CN114095753A - Video stream processing method, apparatus, device, medium, and program product - Google Patents
Video stream processing method, apparatus, device, medium, and program product Download PDFInfo
- Publication number
- CN114095753A CN114095753A CN202111365642.8A CN202111365642A CN114095753A CN 114095753 A CN114095753 A CN 114095753A CN 202111365642 A CN202111365642 A CN 202111365642A CN 114095753 A CN114095753 A CN 114095753A
- Authority
- CN
- China
- Prior art keywords
- video stream
- target video
- target
- computing node
- computing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 33
- 230000000694 effects Effects 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 17
- 230000006399 behavior Effects 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 14
- 206010000117 Abnormal behaviour Diseases 0.000 description 9
- 238000012806 monitoring device Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000001681 protective effect Effects 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
- H04N21/2405—Monitoring of the internal components or processes of the server, e.g. server load
Abstract
The disclosure provides a video stream processing method which can be applied to the technical field of artificial intelligence and the technical field of Internet of things. The video stream processing method comprises the following steps: acquiring a target video stream of information about the behavior and activity of personnel in the protection cabin; determining a target computing node for identifying a target video stream from a computing power pool deployed in a monitoring center based on a preset rule, wherein the computing power pool comprises a plurality of computing nodes; and inputting the target video stream into the target computing node so that the target computing node processes the target video stream to obtain an identification result of the target video stream, wherein the identification result is used for representing that the behavior activity of the person in the target video stream is abnormal or normal. The present disclosure also provides a video stream processing apparatus, a device, a storage medium, and a program product.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technology and the field of internet of things technology, and in particular, to a method, an apparatus, a device, a medium, and a program product for processing a video stream.
Background
The video monitoring technology is widely applied to public places, such as banks, stations and other public places, and is used for timely monitoring and disposing of illegal events, safety accidents and other abnormal events in the public places.
In implementing the disclosed concept, the inventors found that there are at least the following problems in the related art: the video monitoring device has higher investment and operation cost and lower accuracy rate of identifying abnormal behaviors of personnel.
Disclosure of Invention
In view of the foregoing, the present disclosure provides a video stream processing method, apparatus, device, medium, and program product.
According to a first aspect of the present disclosure, there is provided a video stream processing method, including: acquiring a target video stream of information about the behavior and activity of personnel in the protection cabin;
determining a target computing node for identifying the target video stream from a computing power pool deployed in a monitoring center based on a preset rule, wherein the computing power pool comprises a plurality of computing nodes;
and inputting the target video stream into the target computing node, so that the target computing node processes the target video stream to obtain an identification result of the target video stream, wherein the identification result is used for representing that the behavior activity of the personnel in the target video stream is abnormal or normal.
According to an embodiment of the present disclosure, determining a target computing node for identifying the target video stream from a computing power pool deployed in a monitoring center based on a preset rule includes:
calculating the load rate of each calculation node in the calculation pool to obtain a load rate calculation result;
and determining the computing node with the lowest load rate as the target computing node based on the load rate computing result.
According to the embodiment of the disclosure, an image recognition model is arranged in the target computing node;
inputting the target video stream into the target computing node, so that the target computing node processes the target video stream, and obtaining an identification result of the target video stream includes:
inputting the target video stream into the image recognition model;
and identifying the video image in the target video stream by using the image identification model, and outputting the identification result of the target video stream.
According to the embodiment of the disclosure, the image recognition model comprises a convolutional neural network and a long-short term memory network which are sequentially connected.
According to an embodiment of the present disclosure, the target video stream includes a plurality of streams, and each of the target video streams includes a start time;
inputting the target video stream into the target computing node, so that the target computing node processes the target video stream, and obtaining an identification result of the target video stream includes:
establishing a target video stream queue based on respective starting moments of a plurality of target video streams, wherein the arrangement sequence of the target video streams in the target video stream queue is the same as the time sequence of the respective starting moments of the plurality of target video streams;
and distributing a plurality of target video streams to different target computing nodes respectively based on the arrangement sequence of the target video streams in the target video stream queue, so that the target computing nodes can identify the target video streams in parallel to obtain the identification result of each target video stream.
According to an embodiment of the present disclosure, the video processing method further includes:
sending the identification result to monitoring equipment in the monitoring center; and
and outputting alarm information under the condition that the identification result represents that the behavior and activity of the person in the target video stream are abnormal.
