CN106982359A - A kind of binocular video monitoring method, system and computer-readable recording medium - Google Patents
A kind of binocular video monitoring method, system and computer-readable recording medium Download PDFInfo
- Publication number
- CN106982359A CN106982359A CN201710286635.6A CN201710286635A CN106982359A CN 106982359 A CN106982359 A CN 106982359A CN 201710286635 A CN201710286635 A CN 201710286635A CN 106982359 A CN106982359 A CN 106982359A
- Authority
- CN
- China
- Prior art keywords
- convolutional neural
- neural networks
- video image
- terminal device
- tensorflow
- 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.)
- Granted
Links
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- 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
Abstract
The invention belongs to field of intelligent monitoring there is provided a kind of binocular video monitoring method, system and computer-readable recording medium, to improve the degree of accuracy and the efficiency in video monitoring to target identification.Methods described includes：Binocular camera gathers video image and is sent to terminal device；Terminal device carries out the first convolutional neural networks in video image input terminal equipment the preliminary identification of target；If the result tentatively recognized is has suspicious object in video image, video image is uploaded to Cloud Server by terminal device；The second convolutional neural networks that Cloud Server inputs video image on Cloud Server carry out again identifying that for target；If the result again identified that is determines there is suspicious object in video image, the result that Cloud Server would again identify that is back to terminal device, is handled by terminal device is further.On the one hand the technical scheme that the present invention is provided improves the efficiency recognized during video monitoring；On the other hand the accuracy rate recognized during video monitoring is improved.
Description
Technical field
The invention belongs to field of intelligent monitoring, more particularly to a kind of binocular video monitoring method, system and computer-readable
Storage medium.
Background technology
Video monitoring system is generally used for safety-security area, can effectively realize the early warning to illegal invasion, protects the people
The security of the lives and property, be also the important supplementary means kept the peace.In the image recognition of video monitoring system, the back of the body of image
Scape is complicated, ambient light and device pixel limitation cause large effect to imaging effect, in addition, video monitoring system needs
Quickly and accurately it is identified in the case where identification target is blocked, objectively causes the difficulty of algorithm design to increase.
Undoubtedly, the key of video monitoring is the extraction to clarification of objective to be identified, because target to be identified
It is characterized in the important mark that a target to be identified is different from another target to be identified.In current video monitoring, to mesh
Target recognizes that its algorithm often relies on the feature of artificial selection.
However, the data that video monitoring system is related to are often magnanimity, therefore, aforesaid way is difficult to from mass data
Study obtains an effective grader, so as to improve the degree of accuracy to target identification and efficiency.
The content of the invention
It is an object of the invention to provide a kind of binocular video monitoring method, system and computer-readable recording medium, with
Improve the degree of accuracy in video monitoring to target identification and efficiency.
First aspect present invention provides a kind of binocular video monitoring method, and methods described includes：
Binocular camera gathers video image and is sent to terminal device；
The first convolutional neural networks that the terminal device inputs the video image on the terminal device carry out mesh
Target is tentatively recognized；
If the result tentatively recognized is has suspicious object in the video image, the terminal device will be described
Video image is uploaded to Cloud Server；
The second convolutional neural networks that the Cloud Server inputs the video image on the Cloud Server carry out mesh
Target is again identified that；
If the result again identified that is determines to exist in the video image suspicious object, the Cloud Server will
The result again identified that is back to the terminal device, is handled by the terminal device is further.
Second aspect of the present invention provides a kind of binocular video monitoring system, and the system includes binocular camera, terminal and set
Standby and Cloud Server, the terminal device includes preliminary identification module and uploading module, and the Cloud Server includes again identifying that
Module and result return to module；
The binocular camera, for gathering video image and being sent to terminal device；
The preliminary identification module, for the first convolution nerve net for inputting the video image on the terminal device
Network carries out the preliminary identification of target；
The uploading module, if for the preliminary identification module preliminary identification result be the video image in deposit
In suspicious object, then the video image is uploaded to Cloud Server；
It is described to again identify that module, for the second convolution nerve net for inputting the video image on the Cloud Server
Network carries out again identifying that for target；
The result returns to module, if being the determination video for the result again identified that for again identifying that module
There is suspicious object in image, then the result again identified that is back to the terminal device, done by the terminal device
Further processing.
Third aspect present invention provides a kind of binocular video monitoring system, including memory, processor and is stored in institute
The computer program that can be run in memory and on the processor is stated, it is real during computer program described in the computing device
Existing following steps：
Binocular camera gathers video image and is sent to terminal device；
The first convolutional neural networks that the terminal device inputs the video image on the terminal device carry out mesh
Target is tentatively recognized；
If the result tentatively recognized is has suspicious object in the video image, the terminal device will be described
Video image is uploaded to Cloud Server；
The second convolutional neural networks that the Cloud Server inputs the video image on the Cloud Server carry out mesh
Target is again identified that；
If the result again identified that is determines to exist in the video image suspicious object, the Cloud Server will
The result again identified that is back to the terminal device, is handled by the terminal device is further.
Fourth aspect present invention provides a kind of computer-readable recording medium, and the computer-readable recording medium storage has
Computer program, the computer program realizes following steps when being executed by processor：
Binocular camera gathers video image and is sent to terminal device；
The first convolutional neural networks that the terminal device inputs the video image on the terminal device carry out mesh
Target is tentatively recognized；
If the result tentatively recognized is has suspicious object in the video image, the terminal device will be described
Video image is uploaded to Cloud Server；
The second convolutional neural networks that the Cloud Server inputs the video image on the Cloud Server carry out mesh
Target is again identified that；
If the result again identified that is determines to exist in the video image suspicious object, the Cloud Server will
The result again identified that is back to the terminal device, is handled by the terminal device is further.
It was found from the invention described above technical scheme, on the one hand, due to the first convolutional neural networks and the second convolution nerve net
Network can be obtained by training in advance, therefore, can quickly be carried automatically when target being identified using the neutral net trained
Clarification of objective is taken, the efficiency recognized during video monitoring is improved；On the other hand, by recognizing just determination suspicious object twice,
Therefore the accuracy rate recognized during video monitoring is improved.
Brief description of the drawings
Fig. 1 is the implementation process schematic diagram for the intelligent video multi-point monitoring method that the embodiment of the present invention one is provided；
Fig. 2 is the structural representation for the intelligent video multipoint monitoring system that the embodiment of the present invention two is provided；
Fig. 3 is the structural representation for the intelligent video multipoint monitoring system that the embodiment of the present invention three is provided；
Fig. 4 is the structural representation for the intelligent video multipoint monitoring system that the embodiment of the present invention four is provided.
Embodiment
In order that the purpose of the present invention, technical scheme and beneficial effect are more clearly understood, below in conjunction with accompanying drawing and implementation
Example, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only to explain this hair
It is bright, it is not intended to limit the present invention.
The embodiment of the present invention provides a kind of binocular video monitoring method, and methods described includes：Binocular camera gathers video
Image is simultaneously sent to terminal device；The first convolution god that the terminal device inputs the video image on the terminal device
The preliminary identification of target is carried out through network；If is there is suspicious object in the video image in the result tentatively recognized,
The video image is uploaded to Cloud Server by the terminal device；The video image is inputted the cloud by the Cloud Server
The second convolutional neural networks on server carry out again identifying that for target；If the result again identified that is regarded described in determining
There is suspicious object in frequency image, then the result again identified that is back to the terminal device by the Cloud Server, by
The terminal device is further to be handled.The embodiment of the present invention also provides corresponding binocular video monitoring system and computer can
Read storage medium.It is described in detail individually below.
Accompanying drawing 1 is referred to, is the implementation process schematic diagram for the binocular video monitoring method that the embodiment of the present invention one is provided, it is main
Comprise the following steps S101 to step S105, describe in detail as follows：
S101, binocular camera collection video image is simultaneously sent to terminal device.
In embodiments of the present invention, binocular camera is used using the headend equipment of video monitoring, imitate the mankind two
Eyes, gather video image and are sent to terminal device.
The first convolutional neural networks in video image input terminal equipment are carried out the preliminary of target by S102, terminal device
Identification.
In embodiments of the present invention, terminal device can be a microcomputer, for example, raspberry sends 3B type microcomputers,
The first convolutional neural networks are deployed with thereon.As one embodiment of the present of invention, the first convolutional neural networks can be based on
TensorFlow small-sized convolutional neural networks, wherein, TensorFlow is a Machine learning tools, and its great advantage is not
User is needed to grasp advanced mathematical model and optimized algorithm needed for deployment depth neutral net, so as to greatly drag down engineering
The threshold of habit.Then it is artificial neural network as convolutional neural networks (CNN, Convolutional Neural Networks)
One kind, it has also become current speech analyze and field of image recognition study hotspot, its weights share network structure be allowed to more
Similar to biological neural network, the complexity of network model is reduced, the quantity of weights is reduced.Based on the small of TensorFlow
Type convolutional neural networks, refer to the less convolutional neural networks of a kind of scale obtained using TensorFlow.
S103, if the result tentatively recognized is has suspicious object in video image, terminal device is by video image
Reach Cloud Server.
S104, the second convolutional neural networks that Cloud Server inputs video image on Cloud Server carry out target again
Identification.
In embodiments of the present invention, the second convolutional neural networks can be the large-scale convolutional Neural net based on TensorFlow
Network, TensorFlow and convolutional neural networks concept therein in previous embodiment with referring to based on the small-sized of TensorFlow
The TensorFlow of convolutional neural networks is identical with convolutional neural networks concept, except that, based on the big of TensorFlow
Type convolutional neural networks will be far longer than the small-sized convolutional neural networks based on TensorFlow in scale or level.
It should be noted that in embodiments of the present invention, video image can be gathered in binocular camera and end is sent to
Before end equipment, according to the convolutional neural networks model based on TensorFlow, the small-sized convolution based on TensorFlow is obtained
Neutral net and the large-scale convolutional neural networks based on TensorFlow.Specifically, according to the convolution god based on TensorFlow
Through network model, the small-sized convolutional neural networks based on TensorFlow and the large-scale convolutional Neural based on TensorFlow are obtained
Network can be realized with S1 as follows and S2：
S1, builds the convolutional neural networks model based on TensorFlow.
The convolutional neural networks model based on TensorFlow includes the first convolutional layer, the first maximum pond layer, first
Local acknowledgement's normalization layer, the second convolutional layer, the second local acknowledgement normalization layer, the first full connection linearly activated based on amendment
Layer, the second full articulamentum and softmax_linear linearly activated based on amendment, wherein, first convolutional layer, which is used to realize, to be rolled up
Product and rectified linear activation, can specifically use a filter (i.e. convolution kernel) to filter video
Each zonule of image, so as to obtain the characteristic value of these zonules, during hands-on, the value of convolution kernel is to learn
Acquired during habit；First maximum pond layer (max pooling) is a kind of down-sampled operation, and the operation is in each spy
In fixed zonule, maximum can be chosen as output valve；First local acknowledgement normalization layer is used to realize that local acknowledgement is returned
One changes；Second convolutional layer is also to be used to realize convolution and rectified linear activation；Second local acknowledgement's normalizing
It is also to be used to realize that local acknowledgement normalizes to change layer；Second maximum pond layer (max pooling) is a kind of down-sampled operation, should
Operation is in each specific zonule, can to choose maximum as output valve；Above layers are based on eventually through first
Correct the full articulamentum linearly activated and the second full articulamentum linearly activated based on amendment be connected to softmax_linear,
Softmax_linear is substantially a softmax grader, for carrying out linear transformation to export logits.
In embodiments of the present invention, the convolutional neural networks model based on TensorFlow can carry out the convolution of N-dimensional classification
The method that neutral net is used is multinomial logistic regression, and softmax recurrence is called again, and Softmax is returned in the defeated of network
Go out on layer addition of a softmax nonlinearity, and calculate normalized predicted value and label 1-hot
Encoding cross entropy, during regularization, we can be based on to all Variable Learning application weight attenuation losses
The object function of TensorFlow convolutional neural networks model be ask intersection entropy loss and all weight attenuation terms and.
S2, using the TensorFlow cluster servers of cloud computing to the convolutional neural networks model based on TensorFlow
It is trained, to obtain the small-sized convolutional neural networks based on TensorFlow and the large-scale convolutional Neural based on TensorFlow
Network.
After convolutional neural networks model buildings based on TensorFlow are good, it is possible to use the TensorFlow collection of cloud computing
Group's server is trained to the convolutional neural networks model based on TensorFlow, to obtain based on the small-sized of TensorFlow
Convolutional neural networks and the large-scale convolutional neural networks based on TensorFlow.The TensorFlow cluster servers of cloud computing are held
The a series of task of row, these tasks carryings TensorFlow figure is calculated, and each task can be associated with the one of TensorFlow
Individual service, the service is used to create TensorFlow sessions and execution figure is calculated.The TensorFlow cluster servers of cloud computing
One or more operations can also be divided, each operation can include one or more tasks.In cloud computing
In TensorFlow cluster servers, a usual task run on one machine, if the machine supports many GPU equipment,
Multiple tasks can be run on this machine, run by application program controlling task in which GPU equipment；Conventional depth
Habit training pattern is that data parallel, i.e. TensorFlow tasks are enterprising in different small lot data sets using identical model
Row training, then on parameter server more new model shared parameter.
Because the TensorFlow cluster servers of cloud computing have the advantages that distributed system, therefore, cloud computing is utilized
TensorFlow cluster servers the convolutional neural networks model based on TensorFlow is trained, can not only shorten
Train the time of the convolutional neural networks model based on TensorFlow, and the convolutional neural networks model after training exists
Accuracy rate is also higher during video identification.
S105, if the result again identified that is determines there is suspicious object in video image, Cloud Server will be known again
Other result is back to terminal device, is handled by terminal device is further.
The result again identified that terminal device can be returned according to Cloud Server is further to be handled, if for example, can
Doubtful target is dangerous person, then sends alarm immediately, reminds Security Personnel.
It was found from the binocular video monitoring method of the above-mentioned example of accompanying drawing 1, on the one hand, due to the first convolutional neural networks and
Two convolutional neural networks can be obtained by training in advance, therefore, when target being identified using the neutral net trained
The automatic rapid extraction clarification of objective of energy, improves the efficiency recognized during video monitoring；On the other hand, by recognizing twice just really
Determine suspicious object, therefore improve the accuracy rate recognized during video monitoring.
Accompanying drawing 2 is referred to, is the structural representation for the binocular video monitoring system that the embodiment of the present invention two is provided.In order to just
In explanation, accompanying drawing 2 illustrate only the part related to the embodiment of the present invention.The binocular video monitoring system of the example of accompanying drawing 2 is main
Including binocular camera 201, terminal device 202 and Cloud Server 203, terminal device 201 includes preliminary identification module 204 and upper
Transmission module 205, Cloud Server 203 includes again identifying that module 206 and result return to module 207, wherein：
Binocular camera 201, for gathering video image and being sent to terminal device 202；
Preliminary identification module 204, for the first convolutional neural networks in video image input terminal equipment 202 to be carried out
The preliminary identification of target；
Uploading module 205, if the result for the preliminary identification of preliminary identification module 204 is suspicious to exist in video image
Target, then be uploaded to Cloud Server 203 by video image；
Module 206 is again identified that, the second convolutional neural networks for video image to be inputted on Cloud Server 203 are carried out
Target is again identified that；
As a result module 207 is returned to, if for again identifying that the result again identified that of module 206 in determination video image
There is suspicious object, then the result that would again identify that is back to terminal device 202, handled by terminal device 202 is further.
In the system of the above-mentioned example of accompanying drawing 2, the first convolutional neural networks can be the small-sized convolution based on TensorFlow
Neutral net, the second convolutional neural networks can be the large-scale convolutional neural networks based on TensorFlow.
The binocular video monitoring system of the example of accompanying drawing 2 can also include acquisition module 301, and the present invention is real as shown in Figure 3
The binocular video monitoring system of the offer of example three is provided.Acquisition module 301 is used for binocular camera 201 and gathers video image and be sent to
Before terminal device 202, according to the convolutional neural networks model based on TensorFlow, obtain based on the small-sized of TensorFlow
Convolutional neural networks and the large-scale convolutional neural networks based on TensorFlow.
The acquisition module 301 of the example of accompanying drawing 3 can also include model buildings unit 401 and training unit 402, such as accompanying drawing 4
The intelligent video multipoint monitoring system that the shown embodiment of the present invention four is provided, wherein：
Model buildings unit 401, for building the convolutional neural networks model based on TensorFlow, wherein, it is based on
TensorFlow convolutional neural networks model includes the first convolutional layer, the first maximum pond layer, the normalization of the first local acknowledgement
Layer, the second convolutional layer, the second local acknowledgement normalization layer, the first full articulamentum linearly activated based on amendment, second are based on repairing
The full articulamentum and softmax_linear of linear positive activation；
Training unit 402, for the TensorFlow cluster servers using cloud computing to the volume based on TensorFlow
Product neural network model is trained, to obtain small-sized convolutional neural networks based on TensorFlow and based on TensorFlow
Large-scale convolutional neural networks.
It should be noted that the content such as information exchange, implementation procedure between each module/unit of said apparatus, due to
The inventive method embodiment is based on same design, and its technique effect brought is identical with the inventive method embodiment, particular content
Reference can be made to the narration in the inventive method embodiment, here is omitted.
The embodiment of the present invention also provides a kind of binocular video monitoring system, including memory, processor and is stored in
In reservoir and the computer program that can run on a processor, following steps are realized during the computing device computer program：It is double
Mesh camera gathers video image and is sent to terminal device；Terminal device is by the first volume in video image input terminal equipment
Product neutral net carries out the preliminary identification of target；If the result tentatively recognized be video image in there is suspicious object, terminal
Video image is uploaded to Cloud Server by equipment；The second convolution nerve net that Cloud Server inputs video image on Cloud Server
Network carries out again identifying that for target；If the result again identified that is to determine there is suspicious object, Cloud Server in video image
The result that would again identify that is back to terminal device, is handled by terminal device is further.
The embodiment of the present invention also provides a kind of computer-readable recording medium, and the computer-readable recording medium storage has meter
Calculation machine program, realizes following steps when computer program is executed by processor：Binocular camera gathers video image and is sent to
Terminal device；Terminal device carries out the first convolutional neural networks in video image input terminal equipment the preliminary knowledge of target
Not；If the result tentatively recognized is has suspicious object in video image, video image is uploaded to cloud service by terminal device
Device；The second convolutional neural networks that Cloud Server inputs video image on Cloud Server carry out again identifying that for target；If again
The result of secondary identification is determines there is suspicious object in video image, then the result that Cloud Server would again identify that is back to terminal
Equipment, is handled by terminal device is further.
It is apparent to those skilled in the art that, for convenience of description and succinctly, only with above-mentioned each work(
Energy unit, the division progress of module are for example, in practical application, as needed can distribute above-mentioned functions by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completion
The all or part of function of description.Each functional unit, module in embodiment can be integrated in a processing unit, also may be used
To be that unit is individually physically present, can also two or more units it is integrated in a unit, it is above-mentioned integrated
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.In addition, each function list
Member, the specific name of module are also only to facilitate mutually differentiation, is not limited to the protection domain of the application.Said system
The specific work process of middle unit, module, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, without detailed description or note in some embodiment
The part of load, may refer to the associated description of other embodiments.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, depending on the application-specific and design constraint of technical scheme.Professional and technical personnel
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed apparatus and method, others can be passed through
Mode is realized.For example, system embodiment described above is only schematical, for example, the division of the module or unit,
It is only a kind of division of logic function, there can be other dividing mode when actually realizing, such as multiple units or component can be with
With reference to or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, it is shown or discussed
Coupling each other or direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING of device or unit or
Communication connection, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is realized using in the form of SFU software functional unit and as independent production marketing or used
When, it can be stored in a computer read/write memory medium.Understood based on such, the technical scheme of the embodiment of the present invention
The part substantially contributed in other words to prior art or all or part of the technical scheme can be with software products
Form embody, the computer software product is stored in a storage medium, including some instructions are to cause one
Computer equipment (can be personal computer, server, or network equipment etc.) or processor (processor) perform this hair
The all or part of step of each embodiment methods described of bright embodiment.And foregoing storage medium includes：USB flash disk, mobile hard disk,
Read-only storage (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic
Dish or CD etc. are various can be with the medium of store program codes.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to foregoing reality
Example is applied the present invention is described in detail, it will be understood by those within the art that：It still can be to foregoing each
Technical scheme described in embodiment is modified, or carries out equivalent substitution to which part technical characteristic；And these are changed
Or replace, the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme, all should
Within protection scope of the present invention.
Claims (10)
1. a kind of binocular video monitoring method, it is characterised in that methods described includes：
Binocular camera gathers video image and is sent to terminal device；
The first convolutional neural networks that the terminal device inputs the video image on the terminal device carry out target
Preliminary identification；
If the result tentatively recognized is there is suspicious object in the video image, the terminal device is by the video
Image is uploaded to Cloud Server；
The second convolutional neural networks that the Cloud Server inputs the video image on the Cloud Server carry out target
Again identify that；
If the result again identified that is determines to exist in the video image suspicious object, the Cloud Server will be described
The result again identified that is back to the terminal device, is handled by the terminal device is further.
2. the method as described in claim 1, it is characterised in that first convolutional neural networks are based on TensorFlow's
Small-sized convolutional neural networks, second convolutional neural networks are the large-scale convolutional neural networks based on TensorFlow.
3. method as claimed in claim 2, it is characterised in that the binocular camera collection video image is simultaneously sent to terminal
Before equipment, methods described also includes：
According to the convolutional neural networks model based on TensorFlow, the small-sized convolutional Neural based on TensorFlow is obtained
Network and the large-scale convolutional neural networks based on TensorFlow.
4. method as claimed in claim 3, it is characterised in that convolutional neural networks mould of the basis based on TensorFlow
Type, obtains the small-sized convolutional neural networks based on TensorFlow and the large-scale convolutional Neural net based on TensorFlow
Network, including：
Build the convolutional neural networks model based on TensorFlow, the convolutional neural networks model based on TensorFlow
Return including the first convolutional layer, the first maximum pond layer, the first local acknowledgement normalization layer, the second convolutional layer, the second local acknowledgement
One change layer, the first full articulamentum linearly activated based on amendment, second based on the full articulamentum that linearly activates of amendment and
softmax_linear；
The convolutional neural networks model based on TensorFlow is entered using the TensorFlow cluster servers of cloud computing
Row training, to obtain the small-sized convolutional neural networks based on TensorFlow and the god of the large-scale convolution based on TensorFlow
Through network.
5. a kind of binocular video monitoring system, it is characterised in that the system includes binocular camera, terminal device and cloud service
Device, the terminal device includes preliminary identification module and uploading module, and the Cloud Server includes again identifying that module and result
Return to module；
The binocular camera, for gathering video image and being sent to terminal device；
The preliminary identification module, the first convolutional neural networks for the video image to be inputted on the terminal device enter
The preliminary identification of row target；
The uploading module, if the result for the preliminary identification of the preliminary identification module can to exist in the video image
Target is doubted, then the video image is uploaded to Cloud Server；
Described to again identify that module, the second convolutional neural networks for the video image to be inputted on the Cloud Server enter
Row target is again identified that；
The result returns to module, if being the determination video image for the result again identified that for again identifying that module
In there is suspicious object, then the result again identified that is back to the terminal device, done by the terminal device into one
The processing of step.
6. system as claimed in claim 5, it is characterised in that first convolutional neural networks are based on TensorFlow's
Small-sized convolutional neural networks, second convolutional neural networks are the large-scale convolutional neural networks based on TensorFlow.
7. system as claimed in claim 6, it is characterised in that the system also includes：
Acquisition module, gathers for the binocular camera and video image and is sent to before terminal device, according to based on
TensorFlow convolutional neural networks model, obtains the small-sized convolutional neural networks based on TensorFlow and is based on
TensorFlow large-scale convolutional neural networks.
8. system as claimed in claim 7, it is characterised in that the acquisition module includes：
Model buildings unit, it is described to be based on TensorFlow for building the convolutional neural networks model based on TensorFlow
Convolutional neural networks model include the first convolutional layer, the first maximum pond layer, the first local acknowledgement and normalize layer, the second convolution
What layer, the second local acknowledgement normalization layer, the first full articulamentum linearly activated based on amendment, second were linearly activated based on amendment
Full articulamentum and softmax_linear；
Training unit, for the TensorFlow cluster servers using cloud computing to the convolution god based on TensorFlow
It is trained through network model, to obtain the small-sized convolutional neural networks based on TensorFlow and based on TensorFlow
Large-scale convolutional neural networks.
9. a kind of binocular video monitoring system, including memory, processor and it is stored in the memory and can be described
The computer program run on processor, it is characterised in that realize following walk described in the computing device during computer program
Suddenly：
Binocular camera gathers video image and is sent to terminal device；
The first convolutional neural networks that the terminal device inputs the video image on the terminal device carry out target
Preliminary identification；
If the result tentatively recognized is there is suspicious object in the video image, the terminal device is by the video
Image is uploaded to Cloud Server；
The second convolutional neural networks that the Cloud Server inputs the video image on the Cloud Server carry out target
Again identify that；
If the result again identified that is determines to exist in the video image suspicious object, the Cloud Server will be described
The result again identified that is back to the terminal device, is handled by the terminal device is further.
10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, its feature exists
In the computer program realizes following steps when being executed by processor：
Binocular camera gathers video image and is sent to terminal device；
The first convolutional neural networks that the terminal device inputs the video image on the terminal device carry out target
Preliminary identification；
If the result tentatively recognized is there is suspicious object in the video image, the terminal device is by the video
Image is uploaded to Cloud Server；
The second convolutional neural networks that the Cloud Server inputs the video image on the Cloud Server carry out target
Again identify that；
If the result again identified that is determines to exist in the video image suspicious object, the Cloud Server will be described
The result again identified that is back to the terminal device, is handled by the terminal device is further.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710286635.6A CN106982359B (en) | 2017-04-26 | 2017-04-26 | A kind of binocular video monitoring method, system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710286635.6A CN106982359B (en) | 2017-04-26 | 2017-04-26 | A kind of binocular video monitoring method, system and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106982359A true CN106982359A (en) | 2017-07-25 |
| CN106982359B CN106982359B (en) | 2019-11-05 |
Family
ID=59341496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710286635.6A Active CN106982359B (en) | 2017-04-26 | 2017-04-26 | A kind of binocular video monitoring method, system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106982359B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108229379A (en) * | 2017-12-29 | 2018-06-29 | 广东欧珀移动通信有限公司 | Image-recognizing method, device, computer equipment and storage medium |
| CN108549852A (en) * | 2018-03-28 | 2018-09-18 | 中山大学 | Pedestrian detector's Auto-learning Method under special scenes based on the enhancing of depth network |
| CN108805184A (en) * | 2018-05-28 | 2018-11-13 | 广州英卓电子科技有限公司 | A kind of fixed space, image-recognizing method and system on vehicle |
| CN108920995A (en) * | 2018-04-08 | 2018-11-30 | 华中科技大学 | Intelligent security guard video monitoring method and its system and monitor terminal |
| CN108960209A (en) * | 2018-08-09 | 2018-12-07 | 腾讯科技（深圳）有限公司 | Personal identification method, device and computer readable storage medium |
| CN109068145A (en) * | 2018-08-15 | 2018-12-21 | 上海鸢安智能科技有限公司 | Distribution type intelligent video analysis system, method, apparatus, equipment and storage medium |
| CN109413213A (en) * | 2018-12-20 | 2019-03-01 | 泉州装备制造研究所 | Cluster monitoring system based on system on chip |
| CN109670488A (en) * | 2019-01-31 | 2019-04-23 | 湖北省基础地理信息中心（湖北省北斗卫星导航应用技术研究院） | A kind of video data exemplary dynamic object detection method and system |
| CN109685088A (en) * | 2017-10-18 | 2019-04-26 | 上海仪电（集团）有限公司中央研究院 | Narrow band communication intelligent image analysis system based on cloud separation convolutional neural networks |
| CN110415159A (en) * | 2019-06-11 | 2019-11-05 | 汇盈讯科智能科技(佛山市)有限责任公司 | A kind of control system and its control method based on image recognition repeater |
| CN110675449A (en) * | 2019-09-02 | 2020-01-10 | 山东科技大学 | Binocular camera-based offshore flow detection method |
| CN110855934A (en) * | 2018-08-21 | 2020-02-28 | 北京嘀嘀无限科技发展有限公司 | Fatigue driving identification method, device and system, vehicle-mounted terminal and server |
| CN111291748A (en) * | 2020-01-15 | 2020-06-16 | 广州玖峰信息科技有限公司 | Cascade distributed artificial intelligence case number identification system |
| CN111669540A (en) * | 2019-03-07 | 2020-09-15 | 上海思桂信息技术有限公司 | Monitoring system and method based on AI technology |
| CN111785286A (en) * | 2020-05-22 | 2020-10-16 | 南京邮电大学 | Home CNN classification and feature matching combined voiceprint recognition method |
| CN112580481A (en) * | 2020-12-14 | 2021-03-30 | 康佳集团股份有限公司 | Edge node and cloud cooperative video processing method, device and server |
| CN113470653A (en) * | 2020-03-31 | 2021-10-01 | 华为技术有限公司 | Voiceprint recognition method, electronic equipment and system |
| CN113935395A (en) * | 2020-06-25 | 2022-01-14 | 安讯士有限公司 | Training of object recognition neural networks |
| CN115294507A (en) * | 2022-10-10 | 2022-11-04 | 四川川西数据产业有限公司 | Dynamic video data identification method based on fruit appearance |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102779274A (en) * | 2012-07-19 | 2012-11-14 | 冠捷显示科技（厦门）有限公司 | Intelligent television face recognition method based on binocular camera |
| CN105528754A (en) * | 2015-12-28 | 2016-04-27 | 湖南师范大学 | Old people information service system based on dual neural network behavior recognition model |
| CN105976400A (en) * | 2016-05-10 | 2016-09-28 | 北京旷视科技有限公司 | Object tracking method and device based on neural network model |
| CN106295521A (en) * | 2016-07-29 | 2017-01-04 | 厦门美图之家科技有限公司 | A kind of gender identification method based on multi output convolutional neural networks, device and the equipment of calculating |
| US20170061620A1 (en) * | 2015-09-01 | 2017-03-02 | Samsung Electronics Co., Ltd. | Method and apparatus for processing magnetic resonance image |
| CN106548127A (en) * | 2015-09-18 | 2017-03-29 | 松下电器（美国）知识产权公司 | Image-recognizing method |
-
2017
- 2017-04-26 CN CN201710286635.6A patent/CN106982359B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102779274A (en) * | 2012-07-19 | 2012-11-14 | 冠捷显示科技（厦门）有限公司 | Intelligent television face recognition method based on binocular camera |
| US20170061620A1 (en) * | 2015-09-01 | 2017-03-02 | Samsung Electronics Co., Ltd. | Method and apparatus for processing magnetic resonance image |
| CN106548127A (en) * | 2015-09-18 | 2017-03-29 | 松下电器（美国）知识产权公司 | Image-recognizing method |
| CN105528754A (en) * | 2015-12-28 | 2016-04-27 | 湖南师范大学 | Old people information service system based on dual neural network behavior recognition model |
| CN105976400A (en) * | 2016-05-10 | 2016-09-28 | 北京旷视科技有限公司 | Object tracking method and device based on neural network model |
| CN106295521A (en) * | 2016-07-29 | 2017-01-04 | 厦门美图之家科技有限公司 | A kind of gender identification method based on multi output convolutional neural networks, device and the equipment of calculating |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109685088A (en) * | 2017-10-18 | 2019-04-26 | 上海仪电（集团）有限公司中央研究院 | Narrow band communication intelligent image analysis system based on cloud separation convolutional neural networks |
| CN108229379A (en) * | 2017-12-29 | 2018-06-29 | 广东欧珀移动通信有限公司 | Image-recognizing method, device, computer equipment and storage medium |
| CN108549852A (en) * | 2018-03-28 | 2018-09-18 | 中山大学 | Pedestrian detector's Auto-learning Method under special scenes based on the enhancing of depth network |
| CN108549852B (en) * | 2018-03-28 | 2020-09-08 | 中山大学 | Specific scene downlink person detector automatic learning method based on deep network enhancement |
| CN108920995A (en) * | 2018-04-08 | 2018-11-30 | 华中科技大学 | Intelligent security guard video monitoring method and its system and monitor terminal |
| CN108805184A (en) * | 2018-05-28 | 2018-11-13 | 广州英卓电子科技有限公司 | A kind of fixed space, image-recognizing method and system on vehicle |
| CN108805184B (en) * | 2018-05-28 | 2020-07-31 | 广州英卓电子科技有限公司 | Image recognition method and system for fixed space and vehicle |
| CN108960209B (en) * | 2018-08-09 | 2023-07-21 | 腾讯科技（深圳）有限公司 | Identity recognition method, identity recognition device and computer readable storage medium |
| CN108960209A (en) * | 2018-08-09 | 2018-12-07 | 腾讯科技（深圳）有限公司 | Personal identification method, device and computer readable storage medium |
| CN109068145A (en) * | 2018-08-15 | 2018-12-21 | 上海鸢安智能科技有限公司 | Distribution type intelligent video analysis system, method, apparatus, equipment and storage medium |
| CN110855934A (en) * | 2018-08-21 | 2020-02-28 | 北京嘀嘀无限科技发展有限公司 | Fatigue driving identification method, device and system, vehicle-mounted terminal and server |
| CN109413213A (en) * | 2018-12-20 | 2019-03-01 | 泉州装备制造研究所 | Cluster monitoring system based on system on chip |
| CN109670488A (en) * | 2019-01-31 | 2019-04-23 | 湖北省基础地理信息中心（湖北省北斗卫星导航应用技术研究院） | A kind of video data exemplary dynamic object detection method and system |
| CN111669540A (en) * | 2019-03-07 | 2020-09-15 | 上海思桂信息技术有限公司 | Monitoring system and method based on AI technology |
| CN110415159A (en) * | 2019-06-11 | 2019-11-05 | 汇盈讯科智能科技(佛山市)有限责任公司 | A kind of control system and its control method based on image recognition repeater |
| CN110675449A (en) * | 2019-09-02 | 2020-01-10 | 山东科技大学 | Binocular camera-based offshore flow detection method |
| CN111291748A (en) * | 2020-01-15 | 2020-06-16 | 广州玖峰信息科技有限公司 | Cascade distributed artificial intelligence case number identification system |
| CN111291748B (en) * | 2020-01-15 | 2020-12-11 | 广州玖峰信息科技有限公司 | Cascade distributed artificial intelligence case number identification system |
| CN113470653A (en) * | 2020-03-31 | 2021-10-01 | 华为技术有限公司 | Voiceprint recognition method, electronic equipment and system |
| CN111785286A (en) * | 2020-05-22 | 2020-10-16 | 南京邮电大学 | Home CNN classification and feature matching combined voiceprint recognition method |
| CN113935395A (en) * | 2020-06-25 | 2022-01-14 | 安讯士有限公司 | Training of object recognition neural networks |
| CN112580481A (en) * | 2020-12-14 | 2021-03-30 | 康佳集团股份有限公司 | Edge node and cloud cooperative video processing method, device and server |
| CN115294507A (en) * | 2022-10-10 | 2022-11-04 | 四川川西数据产业有限公司 | Dynamic video data identification method based on fruit appearance |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106982359B (en) | 2019-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106982359A (en) | A kind of binocular video monitoring method, system and computer-readable recording medium | |
| CN103914735B (en) | A kind of fault recognition method and system based on Neural Network Self-learning | |
| CN108510194A (en) | Air control model training method, Risk Identification Method, device, equipment and medium | |
| CN106295799B (en) | A kind of implementation method of deep learning multilayer neural network | |
| CN102622515B (en) | A kind of weather prediction method | |
| CN104573669A (en) | Image object detection method | |
| CN107423721A (en) | Interactive action detection method, device, storage medium and processor | |
| CN111368926B (en) | Image screening method, device and computer readable storage medium | |
| CN106778910A (en) | Deep learning system and method based on local training | |
| CN106971145A (en) | A kind of various visual angles action identification method and device based on extreme learning machine | |
| CN104063686A (en) | System and method for performing interactive diagnosis on crop leaf segment disease images | |
| CN103136540B (en) | A kind of Activity recognition method based on implicit structure reasoning | |
| CN115563674A (en) | Initial floorplan generation method and apparatus, electronic device, and storage medium | |
| CN106789149A (en) | Using the intrusion detection method of modified self-organizing feature neural network clustering algorithm | |
| Shokouhifar et al. | A hybrid approach for effective feature selection using neural networks and artificial bee colony optimization | |
| CN107220707A (en) | Dynamic neural network model training method and device based on 2-D data | |
| CN111079930B (en) | Data set quality parameter determining method and device and electronic equipment | |
| CN108604313A (en) | The predictive modeling of automation and frame | |
| CN108073985A (en) | A kind of importing ultra-deep study method for voice recognition of artificial intelligence | |
| CN110309879A (en) | A kind of jujube exterior quality classification method, device, equipment and storage medium | |
| CN111542818A (en) | Network model data access method and device and electronic equipment | |
| CN108074240A (en) | Recognition methods, identification device, computer readable storage medium and program product | |
| CN107832833A (en) | Scene recognition method, apparatus and system based on chaos autonomous development neutral net | |
| Hu et al. | Tree species identification based on the fusion of multiple deep learning models transfer learning | |
| Jia et al. | Lightweight CNN-Based Image Recognition with Ecological IoT Framework for Management of Marine Fishes |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |