CN107358160A - Terminal monitoring method for processing video frequency, monitor terminal and server - Google Patents
Terminal monitoring method for processing video frequency, monitor terminal and server Download PDFInfo
- Publication number
- CN107358160A CN107358160A CN201710431337.1A CN201710431337A CN107358160A CN 107358160 A CN107358160 A CN 107358160A CN 201710431337 A CN201710431337 A CN 201710431337A CN 107358160 A CN107358160 A CN 107358160A
- Authority
- CN
- China
- Prior art keywords
- server
- video image
- monitor terminal
- target signature
- destination object
- 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- Withdrawn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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention proposes a kind of terminal monitoring method for processing video frequency, monitor terminal and server, wherein, this method includes:The target signature collection of the reception server distribution;According to target signature collection, characteristic matching is carried out to the video image of acquisition;It is determined that in the video image obtained, when reaching the destination object of threshold value comprising the matching degree with target signature collection, alert messages are sent to server.This method by target signature collection by being distributed to monitor terminal, and then by monitor terminal, the video image of acquisition is analyzed in real time, and analysis result is sent to server, not only reduce the volume of transmitted data between monitoring device and server, and the processing load of server is reduced, improves the treatment effeciency of video image.
Description
Technical field
The present invention relates to technical field of security and protection, more particularly to a kind of terminal monitoring method for processing video frequency, monitor terminal and clothes
Business device.
Background technology
At present, in order to improve property and personal safety, many public domains or private area are all provided with monitoring device, with
The zone of action information of people is monitored in real time by monitoring device.
In actual use, monitoring device is usually by the video image information of collection, passes through fixed network passage
Send server to, dissection process then is carried out to video image using the computing capability of server, to realize according to video figure
Picture, people or thing can be identified and followed the trail of.
But above-mentioned processing mode, not only need monitoring device real time remote to transmit multitude of video image, take a large amount of logical
Believe bandwidth, it is excessive to also result in the processing load of server, causes treatment effeciency to reduce.
The content of the invention
It is contemplated that at least solves one of technical problem in correlation technique to a certain extent.
Therefore, first purpose of the present invention is to propose a kind of terminal monitoring method for processing video frequency, this method pass through by
Target signature collection is distributed to monitor terminal, and then by monitor terminal, the video image of acquisition is analyzed in real time, and will analyze
As a result send to server, not only reduce the volume of transmitted data between monitoring device and server, and reduce server
Processing load, improve the treatment effeciency of video image.
Second object of the present invention is to propose a kind of terminal monitoring method for processing video frequency.
Third object of the present invention is to propose a kind of monitor terminal.
Fourth object of the present invention is to propose a kind of server.
The 5th purpose of the present invention is to propose a kind of monitoring system.
The 6th purpose of the present invention is to propose a kind of storage medium.
The 7th purpose of the present invention is to propose a kind of storage medium.
For the above-mentioned purpose, embodiment proposes a kind of terminal monitoring method for processing video frequency, bag according to a first aspect of the present invention
Include:
The target signature collection of the reception server distribution;
According to the target signature collection, characteristic matching is carried out to the video image of acquisition;
It is determined that in the video image obtained, the target pair of threshold value is reached comprising the matching degree with the target signature collection
As when, to the server send alert messages.
In the terminal monitoring method for processing video frequency that the present embodiment provides, according to the target signature collection of server distribution, to obtaining
The video image that takes carries out characteristic matching, to determine in the video image obtained whether to reach with the matching degree of target signature collection
During the destination object of threshold value, if any then to server transmission alert messages.Thus, by the way that target signature collection is distributed into monitoring eventually
End, and then by monitor terminal, analyzed in real time the video image of acquisition, and analysis result is sent to server, not only
Reduce the volume of transmitted data between monitoring device and server, and reduce the processing load of server, improve video figure
The treatment effeciency of picture.
In addition, the terminal monitoring method for processing video frequency that the above embodiment of the present invention proposes can also have skill additional as follows
Art feature:
In one embodiment of the invention, after the transmission alert messages to the server, in addition to:
The video image is parsed, determines the motion track of the destination object;
The motion track of the destination object is sent to the server.
In one embodiment of the invention, the terminal monitoring method for processing video frequency, in addition to:
It is determined that in the video image obtained, the target for reaching threshold value with the matching degree of the target signature collection is not included
During object, the characteristic that the video image includes is sent to the server.
For the above-mentioned purpose, the second face embodiment of the invention proposes terminal monitoring method for processing video frequency, including:
Target signature collection is sent to each monitor terminal;
The N bar alert messages that N number of monitor terminal returns respectively are received, are included respectively in the N bars alert messages described N number of
Mark and the destination object mark of monitor terminal, wherein, N is the positive integer more than or equal to 1;
Identified according to the mark of N number of monitor terminal and destination object, determine the position of the destination object.
In the terminal monitoring method for processing video frequency that the present embodiment provides, by sending target signature collection to each monitor terminal,
In order to which the video image that each monitor terminal obtains according to target signature set pair is analyzed and processed, N number of monitoring is then received eventually
The N bar alert messages returned respectively, and N number of monitor terminal mark and destination object mark in N bar alert messages are held, really
Set the goal the position of object.Thus, by the way that target signature collection is distributed into monitor terminal, and then by monitor terminal, to acquisition
Video image is analyzed in real time, and analysis result is sent to server, is not only reduced between monitoring device and server
Volume of transmitted data, and the processing load of server is reduced, improve the treatment effeciency of video image.
In addition, the terminal monitoring method for processing video frequency that the above embodiment of the present invention proposes can also have skill additional as follows
Art feature:
In one embodiment of the invention, the terminal monitoring method for processing video frequency, in addition to:
Obtain the characteristic that each monitor terminal is sent respectively;
According to the characteristic, the target signature collection is updated.
For the above-mentioned purpose, the 3rd face embodiment of the invention proposes a kind of monitor terminal, including:
First receiving module, the target signature collection for the reception server distribution;
Matching characteristic module, for according to the target signature collection, characteristic matching to be carried out to the video image of acquisition;
Alarm module is sent, for it is determined that in the video image obtained, including the matching journey with the target signature collection
When degree reaches the destination object of threshold value, alert messages are sent to the server.
In the monitor terminal that the present embodiment provides, according to the target signature collection of server distribution, to the video image of acquisition
Characteristic matching is carried out, to determine in the video image obtained whether to reach with the matching degree of target signature collection the target pair of threshold value
As when, if any then to server send alert messages.Thus, by the way that target signature collection is distributed into monitor terminal, and then by supervising
Control terminal, the video image of acquisition is analyzed in real time, and analysis result is sent to server, not only reduced monitoring and set
The standby volume of transmitted data between server, and the processing load of server is reduced, improve the treatment effeciency of video image.
In addition, the monitor terminal that the above embodiment of the present invention proposes can also have technical characteristic additional as follows:
In one embodiment of the invention, in addition to:
First determining module, for being parsed to the video image, determine the motion track of the destination object;
Track module is sent, for sending the motion track of the destination object to the server.
In one embodiment of the invention, in addition to:
First sending module, for it is determined that in the video image obtained, not including the matching with the target signature collection
When degree reaches the destination object of threshold value, the characteristic that the video image includes is sent to the server.
For the above-mentioned purpose, fourth face embodiment of the present invention proposes a kind of server, including:
Second sending module, for sending target signature collection to each monitor terminal;
Second receiving module, the N bar alert messages returned respectively for receiving N number of monitor terminal, the N bars alert messages
The middle mark comprising N number of monitor terminal respectively and destination object mark, wherein, N is the positive integer more than or equal to 1;
Second determining module, identified for the mark according to N number of monitor terminal and destination object, determine the target
The position of object.
In the server that the present embodiment provides, by sending target signature collection to each monitor terminal, in order to each monitoring eventually
The video image that end obtains according to target signature set pair is analyzed and processed, and then receives the N bars that N number of monitor terminal returns respectively
Alert messages, and N number of monitor terminal mark and destination object mark in N bar alert messages, determine the position of destination object
Put.Thus, by the way that target signature collection is distributed into monitor terminal, and then by monitor terminal, the video image of acquisition is carried out in fact
When analyze, and analysis result is sent to server, not only reduces the volume of transmitted data between monitoring device and server, and
The processing load of server is reduced, improves the treatment effeciency of video image.
In addition, the server that the above embodiment of the present invention proposes can also have technical characteristic additional as follows:
In one embodiment of the invention, in addition to:
Acquisition module, the characteristic sent respectively for obtaining each monitor terminal;
Update module, for according to the characteristic, being updated to the target signature collection.
For the above-mentioned purpose, the 5th face embodiment of the invention proposes a kind of monitoring system, including:Monitoring as described above
Terminal, and server as described above.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein:
Fig. 1 is the flow chart of the terminal monitoring method for processing video frequency of one embodiment of the present of invention;
Fig. 2 is the flow chart of the terminal monitoring method for processing video frequency of an alternative embodiment of the invention;
Fig. 3 is the flow chart of the terminal monitoring method for processing video frequency of yet another embodiment of the present invention;
Fig. 4 is that the server of the specific embodiment of the present invention carries out the schematic diagram of data interaction with monitor terminal;
Fig. 5 is the structural representation of the monitor terminal of one embodiment of the present of invention;
Fig. 6 is the structural representation of the monitor terminal of an alternative embodiment of the invention;
Fig. 7 is the structural representation of the server of one embodiment of the present of invention;
Fig. 8 is the structural representation of the monitoring system of one embodiment of the present of invention.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and is not considered as limiting the invention.
The video image of collection is sent to service by the embodiment of the present invention mainly in the prior art by monitor terminal
, it is necessary to take mass communication bandwidth during device, and server is after substantial amounts of video image is received, when being focused on
Computation burden is excessive, cause Computer Vision efficiency reduce the problem of, propose a kind of terminal monitoring method for processing video frequency.
Terminal monitoring method for processing video frequency proposed by the present invention, the target signature collection distributed according to server, to acquisition
Video image carries out characteristic matching, to determine whether reach threshold value with the matching degree of target signature collection in the video image obtained
Destination object when, if any then to server send alert messages.Thus, by the way that target signature collection is distributed into monitor terminal,
And then by monitor terminal, the video image of acquisition is analyzed in real time, and analysis result is sent to server, not only reduce
Volume of transmitted data between monitoring device and server, and reduce the processing load of server, improve video image
Treatment effeciency.
In order to clearly be illustrated to terminal monitoring method for processing video frequency provided by the invention, first below to the present invention
Monitor terminal in embodiment illustrates.
In the present embodiment, processing module is provided with monitor terminal, such as, Intelligent treatment chip etc., the processing module
It can realize and the video image collected is analyzed in real time, to obtain the specifying information of video image.Therefore, the present invention is each
In embodiment, if monitor terminal collects video image, then can be by the processing module in monitor terminal to the video figure
As being analyzed in real time, the analysis result of video image is obtained, and analysis result is sent to server.
