above-mentioned each person identification, the above-mentioned each moving object feature information cluster and the above-mentioned moving object information set, wherein the above-mentioned monitoring content structured description information includes archived person structured description information and unfamiliar mobile object structured description information; the storing unit is configured to store the above-mentioned background reference frame corresponding to the above-mentioned monitoring content structured description information and the above-mentioned moving object information set into a preset shared database; the sending unit is configured to send the above-mentioned monitoring content structured description information to the video viewing end, so that the above-mentioned video viewing end can generate a restored monitoring video corresponding to the above-mentioned monitoring content structured description information.

[0012] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0013] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0014] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the security monitoring video sending method of some embodiments of the present disclosure, the waste of network bandwidth resources is reduced. Specifically, the reason for the waste of network bandwidth resources is that the security monitoring video is compressed and sent to the viewing end, and the viewing end decompresses the compressed video to obtain the monitoring restoration video. As people's requirements for video clarity become more and more stringent, the video resolution continues to increase. Even if the security monitoring video is compressed, the amount of data of the obtained compressed monitoring data is still large, and the network resource occupancy rate is still large, which leads to the waste of network bandwidth resources. Based on this, the security monitoring video restoration of some embodiments of the present disclosure first collects a security monitoring video frame set. Thus, a security monitoring video frame set for generating a background reference frame and a moving object information group set can be obtained. Then, the above-mentioned security monitoring video frame set is subjected to video frame parsing processing to obtain a background reference frame and a moving object information group set, wherein a moving object information group in the above-mentioned moving object information group set corresponds to a security monitoring video frame in the security monitoring video frame set. Next, feature extraction processing is performed on the moving object image corresponding to each moving object information in the moving object information set to obtain the moving object feature information corresponding to the moving object information. Thus, each moving object feature information can be obtained. Then, clustering processing is performed on each moving object feature information obtained to obtain each moving object feature information cluster. Thus, each moving object feature information cluster used to determine each moving object identifier can be obtained. Afterwards, the moving object identifier corresponding to each moving object feature information cluster in the moving object feature information cluster is determined to obtain each moving object identifier. Then, each object identifier in the moving object identifier that meets the preset identifier screening condition is determined as each person identifier. Then, based on the each person identifier, the each moving object feature information cluster and the moving object information set, monitoring content structured description information is generated, wherein the monitoring content structured description information includes archived person structured description information and unfamiliar moving object structured description information. Thus, monitoring content structured description information used to describe the monitoring content of the security monitoring video frame set can be obtained. Afterwards, the above-mentioned background reference frame and the above-mentioned moving object information set corresponding to the above-mentioned structured description information of the monitoring content are stored in a preset shared database. Thus, the background reference frame and the above-mentioned moving object information set can be stored in a preset shared database for the viewing end to restore the security monitoring video. Next, the above-mentioned structured description information of the monitoring content is sent to the video viewing end, so that the above-mentioned video viewing end can generate a restored monitoring video corresponding to the above-mentioned structured description information of the monitoring content. The restored monitoring video is generated by sending the structured description information of the monitoring content that describes the monitoring content of the security monitoring video frame set. The amount of monitoring data sent is reduced, and the waste of network bandwidth resources is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0016] Figure 1 is a flow chart of some embodiments of the security monitoring video sending method according to the present disclosure;

[0017] Figure 2 It is a structural schematic diagram of some embodiments of the security monitoring video sending device according to the present disclosure;

[0018] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0020] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0021] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0022] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

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

[0025] Figure 1The process 100 of some embodiments of the security monitoring video sending method according to the present disclosure is shown. The security monitoring video sending method comprises the following steps:

[0026] Step 101, collecting security monitoring video frame sets.

[0027] In some embodiments, the execution subject (e.g., monitoring system) of the security monitoring video sending method may collect a security monitoring video frame set through a security monitoring video acquisition device. The security monitoring video acquisition device may be a security camera. The security monitoring video frame set may be a video frame set corresponding to a security monitoring video.

[0028] Step 102, performing video frame parsing processing on the security monitoring video frame set to obtain a background reference frame and a moving object information group set.

[0029] In some embodiments, the execution subject may perform video frame parsing processing on the security monitoring video frame set to obtain a background reference frame and a moving object information group set. Among them, a moving object information group in the moving object information group set corresponds to a security monitoring video frame in the security monitoring video frame set. Each moving object information group in the moving object information group set may represent each moving object information of each moving object in a security monitoring video frame. Each moving object information in the moving object information may represent each pixel point of the moving object image. The moving object information may include each pixel point information. Each pixel point information in the pixel point information may include a pixel value and a coordinate value.

[0030] In some optional implementations of some embodiments, the execution subject may perform video frame parsing processing on the security monitoring video frame set to obtain a background reference frame and a moving object information set through the following steps:

[0031] The first step is to perform background modeling processing on the security monitoring video frame set to obtain background model information corresponding to the security monitoring video frame set. The background model information includes information of each background point. In practice, the execution subject can generate background model information corresponding to the security monitoring video frame set through a mixed Gaussian model. Each background point information in the background point information can represent a background pixel. For example, the background point information can include: background point position information and background brightness value. The background point position information can be the image coordinates of the background point.

[0032] In the second step, for each security monitoring video frame in the security monitoring video frame set, the following steps are performed:

[0033] In the first sub-step, the following screening steps are performed on each pixel point of the security monitoring video frame in the security monitoring video frame:

[0034] Sub-step 1: determining the position information of the pixel point of the security monitoring video frame as the screening position information, wherein the position information may be the coordinates of the pixel point of the security monitoring video frame in the security monitoring video frame.

[0035] Sub-step 2: determine the background point information corresponding to the above-mentioned screening position information among the above-mentioned background point information as the target background point information. Wherein, the above-mentioned target background point information includes background point position information and background brightness value. The above-mentioned background point position information can represent the position of the background pixel point.

[0036] Sub-step three: Generate a first value based on the pixel value information of the security surveillance video frame pixel. In practice, the execution subject may determine the average of the pixel values ​​of the three color channels of red (R), green (G), and blue (B) contained in the pixel information as the first value.

[0037] Sub-step four: determining the background brightness value as a second value.

[0038] Sub-step 5: generating a difference value based on the first value and the second value. In practice, the execution entity may determine the absolute value of the difference between the first value and the second value as the difference value.

[0039] Sub-step 6: In response to determining that the difference value is greater than a preset threshold, the security monitoring video frame pixel is determined as a foreground pixel. The foreground pixel corresponds to a foreground label. The foreground label can be used to identify the foreground category to which the security monitoring video frame pixel belongs.

[0040] In the second sub-step, the pixel point information corresponding to each determined foreground pixel point is determined as a foreground pixel point information set.

[0041] The third sub-step is to perform connected region segmentation processing on the foreground pixel information set to obtain each connected foreground pixel information group. In practice, the execution subject can segment the foreground pixel information set using a connected region segmentation technology to obtain each connected foreground pixel information group.

[0042] The fourth sub-step is to determine each of the connected foreground pixel information groups as moving object information, and obtain a moving object information group corresponding to the security monitoring video frame. The connected area connected foreground pixel information in the connected area connected foreground pixel information group can represent the foreground pixels identified as the same connected area in the corresponding security monitoring video frame. The foreground pixels are adjacent in the security monitoring video frame.

[0043] In the third step, the obtained moving object information group is determined as a moving object information group set.

[0044] In the fourth step, the security monitoring video frames in the security monitoring video frame set that meet the preset condition are determined as background reference frames. The preset condition may be that the number of foreground pixels contained in the security monitoring video frame is the least.

[0045] The above technical solution combines steps 107 to 109 and their related contents as an inventive point of an embodiment of the present disclosure, and solves the second technical problem mentioned in the background technology: "When the frame difference method is used to detect moving objects with similar colors or larger moving objects in adjacent frames, a hole phenomenon may occur in the detection process (that is, all pixels of the moving object cannot be completely detected). The frame difference method is used to parse the security monitoring video frame set, resulting in low accuracy of the obtained moving object information, which in turn leads to low accuracy of the structured description information of the monitoring content, resulting in a large degree of distortion of the security monitoring video restored based on the structured description information of the monitoring content". The factors that lead to a large degree of distortion of the restored security monitoring video are often as follows: When the frame difference method is used to detect moving objects with similar colors or larger moving objects in adjacent frames, a hole phenomenon may occur in the detection process (that is, all pixels of the moving object cannot be completely detected). The frame difference method is used to parse the security monitoring video frame set, resulting in low accuracy of the obtained moving object information, which in turn leads to low accuracy of the structured description information of the monitoring content, resulting in a large degree of distortion of the security monitoring video restored based on the structured description information of the monitoring content. If the above factors are solved, the degree of distortion of the restored security surveillance video can be reduced. In order to achieve this effect, first, the security surveillance video frame set is subjected to background modeling processing to obtain background model information corresponding to the security surveillance video frame set, wherein the background model information includes information of each background point. Thus, information of each background point used to determine each foreground pixel point can be obtained. Then, for each security surveillance video frame in the security surveillance video frame set, the following steps are performed: a first sub-step, the following screening steps are performed for each security surveillance video frame pixel point in the security surveillance video frame: sub-step 1, the position information of the monitoring pixel point is determined as screening position information. Sub-step 2, the background point information corresponding to the screening position information in the above background point information is determined as target background point information, wherein the target background point information includes background point position information and background brightness value. Sub-step 3, based on the pixel value information of the security surveillance video frame pixel point, a first value is generated. Thus, a first value used to generate a difference value can be obtained. Sub-step 4, the background brightness value is determined as a second value. Thus, a second value used to generate a difference value can be obtained. Sub-step five, generating a difference value based on the first value and the second value. Sub-step six, in response to determining that the difference value is greater than a preset threshold, determining the pixel point of the security monitoring video frame as a foreground pixel point, wherein the foreground pixel point corresponds to a foreground label. Thus, the foreground pixel point can be determined. Second sub-step, determining the pixel point information corresponding to each determined foreground pixel point as a foreground pixel point information set. Thus, a foreground pixel point information set representing the overall image of each moving object in the security monitoring video frame can be obtained.In the third sub-step, the foreground pixel information set is subjected to connected region segmentation processing to obtain each connected foreground pixel information group. Thus, foreground pixel information with similar characteristics can be divided into a group. In the fourth sub-step, each connected foreground pixel information group in the above-mentioned connected foreground pixel information groups is determined as moving object information to obtain a moving object information group corresponding to the above-mentioned security monitoring video frame. Thus, a moving object information group representing each moving object image in the above-mentioned security monitoring video frame can be obtained. Then, the obtained moving object information group is determined as a moving object information group set. Thus, a moving object information group set representing each moving object image in each video frame can be obtained. Next, the security monitoring video frame in the above-mentioned security monitoring video frame set that meets the preset conditions is determined as a background reference frame. Thus, a background reference frame can be obtained. Combined with step 107, based on the above-mentioned individual identifications, the above-mentioned each moving object feature information cluster and the above-mentioned moving object information group set, the monitoring content structured description information is generated. Thus, the monitoring content structured description information can be generated on the basis of the moving object information group set. In combination with step 109, the structured description information of the monitoring content is sent to the video viewing terminal, so that the video viewing terminal can generate a restored monitoring video corresponding to the structured description information of the monitoring content. In this way, the monitoring video can be restored according to the structured description information of the monitoring content. This is also because before the moving object detection is performed on each security monitoring video frame, the background model information is constructed according to the security monitoring video frame set. On the basis of the background model information, the moving object detection is performed on each security monitoring video frame, and the pixel points in the security monitoring video frame that are significantly different from the background points are determined as foreground pixels. Then, the foreground pixel point information set in each video frame is segmented into connected regions, and then a moving object information group set representing each moving object image in each video frame is obtained. The existence of the void phenomenon is reduced, the accuracy of the detected moving object information is improved, and then the accuracy of the structured description information of the monitoring content is improved, and the distortion of the security monitoring video restored based on the structured description information of the monitoring content is reduced.

[0046] Step 103 , performing feature extraction processing on the moving object image corresponding to each moving object information in the moving object information set to obtain moving object feature information corresponding to the moving object information.

[0047] In some embodiments, the execution subject may perform feature extraction processing on the moving object image corresponding to each moving object information in the moving object information group set to obtain moving object feature information corresponding to the moving object information. In practice, the execution subject may input the moving object information into a pre-trained image feature extraction model to obtain moving object feature information corresponding to the moving object information. The image feature extraction model may be a neural network that takes moving object information as input and takes moving object feature information as output. For example, the neural network may be a TransNeXt feature extraction network. The moving object feature information may characterize the features of the moving object image. The moving object feature information may be a feature vector.

[0048] Step 104: clustering the obtained feature information of each moving object to obtain a feature information cluster of each moving object.

[0049] In some embodiments, the execution subject may perform clustering processing on the obtained feature information of each moving object to obtain each moving object feature information cluster. In practice, the execution subject may perform clustering processing on the above-mentioned feature information of each moving object by a k-means clustering algorithm to obtain each moving object feature information cluster. Among them, one moving object feature information cluster in the above-mentioned moving object feature information clusters may represent each feature vector corresponding to a moving object.

[0050] Step 105 , determining the moving object identification corresponding to each moving object characteristic information cluster in each moving object characteristic information cluster, and obtaining each moving object identification.

[0051] In some embodiments, the execution subject may determine the moving object identification corresponding to each moving object characteristic information cluster in the moving object characteristic information clusters to obtain each moving object identification. The moving object identification may be an identification name of the moving object.

[0052] In some optional implementations of some embodiments, the execution subject may determine the moving object identification corresponding to each moving object feature information cluster in the moving object feature information clusters through the following steps to obtain each moving object identification:

[0053] The first step is to store the above-mentioned moving object feature information clusters into a preset queue to obtain a moving object feature information cluster queue.

[0054] The second step is to determine a preset value as the number of identification times. For example, the preset value may be 1.

[0055] The third step is to perform the following identification steps according to the number of identifications and the first moving object feature information cluster in the moving object feature information cluster queue:

[0056] In the first sub-step, the above identification times are determined as an identification identifier.

[0057] The second sub-step is to select a piece of moving object feature information from the first moving object feature information cluster as the feature information to be identified. In practice, the execution subject may randomly select a piece of moving object feature information from the first moving object feature information cluster as the feature information to be identified.

[0058] The third sub-step is to input the feature information to be identified into a pre-trained moving object identification model to obtain an initial object identification. The moving object identification model can be a support vector machine (SVM) model that takes the feature information to be identified as input and the initial object identification as output.

[0059] The fourth sub-step is to concatenate the initial object identification mark and the identification identifier to obtain a moving object identification corresponding to the first moving object characteristic information cluster. As an example, the initial object identification mark may be a car, the identification mark may be 1, and the moving object identification may be car 1.

[0060] The fifth sub-step is to generate an updated value according to the number of identifications and a preset value. For example, the preset value may be 1.

[0061] The sixth sub-step is to determine the update value as the number of identification times to update the number of identification times.

[0062] The seventh sub-step is to remove the first moving object feature information cluster from the moving object feature information cluster queue to update the moving object feature information cluster queue.

[0063] The eighth sub-step is to execute the above identification step again according to the updated identification times and the updated moving object feature information cluster queue.

[0064] Step 106: determine the object identifiers that meet the preset identifier screening condition among the moving object identifiers as the person identifiers.

[0065] In some embodiments, the execution subject may determine each object identification that satisfies a preset identification screening condition among the above-mentioned moving object identifications as each person identification. The above-mentioned preset identification screening condition may be that the identification belongs to a person identification. For example, the above-mentioned each person identification may be person 3 or person 4.

[0066] Step 107: Generate monitoring content structured description information based on each person identification, each moving object feature information cluster and moving object information set.

[0067] In some embodiments, the execution subject may generate monitoring content structured description information based on the above-mentioned individual character identifiers, the above-mentioned individual moving object feature information clusters and the above-mentioned moving object information set. The above-mentioned monitoring content structured description information includes archived person structured description information and unfamiliar moving object structured description information. The above-mentioned monitoring content structured description information may be text information.

[0068] In some optional implementations of some embodiments, the execution subject may generate structured description information of monitoring content based on the above-mentioned individual identifications, the above-mentioned each moving object feature information cluster and the above-mentioned moving object information set through the following steps:

[0069] In the first step, the above-mentioned individual identifications are removed from the above-mentioned moving object identifications to generate the removed moving object identifications as the unknown moving object identification set.

[0070] In the second step, for each of the above character identifiers, perform the following steps:

[0071] In the first sub-step, the moving object feature information cluster corresponding to the above-mentioned person identification among the moving object feature information clusters is determined as the target moving object feature information cluster.

[0072] In the second sub-step, the similarity between the target moving object feature information cluster and each preset character feature vector in the preset character feature vector set is determined as the target similarity to obtain each target similarity. The similarity may be cosine similarity.

[0073] In the third sub-step, in response to determining that there is a target similarity among the above target similarities that satisfies the preset screening condition, the following archived person structured description sub-information generation step is performed according to the above target moving object feature information cluster:

[0074] Sub-step 1: Determine each piece of moving object information corresponding to the target moving object characteristic information cluster in the moving object information group as each piece of moving object information to be processed. Each piece of moving object information to be processed corresponds to a security monitoring video frame number label. The preset screening condition may be that the target similarity is greater than or equal to a preset value. The security monitoring video frame number label may represent the frame number of the video frame where the moving identification information to be processed is located.

[0075] Sub-step 2, input the above-mentioned information of each moving object to be processed into a pre-trained video structured information generation model to obtain the archived character structured descriptor information corresponding to the character identification. Among them, the above-mentioned archived character structured descriptor information corresponds to the above-mentioned target moving object feature information cluster. The above-mentioned video frame structured information generation model can be a GPT-4V model that takes the information of each moving object to be processed as input and the archived character structured descriptor information as output. The above-mentioned archived character structured descriptor information can represent the video content presented by the character corresponding to the character identification in each security monitoring video frame. The above-mentioned archived character structured descriptor information can be text information. For example, the above-mentioned archived character structured descriptor information can be "the position information of character 3 in the security monitoring video frame with the security monitoring video frame serial number label 1 is position information 1, the position information in the security monitoring video frame with the security monitoring video frame serial number label 2 is position information 2, and the expression in the security monitoring video frame with the security monitoring video frame serial number label 2 is smiling". The above-mentioned position information 1 may indicate the position of the person 3 in the security surveillance video frame whose security surveillance video frame serial number label is 1. The above-mentioned position information 1 may include the coordinates of each coordinate point (i.e., indicating the position of the moving object in the security surveillance video frame). The above-mentioned position information 2 may indicate the position of the person 3 in the security surveillance video frame whose security surveillance video frame serial number label is 2. The above-mentioned position information 2 may include the coordinates of each coordinate point.

[0076] In a fourth sub-step, in response to determining that none of the target similarities satisfies the preset screening condition, the person identification is added to the unknown motion object identification set to update the unknown motion object identification set.

[0077] The third step is to determine the generated archived character structured description sub-information as archived character structured description information.

[0078] The fourth step is to generate structured description information of unfamiliar moving objects based on the updated unknown moving object identification set.

[0079] The fifth step is to determine the above-mentioned archived person structured description information and the above-mentioned unfamiliar mobile object structured description information as the monitoring content structured description information.

[0080] In some optional implementations of some embodiments, the execution subject may generate structured description information of the unfamiliar moving object based on the updated unknown moving object identifier set by the following steps:

[0081] In the first step, for each unknown moving object identifier in the above unknown moving object identifier set, the following generation steps are performed:

[0082] In the first sub-step, the moving object feature information cluster corresponding to the unknown moving object identifier is determined as the unknown object feature information cluster.

[0083] In the second sub-step, each moving object information corresponding to the above unknown object feature information cluster is determined as each target moving object information.

[0084] In the third sub-step, each tag information of each security monitoring video frame serial number tag corresponding to each target moving object information is determined as each security monitoring video frame serial number.

[0085] In a fourth sub-step, the unknown moving object identifier and the frame numbers of the security monitoring videos are determined as structured description sub-information of the strange moving object.

[0086] In the second step, each generated unfamiliar mobile object structured description sub-information is determined as unfamiliar mobile object structured description information.

[0087] Step 108: storing the background reference frame and moving object information set corresponding to the structured description information of the monitoring content into a preset shared database.

[0088] In some embodiments, the execution subject may store the background reference frame and the moving object information set corresponding to the structured description information of the monitoring content in a preset shared database, wherein the preset common database may be a NoSQL database.

[0089] Step 109 , sending the structured description information of the monitoring content to the video viewing terminal, so that the video viewing terminal can generate a restored monitoring video corresponding to the structured description information of the monitoring content.

[0090] In some embodiments, the execution subject may send the structured description information of the monitoring content to a video viewing terminal, so that the video viewing terminal can generate a restored monitoring video corresponding to the structured description information of the monitoring content. The video viewing terminal may be a device for viewing video content. For example, the video viewing terminal may be, but is not limited to, one of the following: a smart phone, a tablet computer, or a television.

[0091] In some optional implementations of some embodiments, the restored surveillance video may be generated by the following steps:

[0092] The first step is to determine the received structured description information of the monitoring content as the information to be restored.

[0093] The second step is to obtain a background reference frame corresponding to the information to be restored from the preset shared database.

[0094] The third step is to generate a restored surveillance video based on the above information to be restored and the acquired background reference frame.

[0095] In some optional implementations of some embodiments, the video viewing terminal may generate a restored surveillance video according to the information to be restored and the acquired background reference frame through the following steps:

[0096] In the first step, for each archived character structured description sub-information in the archived character structured description information in the information to be restored, the following steps are performed:

[0097] The first sub-step is to generate a target moving object feature information cluster corresponding to the above-mentioned archived character structured description sub-information.

[0098] In the second sub-step, a piece of moving object information among each moving object information corresponding to the target moving object characteristic information cluster is obtained from the preset shared database as reference moving object information.

[0099] In the second step, each piece of reference moving object information obtained is determined as a reference moving object information set corresponding to the above-mentioned archived person structured description information.

[0100] In the third step, for each unfamiliar mobile object structured description sub-information in the unfamiliar mobile object structured description information in the information to be restored, perform the following steps:

[0101] The first sub-step is to determine the unknown object feature information cluster corresponding to the structured descriptor information of the unfamiliar mobile object.

[0102] The second sub-step is to obtain, from the preset shared database, each target moving object information corresponding to the unknown object feature information cluster as a target moving object information group.

[0103] The fourth step is to determine each acquired target moving object information group as a target moving object information group set corresponding to the above-mentioned structured description information of the strange moving object.

[0104] In the fifth step, the information to be restored, the background reference frame, the reference moving object information set, and the target moving object information set are input into a pre-trained security monitoring video generation model to obtain a restored monitoring video. The security monitoring video generation model may be a Diffusion model that takes the information to be restored, the background reference frame, the reference moving object information set, and the target moving object information set as inputs and takes the restored monitoring video as output.

[0105] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the security monitoring video sending method of some embodiments of the present disclosure, the waste of network bandwidth resources is reduced. Specifically, the reason for the waste of network bandwidth resources is that the security monitoring video is compressed and sent to the viewing end, and the viewing end decompresses the compressed video to obtain the monitoring restoration video. As people's requirements for video clarity become more and more stringent, the video resolution continues to increase. Even if the security monitoring video is compressed, the amount of data of the obtained compressed monitoring data is still large, and the network resource occupancy rate is still large, which leads to the waste of network bandwidth resources. Based on this, the security monitoring video restoration of some embodiments of the present disclosure first collects a security monitoring video frame set. Thus, a security monitoring video frame set for generating a background reference frame and a moving object information group set can be obtained. Then, the above-mentioned security monitoring video frame set is subjected to video frame parsing processing to obtain a background reference frame and a moving object information group set, wherein a moving object information group in the above-mentioned moving object information group set corresponds to a security monitoring video frame in the security monitoring video frame set. Next, feature extraction processing is performed on the moving object image corresponding to each moving object information in the moving object information set to obtain the moving object feature information corresponding to the moving object information. Thus, each moving object feature information can be obtained. Then, clustering processing is performed on each moving object feature information obtained to obtain each moving object feature information cluster. Thus, each moving object feature information cluster used to determine each moving object identifier can be obtained. Afterwards, the moving object identifier corresponding to each moving object feature information cluster in the moving object feature information cluster is determined to obtain each moving object identifier. Then, each object identifier in the moving object identifier that meets the preset identifier screening condition is determined as each person identifier. Then, based on the each person identifier, the each moving object feature information cluster and the moving object information set, monitoring content structured description information is generated, wherein the monitoring content structured description information includes archived person structured description information and unfamiliar moving object structured description information. Thus, monitoring content structured description information used to describe the monitoring content of the security monitoring video frame set can be obtained. Afterwards, the above-mentioned background reference frame and the above-mentioned moving object information set corresponding to the above-mentioned structured description information of the monitoring content are stored in a preset shared database. Thus, the background reference frame and the above-mentioned moving object information set can be stored in a preset shared database for the viewing end to restore the security monitoring video. Next, the above-mentioned structured description information of the monitoring content is sent to the video viewing end, so that the above-mentioned video viewing end can generate a restored monitoring video corresponding to the above-mentioned structured description information of the monitoring content. The restored monitoring video is generated by sending the structured description information of the monitoring content that describes the monitoring content of the security monitoring video frame set. The amount of monitoring data sent is reduced, and the waste of network bandwidth resources is reduced.

[0106] Further references Figure 2 As an implementation of the methods shown in the figures, the present disclosure provides some embodiments of a security monitoring video sending device, and these device embodiments are Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0107] like Figure 2 As shown, the security monitoring video sending device 200 of some embodiments includes: a collection unit 201, a parsing processing unit 202, a feature extraction unit 203, a clustering processing unit 204, a first determination unit 205, a second determination unit 206, a generation unit 207, a storage unit 208 and a sending unit 209. The collection unit is configured to collect a security monitoring video frame set; the parsing processing unit is configured to perform video frame parsing processing on the security monitoring video frame set to obtain a background reference frame and a moving object information group set, wherein a moving object information group in the moving object information group set corresponds to a security monitoring video frame in the security monitoring video frame set; the feature extraction unit is configured to perform feature extraction processing on the moving object image corresponding to each moving object information in the moving object information group set to obtain moving object feature information corresponding to the moving object information; the clustering processing unit is configured to perform clustering processing on each moving object feature information obtained to obtain each moving object feature information cluster; the first determination unit is configured to determine the moving object identifier corresponding to each moving object feature information cluster in the moving object feature information clusters. Obtain the identification of each moving object; the second determination unit is configured to determine each object identification that meets the preset identification screening condition among the above-mentioned moving object identifications as each person identification; the generation unit is configured to generate monitoring content structured description information based on the above-mentioned each person identification, the above-mentioned each moving object feature information cluster and the above-mentioned moving object information set, wherein the above-mentioned monitoring content structured description information includes archived person structured description information and unfamiliar mobile object structured description information; the storage unit is configured to store the above-mentioned background reference frame and the above-mentioned moving object information set corresponding to the above-mentioned monitoring content structured description information into a preset shared database; the sending unit is configured to send the above-mentioned monitoring content structured description information to the video viewing end, so that the above-mentioned video viewing end can generate a restored monitoring video corresponding to the above-mentioned monitoring content structured description information.

[0108] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units contained therein, and will not be described in detail here.

[0109] Reference below Figure 3, which shows a structural schematic diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0110] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0111] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0112] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the functions defined in the method of some embodiments of the present disclosure are executed.

[0113] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0114] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0115] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: collects a security monitoring video frame set; performs video frame parsing processing on the security monitoring video frame set to obtain a background reference frame and a moving object information group set, wherein a moving object information group in the moving object information group set corresponds to a security monitoring video frame in the security monitoring video frame set; performs feature extraction processing on the moving object image corresponding to each moving object information in the moving object information group set to obtain moving object feature information corresponding to the moving object information; performs clustering processing on each moving object feature information obtained to obtain each moving object feature information cluster; determines each moving object feature information in the each moving object feature information cluster. The method comprises the following steps: obtaining a moving object identification corresponding to a feature information cluster, obtaining each moving object identification; determining each object identification that meets a preset identification screening condition among the above moving object identifications as each person identification; generating monitoring content structured description information based on the above each person identification, the above each moving object feature information cluster and the above moving object information set, wherein the above monitoring content structured description information includes archived person structured description information and unfamiliar mobile object structured description information; storing the above background reference frame and the above moving object information set corresponding to the above monitoring content structured description information into a preset shared database; and sending the above monitoring content structured description information to a video viewing terminal, so that the above video viewing terminal can generate a restored monitoring video corresponding to the above monitoring content structured description information.

[0116] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0117] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0118] The units described in some embodiments of the present disclosure may be implemented by software or hardware. The units described may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a parsing processing unit, a feature extraction unit, a clustering processing unit, a first determination unit, a second determination unit, a generation unit, a storage unit, and a sending unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the acquisition unit may also be described as a "unit for acquiring a security monitoring video frame set".

[0119] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0120] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of technical features, but should also cover other technical solutions formed by any combination of technical features or their equivalent features without departing from the inventive concept. For example, a technical solution formed by replacing the features with (but not limited to) the technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for sending a security monitoring video, comprising: Collect security surveillance video frame sets; Performing video frame parsing processing on the security monitoring video frame set to obtain a background reference frame and a moving object information group set, wherein one moving object information group in the moving object information group set corresponds to one security monitoring video frame in the security monitoring video frame set; performing feature extraction processing on a moving object image corresponding to each moving object information in the moving object information group set to obtain moving object feature information corresponding to the moving object information; Performing clustering processing on the obtained feature information of each moving object to obtain a feature information cluster of each moving object; Determine the moving object identification corresponding to each moving object characteristic information cluster in each moving object characteristic information cluster to obtain each moving object identification; Determine each object identification that meets a preset identification screening condition among the various moving object identifications as each person identification; Based on the individual character identifiers, the individual moving object feature information clusters and the moving object information group set, the monitoring content structured description information is generated, wherein the monitoring content structured description information includes archived character structured description information and unfamiliar moving object structured description information, wherein each moving object information group in the moving object information group set corresponds to a security monitoring video frame sequence number label, and the monitoring content structured description information is generated based on the individual character identifiers, the individual moving object feature information clusters and the moving object information group set, including: Removing the individual person identifiers from the individual moving object identifiers to generate the removed individual moving object identifiers as an unknown moving object identifier set; For each of the character identifiers, perform the following steps: Determine the moving object feature information cluster corresponding to the person identification among the moving object feature information clusters as the target moving object feature information cluster; Determine the similarity between the target moving object feature information cluster and each preset character feature vector in the preset character feature vector set as the target similarity, and obtain each target similarity; In response to determining that there is a target similarity that satisfies a preset screening condition among the target similarities, the following archived person structured descriptor information generation step is performed according to the target moving object feature information cluster: Determine each piece of moving object information corresponding to the target moving object characteristic information cluster in the moving object information group set as each piece of moving object information to be processed, wherein each piece of moving object information to be processed corresponds to a security monitoring video frame sequence number label; Inputting each of the to-be-processed moving object information into a pre-trained video structured information generation model to obtain archived character structured descriptor information corresponding to the character identification, wherein the archived character structured descriptor information corresponds to the target moving object feature information cluster; In response to determining that none of the target similarities satisfies the preset screening condition, adding the person identifier to the unknown moving object identifier set to update the unknown moving object identifier set; Determine each generated archived character structured description sub-information as archived character structured description information; Generate structured description information of unfamiliar moving objects based on the updated unknown moving object identification set; Determining the archived person structured description information and the unfamiliar mobile object structured description information as monitoring content structured description information; storing the background reference frame and the moving object information set corresponding to the structured description information of the monitoring content in a preset shared database; The monitoring content structured description information is sent to a video viewing terminal so that the video viewing terminal can generate a restored monitoring video corresponding to the monitoring content structured description information.

2. The method according to claim 1, wherein: The restored surveillance video is generated by the following steps: Determining the received monitoring content structured description information as information to be restored; Acquire a background reference frame corresponding to the information to be restored from the preset shared database; A restored surveillance video is generated according to the information to be restored and the acquired background reference frame.

3. The method according to claim 1, wherein: The step of determining the moving object identification corresponding to each moving object characteristic information cluster in each moving object characteristic information cluster to obtain each moving object identification includes: Storing each moving object feature information cluster into a preset queue to obtain a moving object feature information cluster queue; Determine the preset value as the number of recognition times; According to the recognition times and the first moving object feature information cluster in the moving object feature information cluster queue, the following recognition steps are performed: determining the number of identifications as an identification identifier; Selecting a piece of moving object feature information from the first moving object feature information cluster as feature information to be identified; Inputting the feature information to be identified into a pre-trained moving object identification model to obtain an initial object identification; The initial object identification mark is concatenated with the identification identifier to obtain a moving object identification corresponding to the first moving object characteristic information cluster; Generate an updated value based on the number of recognitions and the preset value; Determine the update value as the number of identifications to update the number of identifications; removing the first moving object feature information cluster from the moving object feature information cluster queue to update the moving object feature information cluster queue; The identification step is performed again according to the updated number of identifications and the updated moving object feature information cluster queue.

4. The method according to claim 1, wherein: The generating of structured description information of unfamiliar moving objects based on the updated unknown moving object identification set includes: For each unknown moving object identifier in the unknown moving object identifier set, the following generating steps are performed: Determine the moving object characteristic information cluster corresponding to the unknown moving object identifier as the unknown object characteristic information cluster; Determine each moving object information corresponding to the unknown object feature information cluster as each target moving object information; Determine each tag information of each security monitoring video frame sequence number tag corresponding to each target moving object information as each security monitoring video frame sequence number; Determine the unknown moving object identifier and the frame numbers of each security monitoring video as structured descriptor information of an unfamiliar moving object; The generated individual unfamiliar mobile object structured description sub-information is determined as unfamiliar mobile object structured description information.

5. The method according to claim 2, wherein: The step of generating a restored surveillance video according to the information to be restored and the acquired background reference frame includes: For each archived character structured description sub-information in the archived character structured description information in the information to be restored, perform the following steps: The target moving object feature information cluster corresponding to the archived character structured descriptor information; Acquire, from the preset shared database, one piece of moving object information among each piece of moving object information corresponding to the target moving object feature information cluster as reference moving object information; Determining each piece of reference moving object information obtained as a reference moving object information set corresponding to the archived character structured description information; For each unfamiliar mobile object structured description sub-information in the unfamiliar mobile object structured description information in the information to be restored, the following steps are performed: Determine the unknown object feature information cluster corresponding to the structured descriptor information of the unfamiliar moving object; Acquire each target moving object information corresponding to the unknown object feature information cluster from the preset shared database as a target moving object information group; Determining each acquired target moving object information group as a target moving object information group set corresponding to the structured description information of the strange moving object; The information to be restored, the background reference frame, the reference moving object information set, and the target moving object information set are input into a pre-trained security monitoring video generation model to obtain a restored monitoring video.

6. A security monitoring video sending device, comprising: A collection unit configured to collect a security monitoring video frame set; a parsing processing unit configured to perform video frame parsing processing on the security monitoring video frame set to obtain a background reference frame and a moving object information group set, wherein one moving object information group in the moving object information group set corresponds to one security monitoring video frame in the security monitoring video frame set; A feature extraction unit is configured to perform feature extraction processing on a moving object image corresponding to each moving object information in the moving object information set to obtain moving object feature information corresponding to the moving object information; A clustering processing unit is configured to perform clustering processing on the obtained feature information of each moving object to obtain a cluster of feature information of each moving object; A first determining unit is configured to determine a moving object identifier corresponding to each moving object feature information cluster in each moving object feature information cluster to obtain each moving object identifier; A second determining unit is configured to determine each object identification that meets a preset identification screening condition among the various moving object identifications as each person identification; A generating unit is configured to generate monitoring content structured description information based on the individual character identifiers, the individual moving object feature information clusters and the moving object information set, wherein the monitoring content structured description information includes archived character structured description information and unfamiliar moving object structured description information, wherein each moving object information group in the moving object information set corresponds to a security monitoring video frame sequence number label, and the generating of monitoring content structured description information based on the individual character identifiers, the individual moving object feature information clusters and the moving object information set includes: removing the individual character identifiers from the individual moving object identifiers to generate the removed individual moving object identifiers as an unknown moving object identifier set; for each of the individual character identifiers, performing the following steps: determining the moving object feature information cluster corresponding to the individual character identifier in the individual moving object feature information clusters as a target moving object feature information cluster; determining the similarity between the target moving object feature information cluster and each preset character feature vector in the preset character feature vector set as a target similarity to obtain each target similarity; in response to determining that the individual target similarities have a target similarity that satisfies a preset screening condition According to the target moving object feature information cluster, the following archived person structured description sub-information generation step is performed: each moving object information corresponding to the target moving object feature information cluster in the moving object information group is determined as each moving object information to be processed, wherein each moving object information to be processed in the each moving object information to be processed corresponds to a security monitoring video frame sequence number label; each moving object information to be processed is input into a pre-trained video structured information generation model to obtain archived person structured description sub-information corresponding to the person identifier, wherein the archived person structured description sub-information corresponds to the target moving object feature information cluster; in response to determining that the target similarities do not have a target similarity that meets the preset screening condition, the person identifier is added to the unknown moving object identifier set to update the unknown moving object identifier set; each generated archived person structured description sub-information is determined as archived person structured description information; based on the updated unknown moving object identifier set, unfamiliar moving object structured description information is generated; the archived person structured description information and the unfamiliar moving object structured description information are determined as monitoring content structured description information; A storage unit configured to store the background reference frame and the moving object information set corresponding to the structured description information of the monitoring content into a preset shared database; The sending unit is configured to send the monitoring content structured description information to the video viewing terminal, so that the video viewing terminal can generate a restored monitoring video corresponding to the monitoring content structured description information.

7. An electronic device comprising: one or more processors; a storage device 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 5.

8. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images