CN114140741A - Monitoring data processing method based on data processing - Google Patents

Abstract

The invention provides a monitoring data processing method based on data processing, and relates to the technical field of data processing. In the invention, a to-be-processed monitoring video sent by each monitoring terminal device is obtained, wherein the monitoring terminal device is used for acquiring and processing image information of a monitoring environment; determining equipment correlation relation information among a plurality of monitoring terminal equipment, and determining video correlation relation information among a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal equipment based on the equipment correlation relation information among the plurality of monitoring terminal equipment; determining a duplicate removal screening mode for carrying out duplicate removal screening processing on a plurality of monitored videos to be processed based on video correlation relation information among the plurality of monitored videos to be processed, and carrying out duplicate removal screening processing on the plurality of monitored videos to be processed based on the duplicate removal screening mode. Based on the method, the problem that the effect of duplicate removal screening on the monitoring video is poor in the prior art can be solved.

Description

Monitoring data processing method based on data processing

Technical Field

The invention relates to the technical field of data processing, in particular to a monitoring data processing method based on data processing.

Background

With the continuous development of computer technology and internet technology, the application of monitoring technology is also widely applied. In the monitoring technology, at least a monitoring terminal device for image acquisition and a server for data processing are generally included. For example, after acquiring a monitoring video, the monitoring terminal device may send the monitoring video to a server for processing, where in order to improve processing efficiency and avoid resource waste and other problems, in the prior art, the monitoring video is generally screened. However, the inventor researches and finds that in the prior art, generally, duplicate removal screening is directly performed on a surveillance video, for example, whether two surveillance videos are the same or not is directly compared, so that a problem that the duplicate removal screening effect on the surveillance videos is not good may exist.

Disclosure of Invention

In view of the above, an object of the present invention is to provide a monitoring data processing method based on data processing, so as to solve the problem in the prior art that the effect of performing duplicate removal and screening on a monitoring video is not good.

In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:

a monitoring data processing method based on data processing is applied to a monitoring data processing server, the monitoring data processing server is in communication connection with a plurality of monitoring terminal devices, and the monitoring data processing method based on data processing comprises the following steps:

acquiring a to-be-processed monitoring video sent by each monitoring terminal device in the plurality of monitoring terminal devices, wherein each monitoring terminal device is used for acquiring and processing image information of a monitoring environment to obtain a corresponding to-be-processed monitoring video;

determining device correlation relationship information among the plurality of monitoring terminal devices, and determining video correlation relationship information among a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation relationship information among the plurality of monitoring terminal devices;

determining a duplicate removal screening mode for performing duplicate removal screening processing on the plurality of monitored videos to be processed based on video correlation relation information among the plurality of monitored videos to be processed, and performing duplicate removal screening processing on the plurality of monitored videos to be processed based on the duplicate removal screening mode.

In some preferred embodiments, in the above monitoring data processing method based on data processing, the step of obtaining the to-be-processed monitoring video sent by each of the plurality of monitoring terminal devices includes:

when it is determined that image information acquisition processing needs to be performed on a monitored environment, generating corresponding image acquisition notification information, and sending the image acquisition notification information to each monitoring terminal device, wherein each monitoring terminal device is used for performing image information acquisition processing on the monitored environment after receiving the image acquisition notification information to obtain a corresponding monitored video to be processed;

and respectively acquiring the to-be-processed monitoring videos acquired and sent by each monitoring terminal device based on the image acquisition notification information to obtain a plurality of corresponding to-be-processed monitoring videos.

In some preferred embodiments, in the above monitoring data processing method based on data processing, the step of generating corresponding image acquisition notification information and sending the image acquisition notification information to each of the monitoring terminal devices when it is determined that image information acquisition processing needs to be performed on a monitoring environment includes:

when it is determined that image information acquisition processing needs to be performed on a monitored environment, acquiring data transmission time length information between the monitoring data processing server and each monitoring terminal device, and determining data transmission time length information with a maximum value from the acquired data transmission time length information;

determining target data transmission duration information which is greater than or equal to the data transmission duration information based on the data transmission duration information with the maximum value, and generating corresponding image acquisition notification information based on the target data transmission duration information;

and sending the image acquisition notification information to each monitoring terminal device, wherein after receiving the image acquisition notification information, the monitoring terminal device starts to acquire image information of the monitoring environment based on the target data transmission duration information carried in the image acquisition notification information and the time information determined by the sending time of the image acquisition notification information, so as to obtain the corresponding to-be-processed monitoring video.

In some preferred embodiments, in the above monitoring data processing method based on data processing, the step of generating corresponding image acquisition notification information and sending the image acquisition notification information to each of the monitoring terminal devices when it is determined that image information acquisition processing needs to be performed on a monitoring environment includes:

when it is determined that image information acquisition processing needs to be performed on a monitored environment, acquiring data transmission time length information between the monitoring data processing server and each monitoring terminal device, and determining data transmission time length information with a maximum value from the acquired data transmission time length information;

determining target data transmission time length information which is larger than or equal to the data transmission time length information based on the data transmission time length information with the maximum value, and determining image acquisition time information based on the target data transmission time length information and target sending time information;

and generating corresponding image acquisition notification information based on the image acquisition time information, and sending the image acquisition notification information to each monitoring terminal device based on the target sending time information, wherein each monitoring terminal device is used for starting image information acquisition processing on the monitoring environment based on the image acquisition time information carried in the image acquisition notification information after receiving the image acquisition notification information, so as to obtain the corresponding to-be-processed monitoring video.

In some preferred embodiments, in the above monitoring data processing method based on data processing, the step of determining device correlation relationship information between the plurality of monitoring terminal devices, and determining video correlation relationship information between a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation relationship information between the plurality of monitoring terminal devices includes:

acquiring the device characteristic information of each monitoring terminal device in the plurality of monitoring terminal devices, and determining the device correlation relation information among the plurality of monitoring terminal devices based on the device characteristic information of each monitoring terminal device;

and determining video correlation relation information among a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation relation information among the plurality of monitoring terminal devices.

In some preferred embodiments, in the above monitoring data processing method based on data processing, the step of obtaining device characteristic information of each of the plurality of monitoring terminal devices, and determining device correlation relationship information between the plurality of monitoring terminal devices based on the device characteristic information of each monitoring terminal device includes:

for each monitoring terminal device in the plurality of monitoring terminal devices, acquiring a device position of the monitoring terminal device, acquiring device position information of the monitoring terminal device, acquiring a region position of a monitoring environment where the monitoring terminal device is located, acquiring region position information of the monitoring terminal device, acquiring an environment background of the monitoring environment where the monitoring terminal device is located, and acquiring an environment background image of the monitoring terminal device;

for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating to obtain device position distance information between the two monitoring terminal devices based on the device position information of the two monitoring terminal devices, and determining first device correlation degree information between the two monitoring terminal devices based on the device position distance information;

for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating to obtain region position distance information between the two monitoring terminal devices based on the region position information of the two monitoring terminal devices, and determining second device correlation degree information between the two monitoring terminal devices based on the region position distance information;

for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating to obtain environment background similarity information between the two monitoring terminal devices based on the environment background images of the two monitoring terminal devices, and determining third device correlation degree information between the two monitoring terminal devices based on the environment background similarity information;

and for every two monitoring terminal devices in the plurality of monitoring terminal devices, performing fusion processing on the first device correlation degree information, the second device correlation degree information and the third device correlation degree information between the two monitoring terminal devices to obtain device correlation relation information between the two monitoring terminal devices.

In some preferred embodiments, in the above monitoring data processing method based on data processing, the step of performing fusion processing on the first device correlation degree information, the second device correlation degree information, and the third device correlation degree information between two monitoring terminal devices to obtain device correlation relationship information between the two monitoring terminal devices, for each two monitoring terminal devices in the multiple monitoring terminal devices, includes:

determining a first weight coefficient, a second weight coefficient and a third weight coefficient corresponding to the first device correlation degree information, the second device correlation degree information and the third device correlation degree information respectively, wherein the first weight coefficient, the second weight coefficient and the third weight coefficient are 1 later, the first weight coefficient is smaller than the second weight coefficient, and the second weight coefficient is smaller than the third weight coefficient;

and for every two monitoring terminal devices in the plurality of monitoring terminal devices, performing weighted summation calculation on the first device correlation degree information, the second device correlation degree information and the third device correlation degree information based on the first weight coefficient, the second weight coefficient and the third weight coefficient to obtain device correlation relation information between the two monitoring terminal devices.

In some preferred embodiments, in the above monitoring data processing method based on data processing, the step of determining video correlation relationship information between a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation relationship information between the plurality of monitoring terminal devices includes:

for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating a video data amount difference value between the to-be-processed monitoring videos of the two monitoring terminal devices, and determining a correlation adjustment coefficient between the two monitoring terminal devices based on the video data amount difference value, wherein the correlation adjustment coefficient and the video data amount difference value have a negative correlation, and all the correlation adjustment coefficients are less than or equal to 1 and greater than 0;

and aiming at every two monitoring terminal devices in the plurality of monitoring terminal devices, adjusting the device correlation information between the two monitoring terminal devices based on the correlation adjustment coefficient between the two monitoring terminal devices to obtain the video correlation information between the two to-be-processed monitoring videos corresponding to the two monitoring terminal devices.

In some preferred embodiments, in the above monitoring data processing method based on data processing, the determining, based on the video correlation relationship information among the multiple monitored videos to be processed, a duplicate removal screening manner for performing duplicate removal screening processing on the multiple monitored videos to be processed, and performing duplicate removal screening processing on the multiple monitored videos to be processed based on the duplicate removal screening manner includes:

clustering the plurality of monitored videos to be processed based on video correlation information among the plurality of monitored videos to be processed to obtain at least one corresponding monitored video cluster, and determining whether the number of the monitored videos to be processed included in each monitored video cluster is larger than a preset number, wherein each monitored video cluster includes at least one monitored video to be processed;

determining each monitoring video cluster with the number of the to-be-processed monitoring videos larger than the preset number as a target monitoring video cluster, and performing duplicate removal screening processing on every two to-be-processed monitoring videos in the target monitoring video cluster aiming at each target monitoring video cluster when at least one target monitoring video cluster exists.

In some preferred embodiments, in the above monitoring data processing method based on data processing, the step of determining each monitoring video cluster, in which the number of the to-be-processed monitoring videos included in the to-be-processed monitoring video cluster is greater than the preset number, as a target monitoring video cluster, and when at least one target monitoring video cluster exists, performing deduplication screening processing on every two to-be-processed monitoring videos in the target monitoring video cluster for each target monitoring video cluster includes:

determining each monitoring video cluster with the number of the monitoring videos to be processed larger than the preset number as a target monitoring video cluster;

when at least one target surveillance video cluster exists, determining every two to-be-processed surveillance videos included in the target surveillance video cluster as corresponding first to-be-processed surveillance videos and second to-be-processed surveillance videos respectively for each target surveillance video cluster, performing target screening operation on the first to-be-processed surveillance videos and the second to-be-processed surveillance videos based on similarity between included environment surveillance video frames, respectively obtaining corresponding first to-be-processed surveillance video segments and corresponding second to-be-processed surveillance video segments, and performing duplicate removal screening processing on the first to-be-processed surveillance video segments and the second to-be-processed surveillance video segments.

In the monitoring data processing method based on data processing provided by the embodiment of the invention, after the to-be-processed monitoring video sent by each monitoring terminal device is obtained, the device correlation relationship information among a plurality of monitoring terminal devices can be determined, the video correlation relationship information among a plurality of corresponding to-be-processed monitoring videos is determined based on the device correlation relationship information among the plurality of monitoring terminal devices, so that the duplicate removal screening mode for carrying out duplicate removal screening processing can be determined based on the video correlation relationship information among the plurality of to-be-processed monitoring videos, and the duplicate removal screening processing is carried out on the plurality of to-be-processed monitoring videos based on the duplicate removal screening mode, so that the determined duplicate removal screening mode has better correlation degree with the obtained plurality of to-be-processed monitoring videos, and the reliability of the duplicate removal screening processing based on the determined duplicate removal screening mode is higher, the method and the device have the advantages that the screening result is better, and the problem that the duplicate removal screening effect of the monitoring video is poor 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 monitoring data processing server according to an embodiment of the present invention.

Fig. 2 is a schematic flowchart of steps included in a monitoring data processing method based on data processing according to an embodiment of the present invention.

Fig. 3 is a block diagram of modules included in a data processing-based monitoring data processing system 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 data processing server. Wherein the monitoring data processing 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 monitoring data processing method based on data processing provided by the embodiment of the present invention.

It is understood that in some preferred embodiments, 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.

It is to be understood that, in some preferred embodiments, the Processor may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), a System on Chip (SoC), etc.; 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 monitoring data processing method based on data processing, which is applicable to the monitoring data processing server. The method steps defined by the relevant flow of the monitoring data processing method based on data processing can be realized by the monitoring data processing server, and the monitoring data processing server is in communication connection with a plurality of monitoring terminal devices.

The specific process shown in FIG. 2 will be described in detail below.

Step S110, obtaining the to-be-processed monitoring video sent by each monitoring terminal device in the plurality of monitoring terminal devices.

In the embodiment of the present invention, the monitoring data processing server may obtain the to-be-processed monitoring video sent by each of the plurality of monitoring terminal devices, so that a plurality of to-be-processed monitoring videos may be obtained. Each monitoring terminal device is used for acquiring and processing image information of the monitoring environment to obtain a corresponding to-be-processed monitoring video.

Step S130, determining device correlation information among the plurality of monitoring terminal devices, and determining video correlation information among a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation information among the plurality of monitoring terminal devices.

In this embodiment of the present invention, the monitoring data processing server may first determine device correlation information between the plurality of monitoring terminal devices, and then determine video correlation information between a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation information between the plurality of monitoring terminal devices.

Step S150, determining a duplicate removal screening mode for carrying out duplicate removal screening processing on the plurality of monitored videos to be processed based on video correlation relation information among the plurality of monitored videos to be processed, and carrying out duplicate removal screening processing on the plurality of monitored videos to be processed based on the duplicate removal screening mode.

In the embodiment of the present invention, the monitoring data processing server may first determine, based on the video correlation relationship information between the multiple monitored videos to be processed, a duplicate removal screening manner for performing duplicate removal screening on the multiple monitored videos to be processed, and then perform duplicate removal screening on the multiple monitored videos to be processed based on the duplicate removal screening manner.

Based on the method, after the to-be-processed monitoring video sent by each monitoring terminal device is obtained, the device correlation relationship information among the multiple monitoring terminal devices can be determined, the video correlation relationship information among the corresponding multiple to-be-processed monitoring videos is determined based on the device correlation relationship information among the multiple monitoring terminal devices, so that the duplicate removal screening mode for performing duplicate removal screening processing can be determined based on the video correlation relationship information among the multiple to-be-processed monitoring videos, and the multiple to-be-processed monitoring videos are subjected to duplicate removal screening processing based on the duplicate removal screening mode, so that the determined duplicate removal screening mode and the obtained multiple to-be-processed monitoring videos have better association degrees, the reliability of the duplicate removal screening processing based on the determined duplicate removal screening mode is higher, and the screening result is better, therefore, the problem that the effect of duplicate removal screening on the monitoring video is poor in the prior art is solved.

It is understood that, in some preferred embodiments, the step S110 in the above embodiments may include the following steps to obtain the to-be-processed monitoring video sent by each monitoring terminal device:

firstly, when determining that image information acquisition processing needs to be carried out on a monitored environment, generating corresponding image acquisition notification information, and sending the image acquisition notification information to each monitoring terminal device, wherein each monitoring terminal device is used for carrying out image information acquisition processing on the monitored environment after receiving the image acquisition notification information to obtain a corresponding monitored video to be processed;

secondly, acquiring the to-be-processed monitoring videos acquired and sent by each monitoring terminal device based on the image acquisition notification information respectively to obtain a plurality of corresponding to-be-processed monitoring videos.

It can be understood that, in some preferred embodiments, the step of generating corresponding image acquisition notification information and sending the image acquisition notification information to each monitoring terminal device when it is determined that image information acquisition processing needs to be performed on the monitoring environment may include the following steps:

firstly, when determining that image information acquisition processing needs to be performed on a monitored environment, acquiring data transmission duration information (such as an average value of calculated historical transmission durations and the like) between the monitoring data processing server and each monitoring terminal device, and determining data transmission duration information with a maximum value from the obtained plurality of data transmission duration information;

secondly, determining target data transmission duration information which is greater than or equal to the data transmission duration information based on the data transmission duration information with the maximum value, and generating corresponding image acquisition notification information based on the target data transmission duration information;

and then sending the image acquisition notification information to each monitoring terminal device, wherein after receiving the image acquisition notification information, the monitoring terminal device starts to acquire image information of the monitoring environment based on the target data transmission duration information carried in the image acquisition notification information and the time information determined by the sending time of the image acquisition notification information, so as to obtain the corresponding to-be-processed monitoring video.

It can be understood that, in other preferred embodiments, the step of generating corresponding image acquisition notification information and sending the image acquisition notification information to each monitoring terminal device when it is determined that image information acquisition processing needs to be performed on the monitoring environment includes the following steps:

firstly, when determining that image information acquisition processing needs to be performed on a monitored environment, acquiring data transmission duration information (such as an average value of calculated historical transmission durations and the like) between the monitoring data processing server and each monitoring terminal device, and determining data transmission duration information with a maximum value from the obtained plurality of data transmission duration information;

secondly, determining target data transmission duration information which is greater than or equal to the data transmission duration information based on the data transmission duration information with the maximum value, and determining image acquisition time information based on the target data transmission duration information and target sending time information (for example, the image acquisition time information is the target sending time information plus the target data transmission duration information);

then, generating corresponding image acquisition notification information based on the image acquisition time information, and sending the image acquisition notification information to each monitoring terminal device based on the target sending time information, wherein each monitoring terminal device is configured to, after receiving the image acquisition notification information, start image information acquisition processing on a monitoring environment where the monitoring terminal device is located based on the image acquisition time information (i.e., the time when the image information acquisition processing is started) carried in the image acquisition notification information, so as to obtain a corresponding to-be-processed monitoring video.

It can be understood that, in some preferred embodiments, the step S130 in the above embodiments may include the following steps to determine video correlation relationship information between a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices:

firstly, acquiring the device characteristic information of each monitoring terminal device in the plurality of monitoring terminal devices, and determining the device correlation relation information among the plurality of monitoring terminal devices based on the device characteristic information of each monitoring terminal device;

secondly, based on the device correlation information among the plurality of monitoring terminal devices, determining video correlation information (such as video correlation degree between every two monitoring terminal devices) among a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices.

It is to be understood that, in some preferred embodiments, the step of obtaining the device feature information of each of the plurality of monitoring terminal devices and determining the device correlation relationship information between the plurality of monitoring terminal devices based on the device feature information of each monitoring terminal device may include the following steps:

firstly, aiming at each monitoring terminal device in the plurality of monitoring terminal devices, acquiring the device position of the monitoring terminal device, acquiring the device position information of the monitoring terminal device, acquiring the regional position of the monitoring environment where the monitoring terminal device is located, acquiring the regional position information of the monitoring terminal device, acquiring the environment background of the monitoring environment where the monitoring terminal device is located, and acquiring the environment background image of the monitoring terminal device;

secondly, calculating to obtain the device position distance information between the two monitoring terminal devices based on the device position information of the two monitoring terminal devices aiming at each two monitoring terminal devices in the plurality of monitoring terminal devices, and determining the first device correlation degree information between the two monitoring terminal devices based on the device position distance information;

then, for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating to obtain region position distance information between the two monitoring terminal devices based on the region position information of the two monitoring terminal devices, and determining second device correlation degree information between the two monitoring terminal devices based on the region position distance information;

then, for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating to obtain environment background similarity information between the two monitoring terminal devices based on the environment background images of the two monitoring terminal devices, and determining third device correlation degree information between the two monitoring terminal devices based on the environment background similarity information;

and finally, aiming at every two monitoring terminal devices in the plurality of monitoring terminal devices, carrying out fusion processing on the first device correlation degree information, the second device correlation degree information and the third device correlation degree information between the two monitoring terminal devices to obtain device correlation relation information between the two monitoring terminal devices.

It can be understood that, in some preferred embodiments, the step of, for each two monitoring terminal devices in the multiple monitoring terminal devices, performing fusion processing on the first device correlation degree information, the second device correlation degree information, and the third device correlation degree information between the two monitoring terminal devices to obtain device correlation relationship information between the two monitoring terminal devices may include the following steps:

firstly, determining a first weight coefficient, a second weight coefficient and a third weight coefficient which respectively correspond to the first device correlation degree information, the second device correlation degree information and the third device correlation degree information, wherein the first weight coefficient, the second weight coefficient and the third weight coefficient are 1 later, the first weight coefficient is smaller than the second weight coefficient, and the second weight coefficient is smaller than the third weight coefficient;

secondly, for every two monitoring terminal devices in the plurality of monitoring terminal devices, performing weighted summation calculation on the first device correlation degree information, the second device correlation degree information and the third device correlation degree information based on the first weight coefficient, the second weight coefficient and the third weight coefficient to obtain device correlation relation information between the two monitoring terminal devices.

It can be understood that, in some preferred embodiments, the step of determining video correlation relationship information between a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation relationship information between the plurality of monitoring terminal devices may include the following steps:

firstly, for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating a video data amount difference value between the to-be-processed monitoring videos of the two monitoring terminal devices, and determining a correlation adjustment coefficient between the two monitoring terminal devices based on the video data amount difference value, wherein the correlation adjustment coefficient and the video data amount difference value have a negative correlation, and all the correlation adjustment coefficients are less than or equal to 1 and greater than 0;

secondly, for each two monitoring terminal devices in the plurality of monitoring terminal devices, based on the correlation adjustment coefficient between the two monitoring terminal devices, the device correlation information between the two monitoring terminal devices is adjusted (for example, the correlation adjustment coefficient is multiplied by the device correlation information), so as to obtain the video correlation information between the two to-be-processed monitoring videos corresponding to the two monitoring terminal devices.

It is understood that, in some preferred embodiments, the step S150 in the above embodiments may include the following steps to perform the deduplication screening process on the plurality of to-be-processed surveillance videos based on the determined deduplication screening manner:

firstly, based on video correlation information among the multiple monitored videos to be processed, clustering the multiple monitored videos to be processed (for example, clustering by using a KNN algorithm, namely, a nearest neighbor algorithm) to obtain at least one corresponding monitored video cluster, and determining whether the number of the monitored videos to be processed included in each monitored video cluster is greater than a preset number, wherein each monitored video cluster includes at least one monitored video to be processed;

secondly, determining each monitoring video cluster with the number of the to-be-processed monitoring videos larger than the preset number (such as 1) as a target monitoring video cluster, and performing duplicate removal screening processing on every two to-be-processed monitoring videos in the target monitoring video cluster aiming at each target monitoring video cluster when at least one target monitoring video cluster exists.

It is to be understood that, in some preferred embodiments, the step of determining each monitored video cluster, in which the number of the monitored videos to be processed is greater than the preset number, as a target monitored video cluster, and performing, for each target monitored video cluster, a deduplication screening process on every two monitored videos to be processed in the target monitored video cluster when at least one target monitored video cluster exists may include the following steps:

firstly, determining each monitoring video cluster with the number of the monitoring videos to be processed larger than the preset number as a target monitoring video cluster;

secondly, when at least one target monitoring video cluster exists, aiming at each target monitoring video cluster, determining every two to-be-processed monitoring videos included in the target monitoring video cluster as a corresponding first to-be-processed monitoring video and a corresponding second to-be-processed monitoring video respectively, and performing target screening operation on the first to-be-processed monitoring video and the second to-be-processed monitoring video based on the similarity between the included environmental monitoring video frames to respectively obtain a corresponding first to-be-processed monitoring video segment and a corresponding second to-be-processed monitoring video segment, and performing duplicate screening processing on the first to-be-processed surveillance video segment and the second to-be-processed surveillance video segment (for example, screening one frame of two identical frames of environmental surveillance video frames, and configuring a corresponding index for the screened frame to be an environmental surveillance video frame of the other frame).

It will be appreciated that in some preferred embodiments, the target screening operation may comprise:

firstly, calculating the mean value of the similarity between each environmental monitoring video frame and each other environmental monitoring video frame in the first to-be-processed monitoring video, obtaining the mean value of the similarity corresponding to the environmental monitoring video frame, and determining a first environmental monitoring video frame and a second environmental monitoring video frame belonging to adjacent video frames in the first to-be-processed monitoring video based on the mean value of the similarity, wherein the first environmental monitoring video frame has the largest mean value of the similarity in the first to-be-processed monitoring video, and the frame timing of the second environmental monitoring video frame is located before the first environmental monitoring video frame (namely, a previous frame);

secondly, calculating the mean value of the similarity between each environmental monitoring video frame and each other environmental monitoring video frame in the second to-be-processed monitoring video, obtaining the mean value of the similarity corresponding to the environmental monitoring video frame, and determining a third environmental monitoring video frame and a fourth environmental monitoring video frame belonging to adjacent video frames in the second to-be-processed monitoring video based on the mean value of the similarity, wherein the third environmental monitoring video frame has the largest mean value of the similarity in the second to-be-processed monitoring video, and the frame timing sequence of the fourth environmental monitoring video frame is positioned before (i.e. the previous frame) the third environmental monitoring video frame;

then, in the first to-be-processed surveillance video, determining a first associated frame timing position (associated frame timing position related to the frame timing position of the first environmental surveillance video frame) of the frame timing position of the first environmental surveillance video frame, and in the second to-be-processed surveillance video, determining a second associated frame timing position (associated frame timing position related to the frame timing position of the third environmental surveillance video frame) of the frame timing position of the third environmental surveillance video frame, wherein a predetermined target feature exists between the first associated frame timing position and the second associated frame timing position;

and finally, obtaining a first to-be-processed monitoring video clip corresponding to the first to-be-processed monitoring video based on each frame of environment monitoring video frame between the first environment monitoring video frame and the environment monitoring video frame corresponding to the first correlation frame time sequence position, and obtaining a second to-be-processed monitoring video clip corresponding to the second to-be-processed monitoring video based on each frame of environment monitoring video frame between the third environment monitoring video frame and the environment monitoring video frame corresponding to the second correlation frame time sequence position.

It will be appreciated that in some preferred embodiments, the target features may include:

(one) the length difference between the frame timing position interval length between the first associated frame timing position and the frame timing position of the first environmental surveillance video frame and the frame timing position interval length between the second associated frame timing position and the frame timing position of the third environmental surveillance video frame is less than or equal to a preconfigured length threshold;

(II) the similarity between the environment monitoring video frame corresponding to the first associated frame time sequence position and the first environment monitoring video frame is greater than or equal to a preset similarity threshold, and the similarity between the environment monitoring video frame corresponding to the second associated frame time sequence position and the third environment monitoring video frame is greater than or equal to the similarity threshold;

and (iii) the similarity between the environmental surveillance video frame (i.e. the previous environmental surveillance video frame) corresponding to the previous adjacent frame time sequence position and the second environmental surveillance video frame is greater than or equal to the similarity threshold, and the similarity between the environmental surveillance video frame (i.e. the previous environmental surveillance video frame) corresponding to the previous adjacent frame time sequence position and the fourth environmental surveillance video frame corresponding to the second associated frame time sequence position is greater than or equal to the similarity threshold.

With reference to fig. 3, an embodiment of the present invention further provides a monitoring data processing system based on data processing, which is applicable to the monitoring data processing server. The monitoring data processing system based on data processing can comprise the following modules:

the monitoring terminal equipment comprises a monitoring video acquisition module, a processing module and a processing module, wherein the monitoring video acquisition module is used for acquiring a to-be-processed monitoring video sent by each monitoring terminal equipment in the plurality of monitoring terminal equipment, and each monitoring terminal equipment is used for acquiring and processing image information of a monitoring environment to obtain a corresponding to-be-processed monitoring video;

the video relation determining module is used for determining equipment correlation relation information among the plurality of monitoring terminal equipment and determining video correlation relation information among a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal equipment based on the equipment correlation relation information among the plurality of monitoring terminal equipment;

and the duplication elimination screening processing module is used for determining duplication elimination screening modes for carrying out duplication elimination screening processing on the plurality of to-be-processed monitoring videos based on the video correlation relation information among the plurality of to-be-processed monitoring videos and carrying out duplication elimination screening processing on the plurality of to-be-processed monitoring videos based on the duplication elimination screening modes.

In summary, the monitoring data processing method based on data processing provided by the present invention, after acquiring the to-be-processed monitoring video sent by each monitoring terminal device, may first determine device correlation relationship information between a plurality of monitoring terminal devices, and determine video correlation relationship information between a plurality of corresponding to-be-processed monitoring videos based on the device correlation relationship information between the plurality of monitoring terminal devices, so that a deduplication screening method for performing deduplication screening processing may be determined based on the video correlation relationship information between the plurality of to-be-processed monitoring videos, and a deduplication screening method may be performed on the plurality of to-be-processed monitoring videos based on the deduplication screening method, so that the determined deduplication screening method has a better degree of association with the acquired plurality of to-be-processed monitoring videos, so that the deduplication screening processing performed based on the determined deduplication screening method has higher reliability, the method and the device have the advantages that the screening result is better, and the problem that the duplicate removal screening effect of the monitoring video is poor 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. A monitoring data processing method based on data processing is characterized in that the method is applied to a monitoring data processing server, the monitoring data processing server is in communication connection with a plurality of monitoring terminal devices, and the monitoring data processing method based on data processing comprises the following steps:

acquiring a to-be-processed monitoring video sent by each monitoring terminal device in the plurality of monitoring terminal devices, wherein each monitoring terminal device is used for acquiring and processing image information of a monitoring environment to obtain a corresponding to-be-processed monitoring video;

determining device correlation relationship information among the plurality of monitoring terminal devices, and determining video correlation relationship information among a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation relationship information among the plurality of monitoring terminal devices;

determining a duplicate removal screening mode for performing duplicate removal screening processing on the plurality of monitored videos to be processed based on video correlation relation information among the plurality of monitored videos to be processed, and performing duplicate removal screening processing on the plurality of monitored videos to be processed based on the duplicate removal screening mode.

2. The monitoring data processing method based on data processing according to claim 1, wherein the step of obtaining the to-be-processed monitoring video sent by each of the plurality of monitoring terminal devices comprises:

when it is determined that image information acquisition processing needs to be performed on a monitored environment, generating corresponding image acquisition notification information, and sending the image acquisition notification information to each monitoring terminal device, wherein each monitoring terminal device is used for performing image information acquisition processing on the monitored environment after receiving the image acquisition notification information to obtain a corresponding monitored video to be processed;

and respectively acquiring the to-be-processed monitoring videos acquired and sent by each monitoring terminal device based on the image acquisition notification information to obtain a plurality of corresponding to-be-processed monitoring videos.

3. The monitoring data processing method based on data processing according to claim 2, wherein the step of generating corresponding image acquisition notification information and sending the image acquisition notification information to each of the monitoring terminal devices when it is determined that image information acquisition processing needs to be performed on the monitoring environment, includes:

when it is determined that image information acquisition processing needs to be performed on a monitored environment, acquiring data transmission time length information between the monitoring data processing server and each monitoring terminal device, and determining data transmission time length information with a maximum value from the acquired data transmission time length information;

determining target data transmission duration information which is greater than or equal to the data transmission duration information based on the data transmission duration information with the maximum value, and generating corresponding image acquisition notification information based on the target data transmission duration information;

and sending the image acquisition notification information to each monitoring terminal device, wherein after receiving the image acquisition notification information, the monitoring terminal device starts to acquire image information of the monitoring environment based on the target data transmission duration information carried in the image acquisition notification information and the time information determined by the sending time of the image acquisition notification information, so as to obtain the corresponding to-be-processed monitoring video.

4. The monitoring data processing method based on data processing according to claim 2, wherein the step of generating corresponding image acquisition notification information and sending the image acquisition notification information to each of the monitoring terminal devices when it is determined that image information acquisition processing needs to be performed on the monitoring environment, includes:

when it is determined that image information acquisition processing needs to be performed on a monitored environment, acquiring data transmission time length information between the monitoring data processing server and each monitoring terminal device, and determining data transmission time length information with a maximum value from the acquired data transmission time length information;

determining target data transmission time length information which is larger than or equal to the data transmission time length information based on the data transmission time length information with the maximum value, and determining image acquisition time information based on the target data transmission time length information and target sending time information;

and generating corresponding image acquisition notification information based on the image acquisition time information, and sending the image acquisition notification information to each monitoring terminal device based on the target sending time information, wherein each monitoring terminal device is used for starting image information acquisition processing on the monitoring environment based on the image acquisition time information carried in the image acquisition notification information after receiving the image acquisition notification information, so as to obtain the corresponding to-be-processed monitoring video.

5. The monitoring data processing method based on data processing according to claim 1, wherein the step of determining the device correlation relationship information among the plurality of monitoring terminal devices, and determining the video correlation relationship information among the plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation relationship information among the plurality of monitoring terminal devices, includes:

acquiring the device characteristic information of each monitoring terminal device in the plurality of monitoring terminal devices, and determining the device correlation relation information among the plurality of monitoring terminal devices based on the device characteristic information of each monitoring terminal device;

and determining video correlation relation information among a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation relation information among the plurality of monitoring terminal devices.

6. The monitoring data processing method based on data processing according to claim 5, wherein the step of obtaining the device characteristic information of each of the plurality of monitoring terminal devices and determining the device correlation relationship information between the plurality of monitoring terminal devices based on the device characteristic information of each monitoring terminal device includes:

for each monitoring terminal device in the plurality of monitoring terminal devices, acquiring a device position of the monitoring terminal device, acquiring device position information of the monitoring terminal device, acquiring a region position of a monitoring environment where the monitoring terminal device is located, acquiring region position information of the monitoring terminal device, acquiring an environment background of the monitoring environment where the monitoring terminal device is located, and acquiring an environment background image of the monitoring terminal device;

for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating to obtain device position distance information between the two monitoring terminal devices based on the device position information of the two monitoring terminal devices, and determining first device correlation degree information between the two monitoring terminal devices based on the device position distance information;

for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating to obtain region position distance information between the two monitoring terminal devices based on the region position information of the two monitoring terminal devices, and determining second device correlation degree information between the two monitoring terminal devices based on the region position distance information;

for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating to obtain environment background similarity information between the two monitoring terminal devices based on the environment background images of the two monitoring terminal devices, and determining third device correlation degree information between the two monitoring terminal devices based on the environment background similarity information;

and for every two monitoring terminal devices in the plurality of monitoring terminal devices, performing fusion processing on the first device correlation degree information, the second device correlation degree information and the third device correlation degree information between the two monitoring terminal devices to obtain device correlation relation information between the two monitoring terminal devices.

7. The monitoring data processing method based on data processing according to claim 6, wherein the step of performing fusion processing on the first device correlation degree information, the second device correlation degree information, and the third device correlation degree information between two monitoring terminal devices to obtain device correlation relationship information between the two monitoring terminal devices, for each two monitoring terminal devices in the plurality of monitoring terminal devices, includes:

determining a first weight coefficient, a second weight coefficient and a third weight coefficient corresponding to the first device correlation degree information, the second device correlation degree information and the third device correlation degree information respectively, wherein the first weight coefficient, the second weight coefficient and the third weight coefficient are 1 later, the first weight coefficient is smaller than the second weight coefficient, and the second weight coefficient is smaller than the third weight coefficient;

and for every two monitoring terminal devices in the plurality of monitoring terminal devices, performing weighted summation calculation on the first device correlation degree information, the second device correlation degree information and the third device correlation degree information based on the first weight coefficient, the second weight coefficient and the third weight coefficient to obtain device correlation relation information between the two monitoring terminal devices.

8. The monitoring data processing method based on data processing according to claim 5, wherein the step of determining video correlation relationship information between a plurality of to-be-processed monitoring videos corresponding to the plurality of monitoring terminal devices based on the device correlation relationship information between the plurality of monitoring terminal devices comprises:

for each two monitoring terminal devices in the plurality of monitoring terminal devices, calculating a video data amount difference value between the to-be-processed monitoring videos of the two monitoring terminal devices, and determining a correlation adjustment coefficient between the two monitoring terminal devices based on the video data amount difference value, wherein the correlation adjustment coefficient and the video data amount difference value have a negative correlation, and all the correlation adjustment coefficients are less than or equal to 1 and greater than 0;

and aiming at every two monitoring terminal devices in the plurality of monitoring terminal devices, adjusting the device correlation information between the two monitoring terminal devices based on the correlation adjustment coefficient between the two monitoring terminal devices to obtain the video correlation information between the two to-be-processed monitoring videos corresponding to the two monitoring terminal devices.

9. The monitoring data processing method based on data processing according to any one of claims 1 to 8, wherein the step of determining a duplicate removal screening manner for performing duplicate removal screening processing on the plurality of monitored videos to be processed based on the video correlation relationship information among the plurality of monitored videos to be processed, and performing duplicate removal screening processing on the plurality of monitored videos to be processed based on the duplicate removal screening manner includes:

clustering the plurality of monitored videos to be processed based on video correlation information among the plurality of monitored videos to be processed to obtain at least one corresponding monitored video cluster, and determining whether the number of the monitored videos to be processed included in each monitored video cluster is larger than a preset number, wherein each monitored video cluster includes at least one monitored video to be processed;

determining each monitoring video cluster with the number of the to-be-processed monitoring videos larger than the preset number as a target monitoring video cluster, and performing duplicate removal screening processing on every two to-be-processed monitoring videos in the target monitoring video cluster aiming at each target monitoring video cluster when at least one target monitoring video cluster exists.

10. The method for processing monitored data based on data processing according to claim 9, wherein said step of determining each monitored video cluster that includes a number of monitored videos to be processed that is greater than the preset number as a target monitored video cluster, and performing, for each target monitored video cluster, a de-duplication screening process on every two monitored videos to be processed in the target monitored video cluster when at least one target monitored video cluster exists comprises:

determining each monitoring video cluster with the number of the monitoring videos to be processed larger than the preset number as a target monitoring video cluster;

when at least one target surveillance video cluster exists, determining every two to-be-processed surveillance videos included in the target surveillance video cluster as corresponding first to-be-processed surveillance videos and second to-be-processed surveillance videos respectively for each target surveillance video cluster, performing target screening operation on the first to-be-processed surveillance videos and the second to-be-processed surveillance videos based on similarity between included environment surveillance video frames, respectively obtaining corresponding first to-be-processed surveillance video segments and corresponding second to-be-processed surveillance video segments, and performing duplicate removal screening processing on the first to-be-processed surveillance video segments and the second to-be-processed surveillance video segments.

Images