CN115294513A - Security monitoring method and system - Google Patents

Security monitoring method and system Download PDF

Info

Publication number
CN115294513A
CN115294513A CN202210778875.9A CN202210778875A CN115294513A CN 115294513 A CN115294513 A CN 115294513A CN 202210778875 A CN202210778875 A CN 202210778875A CN 115294513 A CN115294513 A CN 115294513A
Authority
CN
China
Prior art keywords
monitoring
security monitoring
target
video
security
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.)
Withdrawn
Application number
CN202210778875.9A
Other languages
Chinese (zh)
Inventor
冯军
张�杰
杨艳
张清国
陈月红
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN202210778875.9A priority Critical patent/CN115294513A/en
Publication of CN115294513A publication Critical patent/CN115294513A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/52Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761Proximity, similarity or dissimilarity measures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/40Scenes; Scene-specific elements in video content
    • G06V20/41Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/40Scenes; Scene-specific elements in video content
    • G06V20/46Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames

Abstract

The invention provides a security monitoring method and a security monitoring system, and relates to the technical field of monitoring. In the invention, each security monitoring terminal device is sequentially controlled to monitor a target monitoring area based on the determined monitoring cycle information; the method comprises the steps of sequentially obtaining security monitoring videos obtained by monitoring a plurality of security monitoring terminal devices, determining the currently obtained security monitoring videos as target security monitoring videos, and determining target identification degree information for monitoring and identifying the target security monitoring videos based on corresponding first historical security monitoring videos and second historical security monitoring videos; and determining at least one security monitoring video frame in the target security monitoring video based on the target identification degree information, and monitoring and identifying the at least one security monitoring video frame to obtain a corresponding security monitoring and identifying result. Based on the method, the problem that security monitoring resources are easy to waste in the prior art can be solved.

Description

Security monitoring method and system
Technical Field
The invention relates to the technical field of monitoring, in particular to a security monitoring method and a security monitoring system.
Background
In the monitoring field, more monitoring terminal devices (such as monitoring cameras) are generally deployed to monitor different monitoring areas respectively to obtain corresponding monitoring videos. Moreover, each surveillance video may include a large number of surveillance video frames, and thus, if each surveillance video frame is monitored, identified and processed, a large number of surveillance identification resources may be consumed, and thus, a problem that security and protection surveillance resources are easily wasted may be caused.
Disclosure of Invention
In view of the above, the present invention provides a security monitoring method and system to solve the problem in the prior art that security monitoring resources are easily wasted.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
a security monitoring method is applied to a security monitoring server, the security monitoring server is in communication connection with a plurality of security monitoring terminal devices, each security monitoring terminal device in the plurality of security monitoring terminal devices is respectively arranged in each target monitoring area in a plurality of target monitoring areas, and the security monitoring method comprises the following steps:
after acquiring a regional environment monitoring video acquired by each of the plurality of security monitoring terminal devices for a corresponding target monitoring region, determining monitoring cycle information for monitoring the plurality of target monitoring regions in a sequential cycle manner based on video correlation information among the regional environment monitoring videos, and sequentially controlling each of the security monitoring terminal devices for monitoring the target monitoring region based on the monitoring cycle information, wherein each of the regional environment monitoring videos comprises at least one frame of regional environment monitoring video frame;
the method comprises the steps of sequentially obtaining security monitoring videos obtained by monitoring corresponding target monitoring areas through a plurality of security monitoring terminal devices, determining the currently obtained security monitoring videos as target security monitoring videos, and determining target identification degree information for monitoring and identifying the target security monitoring videos based on first historical security monitoring videos and second historical security monitoring videos corresponding to the target security monitoring videos, wherein the target security monitoring videos comprise a plurality of frames of security monitoring video frames, the first historical security monitoring videos are security monitoring videos obtained last time, and the second historical security monitoring videos are the same as the target monitoring areas corresponding to the target security monitoring videos;
determining at least one security monitoring video frame in the target security monitoring video based on the target identification degree information, and monitoring and identifying the at least one security monitoring video frame to obtain a security monitoring identification result of a target monitoring area corresponding to the target security monitoring video, wherein the security monitoring identification result is used for representing whether an illegal behavior exists in the target monitoring area.
In some preferred embodiments, in the security monitoring method, the step of sequentially obtaining security monitoring videos obtained by monitoring corresponding target monitoring areas by the multiple security monitoring terminal devices, determining a currently obtained security monitoring video as a target security monitoring video, and determining target identification degree information for monitoring and identifying the target security monitoring video based on a first historical security monitoring video and a second historical security monitoring video corresponding to the target security monitoring video includes:
the method comprises the steps of sequentially obtaining security monitoring videos obtained by monitoring corresponding target monitoring areas through a plurality of security monitoring terminal devices, and determining the currently obtained security monitoring videos as the target security monitoring videos, wherein each security monitoring terminal device is used for monitoring the corresponding target monitoring area to obtain the corresponding security monitoring video and then sending the corresponding security monitoring video to a security monitoring server;
acquiring a first historical security monitoring video corresponding to the target security monitoring video, and acquiring a second historical security monitoring video corresponding to the target security monitoring video;
determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and determining target recognition degree information for monitoring and recognizing the target security monitoring video based on the first historical recognition degree information and the second historical recognition degree information.
In some preferred embodiments, in the security monitoring method, the step of determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and determining target recognition degree information for monitoring and recognizing the target security monitoring video based on the first historical recognition degree information and the second historical recognition degree information includes:
determining first historical identification degree information corresponding to the first historical security and protection monitoring video, determining second historical identification degree information corresponding to the second historical security and protection monitoring video, and fusing the first historical identification degree information and the second historical identification degree information to obtain corresponding historical identification degree fused information;
determining a first historical security monitoring identification result corresponding to the first historical security monitoring video, and determining a second historical security monitoring identification result corresponding to the second historical security monitoring video;
and adjusting the historical identification degree fusion information based on the first historical security monitoring identification result and the second historical security monitoring identification result to obtain target identification degree information for monitoring and identifying the target security monitoring video.
In some preferred embodiments, in the security monitoring method, the step of determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and performing fusion processing on the first historical recognition degree information and the second historical recognition degree information to obtain corresponding historical recognition degree fusion information includes:
determining first historical identification degree information corresponding to the first historical security and protection monitoring video, and determining second historical identification degree information corresponding to the second historical security and protection monitoring video;
acquiring a first weighting coefficient configured in advance for the first historical identification degree information, and acquiring a second weighting coefficient configured in advance for the second historical identification degree information, wherein the first weighting coefficient is greater than the second weighting coefficient;
and performing weighted summation calculation on the first historical recognition degree information and the second historical recognition degree information based on the first weighting coefficient and the second weighting coefficient, and taking the calculation result of the weighted summation calculation as corresponding historical recognition degree fusion information.
In some preferred embodiments, in the security monitoring method, the step of adjusting the historical recognition degree fusion information based on the first historical security monitoring recognition result and the second historical security monitoring recognition result to obtain the target recognition degree information for monitoring and recognizing the target security monitoring video includes:
counting the number of security monitoring identification results used for representing that the corresponding target monitoring area has the illegal behavior in the first historical security monitoring identification result and the second historical security monitoring identification result to obtain the corresponding counted number of identification results;
and determining a corresponding recognition degree adjusting coefficient based on the recognition result statistical quantity, and adjusting the historical recognition degree fusion information based on the recognition degree adjusting coefficient to obtain target recognition degree information for monitoring and recognizing the target security monitoring video, wherein the recognition degree adjusting coefficient and the recognition result statistical quantity have positive correlation.
In some preferred embodiments, in the security monitoring method, the step of determining at least one security monitoring video frame in the target security monitoring video based on the target identification degree information, and performing monitoring and identification on the at least one security monitoring video frame to obtain a security monitoring identification result of a target monitoring area corresponding to the target security monitoring video includes:
determining corresponding target screening proportion information based on the target identification degree information, wherein the target screening proportion information and the target identification degree information have positive correlation;
calculating the video frame similarity between two adjacent security monitoring video frames in the target security monitoring video aiming at each two adjacent security monitoring video frames in the target security monitoring video, and sequencing each two adjacent security monitoring video frames in the target security monitoring video according to the sequence of the similarity of the corresponding video frames from small to large to obtain a corresponding video frame combination sequence;
counting the number of security monitoring video frames included in the target security monitoring video to obtain a corresponding video frame counting number, determining a corresponding target screening number based on the video frame counting number and the target screening proportion information, and determining a corresponding number of video frame combinations ranked in the front in the video frame combination sequence based on the target screening number, wherein each video frame combination comprises two adjacent security monitoring video frames, and the difference between the target screening number and the number of the video frame combinations is 1;
performing segmentation processing on the target security monitoring video based on each video frame combination to obtain a plurality of security monitoring video segments, and determining representative security monitoring video frames of the security monitoring video segments based on video frame similarity between each security monitoring video frame and other security monitoring video frames in the security monitoring video segments for each security monitoring video segment, wherein the number of the security monitoring video segments is the target screening number, and two security monitoring video frames in each video frame combination belong to two adjacent security monitoring video segments respectively;
and monitoring and identifying each frame of the representative security monitoring video frame to obtain a security monitoring and identifying result of a target monitoring area corresponding to the target security monitoring video.
In some preferred embodiments, in the security monitoring method, after obtaining a region environment monitoring video acquired by each of the multiple security monitoring terminal devices for a corresponding target monitoring region, the step of determining, based on video correlation relationship information between the region environment monitoring videos, monitoring cycle information for sequentially and cyclically monitoring the multiple target monitoring regions, and sequentially controlling each of the security monitoring terminal devices to monitor the target monitoring regions based on the monitoring cycle information includes:
respectively acquiring a regional environment monitoring video acquired by each of the plurality of security monitoring terminal devices by acquiring a corresponding target monitoring region, and acquiring a plurality of regional environment monitoring videos corresponding to the plurality of security monitoring terminal devices;
determining area correlation relation information among a plurality of corresponding target monitoring areas based on the video correlation relation information among the plurality of area environment monitoring videos;
and determining monitoring cycle information for monitoring the target monitoring areas in a sequential cycle manner based on the relevant area relation information among the target monitoring areas, and sequentially controlling each security monitoring terminal device to monitor the target monitoring areas based on the monitoring cycle information.
The embodiment of the present invention further provides a security monitoring system, which is applied to a security monitoring server, wherein the security monitoring server is communicatively connected with a plurality of security monitoring terminal devices, each of the plurality of security monitoring terminal devices is respectively arranged in each of a plurality of target monitoring areas, and the security monitoring system includes:
the area monitoring control module is used for determining monitoring circulation information for sequentially and circularly monitoring the plurality of target monitoring areas based on video correlation information among the area environment monitoring videos after respectively acquiring an area environment monitoring video acquired by each of the plurality of security monitoring terminal devices for the corresponding target monitoring area, and sequentially controlling each of the security monitoring terminal devices for monitoring the target monitoring area based on the monitoring circulation information, wherein each of the area environment monitoring videos comprises at least one frame of area environment monitoring video frame;
the identification degree determining module is used for sequentially acquiring security monitoring videos obtained by monitoring corresponding target monitoring areas by the plurality of security monitoring terminal devices, determining the currently acquired security monitoring videos as target security monitoring videos, and determining target identification degree information for monitoring and identifying the target security monitoring videos based on first historical security monitoring videos and second historical security monitoring videos corresponding to the target security monitoring videos, wherein the target security monitoring videos comprise multi-frame security monitoring video frames, the first historical security monitoring video is a security monitoring video acquired last time, and the second historical security monitoring video is the same as the target monitoring areas corresponding to the target security monitoring videos;
and the video monitoring and identifying module is used for determining at least one security monitoring video frame in the target security monitoring video based on the target identification degree information, monitoring and identifying the at least one security monitoring video frame to obtain a security monitoring and identifying result of a target monitoring area corresponding to the target security monitoring video, wherein the security monitoring and identifying result is used for representing whether illegal behaviors exist in the target monitoring area.
In some preferred embodiments, in the security monitoring system, the identification degree determining module is specifically configured to:
the method comprises the steps of sequentially obtaining security monitoring videos obtained by monitoring corresponding target monitoring areas through a plurality of security monitoring terminal devices, and determining the currently obtained security monitoring videos as the target security monitoring videos, wherein each security monitoring terminal device is used for monitoring the corresponding target monitoring area to obtain the corresponding security monitoring video and then sending the corresponding security monitoring video to a security monitoring server;
acquiring a first historical security monitoring video corresponding to the target security monitoring video, and acquiring a second historical security monitoring video corresponding to the target security monitoring video;
determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and determining target recognition degree information for monitoring and recognizing the target security monitoring video based on the first historical recognition degree information and the second historical recognition degree information.
In some preferred embodiments, in the security monitoring system, the video monitoring identification module is specifically configured to:
determining corresponding target screening proportion information based on the target identification degree information, wherein the target screening proportion information and the target identification degree information have positive correlation;
calculating the video frame similarity between two adjacent security monitoring video frames in the target security monitoring video aiming at each two adjacent security monitoring video frames in the target security monitoring video, and sequencing each two adjacent security monitoring video frames in the target security monitoring video according to the sequence of the similarity of the corresponding video frames from small to large to obtain a corresponding video frame combination sequence;
counting the number of security monitoring video frames included in the target security monitoring video to obtain a corresponding video frame counting number, determining a corresponding target screening number based on the video frame counting number and the target screening proportion information, and determining a corresponding number of video frame combinations ranked in the front in the video frame combination sequence based on the target screening number, wherein each video frame combination comprises two adjacent security monitoring video frames, and the difference between the target screening number and the number of the video frame combinations is 1;
performing segmentation processing on the target security monitoring video based on each video frame combination to obtain a plurality of security monitoring video segments, and determining representative security monitoring video frames of the security monitoring video segments based on video frame similarity between each security monitoring video frame and other security monitoring video frames in the security monitoring video segments for each security monitoring video segment, wherein the number of the security monitoring video segments is the target screening number, and two security monitoring video frames in each video frame combination belong to two adjacent security monitoring video segments respectively;
and monitoring and identifying each frame of the representative security monitoring video frame to obtain a security monitoring and identifying result of a target monitoring area corresponding to the target security monitoring video.
According to the security monitoring method and system provided by the embodiment of the invention, after each security monitoring terminal device is sequentially controlled to monitor a target monitoring area based on the determined monitoring cycle information, security monitoring videos obtained by monitoring a plurality of security monitoring terminal devices can be sequentially obtained, the currently obtained security monitoring video is determined as the target security monitoring video, and target identification degree information for monitoring and identifying the target security monitoring video is determined based on the corresponding first historical security monitoring video and the second historical security monitoring video, so that at least one frame of security monitoring video frame can be determined in the target security monitoring video based on the target identification degree information, and the corresponding security monitoring identification result is obtained by monitoring and identifying at least one frame of security monitoring video frame, namely, resources consumed by monitoring and identifying the screened part of security monitoring video frame, and thus the problem that the security monitoring resources are easily wasted in the prior art is solved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is a block diagram of a security monitoring server according to an embodiment of the present invention.
Fig. 2 is a schematic flowchart of steps included in the security monitoring method according to the embodiment of the present invention.
Fig. 3 is a schematic diagram of modules included in the security monitoring system provided in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
As shown in fig. 1, an embodiment of the present invention provides a security monitoring server. The security monitoring server may include a memory and a processor.
In detail, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, they may be electrically connected to each other via one or more communication buses or signal lines. The memory can have stored therein at least one software function (computer program) which can be present in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, so as to implement the security monitoring method provided by the embodiment of the present invention (as described later).
By way of example, in some possible implementations, the Memory may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Read Only Memory (EPROM), an electrically Erasable Read Only Memory (EEPROM), and the like.
For example, in some possible implementations, the Processor may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), a System on Chip (SoC), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
Moreover, the structure shown in fig. 1 is only an illustration, and the security monitoring server may further include more or fewer components than those shown in fig. 1, or have a different configuration from that shown in fig. 1, for example, may include a communication unit for information interaction with other devices.
With reference to fig. 2, an embodiment of the present invention further provides a security monitoring method, which is applicable to the security monitoring server. The method steps defined by the related flow of the security monitoring method can be realized by the security monitoring server. The security monitoring server is in communication connection with a plurality of security monitoring terminal devices, and each security monitoring terminal device of the security monitoring terminal devices is respectively arranged in each target monitoring area of a plurality of target monitoring areas (namely, the security monitoring terminal devices correspond to the target monitoring areas one by one).
The specific process shown in fig. 2 will be described in detail below.
Step S100, after obtaining a regional environment monitoring video acquired by each of the plurality of security monitoring terminal devices collecting a corresponding target monitoring region, determining monitoring cycle information for sequentially and cyclically monitoring the plurality of target monitoring regions based on video correlation relation information among the regional environment monitoring videos, and sequentially controlling each of the security monitoring terminal devices to monitor the target monitoring region based on the monitoring cycle information.
In the embodiment of the present invention, the security monitoring server may determine, after obtaining a regional environment monitoring video obtained by each of the plurality of security monitoring terminal devices collecting a corresponding target monitoring region, monitoring cycle information for sequentially and cyclically monitoring the plurality of target monitoring regions based on video correlation information between the regional environment monitoring videos, and sequentially control each of the security monitoring terminal devices to monitor the target monitoring region based on the monitoring cycle information. Each of the regional environment monitoring videos comprises at least one frame of regional environment monitoring video frame.
Step S200, sequentially acquiring security monitoring videos obtained by monitoring corresponding target monitoring areas by the plurality of security monitoring terminal devices, determining the currently acquired security monitoring videos as target security monitoring videos, and determining target identification degree information for monitoring and identifying the target security monitoring videos based on first historical security monitoring videos and second historical security monitoring videos corresponding to the target security monitoring videos.
In the embodiment of the present invention, the security monitoring server may sequentially obtain security monitoring videos obtained by monitoring corresponding target monitoring areas by the multiple security monitoring terminal devices, determine a currently obtained security monitoring video as a target security monitoring video, and determine target identification degree information for monitoring and identifying the target security monitoring video based on a first historical security monitoring video and a second historical security monitoring video corresponding to the target security monitoring video. The target security monitoring video comprises a plurality of frames of security monitoring video frames, the first historical security monitoring video is the security monitoring video obtained last time, and the second historical security monitoring video is the same as the target monitoring area corresponding to the target security monitoring video.
Step S300, determining at least one security monitoring video frame in the target security monitoring video based on the target identification degree information, and monitoring and identifying the at least one security monitoring video frame to obtain a security monitoring and identifying result of a corresponding target monitoring area.
In the embodiment of the present invention, the security monitoring server may determine at least one security monitoring video frame in the target security monitoring video based on the target identification degree information, and perform monitoring identification on the at least one security monitoring video frame to obtain a security monitoring identification result of a corresponding target monitoring area. And the security monitoring and identifying result is used for representing whether an illegal behavior exists in the target monitoring area.
Based on the steps included in the security monitoring method, after each security monitoring terminal device is sequentially controlled to monitor a target monitoring area based on the determined monitoring cycle information, security monitoring videos obtained by monitoring a plurality of security monitoring terminal devices can be sequentially obtained, the currently obtained security monitoring video is determined to be a target security monitoring video, and target identification degree information for monitoring and identifying the target security monitoring video is determined based on the corresponding first historical security monitoring video and the second historical security monitoring video, so that at least one frame of security monitoring video frame can be determined in the target security monitoring video based on the target identification degree information, and the at least one frame of security monitoring video frame is monitored and identified to obtain a corresponding security monitoring identification result, namely, the screened partial security monitoring video frames are monitored and identified, resources consumed by monitoring and identifying can be reduced, and the problem that security monitoring resources are easily wasted in the prior art is solved.
For example, in some possible implementation manners, in step S100, after obtaining a region environment monitoring video obtained by acquiring a corresponding target monitoring region by each of the multiple security monitoring terminal devices, determining monitoring cycle information for sequentially and cyclically monitoring the multiple target monitoring regions based on video correlation information between the region environment monitoring videos, and sequentially controlling each of the security monitoring terminal devices to monitor the target monitoring regions based on the monitoring cycle information, the steps may further include step S110, step S120, and step S130 in the following contents.
Step S110, respectively obtaining a regional environment monitoring video obtained by each security monitoring terminal device in the plurality of security monitoring terminal devices collecting a corresponding target monitoring region, and obtaining a plurality of regional environment monitoring videos corresponding to the plurality of security monitoring terminal devices.
In the embodiment of the present invention, the security monitoring server may respectively obtain the regional environment monitoring video obtained by each of the plurality of security monitoring terminal devices collecting the corresponding target monitoring region, so as to obtain a plurality of regional environment monitoring videos corresponding to the plurality of security monitoring terminal devices. Each of the plurality of security monitoring terminal devices comprises at least one frame of regional environment monitoring video frame.
Step S120, determining area correlation information between a plurality of corresponding target monitoring areas based on the video correlation information between the plurality of area environment monitoring videos.
In the embodiment of the present invention, the security monitoring server may determine the area correlation relationship information between the corresponding multiple target monitoring areas based on the video correlation relationship information between the multiple area environment monitoring videos.
Step S130, determining monitoring cycle information for monitoring the target monitoring areas in a cycle mode in sequence based on the area correlation information among the target monitoring areas, and controlling each security monitoring terminal device in sequence to monitor the target monitoring areas based on the monitoring cycle information.
In the embodiment of the present invention, the security monitoring server may determine monitoring cycle information for sequentially and cyclically monitoring the plurality of target monitoring areas based on the area correlation information between the plurality of target monitoring areas, and sequentially control each of the security monitoring terminal devices to monitor the target monitoring areas based on the monitoring cycle information.
Based on the above steps S110, S120, and S130, a regional environment monitoring video acquired by each of the security monitoring terminal devices for a corresponding target monitoring region may be obtained first, and a plurality of regional environment monitoring videos corresponding to the security monitoring terminal devices may be obtained, and then, based on video correlation relationship information between the plurality of regional environment monitoring videos, regional correlation relationship information between the corresponding target monitoring regions may be determined, so that monitoring cycle information for sequentially and cyclically monitoring the plurality of target monitoring regions may be determined based on the regional correlation relationship information between the plurality of target monitoring regions, and each security monitoring terminal device may be sequentially controlled to monitor the target monitoring region based on the monitoring cycle information. Therefore, sequential circulating monitoring can be realized, monitoring resources can be saved to a certain extent compared with the conventional technical scheme of synchronous monitoring, and the problem that resources are wasted easily in security inspection management in the prior art is solved.
For example, in some possible implementation manners, in step S110, that is, the step of obtaining the area environment monitoring videos obtained by acquiring the corresponding target monitoring area by each security monitoring terminal device in the multiple security monitoring terminal devices respectively to obtain multiple area environment monitoring videos corresponding to the multiple security monitoring terminal devices may further include:
firstly, after establishing communication connection with the plurality of security monitoring terminal devices, generating monitoring area background acquisition notification information, and sending the monitoring area background acquisition notification information to each of the plurality of security monitoring terminal devices, wherein each of the security monitoring terminal devices is used for acquiring a corresponding target monitoring area based on the monitoring area background acquisition notification information after receiving the monitoring area background acquisition notification information, obtaining a corresponding area environment monitoring video and sending the corresponding area environment monitoring video to the security monitoring server;
secondly, respectively acquiring a regional environment monitoring video acquired and sent by each security monitoring terminal device in the plurality of security monitoring terminal devices based on the monitoring region background acquisition notification information, and acquiring a plurality of regional environment monitoring videos corresponding to the plurality of security monitoring terminal devices.
For example, in some possible implementation manners, the step of generating monitoring area background acquisition notification information after establishing communication connection with the plurality of security monitoring terminal devices, and sending the monitoring area background acquisition notification information to each of the plurality of security monitoring terminal devices, may further include:
firstly, after establishing communication connection with the plurality of security monitoring terminal devices, determining target frame number information (determined based on the pre-acquired environment complexity), and generating corresponding monitoring area background acquisition notification information based on the target frame number information;
secondly, sending the background acquisition notification information of the monitoring area to each security monitoring terminal device in the plurality of security monitoring terminal devices, wherein each security monitoring terminal device is used for acquiring a corresponding target monitoring area based on the target frame number information in the background acquisition notification information of the monitoring area to obtain a corresponding area environment monitoring video, and the area environment monitoring video comprises area environment monitoring video frames of which the number is corresponding to the target frame number information.
For example, in some possible implementation manners, in step S120, that is, the step of determining the area correlation relationship information between the corresponding multiple target monitoring areas based on the video correlation relationship information between the multiple area environment monitoring videos, may further include:
firstly, calculating video similarity between every two regional environment monitoring videos in the regional environment monitoring videos, wherein the video similarity is used as video correlation relation information between the regional environment monitoring videos;
secondly, determining area correlation relation information between a plurality of target monitoring areas corresponding to the plurality of area environment monitoring videos based on video similarity between every two area environment monitoring videos in the plurality of area environment monitoring videos.
For example, in some possible implementations, the step of calculating a video similarity between two regional environment monitoring videos in the plurality of regional environment monitoring videos may further include:
firstly, for each region environment monitoring video in the plurality of region environment monitoring videos, performing foreground image matting processing on each frame region environment monitoring video frame included in the region environment monitoring video to obtain a foreground matting monitoring video frame corresponding to each frame region environment monitoring video frame;
secondly, a surveillance video frame is scratched from each frame foreground corresponding to each regional environmental surveillance video in the plurality of regional environmental surveillance videos, a surveillance video frame is scratched from other foregrounds corresponding to each frame of the regional environmental surveillance videos, background supplement processing is carried out on the foreground scratched surveillance video frame, and a target regional environmental surveillance video frame corresponding to the foreground scratched surveillance video frame is obtained (wherein, the parts which are not provided by the other foreground scratched surveillance video frames can be filled with blank images);
then, for every two regional environmental monitoring videos in the plurality of regional environmental monitoring videos, similarity calculation processing is performed on the target regional environmental monitoring video frames corresponding to the two regional environmental monitoring videos, so that the video similarity between the two regional environmental monitoring videos is obtained.
For example, in some possible implementations, the step of correlating the similarity calculation process may further include:
the method comprises the steps that firstly, video frame combination processing is respectively carried out on target area environment monitoring video frames corresponding to two area environment monitoring videos to obtain a first target monitoring video and a second target monitoring video which correspond to each other, wherein each area environment monitoring video comprises a plurality of frames of area environment monitoring video frames, and the plurality of frames of area environment monitoring video frames are obtained by carrying out multi-angle monitoring on the basis of corresponding security protection monitoring terminal equipment;
a second step of sequentially determining multiple frames of first candidate video frames in multiple frames of target area environment surveillance video frames included in the first target surveillance video, and segmenting the first target surveillance video based on the multiple frames of first candidate video frames to obtain multiple first surveillance video segments corresponding to the first target surveillance video, wherein the video frame similarity between each frame of the first candidate video frame and an adjacent previous frame of the first candidate video frame is less than or equal to a preset similarity threshold, and the video frame similarity between the first candidate video frame and a first frame of target area environment surveillance video frame in the first target surveillance video is less than or equal to the similarity threshold;
thirdly, sequentially determining multiple second candidate video frames in multiple target area environment monitoring video frames included in the second target monitoring video, and segmenting the second target monitoring video based on the multiple second candidate video frames to obtain multiple second monitoring video segments corresponding to the second target monitoring video, wherein the video frame similarity between each second candidate video frame and the adjacent second candidate video frame of the previous frame is smaller than or equal to a preset similarity threshold, and the video frame similarity between the first candidate video frame and the first target area environment monitoring video frame in the second target monitoring video is smaller than or equal to the similarity threshold;
fourthly, aiming at each two adjacent target area environment monitoring video frames in each first monitoring video segment in the plurality of first monitoring video segments, determining a non-overlapped part between the two target area environment monitoring video frames based on the angular rotation speed and the frame rate information of image monitoring when the corresponding security monitoring terminal equipment carries out multi-angle monitoring, calculating the similarity of partial video frames between the non-overlapped parts, and aiming at each first monitoring video segment in the plurality of first monitoring video segments, carrying out fusion processing (such as mean value calculation) on the similarity of partial video frames corresponding to the first monitoring video segment to obtain a first similarity fusion value corresponding to the first monitoring segment, and screening out at least one target area environment monitoring video frame from the first monitoring video segments based on the first similarity fusion value to be used as a first representative area environment monitoring video frame corresponding to the first monitoring video segment, wherein the quantity of the first representative area environment monitoring video frames and the first similarity fusion value have a negative correlation;
fifthly, aiming at each two adjacent target area environment monitoring video frames in each second monitoring video segment in the second monitoring video segments, determining a non-overlapped part between the two target area environment monitoring video frames based on the angular rotation speed and the frame rate information of image monitoring when the corresponding security monitoring terminal equipment carries out multi-angle monitoring, calculating the similarity of partial video frames between the non-overlapped parts, and aiming at each second monitoring video segment in the second monitoring video segments, carrying out fusion processing (such as mean value calculation) on the similarity of partial video frames corresponding to the second monitoring video segment to obtain a second similarity fusion value corresponding to the second monitoring video segment, and screening out at least one target area environment monitoring video frame from the second monitoring video segments based on the second similarity fusion value to be used as a second representative area environment monitoring video frame corresponding to the second monitoring video segment, wherein the number of the second representative area environment monitoring video frames and the second similarity fusion value have a negative correlation relationship;
and sixthly, obtaining the video similarity between the two regional environment monitoring videos based on the video frame similarity (such as mean value calculation) between each frame of the first representative region environment monitoring video frame and each frame of the second representative region environment monitoring video frame.
For example, in some possible implementation manners, the step of determining, based on video similarity between every two regional environmental monitoring videos in the multiple regional environmental monitoring videos, region correlation relationship information between multiple target monitoring regions corresponding to the multiple regional environmental monitoring videos may further include:
firstly, for each two target monitoring areas in a plurality of target monitoring areas corresponding to the plurality of area environment monitoring videos, determining an area position distance between the two target monitoring areas, and determining a first area correlation degree between the two target monitoring areas based on the area position distance, wherein the first area correlation degree and the area position distance have a negative correlation relationship;
secondly, for each two target monitoring areas in the plurality of target monitoring areas, determining the area communication degree between the two target monitoring areas, and determining a second area correlation degree between the two target monitoring areas based on the area communication degree, wherein the second area correlation degree and the area communication degree have a positive correlation;
then, for each two target monitoring areas in the multiple target monitoring areas, the first area correlation degree, the second area correlation degree between the two target monitoring areas and the video similarity between the two corresponding area environment monitoring videos are fused to obtain an area correlation degree value (for example, weighted mean calculation) between the two target monitoring areas, where the area correlation degree value is used as the area correlation information between the two corresponding target monitoring areas.
For example, in some possible implementation manners, in the step S130, that is, the step of determining monitoring cycle information for sequentially and cyclically monitoring the multiple target monitoring areas based on the area correlation relationship information between the multiple target monitoring areas, and sequentially controlling each security monitoring terminal device to monitor the target monitoring area based on the monitoring cycle information, may further include:
firstly, aiming at each target monitoring area in the target monitoring areas, respectively determining the relative size relationship between the area correlation degree value between the target monitoring area and each other target monitoring area and a preset correlation degree threshold value based on the area correlation relationship information among the target monitoring areas, and determining other target monitoring areas corresponding to the area correlation degree value which is less than or equal to the correlation degree threshold value as non-correlation monitoring areas corresponding to the target monitoring areas;
secondly, counting the number of the non-relevant monitoring areas corresponding to each target monitoring area to obtain a first area statistical number corresponding to the target monitoring area, determining a target first area statistical number with the maximum value in the first area statistical number corresponding to each target monitoring area in the plurality of target monitoring areas, and determining the target monitoring area corresponding to the target first area statistical number as a first target monitoring area;
then, in each target monitoring area except all the determined first target monitoring areas, determining one target monitoring area with the maximum area correlation degree value between the target monitoring areas which are determined as the first target monitoring areas at the last time, and determining the target monitoring area as the first target monitoring area;
then, repeatedly executing the steps of determining one target monitoring area with the maximum area correlation degree value between the target monitoring area which is determined as the first target monitoring area most recently and each target monitoring area except all the determined first target monitoring areas for multiple times, and determining the target monitoring area as the first target monitoring area until each target monitoring area is determined as the first target monitoring area in sequence;
further, based on the sequence of determining each target monitoring area as the first target monitoring area, determining monitoring cycle information for sequentially and cyclically monitoring the plurality of target monitoring areas (i.e. if the target monitoring areas are determined as the first target monitoring areas, monitoring is performed first in a cycle);
and finally, sequentially controlling each security monitoring terminal device corresponding to the target monitoring areas to monitor the corresponding target monitoring areas based on the monitoring cycle information.
Illustratively, in some possible implementation manners, in step S200, that is, the steps of sequentially obtaining security monitoring videos obtained by monitoring the corresponding target monitoring areas by the multiple security monitoring terminal devices, determining the currently obtained security monitoring videos as target security monitoring videos, and determining target identification degree information for monitoring and identifying the target security monitoring videos based on a first historical security monitoring video and a second historical security monitoring video corresponding to the target security monitoring videos may further include:
firstly, sequentially acquiring security monitoring videos obtained by monitoring corresponding target monitoring areas by the plurality of security monitoring terminal devices, and determining the currently acquired security monitoring videos as the target security monitoring videos, wherein each security monitoring terminal device is used for monitoring the corresponding target monitoring area to obtain the corresponding security monitoring video and then sending the corresponding security monitoring video to the security monitoring server (namely sending the obtained security monitoring video after the monitoring is finished);
secondly, acquiring a first historical security monitoring video corresponding to the target security monitoring video, and acquiring a second historical security monitoring video corresponding to the target security monitoring video;
then, determining first historical identification degree information corresponding to the first historical security monitoring video, determining second historical identification degree information corresponding to the second historical security monitoring video, and determining target identification degree information for monitoring and identifying the target security monitoring video based on the first historical identification degree information and the second historical identification degree information.
For example, in some possible implementation manners, the step of determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and determining target recognition degree information for monitoring and recognizing the target security monitoring video based on the first historical recognition degree information and the second historical recognition degree information may further include:
firstly, determining first historical identification degree information corresponding to a first historical security monitoring video, determining second historical identification degree information corresponding to a second historical security monitoring video, and fusing the first historical identification degree information and the second historical identification degree information to obtain corresponding historical identification degree fusion information;
secondly, determining a first historical security monitoring identification result (namely a security monitoring identification result obtained historically) corresponding to the first historical security monitoring video, and determining a second historical security monitoring identification result corresponding to the second historical security monitoring video;
and then, based on the first historical security monitoring and identifying result and the second historical security monitoring and identifying result, adjusting the historical identification degree fusion information to obtain a target identification degree message for monitoring and identifying the target security monitoring video.
In some possible implementation manners, the determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and performing fusion processing on the first historical recognition degree information and the second historical recognition degree information to obtain corresponding historical recognition degree fusion information may further include:
firstly, determining first historical identification degree information corresponding to the first historical security monitoring video, and determining second historical identification degree information corresponding to the second historical security monitoring video;
secondly, acquiring a first weighting coefficient configured aiming at the first historical identification degree information in advance, and acquiring a second weighting coefficient configured aiming at the second historical identification degree information in advance, wherein the first weighting coefficient is larger than the second weighting coefficient;
then, the first historical recognition degree information and the second historical recognition degree information are subjected to weighted summation calculation based on the first weighting coefficient and the second weighting coefficient, and the calculation result of the weighted summation calculation is used as corresponding historical recognition degree fusion information.
For example, in some possible implementation manners, the step of adjusting the historical recognition degree fusion information based on the first historical security monitoring recognition result and the second historical security monitoring recognition result to obtain the target recognition degree information for monitoring and recognizing the target security monitoring video may further include:
firstly, counting the number of security monitoring identification results used for representing that violation behaviors exist in the corresponding target monitoring area in the first historical security monitoring identification result and the second historical security monitoring identification result to obtain the corresponding identification result counting number;
secondly, determining a corresponding recognition degree adjusting coefficient based on the recognition result statistical quantity, and adjusting the historical recognition degree fusion information based on the recognition degree adjusting coefficient (such as calculating the product of the recognition degree adjusting coefficient and the historical recognition degree fusion information) to obtain the target recognition degree information for monitoring and recognizing the target security monitoring video, wherein the recognition degree adjusting coefficient and the recognition result statistical quantity have positive correlation.
For example, in some possible implementation manners, in step S300, that is, the step of determining at least one security monitoring video frame in the target security monitoring video based on the target identification degree information, and performing monitoring identification on the at least one security monitoring video frame to obtain a security monitoring identification result of a corresponding target monitoring area may further include:
firstly, determining corresponding target screening proportion information based on the target identification degree information, wherein the target screening proportion information and the target identification degree information have positive correlation;
secondly, calculating the similarity of video frames between every two adjacent security monitoring video frames in the target security monitoring video aiming at every two adjacent security monitoring video frames in the target security monitoring video, and sequencing every two adjacent security monitoring video frames in the target security monitoring video according to the sequence of the similarity of the corresponding video frames from small to large to obtain a corresponding video frame combination sequence;
then, counting the number of security monitoring video frames included in the target security monitoring video to obtain a corresponding video frame counting number, determining a corresponding target screening number based on the video frame counting number and the target screening proportion information, and determining a corresponding number of video frame combinations ranked in the front in the video frame combination sequence based on the target screening number, wherein each video frame combination includes two adjacent security monitoring video frames, and the difference between the target screening number and the number of the video frame combinations is 1;
then, performing segmentation processing on the target security monitoring video based on each video frame combination to obtain a plurality of security monitoring video segments, and determining representative security monitoring video frames of the security monitoring video segments based on video frame similarities between each security monitoring video frame and other security monitoring video frames in the security monitoring video segments (for example, an average value of video frame similarities between the representative security monitoring video frames and other security monitoring video frames has a maximum value) for each security monitoring video segment, wherein the number of the plurality of security monitoring video segments is the target screening number, and two security monitoring video frames in each video frame combination respectively belong to two adjacent security monitoring video segments;
and finally, monitoring and identifying (for example, identifying whether special violation behaviors exist or not) each representative security monitoring video frame to obtain a security monitoring and identifying result of a target monitoring area corresponding to the target security monitoring video.
With reference to fig. 3, an embodiment of the present invention further provides a security monitoring system, which is applicable to the security monitoring server. Wherein, security protection monitored control system can include:
the area monitoring control module is used for determining monitoring circulation information for sequentially and circularly monitoring the plurality of target monitoring areas based on video correlation information among the area environment monitoring videos after respectively acquiring an area environment monitoring video acquired by each of the plurality of security monitoring terminal devices for the corresponding target monitoring area, and sequentially controlling each of the security monitoring terminal devices for monitoring the target monitoring area based on the monitoring circulation information, wherein each of the area environment monitoring videos comprises at least one frame of area environment monitoring video frame;
the identification degree determining module is used for sequentially acquiring security monitoring videos obtained by monitoring corresponding target monitoring areas by the plurality of security monitoring terminal devices, determining the currently acquired security monitoring videos as target security monitoring videos, and determining target identification degree information for monitoring and identifying the target security monitoring videos based on first historical security monitoring videos and second historical security monitoring videos corresponding to the target security monitoring videos, wherein the target security monitoring videos comprise multi-frame security monitoring video frames, the first historical security monitoring video is a security monitoring video acquired last time, and the second historical security monitoring video is the same as the target monitoring areas corresponding to the target security monitoring videos;
and the video monitoring and identifying module is used for determining at least one security monitoring video frame in the target security monitoring video based on the target identification degree information, monitoring and identifying the at least one security monitoring video frame to obtain a security monitoring and identifying result of a target monitoring area corresponding to the target security monitoring video, wherein the security monitoring and identifying result is used for representing whether illegal behaviors exist in the target monitoring area.
For example, in some possible implementations, the recognition degree determining module may be specifically configured to: the method comprises the steps of sequentially obtaining security monitoring videos obtained by monitoring corresponding target monitoring areas through a plurality of security monitoring terminal devices, and determining the currently obtained security monitoring videos as the target security monitoring videos, wherein each security monitoring terminal device is used for monitoring the corresponding target monitoring area to obtain the corresponding security monitoring video and then sending the corresponding security monitoring video to a security monitoring server; acquiring a first historical security monitoring video corresponding to the target security monitoring video, and acquiring a second historical security monitoring video corresponding to the target security monitoring video; determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and determining target recognition degree information for monitoring and recognizing the target security monitoring video based on the first historical recognition degree information and the second historical recognition degree information.
For example, in some possible implementations, the video surveillance identification module may be specifically configured to: determining corresponding target screening proportion information based on the target identification degree information, wherein the target screening proportion information and the target identification degree information have positive correlation; calculating the video frame similarity between two adjacent security monitoring video frames in the target security monitoring video aiming at each two adjacent security monitoring video frames in the target security monitoring video, and sequencing each two adjacent security monitoring video frames in the target security monitoring video according to the sequence of the similarity of the corresponding video frames from small to large to obtain a corresponding video frame combination sequence; counting the number of security monitoring video frames included in the target security monitoring video to obtain a corresponding video frame counting number, determining a corresponding target screening number based on the video frame counting number and the target screening proportion information, and determining a corresponding number of video frame combinations ranked in the front in the video frame combination sequence based on the target screening number, wherein each video frame combination comprises two adjacent security monitoring video frames, and the difference between the target screening number and the number of the video frame combinations is 1; performing segmentation processing on the target security monitoring video based on each video frame combination to obtain a plurality of security monitoring video segments, and determining representative security monitoring video frames of the security monitoring video segments based on video frame similarity between each security monitoring video frame and other security monitoring video frames in the security monitoring video segments for each security monitoring video segment, wherein the number of the security monitoring video segments is the target screening number, and two security monitoring video frames in each video frame combination belong to two adjacent security monitoring video segments respectively; and monitoring and identifying each frame of the representative security monitoring video frame to obtain a security monitoring and identifying result of a target monitoring area corresponding to the target security monitoring video.
In summary, according to the security monitoring method and system provided by the present invention, after each security monitoring terminal device is sequentially controlled to monitor a target monitoring area based on the determined monitoring cycle information, a security monitoring video obtained by monitoring a plurality of security monitoring terminal devices may be sequentially obtained, and the currently obtained security monitoring video is determined as a target security monitoring video, and based on the corresponding first historical security monitoring video and second historical security monitoring video, target identification degree information for monitoring and identifying the target security monitoring video is determined, so that at least one security monitoring video frame may be determined in the target security monitoring video based on the target identification degree information, and the at least one security monitoring video frame is monitored and identified to obtain a corresponding security monitoring identification result, that is, by monitoring and identifying a screened part of the security monitoring video frames, resources consumed by monitoring and identifying can be reduced, thereby improving the problem that the security monitoring resources are easily wasted in the prior art.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. The security monitoring method is characterized by being applied to a security monitoring server, the security monitoring server is in communication connection with a plurality of security monitoring terminal devices, each security monitoring terminal device in the plurality of security monitoring terminal devices is respectively arranged in each target monitoring area in a plurality of target monitoring areas, and the security monitoring method comprises the following steps:
after acquiring a regional environment monitoring video acquired by each of the plurality of security monitoring terminal devices for a corresponding target monitoring region, determining monitoring cycle information for monitoring the plurality of target monitoring regions in a sequential cycle manner based on video correlation information among the regional environment monitoring videos, and sequentially controlling each of the security monitoring terminal devices for monitoring the target monitoring region based on the monitoring cycle information, wherein each of the regional environment monitoring videos comprises at least one frame of regional environment monitoring video frame;
the method comprises the steps that security monitoring videos obtained by monitoring corresponding target monitoring areas through a plurality of security monitoring terminal devices are sequentially obtained, the currently obtained security monitoring videos are determined to be target security monitoring videos, target identification degree information for monitoring and identifying the target security monitoring videos is determined based on first historical security monitoring videos and second historical security monitoring videos corresponding to the target security monitoring videos, wherein the target security monitoring videos comprise a plurality of frames of security monitoring video frames, the first historical security monitoring videos are security monitoring videos obtained last time, and the second historical security monitoring videos are the same as the target monitoring areas corresponding to the target security monitoring videos;
determining at least one security monitoring video frame in the target security monitoring video based on the target identification degree information, and monitoring and identifying the at least one security monitoring video frame to obtain a security monitoring identification result of a target monitoring area corresponding to the target security monitoring video, wherein the security monitoring identification result is used for representing whether an illegal behavior exists in the target monitoring area.
2. The security monitoring method according to claim 1, wherein the step of sequentially acquiring security monitoring videos obtained by the plurality of security monitoring terminal devices monitoring corresponding target monitoring areas, determining a currently acquired security monitoring video as a target security monitoring video, and determining target identification degree information for monitoring and identifying the target security monitoring video based on a first historical security monitoring video and a second historical security monitoring video corresponding to the target security monitoring video comprises:
the method comprises the steps of sequentially obtaining security monitoring videos obtained by monitoring corresponding target monitoring areas through a plurality of security monitoring terminal devices, and determining the currently obtained security monitoring videos as the target security monitoring videos, wherein each security monitoring terminal device is used for monitoring the corresponding target monitoring area to obtain the corresponding security monitoring video and then sending the corresponding security monitoring video to a security monitoring server;
acquiring a first historical security monitoring video corresponding to the target security monitoring video, and acquiring a second historical security monitoring video corresponding to the target security monitoring video;
determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and determining target recognition degree information for monitoring and recognizing the target security monitoring video based on the first historical recognition degree information and the second historical recognition degree information.
3. The security monitoring method according to claim 2, wherein the step of determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and determining target recognition degree information for monitoring and recognizing the target security monitoring video based on the first historical recognition degree information and the second historical recognition degree information comprises:
determining first historical identification degree information corresponding to the first historical security and protection monitoring video, determining second historical identification degree information corresponding to the second historical security and protection monitoring video, and fusing the first historical identification degree information and the second historical identification degree information to obtain corresponding historical identification degree fusion information;
determining a first historical security monitoring identification result corresponding to the first historical security monitoring video, and determining a second historical security monitoring identification result corresponding to the second historical security monitoring video;
and adjusting the historical identification degree fusion information based on the first historical security monitoring identification result and the second historical security monitoring identification result to obtain target identification degree information for monitoring and identifying the target security monitoring video.
4. The security monitoring method according to claim 3, wherein the step of determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and fusing the first historical recognition degree information and the second historical recognition degree information to obtain corresponding historical recognition degree fusion information comprises:
determining first historical identification degree information corresponding to the first historical security and protection monitoring video, and determining second historical identification degree information corresponding to the second historical security and protection monitoring video;
acquiring a first weighting coefficient configured in advance for the first historical identification degree information, and acquiring a second weighting coefficient configured in advance for the second historical identification degree information, wherein the first weighting coefficient is greater than the second weighting coefficient;
and performing weighted summation calculation on the first historical identification degree information and the second historical identification degree information based on the first weighting coefficient and the second weighting coefficient, and taking the calculation result of the weighted summation calculation as corresponding historical identification degree fusion information.
5. The security monitoring method according to claim 3, wherein the step of adjusting the historical recognition degree fusion information based on the first historical security monitoring recognition result and the second historical security monitoring recognition result to obtain the target recognition degree information for monitoring and recognizing the target security monitoring video comprises:
counting the number of security monitoring identification results used for representing that illegal behaviors exist in the corresponding target monitoring area in the first historical security monitoring identification result and the second historical security monitoring identification result to obtain the corresponding identification result counting number;
and determining a corresponding recognition degree adjusting coefficient based on the recognition result statistical quantity, and adjusting the historical recognition degree fusion information based on the recognition degree adjusting coefficient to obtain target recognition degree information for monitoring and recognizing the target security monitoring video, wherein the recognition degree adjusting coefficient and the recognition result statistical quantity have positive correlation.
6. The security monitoring method according to claim 1, wherein the step of determining at least one frame of security monitoring video frame in the target security monitoring video based on the target identification degree information, and performing monitoring identification on the at least one frame of security monitoring video frame to obtain the security monitoring identification result of the target monitoring area corresponding to the target security monitoring video comprises:
determining corresponding target screening proportion information based on the target identification degree information, wherein the target screening proportion information and the target identification degree information have positive correlation;
calculating the video frame similarity between two adjacent security monitoring video frames in the target security monitoring video aiming at each two adjacent security monitoring video frames in the target security monitoring video, and sequencing each two adjacent security monitoring video frames in the target security monitoring video according to the sequence of the similarity of the corresponding video frames from small to large to obtain a corresponding video frame combination sequence;
counting the number of security monitoring video frames included in the target security monitoring video to obtain a corresponding video frame counting number, determining a corresponding target screening number based on the video frame counting number and the target screening proportion information, and determining a corresponding number of video frame combinations sequenced in the video frame combination sequence based on the target screening number, wherein each video frame combination comprises two adjacent security monitoring video frames, and the difference value between the target screening number and the number of the video frame combinations is 1;
performing segmentation processing on the target security monitoring video based on each video frame combination to obtain a plurality of security monitoring video segments, and determining representative security monitoring video frames of the security monitoring video segments based on video frame similarity between each security monitoring video frame and other security monitoring video frames in the security monitoring video segments for each security monitoring video segment, wherein the number of the security monitoring video segments is the target screening number, and two security monitoring video frames in each video frame combination belong to two adjacent security monitoring video segments respectively;
and monitoring and identifying each frame of the representative security monitoring video frame to obtain a security monitoring and identifying result of a target monitoring area corresponding to the target security monitoring video.
7. The security monitoring method according to any one of claims 1 to 6, wherein the step of determining, based on video correlation information between the regional environment monitoring videos, monitoring cycle information for sequentially and cyclically monitoring the plurality of target monitoring regions after respectively obtaining the regional environment monitoring videos acquired by each of the plurality of security monitoring terminal devices for a corresponding target monitoring region, and sequentially controlling each of the security monitoring terminal devices for monitoring the target monitoring region based on the monitoring cycle information comprises:
respectively acquiring a regional environment monitoring video acquired by each of the plurality of security monitoring terminal devices by acquiring a corresponding target monitoring region, and acquiring a plurality of regional environment monitoring videos corresponding to the plurality of security monitoring terminal devices;
determining area correlation relation information among a plurality of corresponding target monitoring areas based on the video correlation relation information among the plurality of area environment monitoring videos;
and determining monitoring cycle information for sequentially and circularly monitoring the target monitoring areas based on the area correlation information among the target monitoring areas, and sequentially controlling each security and protection monitoring terminal device to monitor the target monitoring areas based on the monitoring cycle information.
8. The utility model provides a security protection monitored control system, its characterized in that is applied to security protection monitoring server, security protection monitoring server communication connection has a plurality of security protection monitoring terminal equipment, each security protection monitoring terminal equipment among a plurality of security protection monitoring terminal equipment sets up each target monitoring area among a plurality of target monitoring areas respectively, security protection monitored control system includes:
the area monitoring control module is used for determining monitoring circulation information for sequentially and circularly monitoring the plurality of target monitoring areas based on video correlation information among the area environment monitoring videos after respectively acquiring an area environment monitoring video acquired by each of the plurality of security monitoring terminal devices for the corresponding target monitoring area, and sequentially controlling each of the security monitoring terminal devices for monitoring the target monitoring area based on the monitoring circulation information, wherein each of the area environment monitoring videos comprises at least one frame of area environment monitoring video frame;
the identification degree determining module is used for sequentially acquiring security monitoring videos obtained by monitoring corresponding target monitoring areas by the plurality of security monitoring terminal devices, determining the currently acquired security monitoring videos as target security monitoring videos, and determining target identification degree information for monitoring and identifying the target security monitoring videos based on first historical security monitoring videos and second historical security monitoring videos corresponding to the target security monitoring videos, wherein the target security monitoring videos comprise multi-frame security monitoring video frames, the first historical security monitoring video is a security monitoring video acquired last time, and the second historical security monitoring video is the same as the target monitoring areas corresponding to the target security monitoring videos;
and the video monitoring and identifying module is used for determining at least one security monitoring video frame in the target security monitoring video based on the target identification degree information, monitoring and identifying the at least one security monitoring video frame to obtain a security monitoring and identifying result of a target monitoring area corresponding to the target security monitoring video, wherein the security monitoring and identifying result is used for representing whether illegal behaviors exist in the target monitoring area.
9. The security monitoring system of claim 8, wherein the identification degree determination module is specifically configured to:
the method comprises the steps of sequentially obtaining security monitoring videos obtained by monitoring corresponding target monitoring areas through a plurality of security monitoring terminal devices, and determining the currently obtained security monitoring videos as the target security monitoring videos, wherein each security monitoring terminal device is used for monitoring the corresponding target monitoring area to obtain the corresponding security monitoring video and then sending the corresponding security monitoring video to a security monitoring server;
acquiring a first historical security monitoring video corresponding to the target security monitoring video, and acquiring a second historical security monitoring video corresponding to the target security monitoring video;
determining first historical recognition degree information corresponding to the first historical security monitoring video, determining second historical recognition degree information corresponding to the second historical security monitoring video, and determining target recognition degree information for monitoring and recognizing the target security monitoring video based on the first historical recognition degree information and the second historical recognition degree information.
10. The security monitoring system of claim 8, wherein the video monitoring identification module is specifically configured to:
determining corresponding target screening proportion information based on the target identification degree information, wherein the target screening proportion information and the target identification degree information have positive correlation;
for each two adjacent security monitoring video frames in the target security monitoring video, calculating the similarity of the video frames between the two security monitoring video frames, and sequencing each two adjacent security monitoring video frames in the target security monitoring video according to the sequence of the similarity of the corresponding video frames from small to large to obtain a corresponding video frame combination sequence;
counting the number of security monitoring video frames included in the target security monitoring video to obtain a corresponding video frame counting number, determining a corresponding target screening number based on the video frame counting number and the target screening proportion information, and determining a corresponding number of video frame combinations ranked in the front in the video frame combination sequence based on the target screening number, wherein each video frame combination comprises two adjacent security monitoring video frames, and the difference between the target screening number and the number of the video frame combinations is 1;
performing segmentation processing on the target security monitoring video based on each video frame combination to obtain a plurality of security monitoring video segments, and determining representative security monitoring video frames of the security monitoring video segments based on video frame similarity between each security monitoring video frame and other security monitoring video frames in the security monitoring video segments for each security monitoring video segment, wherein the number of the security monitoring video segments is the target screening number, and two security monitoring video frames in each video frame combination belong to two adjacent security monitoring video segments respectively;
and monitoring and identifying each frame of the representative security monitoring video frame to obtain a security monitoring and identifying result of a target monitoring area corresponding to the target security monitoring video.
CN202210778875.9A 2022-06-30 2022-06-30 Security monitoring method and system Withdrawn CN115294513A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210778875.9A CN115294513A (en) 2022-06-30 2022-06-30 Security monitoring method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210778875.9A CN115294513A (en) 2022-06-30 2022-06-30 Security monitoring method and system

Publications (1)

Publication Number Publication Date
CN115294513A true CN115294513A (en) 2022-11-04

Family

ID=83821998

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210778875.9A Withdrawn CN115294513A (en) 2022-06-30 2022-06-30 Security monitoring method and system

Country Status (1)

Country Link
CN (1) CN115294513A (en)

Similar Documents

Publication Publication Date Title
CN114140713A (en) Image recognition system and image recognition method
CN114581856B (en) Agricultural unit motion state identification method and system based on Beidou system and cloud platform
CN114140712A (en) Automatic image recognition and distribution system and method
CN114978037A (en) Solar cell performance data monitoring method and system
CN114724215A (en) Sensitive image identification method and system
CN114139016A (en) Data processing method and system for intelligent cell
CN114697618A (en) Building control method and system based on mobile terminal
CN113902993A (en) Environmental state analysis method and system based on environmental monitoring
CN113868471A (en) Data matching method and system based on monitoring equipment relationship
CN115620243B (en) Pollution source monitoring method and system based on artificial intelligence and cloud platform
CN115294513A (en) Security monitoring method and system
CN114189535A (en) Service request method and system based on smart city data
CN115457467A (en) Building quality hidden danger positioning method and system based on data mining
CN114677615A (en) Environment detection method and system
CN113902412A (en) Environment monitoring method based on data processing
CN115330140A (en) Building risk prediction method based on data mining and prediction system thereof
CN115375886A (en) Data acquisition method and system based on cloud computing service
CN115424193A (en) Training image information processing method and system
CN114095734A (en) User data compression method and system based on data processing
CN113949881A (en) Service processing method and system based on smart city data
CN113537087A (en) Intelligent traffic information processing method and device and server
CN114926973B (en) Video monitoring method, device, system, server and readable storage medium
CN114997343B (en) Fault reason tracing method and system based on air purification detection
CN117523485A (en) Operation management method and system for intelligent park
CN111126261B (en) Video data analysis method and device, raspberry group device and readable storage medium

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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20221104