The terminal monitoring method for processing video frequency proposed below in conjunction with the accompanying drawings to the embodiment of the present invention is described in detail.
Fig. 1 is the flow chart of the terminal monitoring method for processing video frequency of one embodiment of the present of invention.
As shown in figure 1, the terminal monitoring method for processing video frequency may include following steps:
S101, the target signature collection of the reception server distribution.
Specifically, the terminal monitoring method for processing video frequency that the present embodiment provides, can apply in monitor terminal, so that respectively
Monitor terminal is handled monitor video.
Wherein, in the present embodiment, monitor terminal can be the arbitrarily electronic equipment with camera function, such as colored rifle
Formula video camera, thermal camera, mobile terminal etc., the present embodiment is not particularly limited to this.
Connected specifically, monitor terminal can be established with server in several ways.For example, pass through wireless network, indigo plant
Tooth, near field communication (NFC) etc., the application is not construed as limiting to this.
During specific implementation, the network channel that can first establish between monitor terminal and server, then server is special by target
After collection is compressed, each monitor terminal is distributed to by the network channel, to cause each monitor terminal according to reception
To target signature collection, analysis operation is carried out to the video image of collection.
Wherein, the target signature collection of server distribution, the color characteristic, textural characteristics, shape of object to be monitored can be included
Shape feature, spatial relation characteristics etc., the present embodiment is not especially limited to this.
For example, if monitored object is behaved, the target signature of server distribution is concentrated, and characteristic information can be color
Feature, such as hair style color, the information such as clothes color.
If monitored object is automobile, the target signature of server distribution is concentrated, and characteristic information can be color characteristic, such as
Red, black, white etc., or, shape facility, such as pony car, large truck.
It should be noted that in the present embodiment, server can be the equipment or server that are separately provided and
The integrated equipment of source of early warning.
S102, according to target signature collection, characteristic matching is carried out to the video image of acquisition.
Specifically, after monitor terminal receives the target signature collection of server distribution, first target signature collection can be carried out
Decompression operations, and analyze the characteristic information that the target signature collection after decompression includes.
It is determined that after the characteristic information of target signature collection, monitor terminal can be handled the video image of acquisition,
To obtain the characteristic information of video image.
During specific implementation, the video image of acquisition can be handled, by following several ways to obtain video image
Characteristic information.It is illustrated below:
A kind of implementation, each frame video image of acquisition is analyzed, to obtain corresponding characteristic information.
Another implementation, with default frame period, the video image of acquisition is analyzed, to obtain predetermined interval
The characteristic information of video image.
Wherein, default frame period scope can be according to being actually needed any setting, such as can be 3 frame periods, 5
Frame period, 7 frame periods etc., naturally it is also possible to be other frame periods, concrete restriction do not made to it herein.
That is, if default interframe is divided into 3 frames, then monitor terminal is just needed every 3 frames, with regard to once being analyzed
Operation, so as to obtain the characteristic information of video image.
And then the characteristic information that the characteristic information of the video image and target signature are concentrated can be subjected to matching operation.
S103, it is determined that in the video image obtained, the target of threshold value is reached comprising the matching degree with target signature collection
During object, alert messages are sent to server.
Specifically, the comparison result of characteristic information can be concentrated with target signature according to the characteristic information of video image, it is determined that
Whether destination object is included in the video image of acquisition.
If the matching degree of the characteristic information of video image and target signature collection reaches threshold value, illustrate video image
In include destination object.
It should be noted that in the present embodiment, determine whether the characteristic information of video image reaches threshold value, it may include a variety of
Situation.It is illustrated below:
A kind of situation, target signature is concentrated and pre-sets key feature information, if characteristic information and mesh in video image
When marking the key feature information matching in feature set, then it can determine that the characteristic information of video image reaches threshold value.
For example, if the key feature information for the setting that target signature is concentrated is license plate number, then when in video image
During in the presence of concentrating license plate number information identical license plate number with target signature, that is, determine to include target vehicle in video image.
Another situation, server pre-set an amount threshold, if the characteristic information and target signature of video image
The quantity that the characteristic information of concentration matches exceedes the amount threshold, then can determine that the characteristic information of video image reaches threshold value.
Wherein, the amount threshold that server is pre-set in the present embodiment, can according to being actually needed any setting, such as
It can be 3,4,5 etc., naturally it is also possible to be other numerical value, concrete restriction do not made to it herein.
It is understood that when in the video image obtained, disappearing, it is necessary to send warning to server during comprising destination object
Breath, to cause server to carry out the operation such as alarm to public security organ according to alert messages.
In addition, after step s 102, the terminal monitoring method for processing video frequency, in addition to:
S104, it is determined that in the video image obtained, the mesh for reaching threshold value with the matching degree of target signature collection is not included
When marking object, the characteristic that includes of video image is sent to server.
Specifically, it is determined that in video image not comprising destination object when, monitor terminal can be by the feature of video image
Information package is sent to server so that server preserves the characteristic information received in memory, in order to subsequently need
Will be in use, the characteristic information directly invoked in memory be trained, the target signature collection needed.
Further, in order to ensure the security of characteristic information, characteristic information can be also encrypted in the present embodiment, then
Characteristic information is sent to server again.
In the terminal monitoring method for processing video frequency that the present embodiment provides, according to the target signature collection of server distribution, to obtaining
The video image that takes carries out characteristic matching, to determine in the video image obtained whether to reach with the matching degree of target signature collection
During the destination object of threshold value, if any then to server transmission alert messages.Thus, by the way that target signature collection is distributed into monitoring eventually
End, and then by monitor terminal, analyzed in real time the video image of acquisition, and analysis result is sent to server, not only
Reduce the volume of transmitted data between monitoring device and server, and reduce the processing load of server, improve video figure
The treatment effeciency of picture.
By above-mentioned analysis, the target signature collection distributed by the reception server, monitor terminal can regard to acquisition
Frequency image carries out feature matching operation, to determine to whether there is destination object in video image.In a kind of possible reality of the present invention
In existing scene, if including destination object in video image, then after monitor terminal sends alert messages to server, in order to
Server is set to be tracked destination object, the monitor terminal can also determine mesh by being parsed to video image
The motion track of object is marked, so that server is tracked according to the motion track to destination object.With reference to Fig. 2, to upper
Terminal monitoring method for processing video frequency in the case of stating is further described.
The flow chart of the terminal monitoring method for processing video frequency of Fig. 2 an alternative embodiment of the invention.
As shown in Fig. 2 the terminal monitoring method for processing video frequency of the embodiment of the present invention, may comprise steps of:
S201, the target signature collection of the reception server distribution.
S202, according to target signature collection, characteristic matching is carried out to the video image of acquisition.
S203, it is determined that in the video image obtained, the target of threshold value is reached comprising the matching degree with target signature collection
During object, alert messages are sent to server.
S204, video image is parsed, determine the motion track of destination object.
It should be noted that the video image of monitor terminal collection is continuous, therefore alert messages are sent to server
Afterwards, the video image of collection can be also further analyzed, to determine the shifting of the target in video image object obtained
Dynamic rail mark, so as to can determine that the real time position of destination object.
During specific implementation, the motion track of destination object by different tracing algorithms, can be determined.It is illustrated below:
Example one, by continuous adaptive track algorithm (Continuously Adaptive Mean-SHIFT), come true
Make the motion track of destination object.
Specifically, obtaining destination object region in current video image first, the color 2D probability in the region is calculated
Distribution, then with mean shift algorithm (Mean-Shift) restrain, monitor terminal obtain target in video image object with
Track region.
Example two, (Tracking-Learning-Detection, it can be referred to as by single goal long-time track algorithm:
TLD), motion track of destination object etc. is determined.
Illustrate, however, it is determined that destination object be pedestrian A, monitor terminal is No. 1, and corresponding monitor area is also No. 1,
So No. 1 monitor terminal can continuously acquire the video image for including the pedestrian A, to determine pedestrian A motion track.Such as No. 1 prison
Control terminal finds pedestrian A, enters No. 1 monitor area from upper left side, then No. 1 monitor terminal is that can determine that, the pedestrian A be from
No. 1 monitor area that No. 3 adjacent monitor areas of upper left side enter;Then the behavior entered to pedestrian A after No. 1 monitor area
Feature is analyzed, to determine motion tracks of the pedestrian A in No. 1 monitor area, when finding pedestrian A from No. 1 monitor area
When right front is left, No. 1 monitor terminal can determine that the pedestrian A is that No. 4 monitor areas adjacent from right front are left.By
This, you can determine that pedestrian A enters No. 1 monitor area from No. 3 monitor areas, then left from No. 4 monitor areas.
S205, the motion track of destination object is sent to server.
Specifically, it is determined that after the motion track of destination object, target pair can be sent to server by network channel
The motion track of elephant, so that motion track of the server according to destination object, realize the purpose of fast positioning.
That is, motion track of the server according to the destination object received, you can that determines destination object can
The positional information that can occur.
For example, if the motion track for the destination object that server receives is, pedestrian A motion track is, from No. 3
Monitor area enters No. 1 monitor area, is then left from No. 4 monitor areas.So server can be expert at according to the motion track
Pedestrian A positional information is determined in No. 3 monitor areas and No. 4 monitor areas that people A is likely to occur.
The terminal monitoring method for processing video frequency that the present embodiment provides, after sending alert messages to server, in order to
Server is tracked destination object, by being parsed to video image, determine the motion track of destination object,
So that server is tracked according to movement rule to destination object.Thus, the number between monitoring device and server is reduced
According to transmission quantity, and the processing load of server is reduced, improve the treatment effeciency of video image.
Fig. 3 is the flow chart of the terminal monitoring method for processing video frequency of yet another embodiment of the present invention.
As shown in figure 3, the terminal monitoring method for processing video frequency, may comprise steps of:
S301, target signature collection is sent to each monitor terminal.
Specifically, the terminal monitoring method for processing video frequency that the present embodiment provides, can apply in server.With to each prison
The monitoring process of control terminal is controlled or managed.
Connected specifically, server can be established with monitor terminal in several ways.For example, pass through wireless network, indigo plant
Tooth, near field communication (NFC) etc., the application is not construed as limiting to this.
During specific implementation, the network channel that can first establish between monitor terminal and server, then server is special by target
After collection is compressed, each monitor terminal is distributed to by the network channel, to cause each monitor terminal according to reception
To target signature collection, analysis operation is carried out to the video image of collection.
Wherein, the target signature collection of server distribution, the color characteristic, textural characteristics, shape of object to be monitored can be included
Shape feature, spatial relation characteristics etc., the present embodiment is not especially limited to this.
For example, if monitored object is behaved, the target signature of server distribution is concentrated, and characteristic information can be color
Feature, such as hair style color, the information such as clothes color.
If monitored object is automobile, the target signature of server distribution is concentrated, and characteristic information can be color characteristic, such as
Red, black, white etc., or, shape facility, such as pony car, large truck.
In the present embodiment, server can be the collection for equipment or server and the source of early warning being separately provided
Forming apparatus.
That is, when if server is the equipment being separately provided, receive monitor terminal transmission alert messages it
Afterwards, it is necessary to which alert messages are relayed into source of early warning, so as to carry out early warning operation by source of early warning.
If server and source of early warning are integrally disposed, then when integrally disposed server and source of early warning receive it is pre-
During alert message, early warning operation directly can be carried out by source of early warning, avoid the step of server is forwarded, further saved
Operating time.
S302, the N bar alert messages that N number of monitor terminal returns respectively are received, N number of prison is included respectively in N bar alert messages
Mark and the destination object mark of control terminal, wherein, N is the positive integer more than or equal to 1.
Wherein, the mark of N number of monitor terminal, can N number of monitor terminal generate at random when being established according to network channel
ID(Identity);Or MAC (Media Access Control, media access control) address of N number of monitor terminal, when
The identification information of other unique marks N number of monitor terminal is so can also be, the present embodiment is not restricted to this.
The mark of destination object, can be the label of destination object;Or the information such as type of destination object.
Specifically, after server has distributed target signature collection to N number of monitor terminal, N number of monitoring in monitoring system
Terminal, the matching analysis operation is carried out according to the target signature collection received automatically, and in the video image for determining to obtain, bag
When containing destination object, alert message is sent to server, so that the N bars that server is sent according to N number of monitor terminal warn
The operation that message is alarmed.
S303, identified according to the mark of N number of monitor terminal and destination object, determine the position of destination object.
Specifically, server identifies according to the mark and destination object of N number of monitor terminal, the video obtained to monitor terminal
Destination object in image is positioned, to determine the positional information of destination object, so as to further be chased after to destination object
Track and arrest action.
Further, after step S303, the terminal monitoring method for processing video frequency is further comprising the steps of:
Obtain the characteristic that each monitor terminal is sent respectively;
According to characteristic, target signature collection is updated.
Specifically, server can receive the characteristic of N bars monitor terminal transmission, and the characteristic received is preserved
Into the memory of server end, so as to which when server needs to use such characteristic information again, itself can be directly invoked
The characteristic preserved in memory, the target signature collection for being then trained to be needed using the data of calling.So as to
Realize the renewal operation to such target signature collection so that the degree of accuracy of detection is higher, more comprehensively.
For example, if the characteristic information that server target signature is concentrated includes face characteristic, height, then in order that
Target signature concentrate characteristic information it is more careful, more comprehensively, server can inquire about in its memory whether be stored with such
Other characteristic informations, such as face characteristic, hair style, can be by the other characteristic informations of such in memory if inquiring presence
It is added to target signature concentration, to realize the renewal to such target signature collection.
In the terminal monitoring method for processing video frequency that the present embodiment provides, by sending target signature collection to each monitor terminal,
In order to which the video image that each monitor terminal gathers according to target signature set pair is analyzed and processed, N number of monitoring is then received eventually
The N bar alert messages returned respectively, and N number of monitor terminal mark and destination object mark in N bar alert messages are held, really
Set the goal the position of object.Thus, reduce the transmission quantity of video image, reduce the computation burden of server, improve
The treatment effeciency of video image.
Below by a specific embodiment, above-described embodiment terminal monitoring method for processing video frequency is specifically described,
Referring specifically to Fig. 4.Fig. 4 is that the server of the specific embodiment of the present invention carries out the signal of data interaction with monitor terminal
Figure.
Assuming that the monitoring system includes a server A, N number of monitor terminal B, then server A and N number of monitor terminal B
Interaction may include following steps:
S401:Server A sends target signature collection 1 to N number of monitor terminal B.
Connected specifically, server A can be established with N number of monitor terminal B in several ways.For example, pass through wireless network
Network, bluetooth, near field communication (NFC) etc., the application is not construed as limiting to this.
S402:N number of monitor terminal B receives target signature collection 1, and the video image of acquisition is entered according to target signature collection 1
Row characteristic matching.
Specifically, N number of monitor terminal B parses to the video image of acquisition first, to determine the spy in video image
Reference ceases, and then is compared characteristic information is obtained with the characteristic information in target signature collection 1.
S403, N number of monitor terminal B determined in the video image that obtains, comprising reaching threshold with the matching degree of target signature collection 1
During the destination object of value, N number of monitor terminal performs step S404, otherwise, performs step S408.
S404, N number of monitor terminal B actively send alert messages to server A.
Specifically, N number of monitor terminal B can be sent alert messages to server A by network channel, to cause server
A carries out alarm operation according to the alert messages to police office.
S405, N number of monitor terminal B is tracked to the motion track of destination object, and determines the movement of destination object
Track.
Specifically, N number of monitor terminal can pass through continuous adaptive track algorithm (Continuously Adaptive
Mean-SHIFT), the motion track of destination object is determined.
Or (Tracking-Learning-Detection, it can be also referred to as by single goal long-time track algorithm:
TLD), the motion track of destination object is determined.
S406, the motion track of destination object is sent to server A
S407, server A receives the alert messages of N number of monitor terminal B transmissions and the motion track of destination object, to target
The position of object is positioned.
S408, the characteristic included to server A transmission video image.
S409, server A are preserved this feature data.
Specifically, server can preserve the characteristic of reception into storage;Or be uploaded in Cloud Server, this
Embodiment is not specifically limited to this.
By in above-described embodiment monitoring system, by being analyzed on monitor terminal the video image of acquisition
Processing so that server need not carry out substantial amounts of calculate and operate, and reduce processing load, and also improve treatment effeciency, full
Foot user's request, improves Consumer's Experience.
The monitor terminal of proposition of the embodiment of the present invention is described with reference to the accompanying drawings.
Fig. 5 is the structural representation of the monitor terminal of one embodiment of the present of invention.
Reference picture 5, the monitor terminal include:First receiving module 11, matching characteristic module 12, send alarm module 13 with
And first sending module 14.
Wherein, monitor terminal is N number of, wherein, N is the positive integer more than or equal to 1,
Wherein, the first receiving module 11 is used for the target signature collection of the reception server distribution;
Matching characteristic module 12 is used for according to target signature collection, and characteristic matching is carried out to the video image of acquisition;
Alarm module 13 is sent to be used to, it is determined that in the video image obtained, reach comprising the matching degree with target signature collection
To threshold value destination object when, to server send alert messages.
First sending module 14 is used to, it is determined that in the video image obtained, not include the matching with the target signature collection
When degree reaches the destination object of threshold value, the characteristic that the video image includes is sent to the server.
It should be noted that the implementation process and technical principle of the monitor terminal of the present embodiment referring to foregoing to terminal monitoring
The explanation of method for processing video frequency embodiment, here is omitted.
In the monitor terminal that the present embodiment provides, according to the target signature collection of server distribution, to the video image of acquisition
Characteristic matching is carried out, to determine in the video image obtained whether to reach with the matching degree of target signature collection the target pair of threshold value
As when, if any then to server send alert messages.Thus, by the way that target signature collection is distributed into monitor terminal, and then by supervising
Control terminal, the video image of acquisition is analyzed in real time, and analysis result is sent to server, not only reduced monitoring and set
The standby volume of transmitted data between server, and the processing load of server is reduced, improve the treatment effeciency of video image.
Fig. 6 is the structural representation of the monitor terminal of an alternative embodiment of the invention.
As shown in fig. 6, the monitor terminal shown in Fig. 6 also includes:First determining module 15 and transmission track module 16.
Wherein, the first determining module 15 is used to parse the video image, determines the movement of the destination object
Track;
Send the motion track that track module 16 is used to send the destination object to the server.
It should be noted that the implementation process and technical principle of the monitor terminal of the present embodiment referring to foregoing to terminal monitoring
The explanation of method for processing video frequency embodiment, here is omitted.
In the monitor terminal that the present embodiment provides, after sending alert messages to server, in order that server can
To be tracked to destination object, by being parsed to video image, the motion track of destination object is determined, so that server
According to movement rule, destination object is tracked.Thus, the volume of transmitted data between monitoring device and server is reduced,
And the processing load of server is reduced, improves the treatment effeciency of video image.
In order to realize above-described embodiment, the invention also provides a kind of server.
Fig. 7 is the structural representation of the server of one embodiment of the invention.
As shown in fig. 7, the server shown in Fig. 7, including:Second sending module 21, the second receiving module 22 and second
Determining module 23.
Wherein, the second sending module 21 is used to send target signature collection to each monitor terminal;
Second receiving module 22 is used to receive the N bar alert messages that N number of monitor terminal returns respectively, and the N bars warning disappears
The mark comprising N number of monitor terminal and destination object identify respectively in breath, wherein, N is the positive integer more than or equal to 1;
Second determining module 23 is used to be identified according to the mark and destination object of N number of monitor terminal, determines the mesh
Mark the position of object.
In addition, the server also includes:Acquisition module and update module.
Wherein, acquisition module is used to obtain the characteristic that each monitor terminal is sent respectively;
Update module is used for according to the characteristic, and the target signature collection is updated.
It should be noted that the implementation process and technical principle of the server of the present embodiment regard referring to foregoing to terminal monitoring
The explanation of frequency processing method embodiment, here is omitted.
In the server that the present embodiment provides, by sending target signature collection to each monitor terminal, in order to each monitoring eventually
The video image that end gathers according to target signature set pair is analyzed and processed, and then receives the N bars that N number of monitor terminal returns respectively
Alert messages, and N number of monitor terminal mark and destination object mark in N bar alert messages, determine the position of destination object
Put.Thus, reduce the transmission quantity of video image, reduce the computation burden of server, improve the processing of video image
Efficiency.
In order to realize above-described embodiment, the invention also provides a kind of monitoring system.
Fig. 8 is the structural representation of the monitoring system of one embodiment of the invention.
As shown in figure 8, the monitoring system 100, including N number of monitor terminal 10 and server 20.
It should be noted that the foregoing explanation to terminal monitoring method for processing video frequency embodiment is also applied for the implementation
The monitoring system of example, its realization principle is similar, and here is omitted.
In the monitoring system that the present embodiment provides, by being carried out on monitor terminal to the video image of acquisition at analysis
Reason so that server need not carry out substantial amounts of calculate and operate, and reduce processing load, and also improve treatment effeciency, meet
User's request, improves Consumer's Experience.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can be expressed or
Implicitly include at least one this feature.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized:With the logic gates for realizing logic function to data-signal
Discrete logic, have suitable combinational logic gate circuit application specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that by program the hardware of correlation can be instructed to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although have been shown and retouch above
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (13)
- A kind of 1. terminal monitoring method for processing video frequency, applied to monitor terminal, it is characterised in that including:The target signature collection of the reception server distribution;According to the target signature collection, characteristic matching is carried out to the video image of acquisition;It is determined that in the video image obtained, the destination object of threshold value is reached comprising the matching degree with the target signature collection When, send alert messages to the server.
- 2. the method as described in claim 1, it is characterised in that after the transmission alert messages to the server, also wrap Include:The video image is parsed, determines the motion track of the destination object;The motion track of the destination object is sent to the server.
- 3. method as claimed in claim 1 or 2, it is characterised in that also include:It is determined that in the video image obtained, the destination object for reaching threshold value with the matching degree of the target signature collection is not included When, send the characteristic that the video image includes to the server.
- A kind of 4. terminal monitoring method for processing video frequency, applied to server, it is characterised in that including:Target signature collection is sent to each monitor terminal;The N bar alert messages that N number of monitor terminal returns respectively are received, N number of monitoring is included respectively in the N bars alert messages Mark and the destination object mark of terminal, wherein, N is the positive integer more than or equal to 1;Identified according to the mark of N number of monitor terminal and destination object, determine the position of the destination object.
- 5. method as claimed in claim 4, it is characterised in that also include:Obtain the characteristic that each monitor terminal is sent respectively;According to the characteristic, the target signature collection is updated.
- A kind of 6. monitor terminal, it is characterised in that including:First receiving module, the target signature collection for the reception server distribution;Matching characteristic module, for according to the target signature collection, characteristic matching to be carried out to the video image of acquisition;Alarm module is sent, for it is determined that in the video image obtained, being reached comprising the matching degree with the target signature collection To threshold value destination object when, to the server send alert messages.
- 7. terminal as claimed in claim 6, it is characterised in that also include:First determining module, for being parsed to the video image, determine the motion track of the destination object;Track module is sent, for sending the motion track of the destination object to the server.
- 8. terminal as claimed in claims 6 or 7, it is characterised in that also include:First sending module, for it is determined that in the video image obtained, not including the matching degree with the target signature collection When reaching the destination object of threshold value, the characteristic that the video image includes is sent to the server.
- A kind of 9. server, it is characterised in that including:Second sending module, for sending target signature collection to each monitor terminal;Second receiving module, the N bar alert messages returned respectively for receiving N number of monitor terminal, in the N bars alert messages point The mark and destination object mark of N number of monitor terminal are not included, wherein, N is the positive integer more than or equal to 1;Second determining module, identified for the mark according to N number of monitor terminal and destination object, determine the destination object Position.
- 10. server as claimed in claim 9, it is characterised in that also include:Acquisition module, the characteristic sent respectively for obtaining each monitor terminal;Update module, for according to the characteristic, being updated to the target signature collection.
- A kind of 11. monitoring system, it is characterised in that including:Monitor terminal as described in claim 6-8 is any, and as weighed Profit requires any described servers of 9-10.
- 12. a kind of storage medium, it is characterised in that real when the application program is executed by processor for storing application program The now terminal monitoring method for processing video frequency as any one of claim 1-3.
- 13. a kind of storage medium, it is characterised in that real when the application program is executed by processor for storing application program The now terminal monitoring method for processing video frequency as described in claim 4-5 is any.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710431337.1A CN107358160A (en) | 2017-06-08 | 2017-06-08 | Terminal monitoring method for processing video frequency, monitor terminal and server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710431337.1A CN107358160A (en) | 2017-06-08 | 2017-06-08 | Terminal monitoring method for processing video frequency, monitor terminal and server |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107358160A true CN107358160A (en) | 2017-11-17 |
Family
ID=60272618
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710431337.1A Withdrawn CN107358160A (en) | 2017-06-08 | 2017-06-08 | Terminal monitoring method for processing video frequency, monitor terminal and server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107358160A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108009530A (en) * | 2017-12-27 | 2018-05-08 | 欧普照明股份有限公司 | A kind of identity calibration system and method |
CN109413373A (en) * | 2018-02-07 | 2019-03-01 | 中科太网科技(北京)有限公司 | Video monitoring equipment control method, device, video monitoring equipment and server |
CN109413374A (en) * | 2018-02-07 | 2019-03-01 | 中科太网科技(北京)有限公司 | Monitor video processing method, device, video processing equipment and processing system for video |
CN109729318A (en) * | 2019-01-07 | 2019-05-07 | 深圳英飞拓科技股份有限公司 | Video data playback process method, apparatus, computer equipment and storage medium |
WO2019128883A1 (en) * | 2017-12-27 | 2019-07-04 | 苏州欧普照明有限公司 | Identity labeling and determining system and method |
CN110121172A (en) * | 2019-05-15 | 2019-08-13 | 上海良相智能化工程有限公司 | A kind of remote power feeding system applied to Android phone |
CN110503028A (en) * | 2019-08-21 | 2019-11-26 | 腾讯科技(深圳)有限公司 | Determine the sensor of the distribution of object, system, method and medium in region |
CN111212264A (en) * | 2019-12-27 | 2020-05-29 | 中移(杭州)信息技术有限公司 | Image processing method and device based on edge calculation and storage medium |
WO2020151084A1 (en) * | 2019-01-24 | 2020-07-30 | 北京明略软件***有限公司 | Target object monitoring method, apparatus, and system |
CN113923330A (en) * | 2021-10-11 | 2022-01-11 | 中国人民解放军63921部队 | Multi-target measurement system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020067258A1 (en) * | 2000-12-06 | 2002-06-06 | Philips Electronics North America Corporation | Method and apparatus to select the best video frame to transmit to a remote station for cctv based residential security monitoring |
CN101404107A (en) * | 2008-11-19 | 2009-04-08 | 公安部第三研究所 | Internet bar monitoring and warning system based on human face recognition technology |
CN101877780A (en) * | 2009-04-28 | 2010-11-03 | 北京中星微电子有限公司 | Real-time intelligent video monitoring system |
CN104284163A (en) * | 2014-10-29 | 2015-01-14 | 广州中国科学院软件应用技术研究所 | Device and system for video analysis |
-
2017
- 2017-06-08 CN CN201710431337.1A patent/CN107358160A/en not_active Withdrawn
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020067258A1 (en) * | 2000-12-06 | 2002-06-06 | Philips Electronics North America Corporation | Method and apparatus to select the best video frame to transmit to a remote station for cctv based residential security monitoring |
CN101404107A (en) * | 2008-11-19 | 2009-04-08 | 公安部第三研究所 | Internet bar monitoring and warning system based on human face recognition technology |
CN101877780A (en) * | 2009-04-28 | 2010-11-03 | 北京中星微电子有限公司 | Real-time intelligent video monitoring system |
CN104284163A (en) * | 2014-10-29 | 2015-01-14 | 广州中国科学院软件应用技术研究所 | Device and system for video analysis |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11113509B2 (en) | 2017-12-27 | 2021-09-07 | Opple Lighting Co., Ltd. | Identity determination system and method |
CN108009530A (en) * | 2017-12-27 | 2018-05-08 | 欧普照明股份有限公司 | A kind of identity calibration system and method |
WO2019128883A1 (en) * | 2017-12-27 | 2019-07-04 | 苏州欧普照明有限公司 | Identity labeling and determining system and method |
CN108009530B (en) * | 2017-12-27 | 2024-02-20 | 欧普照明股份有限公司 | Identity calibration system and method |
CN109413373A (en) * | 2018-02-07 | 2019-03-01 | 中科太网科技(北京)有限公司 | Video monitoring equipment control method, device, video monitoring equipment and server |
CN109413374A (en) * | 2018-02-07 | 2019-03-01 | 中科太网科技(北京)有限公司 | Monitor video processing method, device, video processing equipment and processing system for video |
CN109729318A (en) * | 2019-01-07 | 2019-05-07 | 深圳英飞拓科技股份有限公司 | Video data playback process method, apparatus, computer equipment and storage medium |
WO2020151084A1 (en) * | 2019-01-24 | 2020-07-30 | 北京明略软件***有限公司 | Target object monitoring method, apparatus, and system |
CN110121172A (en) * | 2019-05-15 | 2019-08-13 | 上海良相智能化工程有限公司 | A kind of remote power feeding system applied to Android phone |
CN110503028A (en) * | 2019-08-21 | 2019-11-26 | 腾讯科技(深圳)有限公司 | Determine the sensor of the distribution of object, system, method and medium in region |
CN110503028B (en) * | 2019-08-21 | 2023-12-15 | 腾讯科技(深圳)有限公司 | Sensor, system, method and medium for determining distribution of objects in an area |
CN111212264A (en) * | 2019-12-27 | 2020-05-29 | 中移(杭州)信息技术有限公司 | Image processing method and device based on edge calculation and storage medium |
CN113923330A (en) * | 2021-10-11 | 2022-01-11 | 中国人民解放军63921部队 | Multi-target measurement system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107358160A (en) | Terminal monitoring method for processing video frequency, monitor terminal and server | |
US11575750B2 (en) | Communication methods and devices in intelligent transport systems | |
Vinel et al. | An overtaking assistance system based on joint beaconing and real-time video transmission | |
US10691949B2 (en) | Action recognition in a video sequence | |
US20180308344A1 (en) | Vehicle-to-infrastructure (v2i) accident management | |
CN102932635A (en) | Real-time image processing system and method | |
US20180046863A1 (en) | Methods and systems of maintaining lost object trackers in video analytics | |
WO2018105319A1 (en) | Information processing device and information processing method | |
US20180046857A1 (en) | Methods and systems of updating motion models for object trackers in video analytics | |
CN116094621A (en) | Method for adjusting a preprocessing device in vehicle-to-X communication, vehicle-to-X communication system, and computer-readable storage medium | |
CN111565303B (en) | Video monitoring method, system and readable storage medium based on fog calculation and deep learning | |
JP7036579B2 (en) | A method for detecting an event and a device for detecting an event. | |
Karaadi et al. | Multimedia communications in internet of things QoT or QoE? | |
CN102469305B (en) | Dispensing device and sending method | |
CN117201501B (en) | Intelligent engineering sharing management system and operation method | |
CN110881141B (en) | Video display method and device, storage medium and electronic device | |
KR102326793B1 (en) | System for analyzing accident images and method for using the same | |
US20240102817A1 (en) | Road accident detection and avoidance using blockchain | |
CN107181929A (en) | Method and apparatus for video monitoring | |
KR20220156373A (en) | Realtime traffic information provision system for autonomous driving based on c-its mec | |
CN115100572A (en) | System and method for analyzing abnormal behaviors of campus | |
Onsu et al. | Anomalous Behaviour Detection via Event-Based Metric with Sequential Tracking in a V2X Environment | |
Seymer et al. | Smart Parking Zones using Dual Mode Routed Bluetooth Fogged Meshes. | |
CN106162059A (en) | A kind of video monitoring alarm method and system | |
US20190387201A1 (en) | Systems and methods for using artificial intelligence monitoring in legacy surveillance systems |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20190903 Address after: 100192 Dongsheng Science Park, Zhongguancun, 66 Xixiaokou Road, Haidian District, Beijing Applicant after: Green Bay Network Technology Co., Ltd. Address before: 100089 Beijing Haidian District Xixiaokou Road 66 Zhongguancun Dongsheng Science Park B-6 Building B 5 floors Applicant before: Grass count language (Beijing) Technology Co., Ltd. |
|
TA01 | Transfer of patent application right | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171117 |
|
WW01 | Invention patent application withdrawn after publication |