A second aspect of the present disclosure provides a video stream processing apparatus including:
the acquisition module is used for acquiring a target video stream of the personnel behavior activity information in the protection cabin;
the determining module is used for determining a target computing node for identifying the target video stream from a computing power pool deployed in a monitoring center based on a preset rule, wherein the computing power pool comprises a plurality of computing nodes; and
and the identification module is used for inputting the target video stream into the target computing node so that the target computing node can process the target video stream to obtain an identification result of the target video stream, wherein the identification result is used for representing that the behavior activity of the person in the target video stream is abnormal or normal.
A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the video stream processing method described above.
A fourth aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above-mentioned video stream processing method.
A fifth aspect of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the video stream processing method described above.
Drawings
The foregoing and other objects, features and advantages of the disclosure will be apparent from the following description of embodiments of the disclosure, taken in conjunction with the accompanying drawings of which:
fig. 1 schematically illustrates an application scenario diagram of a video stream processing method, apparatus, device, medium and program product according to embodiments of the present disclosure;
fig. 2 schematically shows a flow chart of a video stream processing method according to an embodiment of the present disclosure;
fig. 3 schematically shows a flowchart of operation S230 according to an embodiment of the present disclosure;
fig. 4 schematically shows a schematic diagram of an output target video stream recognition result according to an embodiment of the present disclosure;
fig. 5 schematically shows a flowchart of operation S230 according to an embodiment of the present disclosure;
fig. 6 schematically shows an application scene diagram of a video stream processing method according to another embodiment of the present disclosure;
fig. 7 schematically shows a block diagram of a structure of a video stream processing apparatus according to an embodiment of the present disclosure; and
fig. 8 schematically shows a block diagram of an electronic device adapted to implement a video stream processing method according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
In the field of security cabin applications and finance, for example, bank ATM machines (automatic teller machines) may be installed in security cabins. In order to guarantee the personal safety and property safety of customers, a video monitoring device is installed in the protection cabin and used for monitoring the behavior activities of personnel in the protection cabin and identifying abnormal behaviors of the personnel in the protection cabin in time, wherein the abnormal behaviors can be related illegal behaviors.
In the process of realizing the concept disclosed by the invention, the inventor finds that at least the following technical problems exist in the related technology, and the abnormal behaviors of the personnel in the protection cabin can not be found in time by monitoring the video stream in the protection cabin in real time by related personnel, so that the identification accuracy of the abnormal behaviors of the personnel is low. Through the video monitoring device and the artificial intelligence image recognition device which are arranged in the protection cabin, the abnormal behaviors of personnel in the protection cabin are recognized, and the recognition result is transmitted to the monitoring center. Because the quantity of protection cabin is more, and the protection cabin is in the vacant state often, leads to artificial intelligence image recognition device, and the idle rate is higher, and the input cost and the operation cost of video monitoring device and artificial intelligence image recognition device are higher.
In order to at least partially solve the technical problems in the related art, the disclosure provides a video stream processing method, which can be applied to the financial field, the artificial intelligence technical field and the internet of things technical field. The video stream processing method comprises the following steps: acquiring a target video stream of information about the behavior and activity of personnel in the protection cabin; determining a target computing node for identifying a target video stream from a computing power pool deployed in a monitoring center based on a preset rule, wherein the computing power pool comprises a plurality of computing nodes; and inputting the target video stream into the target computing node so that the target computing node can process the target video stream to obtain an identification result of the target video stream, wherein the identification result is used for representing that the behavior activity of the personnel in the target video stream is abnormal or normal. The present disclosure also provides a video stream processing apparatus, a device, a storage medium, and a program product.
It should be noted that the method and apparatus of the embodiments of the present disclosure may be applied to the financial field, the artificial intelligence technical field, and the internet of things technical field, and may also be applied to any fields other than the financial field, the artificial intelligence technical field, and the internet of things technical field, and the application fields of the method and apparatus of the embodiments of the present disclosure are not limited.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, necessary security measures are taken, and the commonness and the customs are not violated.
Fig. 1 schematically illustrates an application scenario diagram of a video stream processing method, apparatus, device, medium, and program product according to embodiments of the present disclosure.
As shown in fig. 1, an application scenario 100 according to this embodiment may include a containment bay 110, a network 120, and a computing power pool 130. The network 120 serves as a medium for providing a communication link between the containment vessel 110 and the force pool 130. Network 120 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The protective cabin 110 may be provided with a video monitoring device by which a video stream may be generated that records the behavioral activities of the personnel within the protective cabin 110.
The computing pool 130 may include computing nodes 131, 132, 133. Each of the compute nodes 131, 132, 133 may be provided with one or more artificial intelligence servers. The artificial intelligence server can be used for processing the video stream transmitted to the computing power pool 130 by the protective cabin 110, and obtaining the identification result of the video stream.
It should be noted that the video stream processing method provided by the embodiment of the present disclosure may be generally performed by the computing pool 130. Accordingly, the video stream processing apparatus provided by the embodiment of the present disclosure may be generally disposed in the computing pool 130.
It should be understood that the number of guard bays, networks, force pools, and compute nodes in fig. 1 are merely illustrative. There may be any number of guard bays, networks, force pools, and compute nodes, as desired for implementation.
The video stream processing method of the disclosed embodiment will be described in detail below with fig. 2 to 6 based on the scenario described in fig. 1.
Fig. 2 schematically shows a flow chart of a video stream processing method according to an embodiment of the present disclosure.
As shown in fig. 2, the video stream processing method of this embodiment may include operations S210 to S230.
In operation S210, a target video stream regarding the information on the human behavioral activities within the protection cabin is acquired.
According to the embodiment of the disclosure, the protection cabin can be a device provided with an ATM (automatic teller machine) and a video monitoring device in the related art, and the video monitoring device can generate a target video stream for recording the behavior and activity information of people in the protection cabin.
According to an embodiment of the present disclosure, the target video stream may be a video stream generated based on a Real Time Streaming Protocol (RTSP).
According to the embodiment of the disclosure, a person can enter the protection cabin through the entrance guard control device or the infrared detection device arranged in the protection cabin. And under the condition that a person enters the protection cabin, generating a target video stream for recording the behavior and activity information of the person in the protection cabin through the video monitoring device.
In operation S220, a target computing node for identifying a target video stream is determined from a computation power pool deployed in a monitoring center based on a preset rule, wherein the computation power pool includes a plurality of computing nodes.
According to the embodiment of the disclosure, the preset rule may be determined based on the computing power of the computing nodes in the computing power pool, and may also be determined based on the time sequence for acquiring the target video stream.
In operation S230, the target video stream is input into the target computing node, so that the target computing node processes the target video stream to obtain a recognition result of the target video stream, where the recognition result is used to characterize abnormal or normal human behavior in the target video stream.
According to an embodiment of the present disclosure, the computation power pool may include a plurality of computation nodes, wherein each computation node may be provided with one or more video processing engines, and the one or more video processing engines may be configured to process the target video stream to obtain a recognition result of the target video stream. It should be noted that, the target computing node may be provided with a device or apparatus constructed based on neural network technology, for processing the target video stream.
According to an embodiment of the present disclosure, the recognition result may include normal or abnormal. In the case that the recognition result is normal, the personnel behavior activity in the protection cabin can be determined to be normal behavior activity. In the case that the identification result is abnormal, the personnel behavior activity in the protection cabin can be determined to be abnormal behavior activity.
According to the embodiment of the disclosure, the target video stream is recorded with the personnel behavior activity information in the protection cabin, the target video stream can be acquired under the condition that personnel enter the protection cabin, and the video stream is not acquired under the condition that the protection cabin is in the vacant state, so that the condition that the resource waste is caused by acquiring and transmitting the video stream in the protection cabin under the condition that the protection cabin is in the vacant state can be avoided, the data volume of the video stream to be transmitted is reduced, and the investment cost of a transmission medium for transmitting the video stream in the protection cabin is reduced. Meanwhile, the data volume of the transmitted video stream is reduced, and the computing resources of a computing power pool for processing the video stream can be reduced and saved, so that the construction investment cost and the operation cost of the computing power pool are reduced.
According to the embodiment of the disclosure, the target computing node for identifying the target video stream is determined from the computational power pool deployed in the monitoring center based on the preset rule, and the computing node for identifying the target video stream can be adjusted in real time according to the running condition of each computing node in the computational power pool, so that the processing efficiency of the target computing node is improved, and the accuracy of the target identification result is improved.
Fig. 3 schematically shows a flowchart of operation S230 according to an embodiment of the present disclosure.
According to the embodiment of the disclosure, an image recognition model is arranged in the target computing node;
as shown in fig. 3, the operation S230 of inputting the target video stream into the target computing node so that the target computing node processes the target video stream to obtain the recognition result of the target video stream may include operations S310 to S320:
in operation S310, a target video stream is input into an image recognition model.
In operation S320, a video image in the target video stream is recognized using the image recognition model, and a recognition result of the target video stream is output.
According to embodiments of the present disclosure, the image recognition model may include a model constructed based on a neural network, such as a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a long short term memory network (LSTM). The specific structural form of the image recognition model can be designed by those skilled in the art according to actual requirements.
According to the embodiment of the disclosure, the video images in the target video stream are processed by using the image recognition model, and compared with the method for monitoring and recognizing the target video stream by using the personnel in charge of monitoring, misjudgment on the recognition of the behavior activities of the personnel in the target video stream due to negligence or error of the personnel in charge of monitoring can be avoided, the accuracy of the recognition result of the target video stream is improved, and the emergency disposal cost caused by misjudgment is avoided.
According to an embodiment of the present disclosure, an image recognition model includes a convolutional neural network and a long-short term memory network connected in sequence.
Fig. 4 schematically shows a schematic diagram of an identification result of an output target video stream according to an embodiment of the present disclosure.
As shown in fig. 4, the target video stream 410 may be input into the target recognition model 420, the target recognition model 420 may include a convolutional neural network 421 and a long-short term memory network 422 which are connected in sequence, the convolutional neural network 421 may extract feature information of video images in the target video stream 410, the feature information is processed by using the long-short term memory network 422, and classification information, i.e., recognition results, of the target video stream 410 may be output. The recognition result of the target video stream may include normal 430 or abnormal 440.
According to an embodiment of the present disclosure, the determining, in operation S220, a target computing node for identifying a target video stream from a computational pool deployed in a monitoring center based on a preset rule may include:
calculating the load rate of each calculation node in the calculation power pool to obtain a load rate calculation result; and determining the computing node with the lowest load rate as a target computing node based on the load rate computing result.
According to the embodiment of the disclosure, each computing node may include one or more video processing engines, and in each computing node, a calculation result of the load rate of the computing node may be obtained by calculating the load rate of each video processing engine in the computing node. By comparing the load rate calculation results of the calculation nodes in the calculation power pool, the calculation node with the lowest load rate can be determined as the target calculation node.
It should be noted that the load rate of the computing node may represent the real-time computing capability of the computing node, that is, the lower the load rate of the computing node, the higher the real-time computing capability of the computing node may be represented. The calculation node with the lowest load rate is determined as the target calculation node, and the target video stream is input into the target calculation node, so that the speed of processing the target video stream by the target calculation node can be increased, the processing efficiency of the identification result of the target video stream is improved, abnormal behavior activities of personnel in the protection cabin can be found in time, and the early warning speed of the abnormal behavior activities of the personnel in the protection cabin is increased.
Fig. 5 schematically shows a flowchart of operation S230 according to an embodiment of the present disclosure.
According to an embodiment of the present disclosure, the target video stream includes a plurality of streams, each of which includes a start time.
As shown in fig. 5, the inputting of the target video stream into the target computing node in operation S230 so that the target computing node processes the target video stream to obtain the recognition result of the target video stream may include operations S510 to S520.
In operation S510, a target video stream queue is established based on respective start times of a plurality of target video streams, wherein an arrangement order of the target video streams in the target video stream queue is the same as a time order of the respective start times of the plurality of target video streams.
In operation S520, the plurality of target video streams are respectively allocated to different target computing nodes based on the arrangement order of the target video streams in the target video stream queue, so that the target computing nodes concurrently identify the target video streams, and an identification result of each target video stream is obtained.
According to the embodiment of the disclosure, the starting time of the target video stream can represent the starting time of the behavior activity of the person in the target video stream, namely the time when the person enters the protection cabin. The arrangement sequence of the target video streams in the target video stream queue is determined based on the time when the personnel enter the protection cabin, so that the personnel behavior activities in the protection cabin can be processed in time, the technical problem that the abnormal conditions of the personnel behavior activities cannot be recognized in time due to the fact that the target video streams cannot be processed by the computing nodes in time after the personnel enter the protection cabin is solved, and the instantaneity of recognizing the abnormal conditions of the personnel behavior activities in the target video streams can be improved.
According to an embodiment of the present disclosure, the video stream processing method may further include:
sending the identification result to monitoring equipment in the monitoring center; and outputting alarm information under the condition that the recognition result represents that the behavior and activity of the person in the target video stream are abnormal.
According to the embodiment of the disclosure, relevant personnel can take relevant measures, such as emergency handling measures, according to the output alarm information to intervene or handle the personnel behavior activities in the corresponding protection cabin, so that the identification accuracy rate of the personnel behavior activity abnormity in the protection cabin and the effectiveness of the relevant handling measures are improved, and the safety of users in the protection cabin is guaranteed in time.
Fig. 6 schematically shows an application scene diagram of a video stream processing method according to another embodiment of the present disclosure.
As shown in fig. 6, the target video stream queue 610 may be established according to the time sequence of the respective start times of the target video streams 611, 612, 613. The target video streams 611, 612 and 613 are input into the computing nodes of the computing pool 620 according to the arrangement order. The computing pool 620 may include a distribution unit 621, computing nodes 622a, 622b, 622 c. In this embodiment, the target video stream 611 may be the first-ranked target video stream in the target video stream queue 610, and the allocation unit 621 may determine, based on the load rate calculation result of each computing node in the computing pool 620, the computing node with the lowest load rate as the target computing node, for example, may determine the computing node 622a as the target computing node. The target video stream 611 is input to the computing node 622a, and after being processed by the computing node 622a, the recognition result 631a of the target video stream 611 is obtained, and the recognition result 631a may be, for example, an exception.
Based on the same or similar processing method, the target video streams 612 and 613 can be input into the computing nodes 622b and 622c, respectively, and obtain corresponding recognition results 631b and 631c, respectively. Here, both the recognition result 631b and the recognition result 631c may be normal.
The identification result 631a, the identification result 631b and the identification result 631c may be sent to the monitoring device 640 in the monitoring center, and based on that the identification result 631a is abnormal, alarm information 650 may be sent to prompt that the identification result of the personnel activity behavior in the protection cabin recorded by the target video stream 611 of the relevant personnel is abnormal, and the relevant personnel may take relevant measures in time according to the alarm information 650, for example, call the target video stream 611 for manual confirmation, and report the relevant department or the relevant personnel based on the result of the manual confirmation, so as to ensure the safety of the personnel in the protection cabin.
Based on the video stream processing method, the disclosure also provides a video stream processing device. The apparatus will be described in detail below with reference to fig. 7.
Fig. 7 schematically shows a block diagram of a video stream processing apparatus according to an embodiment of the present disclosure.
As shown in fig. 7, the video stream processing apparatus 700 of this embodiment includes an obtaining module 710, a determining module 720, and an identifying module 730.
The obtaining module 710 is used for obtaining a target video stream of the information about the personnel behavior activity in the protection cabin.
The determining module 720 is configured to determine a target computing node for identifying a target video stream from a computation power pool deployed in the monitoring center based on a preset rule, where the computation power pool includes a plurality of computing nodes.
The recognition module 730 is configured to input the target video stream into the target computing node, so that the target computing node processes the target video stream to obtain a recognition result of the target video stream, where the recognition result is used to characterize that the human behavior in the target video stream is abnormal or normal.
According to an embodiment of the present disclosure, the determining module 720 may include: the device comprises a calculating unit and a first determining unit.
The calculation unit is used for calculating the load rate of each calculation node in the calculation power pool to obtain a load rate calculation result.
The first determining unit is used for determining the computing node with the lowest load rate as the target computing node based on the load rate computing result.
According to the embodiment of the disclosure, an image recognition model is arranged in the target computing node.
The identifying module 730 may include: an input unit and an identification unit.
The input unit is used for inputting the target video stream into the image recognition model.
The identification unit is used for identifying the video image in the target video stream by using the image identification model and outputting the identification result of the target video stream.
According to an embodiment of the present disclosure, an image recognition model includes a convolutional neural network and a long-short term memory network connected in sequence.
According to an embodiment of the present disclosure, a target video stream includes a plurality of, each target video stream including a start time;
the identification module may include: a queue establishing unit and a distributing unit.
The queue establishing unit is used for establishing a target video stream queue based on the respective starting time of the plurality of target video streams, wherein the arrangement sequence of the target video streams in the target video stream queue is the same as the time sequence of the respective starting time of the plurality of target video streams.
The distribution unit is used for distributing the plurality of target video streams to different target computing nodes respectively based on the arrangement sequence of the target video streams in the target video stream queue so that the target computing nodes can identify the target video streams in parallel and obtain the identification result of each target video stream
According to an embodiment of the present disclosure, the video stream processing apparatus may further include: a sending module and an alarm module.
The sending module is used for sending the identification result to the monitoring equipment in the monitoring center.
And the alarm module is used for outputting alarm information under the condition that the recognition result represents that the behavior and activity of the person in the target video stream are abnormal.
According to an embodiment of the present disclosure, any plurality of the obtaining module 710, the determining module 720 and the identifying module 730 may be combined into one module to be implemented, or any one of the modules may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the obtaining module 710, the determining module 720 and the identifying module 730 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware by any other reasonable way of integrating or packaging a circuit, or in any one of three implementations of software, hardware and firmware, or in any suitable combination of any of them. Alternatively, at least one of the obtaining module 710, the determining module 720 and the identifying module 730 may be at least partially implemented as a computer program module, which when executed, may perform a corresponding function.
Fig. 8 schematically shows a block diagram of an electronic device adapted to implement a video stream processing method according to an embodiment of the present disclosure.
As shown in fig. 8, an electronic device 800 according to an embodiment of the present disclosure includes a processor 801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. The processor 801 may include, for example, a general purpose microprocessor (e.g., CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., Application Specific Integrated Circuit (ASIC)), among others. The processor 801 may also include on-board memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flows according to embodiments of the present disclosure.
In the RAM 803, various programs and data necessary for the operation of the electronic apparatus 800 are stored. The processor 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. The processor 801 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM 802 and/or RAM 803. Note that the programs may also be stored in one or more memories other than the ROM 802 and RAM 803. The processor 801 may also perform various operations of method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.
The present disclosure also provides a computer-readable storage medium, which may be embodied in the device/apparatus/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM 802 and/or RAM 803 described above and/or one or more memories other than the ROM 802 and RAM 803.
Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method illustrated in the flow chart. When the computer program product runs in a computer system, the program code is used for causing the computer system to realize the video stream processing method provided by the embodiment of the disclosure.
The computer program performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure when executed by the processor 801. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted in the form of a signal on a network medium, distributed, downloaded and installed via communication section 809, and/or installed from removable media 811. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 809 and/or installed from the removable medium 811. The computer program, when executed by the processor 801, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments of the present disclosure and/or the claims may be made without departing from the spirit and teachings of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.
The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.
Claims (10)
1. A video stream processing method, comprising:
acquiring a target video stream of personnel behavior activity information in a protection cabin;
determining a target computing node for identifying the target video stream from a computing power pool deployed in a monitoring center based on a preset rule, wherein the computing power pool comprises a plurality of computing nodes;
and inputting the target video stream into the target computing node so that the target computing node can process the target video stream to obtain an identification result of the target video stream, wherein the identification result is used for representing that the behavior activity of the personnel in the target video stream is abnormal or normal.
2. The video stream processing method according to claim 1, wherein determining a target computing node for identifying the target video stream from a computing power pool deployed in a monitoring center based on a preset rule comprises:
calculating the load rate of each calculation node in the calculation power pool to obtain a load rate calculation result;
and determining the computing node with the lowest load rate as the target computing node based on the load rate computing result.
3. The video stream processing method according to claim 1, wherein an image recognition model is provided in the target computing node;
inputting the target video stream into the target computing node so that the target computing node processes the target video stream, and obtaining an identification result of the target video stream includes:
inputting the target video stream into the image recognition model;
and identifying the video image in the target video stream by using the image identification model, and outputting the identification result of the target video stream.
4. The video stream processing method according to claim 3, wherein the image recognition model comprises a convolutional neural network and a long-short term memory network connected in sequence.
5. The video stream processing method according to claim 1, wherein the target video stream includes a plurality, each of the target video streams including a start time;
inputting the target video stream into the target computing node so that the target computing node processes the target video stream, and obtaining an identification result of the target video stream includes:
establishing a target video stream queue based on respective starting moments of a plurality of target video streams, wherein the arrangement sequence of the target video streams in the target video stream queue is the same as the time sequence of the respective starting moments of the plurality of target video streams;
and respectively distributing the plurality of target video streams to different target computing nodes based on the arrangement sequence of the target video streams in the target video stream queue, so that the target computing nodes can identify the target video streams in parallel to obtain the identification result of each target video stream.
6. The video stream processing method of claim 1, further comprising:
sending the identification result to monitoring equipment in the monitoring center; and
and outputting alarm information under the condition that the identification result represents that the behavior and activity of the personnel in the target video stream are abnormal.
7. A video stream processing apparatus comprising:
the acquisition module is used for acquiring a target video stream of the personnel behavior activity information in the protection cabin;
the determining module is used for determining a target computing node for identifying the target video stream from a computational power pool deployed in a monitoring center based on a preset rule, wherein the computational power pool comprises a plurality of computing nodes; and
and the identification module is used for inputting the target video stream into the target computing node so that the target computing node can process the target video stream to obtain an identification result of the target video stream, wherein the identification result is used for representing that the behavior activity of the personnel in the target video stream is abnormal or normal.
8. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-6.
9. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program which, when executed by a processor, implements a method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111365642.8A CN114095753A (en) | 2021-11-17 | 2021-11-17 | Video stream processing method, apparatus, device, medium, and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111365642.8A CN114095753A (en) | 2021-11-17 | 2021-11-17 | Video stream processing method, apparatus, device, medium, and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114095753A true CN114095753A (en) | 2022-02-25 |
Family
ID=80301812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111365642.8A Pending CN114095753A (en) | 2021-11-17 | 2021-11-17 | Video stream processing method, apparatus, device, medium, and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114095753A (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140313330A1 (en) * | 2013-04-19 | 2014-10-23 | James Carey | Video identification and analytical recognition system |
| CN105100689A (en) * | 2014-05-13 | 2015-11-25 | 杭州海康威视数字技术股份有限公司 | Automatic teller machine (ATM) video surveillance method and apparatus |
| CN109241946A (en) * | 2018-10-11 | 2019-01-18 | 平安科技（深圳）有限公司 | Abnormal behaviour monitoring method, device, computer equipment and storage medium |
| CN109961587A (en) * | 2017-12-26 | 2019-07-02 | 天地融科技股份有限公司 | A kind of monitoring system of self-service bank |
| CN110443109A (en) * | 2019-06-11 | 2019-11-12 | 万翼科技有限公司 | Abnormal behaviour monitor processing method, device, computer equipment and storage medium |
| CN110895861A (en) * | 2018-09-13 | 2020-03-20 | 杭州海康威视数字技术股份有限公司 | Abnormal behavior early warning method and device, monitoring equipment and storage medium |
| CN111126411A (en) * | 2019-11-07 | 2020-05-08 | 浙江大华技术股份有限公司 | Abnormal behavior identification method and device |
| CN111563396A (en) * | 2019-01-25 | 2020-08-21 | 北京嘀嘀无限科技发展有限公司 | Method and device for online identifying abnormal behavior, electronic equipment and readable storage medium |
| CN111626199A (en) * | 2020-05-27 | 2020-09-04 | 多伦科技股份有限公司 | Abnormal behavior analysis method for large-scale multi-person carriage scene |
| CN111698470A (en) * | 2020-06-03 | 2020-09-22 | 河南省民盛安防服务有限公司 | Security video monitoring system based on cloud edge cooperative computing and implementation method thereof |
| CN111986228A (en) * | 2020-09-02 | 2020-11-24 | 华侨大学 | Pedestrian tracking method, device and medium based on LSTM model escalator scene |
| CN112836676A (en) * | 2021-03-01 | 2021-05-25 | 创新奇智(北京)科技有限公司 | Abnormal behavior detection method and device, electronic equipment and storage medium |
| CN113065026A (en) * | 2021-04-15 | 2021-07-02 | 上海交通大学 | Intelligent abnormal event detection system, method and medium based on security micro-service architecture |
| US20210258640A1 (en) * | 2020-02-18 | 2021-08-19 | JBF Interlude 2009 LTD | System and methods for detecting anomalous activities for interactive videos |
| CN113329139A (en) * | 2020-02-28 | 2021-08-31 | 中国电信股份有限公司 | Video stream processing method, device and computer readable storage medium |
| CN113569671A (en) * | 2021-07-13 | 2021-10-29 | 北京大数医达科技有限公司 | Abnormal behavior alarm method and device |
-
2021
- 2021-11-17 CN CN202111365642.8A patent/CN114095753A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140313330A1 (en) * | 2013-04-19 | 2014-10-23 | James Carey | Video identification and analytical recognition system |
| CN105100689A (en) * | 2014-05-13 | 2015-11-25 | 杭州海康威视数字技术股份有限公司 | Automatic teller machine (ATM) video surveillance method and apparatus |
| CN109961587A (en) * | 2017-12-26 | 2019-07-02 | 天地融科技股份有限公司 | A kind of monitoring system of self-service bank |
| CN110895861A (en) * | 2018-09-13 | 2020-03-20 | 杭州海康威视数字技术股份有限公司 | Abnormal behavior early warning method and device, monitoring equipment and storage medium |
| CN109241946A (en) * | 2018-10-11 | 2019-01-18 | 平安科技（深圳）有限公司 | Abnormal behaviour monitoring method, device, computer equipment and storage medium |
| CN111563396A (en) * | 2019-01-25 | 2020-08-21 | 北京嘀嘀无限科技发展有限公司 | Method and device for online identifying abnormal behavior, electronic equipment and readable storage medium |
| CN110443109A (en) * | 2019-06-11 | 2019-11-12 | 万翼科技有限公司 | Abnormal behaviour monitor processing method, device, computer equipment and storage medium |
| CN111126411A (en) * | 2019-11-07 | 2020-05-08 | 浙江大华技术股份有限公司 | Abnormal behavior identification method and device |
| US20210258640A1 (en) * | 2020-02-18 | 2021-08-19 | JBF Interlude 2009 LTD | System and methods for detecting anomalous activities for interactive videos |
| CN113329139A (en) * | 2020-02-28 | 2021-08-31 | 中国电信股份有限公司 | Video stream processing method, device and computer readable storage medium |
| CN111626199A (en) * | 2020-05-27 | 2020-09-04 | 多伦科技股份有限公司 | Abnormal behavior analysis method for large-scale multi-person carriage scene |
| CN111698470A (en) * | 2020-06-03 | 2020-09-22 | 河南省民盛安防服务有限公司 | Security video monitoring system based on cloud edge cooperative computing and implementation method thereof |
| CN111986228A (en) * | 2020-09-02 | 2020-11-24 | 华侨大学 | Pedestrian tracking method, device and medium based on LSTM model escalator scene |
| CN112836676A (en) * | 2021-03-01 | 2021-05-25 | 创新奇智(北京)科技有限公司 | Abnormal behavior detection method and device, electronic equipment and storage medium |
| CN113065026A (en) * | 2021-04-15 | 2021-07-02 | 上海交通大学 | Intelligent abnormal event detection system, method and medium based on security micro-service architecture |
| CN113569671A (en) * | 2021-07-13 | 2021-10-29 | 北京大数医达科技有限公司 | Abnormal behavior alarm method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3279700A1 (en) | Security inspection centralized management system | |
| CN109379374A (en) | Threat identification method for early warning and system based on event analysis | |
| CN111523362A (en) | Data analysis method and device based on electronic purse net and electronic equipment | |
| CN116822715A (en) | Safety production monitoring and early warning system based on artificial intelligence | |
| CN113905215B (en) | Bus safe driving monitoring system | |
| US11027686B2 (en) | Vehicle-associated control system to safeguard an occupant to depart the vehicle | |
| CN111581436B (en) | Target identification method, device, computer equipment and storage medium | |
| CN111259682A (en) | Method and device for monitoring the safety of a construction site | |
| CN112419639A (en) | Video information acquisition method and device | |
| CN115273231A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
| CN110414603B (en) | Method, apparatus, computer system, and medium for detecting mobile device | |
| CN113596012A (en) | Method, device, equipment, medium and program product for identifying attack behavior | |
| CN114095753A (en) | Video stream processing method, apparatus, device, medium, and program product | |
| CN113392779A (en) | Crowd monitoring method, device, equipment and medium based on generation of confrontation network | |
| CN110853364B (en) | Data monitoring method and device | |
| CN113313919B (en) | Alarm method and device using multilayer feedforward network model and electronic equipment | |
| CN112419638B (en) | Method and device for acquiring alarm video | |
| CN110415110B (en) | Progress monitoring method, progress monitoring device and electronic equipment | |
| US11403845B2 (en) | Dynamic detection of building structure | |
| CN113743326A (en) | Safety belt wearing state monitoring system, method and device and computer equipment | |
| CN113961441A (en) | Alarm event processing method, auditing method, device, equipment, medium and product | |
| GB2554948A (en) | Video monitoring using machine learning | |
| CN112582054A (en) | Medical insurance data supervision method and device, electronic equipment and medium | |
| CN111626870B (en) | Nuclear data processing method, device and equipment for cleaning physical examination piece | |
| US20130340032A1 (en) | System and method for achieving compliance through a closed loop integrated compliance framework and toolkit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |