CN114155459A - Smart city monitoring method and system based on data analysis - Google Patents
Smart city monitoring method and system based on data analysis Download PDFInfo
- Publication number
- CN114155459A CN114155459A CN202111399094.0A CN202111399094A CN114155459A CN 114155459 A CN114155459 A CN 114155459A CN 202111399094 A CN202111399094 A CN 202111399094A CN 114155459 A CN114155459 A CN 114155459A
- Authority
- CN
- China
- Prior art keywords
- video
- monitoring
- historical
- processed
- target
- 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- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Abstract
The invention provides a smart city monitoring method and system based on data analysis, and relates to the technical field of monitoring. Firstly, acquiring a to-be-processed monitoring video sent by monitoring terminal equipment; secondly, obtaining a target historical surveillance video corresponding to the surveillance video to be processed, and determining video correlation information between the target historical surveillance video and the surveillance video to be processed, wherein the target historical surveillance video comprises a plurality of frames of target historical surveillance video frames, and the plurality of frames of target historical surveillance video frames are obtained by monitoring a target surveillance area historically based on the surveillance terminal equipment; and then, based on the video correlation information and the target historical monitoring video, performing video frame screening processing on the monitoring video to be processed to obtain the target monitoring video corresponding to the monitoring video to be processed. Based on the method, the problem of poor reliability of video screening in the prior art can be solved.
Description
Technical Field
The invention relates to the technical field of monitoring, in particular to a smart city monitoring method and system based on data analysis.
Background
In the implementation of smart cities, the application of monitoring technology is essential. The monitoring technology generally includes audio monitoring, video monitoring, monitoring based on other types of sensors, and the like. For example, for video surveillance, the data amount of the collected surveillance video is generally large, and there are repetitive video contents, so the collected surveillance video is generally subjected to a screening process, such as deduplication screening, but in the prior art, the screening is generally performed based on a fixed screening ratio, and thus, a problem of poor reliability of video screening may be caused.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for monitoring a smart city based on data analysis, so as to solve the problem of poor reliability of video screening in the prior art.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
a smart city monitoring method based on data analysis is applied to a monitoring background server, the monitoring background server is in communication connection with monitoring terminal equipment, and the smart city monitoring method based on data analysis comprises the following steps:
acquiring a to-be-processed monitoring video sent by the monitoring terminal equipment, wherein the to-be-processed monitoring video comprises a plurality of frames of to-be-processed monitoring video frames, and the plurality of frames of to-be-processed monitoring video frames are obtained by monitoring a target monitoring area based on the monitoring terminal equipment;
acquiring a target historical surveillance video corresponding to the surveillance video to be processed, and determining video correlation information between the target historical surveillance video and the surveillance video to be processed, wherein the target historical surveillance video comprises multiple frames of target historical surveillance video frames, and the multiple frames of target historical surveillance video frames are obtained by monitoring a target surveillance area historically based on the surveillance terminal equipment;
and based on the video correlation information and the target historical surveillance video, performing video frame screening processing on the surveillance video to be processed to obtain a target surveillance video corresponding to the surveillance video to be processed, wherein the target surveillance video comprises at least one frame of the surveillance video to be processed.
In some preferred embodiments, in the above method for monitoring a smart city based on data analysis, the step of obtaining a to-be-processed monitoring video sent by the monitoring terminal device includes:
after receiving monitoring request information sent by the monitoring terminal equipment or other communication connected terminal equipment, or when an execution result of a target program obtained by executing a preset target program meets a preset target result condition, generating corresponding monitoring start notification information;
sending the monitoring start notification information to the monitoring terminal equipment, wherein the monitoring terminal equipment is used for monitoring the target monitoring area after receiving the monitoring start notification information to obtain a corresponding to-be-processed monitoring video, and performing video data packaging processing on the to-be-processed monitoring video to obtain a corresponding video data packet;
and acquiring the video data packet acquired and sent by the monitoring terminal equipment based on the monitoring start notification information, and analyzing and processing the video data packet to obtain the to-be-processed monitoring video corresponding to the video data packet.
In some preferred embodiments, in the method for monitoring a smart city based on data analysis, the step of obtaining a target historical monitoring video corresponding to the monitoring video to be processed and determining video correlation information between the target historical monitoring video and the monitoring video to be processed includes:
acquiring historical monitoring videos obtained by monitoring the target monitoring area by the monitoring terminal device in a plurality of historical time periods respectively to obtain a plurality of historical monitoring videos;
determining a historical monitoring video which has a corresponding relation with the monitoring video to be processed in the plurality of historical monitoring videos, and using the historical monitoring video as a target historical monitoring video corresponding to the monitoring video to be processed;
and determining the correlation between the target historical monitoring video and the monitoring video to be processed to obtain corresponding video correlation information.
In some preferred embodiments, in the method for monitoring a smart city based on data analysis, the step of determining, from the plurality of historical monitoring videos, a historical monitoring video having a corresponding relationship with the to-be-processed monitoring video as a target historical monitoring video corresponding to the to-be-processed monitoring video includes:
performing time analysis processing on the monitored video to be processed to obtain a first time period corresponding to the monitored video to be processed, wherein the first time period is determined based on the time corresponding to a first frame of monitored video to be processed and a last frame of monitored video to be processed in the monitored video to be processed;
for each historical monitoring video in the plurality of historical monitoring videos, calculating a first time interval and a second time interval between the historical period and the first time period corresponding to the historical monitoring video, and determining a first time correlation between the historical monitoring video and the monitoring video to be processed based on the first time interval and the second time interval, wherein the first time interval is used for representing a time interval between the latest moment of the historical period and the earliest moment of the first time period, and the second time interval is used for representing a time interval between the earliest moment of the historical period and the latest moment of the first time period;
for each historical monitoring video in the plurality of historical monitoring videos, calculating the historical time period corresponding to the historical monitoring video and the first time period in a preset time cycle dimension to obtain a second time correlation degree between the historical monitoring video and the monitoring video to be processed;
and for each historical surveillance video in the plurality of historical surveillance videos, fusing the first time correlation degree and the second time correlation degree between the historical surveillance video and the surveillance video to be processed to obtain the time correlation degree between the historical surveillance video and the surveillance video to be processed, and determining a target historical surveillance video corresponding to the surveillance video to be processed in the plurality of historical surveillance videos based on the time correlation degree between each historical surveillance video in the plurality of historical surveillance videos and the surveillance video to be processed.
In some preferred embodiments, in the above method for monitoring a smart city based on data analysis, the step of calculating, for each historical surveillance video in the plurality of historical surveillance videos, a first time interval and a second time interval between the historical time period and the first time period corresponding to the historical surveillance video, and determining a first time correlation between the historical surveillance video and the surveillance video to be processed based on the first time interval and the second time interval includes:
for each historical monitoring video in the plurality of historical monitoring videos, calculating a first time interval and a second time interval between the historical time period and the first time period corresponding to the historical monitoring video, and calculating a weighted sum value between the first time interval and the second time interval to obtain a weighted sum value of the time intervals corresponding to the historical monitoring video, wherein the weighting coefficient corresponding to the first time interval is greater than the weighting coefficient corresponding to the second time interval;
for each historical monitoring video in the plurality of historical monitoring videos, obtaining a first time correlation degree between the historical monitoring video and the monitoring video to be processed based on the time interval weighted sum value corresponding to the historical monitoring video, wherein the first time correlation degree and the time interval weighted sum value have a negative correlation relationship.
In some preferred embodiments, in the method for monitoring a smart city based on data analysis, for each historical surveillance video of the plurality of historical surveillance videos, the step of calculating the historical time period corresponding to the historical surveillance video and the first time period in a preset time cycle dimension to obtain a second time correlation between the historical surveillance video and the surveillance video to be processed includes:
determining time slices to which the first time period belongs within a preset time period, wherein each time period is formed on the basis of a plurality of continuous time slices;
for each historical monitoring video in the plurality of historical monitoring videos, determining a time slice to which the historical time period corresponding to the historical monitoring video belongs within a preset time period;
and calculating the time segment interval between the time segment to which the historical time period belongs and the time segment to which the first time period belongs, which corresponds to each historical monitoring video in the plurality of historical monitoring videos, and calculating a second time correlation degree between the historical monitoring video and the monitoring video to be processed based on the time segment interval, wherein the second time correlation degree has a negative correlation with the time segment interval.
In some preferred embodiments, in the above method for monitoring a smart city based on data analysis, the step of performing video frame screening processing on the to-be-processed monitoring video based on the video correlation information and the target historical monitoring video to obtain a target monitoring video corresponding to the to-be-processed monitoring video includes:
carrying out object identification processing on historical monitoring video frames included in the target historical monitoring video, and determining object flow corresponding to the target historical monitoring video based on the obtained object identification result to obtain historical object flow information corresponding to the target historical monitoring video;
fusing the video correlation relation information and the historical object flow information to obtain a corresponding object flow characteristic value, and determining a ratio between the object flow characteristic value and a preset object flow threshold value to obtain a corresponding target flow ratio;
and determining the maximum screening proportion information for carrying out video frame screening and reselection on the monitored video to be processed based on the target flow ratio, and carrying out video frame de-emphasis screening on the monitored video to be processed based on the maximum screening proportion information to obtain the corresponding target monitored video.
The embodiment of the invention also provides a smart city monitoring system based on data analysis, which is applied to a monitoring background server, wherein the monitoring background server is in communication connection with a monitoring terminal device, and the smart city monitoring system based on data analysis comprises:
the monitoring terminal equipment is used for monitoring a target monitoring area, and comprises a monitoring video acquisition unit used for acquiring a to-be-processed monitoring video sent by the monitoring terminal equipment, wherein the to-be-processed monitoring video comprises a plurality of frames of to-be-processed monitoring video frames which are obtained by monitoring the target monitoring area based on the monitoring terminal equipment;
a video correlation determining unit, configured to obtain a target historical surveillance video corresponding to the to-be-processed surveillance video, and determine video correlation information between the target historical surveillance video and the to-be-processed surveillance video, where the target historical surveillance video includes multiple frames of target historical surveillance video frames, and the multiple frames of target historical surveillance video frames are obtained by monitoring a target surveillance area historically based on the surveillance terminal device;
and the video frame screening unit is used for carrying out video frame screening processing on the monitored video to be processed based on the video correlation relation information and the target historical monitored video to obtain the target monitored video corresponding to the monitored video to be processed, wherein the target monitored video comprises at least one frame of the monitored video frame to be processed.
In some preferred embodiments, in the smart city monitoring system based on data analysis, the video correlation determination unit is specifically configured to:
acquiring historical monitoring videos obtained by monitoring the target monitoring area by the monitoring terminal device in a plurality of historical time periods respectively to obtain a plurality of historical monitoring videos;
determining a historical monitoring video which has a corresponding relation with the monitoring video to be processed in the plurality of historical monitoring videos, and using the historical monitoring video as a target historical monitoring video corresponding to the monitoring video to be processed;
and determining the correlation between the target historical monitoring video and the monitoring video to be processed to obtain corresponding video correlation information.
In some preferred embodiments, in the above smart city monitoring system based on data analysis, the video frame filtering unit is specifically configured to:
carrying out object identification processing on historical monitoring video frames included in the target historical monitoring video, and determining object flow corresponding to the target historical monitoring video based on the obtained object identification result to obtain historical object flow information corresponding to the target historical monitoring video;
fusing the video correlation relation information and the historical object flow information to obtain a corresponding object flow characteristic value, and determining a ratio between the object flow characteristic value and a preset object flow threshold value to obtain a corresponding target flow ratio;
and determining the maximum screening proportion information for carrying out video frame screening and reselection on the monitored video to be processed based on the target flow ratio, and carrying out video frame de-emphasis screening on the monitored video to be processed based on the maximum screening proportion information to obtain the corresponding target monitored video.
According to the smart city monitoring method and system based on data analysis, after the to-be-processed monitoring video sent by the monitoring terminal device is obtained, the target historical monitoring video corresponding to the to-be-processed monitoring video can be obtained first, and the video correlation information between the target historical monitoring video and the to-be-processed monitoring video is determined, so that the to-be-processed monitoring video can be subjected to video frame screening processing based on the video correlation information and the target historical monitoring video to obtain the corresponding target monitoring video, namely when the video frame screening processing is carried out, the historical monitoring video is referred to, the reliability of the video frame screening processing can be improved, and the problem that the reliability of the video screening in the prior art is poor 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 monitoring background server according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating steps included in a smart city monitoring method based on data analysis according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of units (modules) included in the smart city monitoring system based on data analysis according to an 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.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a monitoring backend server. Wherein the monitoring backend 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 may have stored therein at least one software function (a computer program, such as a data analysis-based smart city monitoring system described below) that may 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 method for monitoring a smart city based on data analysis according to the embodiment of the present invention, which is explained later with reference to the following description.
For example, in an alternative example, the Memory may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Read-Only Memory (EPROM), electrically Erasable Read-Only Memory (EEPROM), and the like.
For example, in an alternative example, 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.
With reference to fig. 2, an embodiment of the present invention further provides a smart city monitoring method based on data analysis, which can be applied to the monitoring background server. The method steps defined by the relevant process of the smart city monitoring method based on data analysis can be realized by the monitoring background server. And the monitoring background server is in communication connection with the monitoring terminal equipment.
The specific process shown in FIG. 2 will be described in detail below.
Step S110, acquiring the to-be-processed monitoring video sent by the monitoring terminal equipment.
In the embodiment of the present invention, the monitoring background server may first obtain the to-be-processed monitoring video sent by the monitoring terminal device. The to-be-processed monitoring video may include multiple frames of to-be-processed monitoring video frames, and the multiple frames of to-be-processed monitoring video frames may be obtained by monitoring (i.e., acquiring images) a target monitoring area based on the monitoring terminal device.
Step S120, a target historical surveillance video corresponding to the surveillance video to be processed is obtained, and video correlation information between the target historical surveillance video and the surveillance video to be processed is determined.
In the embodiment of the invention, the monitoring background server can acquire a target historical monitoring video corresponding to the monitoring video to be processed and determine video correlation information between the target historical monitoring video and the monitoring video to be processed. The target historical monitoring video comprises a plurality of frames of target historical monitoring video frames, and the plurality of frames of target historical monitoring video frames are obtained by monitoring a target monitoring area historically based on the monitoring terminal equipment.
Step S130, based on the video correlation information and the target historical monitoring video, performing video frame screening processing on the monitoring video to be processed to obtain a corresponding target monitoring video.
In the embodiment of the present invention, the monitoring background server may perform video frame screening processing on the to-be-processed monitoring video based on the video correlation information and the target historical monitoring video, so as to obtain the target monitoring video corresponding to the to-be-processed monitoring video. The target monitoring video comprises at least one frame of the monitoring video frame to be processed.
Based on this (i.e., in each step in the above example), after the to-be-processed monitoring video sent by the monitoring terminal device is obtained, the target historical monitoring video corresponding to the to-be-processed monitoring video may be obtained first, and the video correlation information between the target historical monitoring video and the to-be-processed monitoring video is determined, so that the to-be-processed monitoring video may be subjected to video frame screening processing based on the video correlation information and the target historical monitoring video to obtain the corresponding target monitoring video, that is, when the video frame screening processing is performed, the historical monitoring video is referred to, which may improve the reliability of the video frame screening processing, and improve the problem in the prior art that the reliability of the video screening is poor.
For example, in an alternative example, the step S110 in the above example may include the following steps to obtain the to-be-processed monitoring video sent by the monitoring terminal device:
firstly, after receiving monitoring request information sent by the monitoring terminal equipment or other communication connected terminal equipment, or when an object program execution result obtained by executing a pre-configured object program meets a pre-configured object result condition, generating corresponding monitoring start notification information;
secondly, sending the monitoring start notification information to the monitoring terminal equipment, wherein the monitoring terminal equipment is used for monitoring the target monitoring area after receiving the monitoring start notification information to obtain a corresponding to-be-processed monitoring video, and performing video data packaging processing on the to-be-processed monitoring video to obtain a corresponding video data packet;
and then, acquiring the video data packet acquired and sent by the monitoring terminal device based on the monitoring start notification information, and analyzing and processing the video data packet to obtain the to-be-processed monitoring video corresponding to the video data packet.
For example, in an alternative example, the step S120 in the above example may include the following steps to determine the video correlation information between the target historical surveillance video and the to-be-processed surveillance video:
firstly, acquiring historical monitoring videos obtained by monitoring the target monitoring area by the monitoring terminal device in a plurality of historical time periods respectively to obtain a plurality of historical monitoring videos;
secondly, determining a historical monitoring video which has a corresponding relation with the monitoring video to be processed in the plurality of historical monitoring videos, and using the historical monitoring video as a target historical monitoring video corresponding to the monitoring video to be processed;
and then, determining the correlation between the target historical monitoring video and the monitoring video to be processed to obtain corresponding video correlation information.
For example, in an alternative example, the step of determining, from the plurality of historical surveillance videos, a historical surveillance video having a corresponding relationship with the to-be-processed surveillance video as a target historical surveillance video corresponding to the to-be-processed surveillance video may include the following steps:
firstly, performing time analysis processing on the to-be-processed monitoring video to obtain a first time period corresponding to the to-be-processed monitoring video, wherein the first time period is determined based on the time corresponding to a first to-be-processed monitoring video frame and a last to-be-processed monitoring video frame in the to-be-processed monitoring video (namely the time period between the two times);
secondly, for each historical monitoring video in the plurality of historical monitoring videos, calculating a first time interval and a second time interval between the historical period and the first time period corresponding to the historical monitoring video, and determining a first time correlation between the historical monitoring video and the monitoring video to be processed based on the first time interval and the second time interval, wherein the first time interval is used for representing a time interval between the latest moment of the historical period and the earliest moment of the first time period, and the second time interval is used for representing a time interval between the earliest moment of the historical period and the latest moment of the first time period;
then, for each historical monitoring video in the plurality of historical monitoring videos, calculating the historical time period corresponding to the historical monitoring video and the first time period in a preset time cycle dimension to obtain a second time correlation between the historical monitoring video and the monitoring video to be processed (for example, the time period is one day, the time correlation can be divided by time, for example, the historical time period is 11 to 12 points, and the first time period is 13 to 14 points);
finally, for each historical surveillance video in the plurality of historical surveillance videos, the first time correlation and the second time correlation between the historical surveillance video and the surveillance video to be processed are fused (for example, an average value is calculated), so that the time correlation between the historical surveillance video and the surveillance video to be processed is obtained, and a target historical surveillance video corresponding to the surveillance video to be processed is determined in the plurality of historical surveillance videos based on the time correlation between each historical surveillance video in the plurality of historical surveillance videos and the surveillance video to be processed.
For example, in an alternative example, the step of calculating, for each historical surveillance video in the plurality of historical surveillance videos, a first time interval and a second time interval between the historical time period corresponding to the historical surveillance video and the first time period, and determining a first time correlation between the historical surveillance video and the surveillance video to be processed based on the first time interval and the second time interval may include the following steps:
firstly, for each historical monitoring video in the plurality of historical monitoring videos, calculating a first time interval and a second time interval between the historical time period and the first time period corresponding to the historical monitoring video, and calculating a weighted sum value between the first time interval and the second time interval to obtain a weighted sum value of the time intervals corresponding to the historical monitoring video, wherein the weighting coefficient corresponding to the first time interval is greater than the weighting coefficient corresponding to the second time interval;
secondly, for each historical monitoring video in the plurality of historical monitoring videos, obtaining a first time correlation degree between the historical monitoring video and the monitoring video to be processed based on the time interval weighted sum value corresponding to the historical monitoring video, wherein the first time correlation degree and the time interval weighted sum value have a negative correlation relationship.
For example, in an alternative example, the step of calculating, for each historical surveillance video in the plurality of historical surveillance videos, the historical time period corresponding to the historical surveillance video and the first time period in a preset time cycle dimension to obtain the second time correlation between the historical surveillance video and the to-be-processed surveillance video may include the following steps:
firstly, determining time slices to which the first time period belongs within a preset time period, wherein each time period is formed on the basis of a plurality of continuous time slices;
secondly, determining a time segment of the historical time period corresponding to each historical monitoring video in a preset time period for each historical monitoring video in the plurality of historical monitoring videos;
then, for each historical monitoring video in the plurality of historical monitoring videos, calculating a time segment interval between a time segment to which the historical time period belongs and a time segment to which the first time period belongs, which corresponds to the historical monitoring video, and calculating a second time correlation between the historical monitoring video and the monitoring video to be processed based on the time segment interval, wherein the second time correlation has a negative correlation with the time segment interval.
For example, in an alternative example, the step S130 in the above example may include the following steps, so as to perform video frame screening processing on the to-be-processed monitoring video based on the video correlation information and the target historical monitoring video, to obtain a target monitoring video corresponding to the to-be-processed monitoring video:
firstly, carrying out object identification processing on historical monitoring video frames included in the target historical monitoring video, and determining object flow corresponding to the target historical monitoring video based on an obtained object identification result to obtain historical object flow information corresponding to the target historical monitoring video;
secondly, fusing (for example, calculating a product between the video correlation information (such as the time correlation) and the historical object flow information) to obtain a corresponding object flow characteristic value, and determining a ratio between the object flow characteristic value and a preset object flow threshold value to obtain a corresponding target flow ratio;
then, determining the maximum screening proportion information for carrying out video frame screening and reselection processing on the monitored video to be processed based on the target flow ratio, and carrying out video frame de-emphasis screening processing on the monitored video to be processed based on the maximum screening proportion information to obtain the corresponding target monitored video.
For example, in an alternative example, the step of determining, based on the target flow ratio, maximum filtering ratio information for performing video frame deduplication screening processing on the to-be-processed monitored video, and performing video frame deduplication screening processing on the to-be-processed monitored video based on the maximum filtering ratio information to obtain a corresponding target monitored video may include the following steps:
firstly, sampling processing is carried out on the monitored video to be processed based on a pre-configured video frame sampling parameter, and a plurality of corresponding frames of first monitored video frames to be processed are obtained;
secondly, aiming at each first to-be-processed monitoring video frame in the multiple first to-be-processed monitoring video frames, a plurality of video segments corresponding to the first to-be-processed monitoring video frame are obtained based on the first to-be-processed monitoring video frame and a preset video frame number threshold value set, wherein the video frame number threshold value set comprises a multiple video frame number threshold value, and each video segment is formed by the to-be-processed video frames based on the first to-be-processed monitoring video frame and the adjacent video frame number threshold value frame of the first to-be-processed monitoring video frame;
then, performing deduplication processing on a plurality of video clips corresponding to each first to-be-processed surveillance video frame in the plurality of frames of first to-be-processed surveillance video frames to obtain a plurality of first video clips corresponding to the plurality of frames of first to-be-processed surveillance video frames, determining whether two continuous first video clips exist in the plurality of first video clips, and merging the two first video clips for every two first video clips when two continuous first video clips exist to obtain a corresponding new first video clip;
then, for each first video segment which is not combined and each new first video segment, based on the frame timing position of the first video segment or the new first video segment in the monitored video to be processed, determining a historical video segment corresponding to the frame timing position in the target historical monitored video, and counting historical object flow sub-information corresponding to the historical video segment, and based on the historical object flow sub-information, determining maximum screening proportion sub-information for performing video frame screening processing on the first video segment or the new first video segment;
finally, for each first video segment which is not combined and each new first video segment, based on the maximum screening proportion sub-information and the maximum screening proportion information corresponding to the first video segment or the new first video segment, performing video frame de-rescreening processing on the first video segment or the new first video segment (that is, the proportion of the video frames screened out of each first video segment does not exceed the corresponding maximum screening proportion sub-information, that is, the total proportion of the video frames screened out of all the first video segments does not exceed the maximum screening proportion information) to obtain a corresponding target surveillance video.
With reference to fig. 3, an embodiment of the present invention further provides a smart city monitoring system based on data analysis, which can be applied to the monitoring background server. Wherein, the smart city monitoring system based on data analysis may include:
the monitoring terminal equipment is used for monitoring a target monitoring area, and comprises a monitoring video acquisition unit used for acquiring a to-be-processed monitoring video sent by the monitoring terminal equipment, wherein the to-be-processed monitoring video comprises a plurality of frames of to-be-processed monitoring video frames which are obtained by monitoring the target monitoring area based on the monitoring terminal equipment;
a video correlation determining unit, configured to obtain a target historical surveillance video corresponding to the to-be-processed surveillance video, and determine video correlation information between the target historical surveillance video and the to-be-processed surveillance video, where the target historical surveillance video includes multiple frames of target historical surveillance video frames, and the multiple frames of target historical surveillance video frames are obtained by monitoring a target surveillance area historically based on the surveillance terminal device;
and the video frame screening unit is used for carrying out video frame screening processing on the monitored video to be processed based on the video correlation relation information and the target historical monitored video to obtain the target monitored video corresponding to the monitored video to be processed, wherein the target monitored video comprises at least one frame of the monitored video frame to be processed.
For example, in an alternative example, the video correlation determination unit may be specifically configured to: acquiring historical monitoring videos obtained by monitoring the target monitoring area by the monitoring terminal device in a plurality of historical time periods respectively to obtain a plurality of historical monitoring videos; determining a historical monitoring video which has a corresponding relation with the monitoring video to be processed in the plurality of historical monitoring videos, and using the historical monitoring video as a target historical monitoring video corresponding to the monitoring video to be processed; and determining the correlation between the target historical monitoring video and the monitoring video to be processed to obtain corresponding video correlation information.
For example, in an alternative example, the video frame filtering unit may specifically be configured to: carrying out object identification processing on historical monitoring video frames included in the target historical monitoring video, and determining object flow corresponding to the target historical monitoring video based on the obtained object identification result to obtain historical object flow information corresponding to the target historical monitoring video; fusing the video correlation relation information and the historical object flow information to obtain a corresponding object flow characteristic value, and determining a ratio between the object flow characteristic value and a preset object flow threshold value to obtain a corresponding target flow ratio; and determining the maximum screening proportion information for carrying out video frame screening and reselection on the monitored video to be processed based on the target flow ratio, and carrying out video frame de-emphasis screening on the monitored video to be processed based on the maximum screening proportion information to obtain the corresponding target monitored video.
In summary, according to the smart city monitoring method and system based on data analysis provided by the invention, after the to-be-processed monitoring video sent by the monitoring terminal device is obtained, the target historical monitoring video corresponding to the to-be-processed monitoring video is obtained first, and the video correlation information between the target historical monitoring video and the to-be-processed monitoring video is determined, so that the to-be-processed monitoring video can be subjected to video frame screening processing based on the video correlation information and the target historical monitoring video to obtain the corresponding target monitoring video, that is, the historical monitoring video is referred to during the video frame screening processing, the reliability of the video frame screening processing can be improved, and the problem of poor reliability of the video screening in the prior art is solved.
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 smart city monitoring method based on data analysis is applied to a monitoring background server, the monitoring background server is in communication connection with monitoring terminal equipment, and the smart city monitoring method based on data analysis comprises the following steps:
acquiring a to-be-processed monitoring video sent by the monitoring terminal equipment, wherein the to-be-processed monitoring video comprises a plurality of frames of to-be-processed monitoring video frames, and the plurality of frames of to-be-processed monitoring video frames are obtained by monitoring a target monitoring area based on the monitoring terminal equipment;
acquiring a target historical surveillance video corresponding to the surveillance video to be processed, and determining video correlation information between the target historical surveillance video and the surveillance video to be processed, wherein the target historical surveillance video comprises multiple frames of target historical surveillance video frames, and the multiple frames of target historical surveillance video frames are obtained by monitoring a target surveillance area historically based on the surveillance terminal equipment;
and based on the video correlation information and the target historical surveillance video, performing video frame screening processing on the surveillance video to be processed to obtain a target surveillance video corresponding to the surveillance video to be processed, wherein the target surveillance video comprises at least one frame of the surveillance video to be processed.
2. The smart city monitoring method based on data analysis as claimed in claim 1, wherein the step of obtaining the to-be-processed monitoring video transmitted by the monitoring terminal device comprises:
after receiving monitoring request information sent by the monitoring terminal equipment or other communication connected terminal equipment, or when an execution result of a target program obtained by executing a preset target program meets a preset target result condition, generating corresponding monitoring start notification information;
sending the monitoring start notification information to the monitoring terminal equipment, wherein the monitoring terminal equipment is used for monitoring the target monitoring area after receiving the monitoring start notification information to obtain a corresponding to-be-processed monitoring video, and performing video data packaging processing on the to-be-processed monitoring video to obtain a corresponding video data packet;
and acquiring the video data packet acquired and sent by the monitoring terminal equipment based on the monitoring start notification information, and analyzing and processing the video data packet to obtain the to-be-processed monitoring video corresponding to the video data packet.
3. The smart city monitoring method based on data analysis as claimed in claim 1, wherein the step of obtaining the target historical monitoring video corresponding to the monitoring video to be processed and determining the video correlation information between the target historical monitoring video and the monitoring video to be processed includes:
acquiring historical monitoring videos obtained by monitoring the target monitoring area by the monitoring terminal device in a plurality of historical time periods respectively to obtain a plurality of historical monitoring videos;
determining a historical monitoring video which has a corresponding relation with the monitoring video to be processed in the plurality of historical monitoring videos, and using the historical monitoring video as a target historical monitoring video corresponding to the monitoring video to be processed;
and determining the correlation between the target historical monitoring video and the monitoring video to be processed to obtain corresponding video correlation information.
4. The method according to claim 3, wherein the step of determining a historical surveillance video corresponding to the surveillance video to be processed as the target historical surveillance video corresponding to the surveillance video to be processed includes:
performing time analysis processing on the monitored video to be processed to obtain a first time period corresponding to the monitored video to be processed, wherein the first time period is determined based on the time corresponding to a first frame of monitored video to be processed and a last frame of monitored video to be processed in the monitored video to be processed;
for each historical monitoring video in the plurality of historical monitoring videos, calculating a first time interval and a second time interval between the historical period and the first time period corresponding to the historical monitoring video, and determining a first time correlation between the historical monitoring video and the monitoring video to be processed based on the first time interval and the second time interval, wherein the first time interval is used for representing a time interval between the latest moment of the historical period and the earliest moment of the first time period, and the second time interval is used for representing a time interval between the earliest moment of the historical period and the latest moment of the first time period;
for each historical monitoring video in the plurality of historical monitoring videos, calculating the historical time period corresponding to the historical monitoring video and the first time period in a preset time cycle dimension to obtain a second time correlation degree between the historical monitoring video and the monitoring video to be processed;
and for each historical surveillance video in the plurality of historical surveillance videos, fusing the first time correlation degree and the second time correlation degree between the historical surveillance video and the surveillance video to be processed to obtain the time correlation degree between the historical surveillance video and the surveillance video to be processed, and determining a target historical surveillance video corresponding to the surveillance video to be processed in the plurality of historical surveillance videos based on the time correlation degree between each historical surveillance video in the plurality of historical surveillance videos and the surveillance video to be processed.
5. The method as claimed in claim 4, wherein the step of calculating, for each of the plurality of historical surveillance videos, a first time interval and a second time interval between the historical time period and the first time period corresponding to the historical surveillance video, and determining a first time correlation between the historical surveillance video and the surveillance video to be processed based on the first time interval and the second time interval comprises:
for each historical monitoring video in the plurality of historical monitoring videos, calculating a first time interval and a second time interval between the historical time period and the first time period corresponding to the historical monitoring video, and calculating a weighted sum value between the first time interval and the second time interval to obtain a weighted sum value of the time intervals corresponding to the historical monitoring video, wherein the weighting coefficient corresponding to the first time interval is greater than the weighting coefficient corresponding to the second time interval;
for each historical monitoring video in the plurality of historical monitoring videos, obtaining a first time correlation degree between the historical monitoring video and the monitoring video to be processed based on the time interval weighted sum value corresponding to the historical monitoring video, wherein the first time correlation degree and the time interval weighted sum value have a negative correlation relationship.
6. The method as claimed in claim 4, wherein the step of calculating, for each historical surveillance video of the plurality of historical surveillance videos, the historical time period corresponding to the historical surveillance video and the first time period in a preset time cycle dimension to obtain the second time correlation between the historical surveillance video and the surveillance video to be processed includes:
determining time slices to which the first time period belongs within a preset time period, wherein each time period is formed on the basis of a plurality of continuous time slices;
for each historical monitoring video in the plurality of historical monitoring videos, determining a time slice to which the historical time period corresponding to the historical monitoring video belongs within a preset time period;
and calculating the time segment interval between the time segment to which the historical time period belongs and the time segment to which the first time period belongs, which corresponds to each historical monitoring video in the plurality of historical monitoring videos, and calculating a second time correlation degree between the historical monitoring video and the monitoring video to be processed based on the time segment interval, wherein the second time correlation degree has a negative correlation with the time segment interval.
7. The smart city monitoring method based on data analysis as claimed in any one of claims 1 to 6, wherein the step of performing video frame screening processing on the monitored video to be processed based on the video correlation information and the target historical monitored video to obtain the target monitored video corresponding to the monitored video to be processed comprises:
carrying out object identification processing on historical monitoring video frames included in the target historical monitoring video, and determining object flow corresponding to the target historical monitoring video based on the obtained object identification result to obtain historical object flow information corresponding to the target historical monitoring video;
fusing the video correlation relation information and the historical object flow information to obtain a corresponding object flow characteristic value, and determining a ratio between the object flow characteristic value and a preset object flow threshold value to obtain a corresponding target flow ratio;
and determining the maximum screening proportion information for carrying out video frame screening and reselection on the monitored video to be processed based on the target flow ratio, and carrying out video frame de-emphasis screening on the monitored video to be processed based on the maximum screening proportion information to obtain the corresponding target monitored video.
8. The utility model provides a wisdom city monitored control system based on data analysis, its characterized in that is applied to control backend server, control backend server communication connection monitor terminal equipment, wisdom city monitored control system based on data analysis includes:
the monitoring terminal equipment is used for monitoring a target monitoring area, and comprises a monitoring video acquisition unit used for acquiring a to-be-processed monitoring video sent by the monitoring terminal equipment, wherein the to-be-processed monitoring video comprises a plurality of frames of to-be-processed monitoring video frames which are obtained by monitoring the target monitoring area based on the monitoring terminal equipment;
a video correlation determining unit, configured to obtain a target historical surveillance video corresponding to the to-be-processed surveillance video, and determine video correlation information between the target historical surveillance video and the to-be-processed surveillance video, where the target historical surveillance video includes multiple frames of target historical surveillance video frames, and the multiple frames of target historical surveillance video frames are obtained by monitoring a target surveillance area historically based on the surveillance terminal device;
and the video frame screening unit is used for carrying out video frame screening processing on the monitored video to be processed based on the video correlation relation information and the target historical monitored video to obtain the target monitored video corresponding to the monitored video to be processed, wherein the target monitored video comprises at least one frame of the monitored video frame to be processed.
9. The smart city monitoring system according to claim 8, wherein the video correlation determination unit is specifically configured to:
acquiring historical monitoring videos obtained by monitoring the target monitoring area by the monitoring terminal device in a plurality of historical time periods respectively to obtain a plurality of historical monitoring videos;
determining a historical monitoring video which has a corresponding relation with the monitoring video to be processed in the plurality of historical monitoring videos, and using the historical monitoring video as a target historical monitoring video corresponding to the monitoring video to be processed;
and determining the correlation between the target historical monitoring video and the monitoring video to be processed to obtain corresponding video correlation information.
10. The smart city monitoring system according to claim 8, wherein the video frame filtering unit is specifically configured to:
carrying out object identification processing on historical monitoring video frames included in the target historical monitoring video, and determining object flow corresponding to the target historical monitoring video based on the obtained object identification result to obtain historical object flow information corresponding to the target historical monitoring video;
fusing the video correlation relation information and the historical object flow information to obtain a corresponding object flow characteristic value, and determining a ratio between the object flow characteristic value and a preset object flow threshold value to obtain a corresponding target flow ratio;
and determining the maximum screening proportion information for carrying out video frame screening and reselection on the monitored video to be processed based on the target flow ratio, and carrying out video frame de-emphasis screening on the monitored video to be processed based on the maximum screening proportion information to obtain the corresponding target monitored video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111399094.0A CN114155459A (en) | 2021-11-19 | 2021-11-19 | Smart city monitoring method and system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111399094.0A CN114155459A (en) | 2021-11-19 | 2021-11-19 | Smart city monitoring method and system based on data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114155459A true CN114155459A (en) | 2022-03-08 |
Family
ID=80457088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111399094.0A Withdrawn CN114155459A (en) | 2021-11-19 | 2021-11-19 | Smart city monitoring method and system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114155459A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114418460A (en) * | 2022-03-28 | 2022-04-29 | 四川高速公路建设开发集团有限公司 | Construction process information analysis method and construction management system applied to BIM |
| CN114998811A (en) * | 2022-07-28 | 2022-09-02 | 创域智能(常熟)网联科技有限公司 | Big data processing method and system based on intelligent network interconnection |
| CN115205765A (en) * | 2022-09-15 | 2022-10-18 | 成都中轨轨道设备有限公司 | FPGA-based video analysis method and system |
-
2021
- 2021-11-19 CN CN202111399094.0A patent/CN114155459A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114418460A (en) * | 2022-03-28 | 2022-04-29 | 四川高速公路建设开发集团有限公司 | Construction process information analysis method and construction management system applied to BIM |
| CN114998811A (en) * | 2022-07-28 | 2022-09-02 | 创域智能(常熟)网联科技有限公司 | Big data processing method and system based on intelligent network interconnection |
| CN115205765A (en) * | 2022-09-15 | 2022-10-18 | 成都中轨轨道设备有限公司 | FPGA-based video analysis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114155459A (en) | Smart city monitoring method and system based on data analysis | |
| CN114581856B (en) | Agricultural unit motion state identification method and system based on Beidou system and cloud platform | |
| CN114140713A (en) | Image recognition system and image recognition method | |
| CN114697618A (en) | Building control method and system based on mobile terminal | |
| CN114140710A (en) | Monitoring data transmission method and system based on data processing | |
| CN114140712A (en) | Automatic image recognition and distribution system and method | |
| CN113902993A (en) | Environmental state analysis method and system based on environmental monitoring | |
| CN113672782A (en) | Internet of things equipment importance matching method based on data query | |
| CN114173088A (en) | Service adjusting method and system based on smart city monitoring | |
| CN115620243B (en) | Pollution source monitoring method and system based on artificial intelligence and cloud platform | |
| CN115457467A (en) | Building quality hidden danger positioning method and system based on data mining | |
| CN114677615A (en) | Environment detection method and system | |
| CN115375886A (en) | Data acquisition method and system based on cloud computing service | |
| CN114189535A (en) | Service request method and system based on smart city data | |
| CN115019219A (en) | Intelligent construction progress management method and system for intelligent construction site | |
| CN113821402A (en) | Chip use warning method and system based on chip running state | |
| CN113949881A (en) | Service processing method and system based on smart city data | |
| CN114095734A (en) | User data compression method and system based on data processing | |
| CN113238911A (en) | Alarm processing method and device | |
| CN114827538A (en) | Construction progress monitoring method and system for intelligent construction site | |
| CN114156495B (en) | Laminated battery assembly processing method and system based on big data | |
| CN115471767A (en) | Building quality prediction method and system based on data mining | |
| CN114139017A (en) | Safety protection method and system for intelligent cell | |
| CN114817339B (en) | Water quality monitoring method and system for multiple water areas, storage medium and electronic equipment | |
| CN114201676A (en) | User recommendation method and system based on intelligent cell user matching |
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 |
Application publication date: 20220308 |
|
| WW01 | Invention patent application withdrawn after publication |