CN106341660A - Image processing method and apparatus thereof, and unmanned aerial vehicle image processing system - Google Patents
Image processing method and apparatus thereof, and unmanned aerial vehicle image processing system Download PDFInfo
- Publication number
- CN106341660A CN106341660A CN201610817848.2A CN201610817848A CN106341660A CN 106341660 A CN106341660 A CN 106341660A CN 201610817848 A CN201610817848 A CN 201610817848A CN 106341660 A CN106341660 A CN 106341660A
- Authority
- CN
- China
- Prior art keywords
- image
- compression
- image processing
- module
- processing method
- 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.)
- Pending
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
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention provides an image processing method and an apparatus thereof, and a unmanned aerial vehicle image processing system. The unmanned aerial vehicle image processing system comprises an image acquisition apparatus, an image sending terminal and an image receiving terminal. The image acquisition apparatus and the image sending terminal are arranged on a unmanned aerial vehicle. The image receiving terminal is arranged on ground. When being applied to the image sending terminal, the image processing apparatus comprises an image compression module, an image classification module and an image sending module, wherein the image compression module is used for acquiring original images collected by the image acquisition apparatus and compressing the original images; the image classification module is used for classifying the compressed images according to a prestored classification information; and the image sending module is used for packing the compressed images belonging to one kind and then sending the images. Based on the above design, the image processing apparatus compresses the images and then can carry out image classification processing; a workload of image processing is effectively reduced; and image processing efficiency is increased.
Description
Technical field
The present invention relates to technical field of image processing, in particular to a kind of image processing method, device and unmanned plane
Image processing system.
Background technology
In prior art, image is compressed, decompresses and during identifying processing, compression of images, image classification and image decompression
To be realized using independent algorithm, and image classification be based on image decompression after the completion of, classification that original image is carried out
Process.So, larger memory space can be taken in image processing process, and image procossing can be caused using algorithms of different
Slowly the problem that, workload of image procossing is big and efficiency is low.
Content of the invention
In view of this, it is an object of the invention to provide a kind of image processing method, device and unmanned plane image procossing system
System, to improve the problems of the prior art.
For achieving the above object, the embodiment of the present invention adopts the following technical scheme that
The present invention provides a kind of image processing method, is applied to image transmitting terminal, described image processing method includes:
Obtain the original image that image acquisition device arrives, and described original image is compressed obtaining compression figure
Picture.
According to the classification information prestoring, described compression image is classified.
It will be transmitted after of a sort compression image packing will be belonged to.
Optionally, described image processing method also includes:
Extract the characteristic information of described compression image, the characteristic information according to described compression image is to described compression image
Content is identified.
According to the content identifying, described compression image is identified, obtains the compression image including content identification.
Described include belonging to the step that is transmitted after of a sort compression image packing:
It is transmitted after the compression image belonging to same class and inclusion content identification is packed.
Optionally, the step described original image being compressed obtaining compressing image includes:
Using multiple convolution kernels, described original image is carried out with convolution, generate multiple new images.
Multiple convolution is carried out to the plurality of new images, obtains multiple block of pixels.
The plurality of block of pixels is carried out with a convolution synthesis compression image.
Another embodiment of the present invention provides a kind of image processing method, is applied to image-receptive end, described image process side
Method includes:
Receive the compression image that image transmitting terminal sends.
According to the classification information prestoring, described compression image is classified.
Of a sort compression image will be belonged to carry out decompression and obtain sorted original image.
Optionally, described image processing method also includes:
Extract the characteristic information of described compression image, the characteristic information according to described compression image is to described compression image
Content is identified.
According to the content identifying, described compression image is identified, obtains the compression image including content identification.
Described obtain belonging to of a sort compression image and carry out decompressing the step of sorted original image and include:
The compression image belonging to same class and inclusion content identification is carried out after decompression is classified and carries content identification
Original image.
Optionally, described will belong to same class and include the compression image of content identification and carry out after decompression classify and band
The step having the original image of content identification includes:
Belong to same class and include the compression image of content identification and once carry out deconvolution and obtain multiple block of pixels to described.
Multiple deconvolution is carried out to the plurality of block of pixels and obtains multiple new images.
Using multiple convolution kernels, the plurality of new images are carried out after deconvolution is classified and former with content identification
Beginning image.
Another embodiment of the present invention provides a kind of image processing apparatus, is applied to image transmitting terminal, and described image processes dress
Put including:
Image compression module, for obtaining the original image that image acquisition device arrives, and enters to described original image
Row compression obtains compressing image.
Image classification module, for classifying to described compression image according to the classification information prestoring.
Image sending module, is transmitted after of a sort compression image packing for belonging to.
Another embodiment of the present invention provides a kind of image processing apparatus, is applied to image-receptive end, and described image processes dress
Put including:
Image receiver module, for receiving the compression image of image transmitting terminal transmission.
Image classification module, for classifying to described compression image according to the classification information prestoring.
Image decompression module, carries out decompression and obtains sorted original image for belonging to of a sort compression image.
Another embodiment of the present invention also provides a kind of unmanned plane image processing system, sends out including image collecting device, image
Sending end and image-receptive end, described image harvester and image transmitting terminal are arranged at unmanned plane, and described image receiving terminal is arranged
In ground.
Described image transmitting terminal includes being applied to the image processing apparatus of described image transmitting terminal, and described image receiving terminal is used
The of a sort compression image that belongs to after the packing that described image transmitting terminal is sent decompresses, and obtains sorted original
Image.Or
The original image that described image transmitting terminal is used for described image harvester is collected is compressed being compressed
Image, and described compression image is sent to described image receiving terminal, described image receiving terminal includes being applied to described image connecing
The image processing apparatus of receiving end.
Optionally, described image transmitting terminal or image-receptive end are additionally operable to extract the characteristic information of described compression image, root
Characteristic information according to described compression image is identified to the content of described compression image, according to identification content to described compression figure
As being identified, obtain the compression image including content identification.
The present invention provides a kind of image processing method, device and unmanned plane image processing system.By ingehious design so that
Image processing apparatus can carry out image classification process after image is compressed or after receiving compression image, thus effectively
Improve the problem taking larger memory space in image processing process, reduce the workload of image procossing, improve image procossing
Efficiency.
For enabling the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below will be attached to use required in embodiment
Figure is briefly described it will be appreciated that the following drawings illustrate only the section Example of the present invention, and it is right to be therefore not construed as
The restriction of the scope of the present invention, for those of ordinary skill in the art, on the premise of not paying creative work, also
Other related accompanying drawings can be obtained according to these accompanying drawings.
Fig. 1 is a kind of block diagram of unmanned plane image processing system provided in an embodiment of the present invention.
Fig. 2 is a kind of block diagram of the image transmitting terminal 20 shown in Fig. 1.
Fig. 3 is a kind of another block diagram of unmanned plane image processing system provided in an embodiment of the present invention.
Fig. 4 is a kind of another block diagram of unmanned plane image processing system provided in an embodiment of the present invention.
A kind of flow process of image processing method being applied to image transmitting terminal that Fig. 5 provides for another embodiment of the present invention is shown
It is intended to.
Fig. 6 is the sub-step schematic diagram of step s110 in Fig. 5.
A kind of flow process of image processing method being applied to image-receptive end that Fig. 7 provides for another embodiment of the present invention is shown
It is intended to.
Fig. 8 is the sub-step schematic diagram of step s250 in Fig. 7;
Icon: 10- image collecting device;20- image transmitting terminal;30- image-receptive end;40- image processing apparatus;50-
Memorizer;60- processor;70- mixed-media network modules mixed-media;100- image compression module;200- image classification module;300- image recognition mould
Block;400- image identification module;500- image sending module;600- image receiver module;700- image decompression module.
Specific embodiment
Purpose, technical scheme and advantage for making the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the present invention is applied with the technical scheme in example and is clearly and completely described it is clear that described embodiment is this
Invent a part of embodiment, rather than whole embodiments.The embodiment of the present invention generally described and illustrated in accompanying drawing herein
Assembly can be arranged with various different configurations and design.
Therefore, below the detailed description of the embodiments of the invention providing in the accompanying drawings is not intended to limit claimed
The scope of the present invention, but be merely representative of the selected embodiment of the present invention.Based on the embodiment in the present invention, this area is common
The every other embodiment that technical staff is obtained under the premise of not making creative work, broadly falls into the model of present invention protection
Enclose.
It should also be noted that similar label and letter expression similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined in individual accompanying drawing, then do not need it to be defined further and explains in subsequent accompanying drawing.
In describing the invention in addition it is also necessary to explanation, unless otherwise clearly defined and limited, term " setting ",
" connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or is integrally connected;Can be
It is mechanically connected or electrically connect;Can be to be joined directly together it is also possible to be indirectly connected to by intermediary, can be two
The connection of element internal.For the ordinary skill in the art, above-mentioned term can be understood in the present invention with concrete condition
In concrete meaning.
In unmanned plane image delivering system used in prior art, unmanned plane completes image acquisition and obtains original image,
Original image is compressed obtain compressing image, by compression image being sent to earth station, earth station using being wirelessly transferred
Receive compression image and carry out after decompression obtains original image, reuse independent algorithm and the original image after decompression is carried out point
Class is processed.Make image procossing difficult using two kinds of independent algorithm, cause the efficiency of image procossing low.Image classification is on ground
Station is carried out, so that the processing pressure of earth station is big.
Refer to shown in Fig. 1, a kind of unmanned plane image processing system, it includes image collecting device 10, image transmitting terminal
20 and image-receptive end 30.Described image harvester 10 and image transmitting terminal 20 are arranged at unmanned plane, described image receiving terminal
30 are arranged at ground.
As shown in Fig. 2 being a kind of block diagram of image transmitting terminal 20 provided in an embodiment of the present invention.Comprising: figure
As processing meanss 40, memorizer 50, processor 60 and mixed-media network modules mixed-media 70.
Described memorizer 50, processor 60 and mixed-media network modules mixed-media 70 are directly or indirectly electrically connected with, each other with reality
The transmission of existing data or interaction.For example, these elements can be realized by one or more communication bus or holding wire each other
It is electrically connected with.Be stored with memorizer 50 image processing apparatus 40, and described image processing meanss 40 include at least one can be soft
The form of part or firmware (firmware) is stored in the software function module in described memorizer 50, and described processor 60 passes through fortune
Row is stored in software program and module in memorizer 50, the such as image processing apparatus 40 in the embodiment of the present invention, thus holding
Row various function application and data processing, that is, realize the image processing method in the embodiment of the present invention.
Wherein, described memorizer 50 may be, but not limited to, random access memory (random access memory,
Ram), read only memory (read only memory, rom), programmable read only memory (programmable read-only
Memory, prom), erasable read-only memory (erasable programmable read-only memory, eprom),
Electricallyerasable ROM (EEROM) (electric erasable programmable read-only memory, eeprom) etc..
Wherein, memorizer 50 is used for storage program, and described processor 60, after receiving execute instruction, executes described program.Further
Ground, in above-mentioned memorizer 50 image processing apparatus 40 may include various for management system task (such as memory management, storage set
Standby control, power management etc.) component software and/or driving, and mutually can communicate with various hardware or component software, thus carrying
Running environment for other software assembly.
Described processor 60 is probably a kind of IC chip, has the disposal ability of signal.Above-mentioned processor 60
Can be general processor, including central processing unit (central processing unit, cpu), network processing unit
(network processor, np) etc..Can also be digital signal processor (dsp)), special IC (asic), ready-made
Programmable gate array (fpga) or other PLDs, discrete gate or transistor logic, discrete hardware group
Part.Can realize or execute disclosed each method in the embodiment of the present invention, step and logic diagram.General processor is permissible
It is microprocessor or this processor can also be any conventional processor etc..
Mixed-media network modules mixed-media 70 is used for by the communication connection between network and external communications terminals, realizes network signal and data
Transmitting-receiving operation.Above-mentioned network signal may include wireless signal or wire signal.
It is appreciated that the structure shown in Fig. 2 be only illustrate, image transmitting terminal 20 may also include more more than shown in Fig. 2 or
The less assembly of person, or there are the configurations different from shown in Fig. 2.Each assembly shown in Fig. 2 can using hardware, software or
A combination thereof is realized.
The each group that a kind of block diagram being applied to image-receptive end 30 that another embodiment of the present invention provides includes
The concrete structure of part and each assembly and connected mode, each assembly including with the block diagram of above-mentioned image transmitting terminal 20
And the concrete structure knot of each assembly is identical with connected mode, will not be described here.
Incorporated by reference to shown in Fig. 3, described unmanned plane image processing system may is that image-receptive end 30 and includes image procossing
The image transmitting terminal 20 of device 40.
Described image processing meanss 40 include: image compression module 100, image classification module 200 and image sending module
500.Described image compression module 100 is used for obtaining the original image that image collecting device 10 collects, and to described original graph
As being compressed, obtain compressing image.Described image sort module 200 is used for according to the classification information prestoring to described compression figure
As being classified.Specifically, to multiple described compression image classify when, described image sort module 200 is according to described
Multiple described compression images are divided into different classifications by classification information.
Optionally, the described image processing apparatus 40 being applied to image transmitting terminal 20 are also included for extracting described compression figure
The characteristic information of picture, the image recognition that the characteristic information according to described compression image is identified to the content of described compression image
Module 300.According to identification content, described compression image is identified, after obtaining including classifying and include the pressure of content identification
The image identification module 400 of contract drawing picture.It is arranged so that described image transmitting terminal 20 is realized original image is compressed, divided
After class and identification are classified and include the compression image of content identification, and same class will be belonged to and include content identification
Compression image transmits.
Described image receiving terminal 30 includes: for receive described image transmitting terminal 20 transmission packing after belong to same class
Compression image image receiver module 600, by belong to of a sort compression image carrying out decompress, obtain is sorted former
The image decompression module 700 of beginning image.Specifically, described image receiving terminal 30 receives and belongs to same class described in decompressing and comprise
The compression image of content identification obtains classifying and all carries the original image of content identification.
Incorporated by reference to shown in Fig. 4, described unmanned plane image processing system is it may also is that image transmitting terminal 20 and including at image
The image-receptive end 30 of reason device 40.
Described image transmitting terminal 20 includes: for receiving the original image that described image harvester 10 collects and carrying out
Compression obtains compressing the image compression module 100 of image, and described compression image is sent to the image of described image receiving terminal 30
Sending module 500.
The described image processing apparatus 40 being applied to image-receptive end 30 include image receiver module 600, image classification mould
Block 200 and image decompression module 700.Described image receiver module 600, for receiving the compression of image sending module 500 transmission
Image.Described image sort module 200, for classifying to described compression image according to the classification information prestoring.Optionally,
To multiple described compression image classify when, according to described classification information by multiple described compression images be divided into different classes
Not.
Optionally, described image receiving terminal 30 also includes the characteristic information for extracting described compression image, according to described
The picture recognition module 300 that the characteristic information of compression image is identified to the content of described compression image.According to identification content
To described compression image be identified, obtain include classification after and include content identification compress image image identification module
400.
Optionally, described image decompression module 700, is decompressed for belonging to of a sort compression image, is divided
Original image after class.Specifically, the compression image belonging to same class and inclusion content identification is decompressed by described receiving terminal,
After being classified and with content identification original image.
It should be noted that described image harvester 10 can be video camera, photographing unit and mobile phone etc. can take pictures
?.The form of described original image can be jpg, gif, psd, png or bmp.Described classification information include sky, land,
Desert and ocean.Described characteristic information includes specific personage, building and vehicle etc. in image.Described content identification can be one
Section comprises the code of one or more information such as personage, building and the vehicle of picture.
Above two set-up mode can complete the compression of image in unmanned plane image procossing, classification, identification are conciliate
The task of pressure.According to above two set-up mode, described image sort module 200 and described image identification module 300 were both
The image transmitting terminal 20 that unmanned plane can be arranged at can be arranged at the image-receptive end 30 on ground, thus realizing unmanned plane figure again
As elasticity airborne and floor treatment task can be distributed in processing procedure.
Refer to shown in Fig. 5, a kind of flow chart of image processing method that another embodiment of the present invention provides, described image
Processing method is applied to image transmitting terminal 20, the idiographic flow in Fig. 5 will be described in detail below.
Step s110: obtain the original image that image collecting device 10 collects, and described original image is compressed
Obtain compressing image.In the present embodiment, described step s110 can be executed by the image compression module 100 in Fig. 3.
Step s120: described compression image is classified according to the classification information prestoring.In the present embodiment, described step
Rapid s120 is to be executed by the image classification module 200 in Fig. 3.Described according to prestored information to described compression image classify
May is that and adopt the method for linear regression to realize classification described compression image.
Step s130: extract the characteristic information of described compression image, according to described characteristic information, described compression image is entered
Row identification.In the present embodiment, described step s130 is to be executed by the picture recognition module 300 in Fig. 3.
Step s140: according to the content identifying, described compression image is identified, obtains the pressure including content identification
Contract drawing picture.In the present embodiment, described step s140 is to be executed by the image identification module 400 in Fig. 3.
Step s150: be transmitted after the compression image belonging to same class and inclusion content identification is packed.In this reality
Apply in example, described step s150 is to be executed by the image sending module 500 in Fig. 3.Different classes of image is being passed
When sending, different classes of image must be packed respectively, just enable the sort pass of image.Optionally, at described image
The method of reason can also be and transmitted belonging to of a sort image.
Incorporated by reference to shown in Fig. 6, for ensureing the safety of Compressed Image Transmission, optionally, step s110 is by described original graph
Method as being compressed obtaining compressing image includes following several sub-steps:
Sub-step s112: using multiple convolution kernels, described original image is carried out with convolution, generate multiple new images.In this reality
Apply in example, described sub-step s112 is to be executed by the image compression module 100 in Fig. 3.
Sub-step s114: multiple convolution is carried out to the plurality of new images, obtains multiple block of pixels.In the present embodiment,
Described sub-step s112 is to be executed by the image compression module 100 in Fig. 3.Described according to described characteristic information to described compression
Image is identified may is that and adopts linear regression according to described characteristic information to the plurality of new images or multiple block of pixels
Method is identified.
Sub-step s116: multiple block of pixels are carried out with a convolution synthesis compression image.In the present embodiment, described sub-step
Rapid s112 is to be executed by the image compression module 100 in Fig. 3.
Specifically, the method described original image being compressed obtaining compressing image is: uses m1 to original image
Convolution kernel convolution, generates m1 new images.When the size of convolution kernel is k1, the sampling interval is s1, the new images size of generation is
(m1-k1)/s1+1.The process of above-mentioned use convolution kernel convolution is repeated several times after obtaining new images, but palpus in convolution process
Change the number of convolution kernel and the size in sampling interval, obtain multiple block of pixels.A convolution is adopted after obtaining multiple block of pixels,
Synthesize described compression image.Additionally, being classified to described compression image according to the classification information prestoring, can be that basis prestores
Classification information to described compression image adopt linear regression realize classification.
It is arranged so that described image processing meanss 40 can carry out image classification and image after carrying out compression of images
The work of identification.Additionally, by being stolen so that compressing image using different convolution kernels and sampling interval in convolution process
Be extracted afterwards decoding probability little, and then ensure that the safety of Compressed Image Transmission.
Refer to shown in Fig. 7, be a kind of image processing method that another embodiment of the present invention provides, described image process side
Method is applied to image-receptive end 30, and described image processing method comprises the following steps:
Step s210: receive the compression image that image transmitting terminal 20 sends.In the present embodiment, described step s210 be by
Image receiver module 600 execution in Fig. 4.
Step s220: described compression image is classified according to prestored information.In the present embodiment, described step s220
It is to be executed by the image classification module 200 in Fig. 4.Described according to prestored information, described compression image is carried out by classification can be
The method of linear regression is adopted to realize described compression image.
It should be noted that the method that described compression image is classified refers to one kind described above and is applied to figure
Image processing method as transmitting terminal 20.
Step s230: extract the characteristic information of described compression image, the characteristic information according to described compression image is to described
The content of compression image is identified.In the present embodiment, described step s230 is to be held by the picture recognition module 300 in Fig. 4
Row.
Step s240: be identified to described compression image according to the content identifying, obtain including content identification
Compression image.In the present embodiment, described step s240 is to be executed by the image identification module 400 in Fig. 4.
It should be noted that being identified to described compression image and the method that identifies refers to above-mentioned one kind and is applied to
The image processing method of image transmitting terminal 20.
By belong to of a sort compression image decompressed to sorted original image, can be by described belong to
The compression image of one class carries out decompression and obtains sorted original image, and its method includes step s250: will belong to same class and
Including content identification compression image carry out decompressing classify after and carry the original image of content identification.In the present embodiment
In, described step s250 is to be executed by the image decompression module 700 in Fig. 4.
Incorporated by reference to shown in Fig. 8, optionally, by the described compression figure belonging to same class and including content identification in step s250
As carry out decompressing classify after carry content identification the method for original image include following sub-step.
Sub-step s252: belong to same class and include the compression image of content identification and carry out a deconvolution and obtain to described
Multiple block of pixels.In the present embodiment, described step s252 is to be executed by the image decompression module 700 in Fig. 4.Optionally,
The described characteristic information according to described compression image is identified may is that according to described feature to the content of described compression image
Information is identified using the method for linear regression to the plurality of new images or multiple block of pixels.
Sub-step s254: multiple deconvolution is carried out to the plurality of block of pixels and obtains multiple new images.In the present embodiment,
Described step s252 is to be executed by the image decompression module 700 in Fig. 4.
Sub-step s256: the plurality of new images are carried out after deconvolution is classified and with interior using multiple convolution kernels
Hold the original image of mark.In the present embodiment, described step s252 is to be executed by the image decompression module 700 in Fig. 4.
It should be noted that belonging to described same class and include the compression image of content identification and carry out decompression and classified
The method carrying the original image of content identification afterwards is a kind of image processing method being applied to image transmitting terminal 20 described above
The inverse process to compression image to the compression of described original image in method.
It is arranged so that described image receiving terminal 30 can complete classification, identification and the decompression of image, need not be to figure
As being classified after being decompressed and identifying, it is prevented effectively from because causing the difficult problem of image procossing using many algorithms.
In sum, the present invention provides a kind of image processing method, device and unmanned plane image processing system, by using
Above-mentioned image processing method, can achieve the process of the compression to original image, classification, identification and decompression using an algorithm,
And using in algorithm, the data in algorithm can be changed.Effectively improve compression of images in prior art, image solution
Pressure, image classification and the algorithm that image recognition is three class independences, algorithm is complicated, and image classification and image recognition can only be based on solutions
Original image after pressure processes the problem it is impossible to realize in an algorithm simultaneously.Make unmanned plane in transmission compressed picture mistake
Even if misinformation occurring in journey or being stolen, it is not easy to be cracked and decompresses.
By image classification module 200, picture recognition module 300 and image identification module 400 are arranged at according to demand
The image transmitting terminal 20 of unmanned plane image processing system or image-receptive end 30.So can effectively alleviate of the prior art unmanned
In machine image processing system, when there being multiple unmanned planes jointly in the case of execution task, unmanned plane mainly undertakes collection image simultaneously
The task of compression transmission, after the image-receptive end 30 reception compressed picture on ground is decompressed, then to image classification and identification, if
It is placed in the overweight problem of image-receptive end 30 image processing tasks on ground.Realize elasticity distribution image receiving terminal 20 and image is sent out
The process task of sending end 30.
It should be understood that disclosed method, device are it is also possible to pass through other in embodiment provided by the present invention
Mode realize.Device embodiment described above is only that schematically for example, the flow chart in accompanying drawing and block diagram show
Devices in accordance with embodiments of the present invention, the architectural framework in the cards of method and computer program product, function and behaviour
Make.At this point, each square frame in flow chart or block diagram can represent a part for a module, program segment or code, institute
The part stating module, program segment or code comprises the executable instruction of one or more logic functions for realizing regulation.
It should also be noted that at some as in the implementation replaced, the function of being marked in square frame can also be with different from accompanying drawing
The order being marked occurs.For example, two continuous square frames can essentially execute substantially in parallel, and they sometimes can also be by
Contrary order execution, this is depending on involved function.It is also noted that each square frame in block diagram and/or flow chart,
And the combination of the square frame in block diagram and/or flow chart, can with the function of execution regulation or action special based on hardware
System realizing, or can be realized with combining of computer instruction with specialized hardware.
In addition, each functional module in embodiments of the present invention can integrate one independent part of formation,
Can be modules individualism it is also possible to two or more modules are integrated to form an independent part.
If described function realized using in the form of software function module and as independent production marketing or use when, permissible
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
Partly being embodied in the form of software product of part that prior art is contributed or this technical scheme, this meter
Calculation machine software product is stored in a storage medium, including some instructions with so that a computer equipment (can be individual
People's computer, server, or network equipment etc.) execution each embodiment methods described of the present invention all or part of step.
It should be noted that herein, such as first and second or the like relational terms are used merely to an entity or behaviour
Make with another entity or operation make a distinction, and not necessarily require or imply these entities or operate between exist any this
Plant actual relation or order.And, term " inclusion " or any other variant are intended to comprising of nonexcludability, from
And make the process, method, article or the equipment that include a series of key elements not only include those key elements, but also include not bright
Other key elements really listed, or also include for this process, method, article or the intrinsic key element of equipment.Do not having
More limit in the case of, the key element that limited by sentence "including a ..." it is not excluded that include described key element process,
Also there is other identical element in method, article or equipment.
The above, the only specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, and any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, all should contain
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should described be defined by scope of the claims.
Claims (10)
1. a kind of image processing method, is applied to image transmitting terminal it is characterised in that described image processing method includes:
Obtain the original image that image acquisition device arrives, and described original image is compressed obtain compressing image;
According to the classification information prestoring, described compression image is classified;
It will be transmitted after of a sort compression image packing will be belonged to.
2. image processing method according to claim 1 is it is characterised in that described image processing method also includes:
Extract the characteristic information of described compression image, the content to described compression image for the characteristic information according to described compression image
It is identified;
According to the content identifying, described compression image is identified, obtains the compression image including content identification;
Described include belonging to the step that is transmitted after of a sort compression image packing:
It is transmitted after the compression image belonging to same class and inclusion content identification is packed.
3. image processing method according to claim 1 is it is characterised in that be compressed being pressed to described original image
The step of contract drawing picture includes:
Using multiple convolution kernels, described original image is carried out with convolution, generate multiple new images;
Multiple convolution is carried out to the plurality of new images, obtains multiple block of pixels;
The plurality of block of pixels is carried out with a convolution synthesis compression image.
4. a kind of image processing method, is applied to image-receptive end it is characterised in that described image processing method includes:
Receive the compression image that image transmitting terminal sends;
According to the classification information prestoring, described compression image is classified;
Of a sort compression image will be belonged to carry out decompression and obtain sorted original image.
5. image processing method according to claim 4 is it is characterised in that described image processing method also includes:
Extract the characteristic information of described compression image, the content to described compression image for the characteristic information according to described compression image
It is identified;
According to the content identifying, described compression image is identified, obtains the compression image including content identification;
Described obtain belonging to of a sort compression image and carry out decompressing the step of sorted original image and include:
By belong to same class and include content identification compression image carry out decompressing classify after and carry the former of content identification
Beginning image.
6. image processing method according to claim 5 will be it is characterised in that described will belong to same class and include content mark
The compression image known carry out decompressing classify after and the step of the original image that carries content identification include:
Belong to same class and include the compression image of content identification and once carry out deconvolution and obtain multiple block of pixels to described;
Multiple deconvolution is carried out to the plurality of block of pixels and obtains multiple new images;
The plurality of new images are carried out after deconvolution is classified using multiple convolution kernels and carry the original graph of content identification
Picture.
7. a kind of image processing apparatus, are applied to image transmitting terminal it is characterised in that described image processing meanss include:
Image compression module, for obtaining the original image that image acquisition device arrives, and presses to described original image
Contracting obtains compressing image;
Image classification module, for classifying to described compression image according to the classification information prestoring;
Image sending module, is transmitted after of a sort compression image packing for belonging to.
8. a kind of image processing apparatus, are applied to image-receptive end it is characterised in that described image processing meanss include:
Image receiver module, for receiving the compression image of image transmitting terminal transmission;
Image classification module, for classifying to described compression image according to the classification information prestoring;
Image decompression module, carries out decompression and obtains sorted original image for belonging to of a sort compression image.
9. a kind of unmanned plane image processing system is it is characterised in that include image collecting device, image transmitting terminal and image-receptive
End, described image harvester and image transmitting terminal are arranged at unmanned plane, and described image receiving terminal is arranged at ground;
Described image transmitting terminal includes the image processing apparatus described in claim 7, and described image receiving terminal is used for described figure
As the of a sort compression image that belongs to after the packing that transmitting terminal sends is decompressed, obtain sorted original image;Or
The original image that described image transmitting terminal is used for that described image harvester is collected is compressed obtaining compressing image,
And send described compression image to described image receiving terminal, described image receiving terminal is included at the image described in claim 8
Reason device.
10. unmanned plane image processing system according to claim 9 is it is characterised in that described image transmitting terminal or image
Receiving terminal is additionally operable to extract the characteristic information of described compression image, and the characteristic information according to described compression image is to described compression figure
The content of picture is identified, and according to identification content, described compression image is identified, obtains the compression figure including content identification
Picture.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610817848.2A CN106341660A (en) | 2016-09-12 | 2016-09-12 | Image processing method and apparatus thereof, and unmanned aerial vehicle image processing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610817848.2A CN106341660A (en) | 2016-09-12 | 2016-09-12 | Image processing method and apparatus thereof, and unmanned aerial vehicle image processing system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106341660A true CN106341660A (en) | 2017-01-18 |
Family
ID=57838694
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610817848.2A Pending CN106341660A (en) | 2016-09-12 | 2016-09-12 | Image processing method and apparatus thereof, and unmanned aerial vehicle image processing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106341660A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109462762A (en) * | 2018-10-26 | 2019-03-12 | 西安科锐盛创新科技有限公司 | Image processing method for unmanned plane |
CN109996004A (en) * | 2019-05-14 | 2019-07-09 | 北京筑梦园科技有限公司 | A kind of low power image imaging method, processor and device |
CN110012205A (en) * | 2019-05-14 | 2019-07-12 | 北京筑梦园科技有限公司 | A kind of low-power-consumption video imaging method, processor and device |
CN110189385A (en) * | 2019-06-05 | 2019-08-30 | 京东方科技集团股份有限公司 | Model training and picture compression, decompressing method, device, medium and electronic equipment |
CN113055677A (en) * | 2021-04-07 | 2021-06-29 | 南京云格信息技术有限公司 | Image compression method based on FPGA |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101584571A (en) * | 2009-06-15 | 2009-11-25 | 无锡骏聿科技有限公司 | Capsule endoscopy auxiliary film reading method |
CN101763269A (en) * | 2010-01-27 | 2010-06-30 | 中兴通讯股份有限公司 | Method for making software installation package |
US20110125998A1 (en) * | 2009-11-25 | 2011-05-26 | Electronics And Telecommunications Research Institute | Network photographing apparatus having a partial encryption function |
CN103905733A (en) * | 2014-04-02 | 2014-07-02 | 哈尔滨工业大学深圳研究生院 | Method and system for conducting real-time tracking on faces by monocular camera |
CN105138997A (en) * | 2015-09-06 | 2015-12-09 | 湖南大学 | Method for identifying movement in wireless body area network based on compression classification |
-
2016
- 2016-09-12 CN CN201610817848.2A patent/CN106341660A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101584571A (en) * | 2009-06-15 | 2009-11-25 | 无锡骏聿科技有限公司 | Capsule endoscopy auxiliary film reading method |
US20110125998A1 (en) * | 2009-11-25 | 2011-05-26 | Electronics And Telecommunications Research Institute | Network photographing apparatus having a partial encryption function |
CN101763269A (en) * | 2010-01-27 | 2010-06-30 | 中兴通讯股份有限公司 | Method for making software installation package |
CN103905733A (en) * | 2014-04-02 | 2014-07-02 | 哈尔滨工业大学深圳研究生院 | Method and system for conducting real-time tracking on faces by monocular camera |
CN105138997A (en) * | 2015-09-06 | 2015-12-09 | 湖南大学 | Method for identifying movement in wireless body area network based on compression classification |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109462762A (en) * | 2018-10-26 | 2019-03-12 | 西安科锐盛创新科技有限公司 | Image processing method for unmanned plane |
CN109996004A (en) * | 2019-05-14 | 2019-07-09 | 北京筑梦园科技有限公司 | A kind of low power image imaging method, processor and device |
CN110012205A (en) * | 2019-05-14 | 2019-07-12 | 北京筑梦园科技有限公司 | A kind of low-power-consumption video imaging method, processor and device |
CN110189385A (en) * | 2019-06-05 | 2019-08-30 | 京东方科技集团股份有限公司 | Model training and picture compression, decompressing method, device, medium and electronic equipment |
CN113055677A (en) * | 2021-04-07 | 2021-06-29 | 南京云格信息技术有限公司 | Image compression method based on FPGA |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106341660A (en) | Image processing method and apparatus thereof, and unmanned aerial vehicle image processing system | |
CN109639481A (en) | A kind of net flow assorted method, system and electronic equipment based on deep learning | |
CN108683877B (en) | Spark-based distributed massive video analysis system | |
US20170041540A1 (en) | Energy-efficient secure vision processing applying object detection algorithms | |
CN106790491B (en) | The implementation method of the Internet of Things movable termination intelligent platform of data-oriented | |
CN107741899B (en) | Method, device and system for processing terminal data | |
CN115249331B (en) | Mine ecological safety identification method based on convolutional neural network model | |
CN110830807A (en) | Image compression method, device and storage medium | |
CN104320622A (en) | Embedded video enhancement system for open source server software | |
CN110599554A (en) | Method and device for identifying face skin color, storage medium and electronic device | |
CN111314707B (en) | Data mapping identification method, device and equipment and readable storage medium | |
CN111723772B (en) | Perishable garbage identification method and device based on image identification and computer equipment | |
CN111835836A (en) | Intelligent Internet of things terminal data processing device and method | |
CN114970899A (en) | Intelligent park operation and maintenance system, method, medium and electronic equipment | |
CN114996518A (en) | Ultra-high-definition video data storage and classification management system based on cloud platform | |
CN103106638A (en) | Graphic processing device for real-time image processing | |
CN112016380A (en) | Wild animal monitoring method and system | |
CN114241012A (en) | High-altitude parabolic determination method and device | |
CN110363075A (en) | Suspicious ill face detection system based on big data server | |
CN113657389A (en) | Software-defined satellite semantic segmentation method, device and medium | |
CN110414322B (en) | Method, device, equipment and storage medium for extracting picture | |
CN108600046B (en) | Equipment state monitoring terminal, system and method based on perceptual hash | |
CN104079860A (en) | Information processing method and electronic equipment | |
CN115223051A (en) | Satellite-borne optical remote sensing image target detection system | |
CN114549628A (en) | Power pole inclination detection method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170118 |