Summary of the invention
The main purpose of the present invention is to provide a kind of information fusion method, device and computer readable storage medium, purports
Solving the problems, such as that information effective rate of utilization is low.
To achieve the above object, the present invention provides a kind of information fusion method, the described method comprises the following steps:
The data volume of information transmission in current network is obtained, and determines whether the data volume is greater than preset threshold;
If the data volume is greater than preset threshold, information fusion is carried out using the first fusion mode;
If the data volume is less than or equal to the preset threshold, information fusion is carried out using the second fusion mode.
Preferably, described the step of carrying out information fusion using the first fusion mode, includes:
Each camera acquired image is obtained, and described image is pre-processed, to obtain pretreated figure
As information;
Described image information is uploaded to server, wherein server shares described image information to each camera,
Each camera obtains the information of interest in described image information;
Information fusion is carried out based on the information of interest.
Preferably, described and pre-process to described image, to obtain pretreated image information the step of includes:
Image perception is carried out to described image, demarcates and identifies target object;
The parameter information for obtaining the target object, using the parameter information as pretreated image information.
Preferably, described to pre-process to described image, to obtain pretreated image information the step of includes:
Acquired image is filtered according to preset condition, to obtain filtered described image information.
Preferably, described the step of carrying out information fusion using the second fusion mode, includes:
The collected raw image data of each camera is obtained, and the raw image data is uploaded to server;
Information fusion is carried out based on the raw image data, wherein the server divides the raw image data
It enjoys to each camera.
In addition, to achieve the above object, the present invention also provides a kind of information fuse device, the information fuse device packet
It includes:The information fusion program that memory, processor and being stored in can be run on the memory and on the processor, it is described
Information fusion program realizes following steps when being executed by the processor:
The data volume of information transmission in current network is obtained, and determines whether the data volume is greater than preset threshold;
If the data volume is greater than preset threshold, information fusion is carried out using the first fusion mode;
If the data volume is less than or equal to the preset threshold, information fusion is carried out using the second fusion mode.
Preferably, described the step of carrying out information fusion using the first fusion mode, includes:
Each camera acquired image is obtained, and described image is pre-processed, to obtain pretreated figure
As information;
Described image information is uploaded to server, wherein server shares described image information to each camera,
Each camera obtains the information of interest in described image information;
Information fusion is carried out based on the information of interest.
Preferably, described and pre-process to described image, to obtain pretreated image information the step of includes:
Image perception is carried out to described image, demarcates and identifies target object;
The parameter information for obtaining the target object, using the parameter information as pretreated image information.
Preferably, described to pre-process to described image, to obtain pretreated image information the step of includes:
Acquired image is filtered according to preset condition, to obtain filtered described image information.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Information fusion program is stored on storage medium, the information fusion program realizes following steps when being executed by processor:
The data volume of information transmission in current network is obtained, and determines whether the data volume is greater than preset threshold;
If the data volume is greater than preset threshold, information fusion is carried out using the first fusion mode;
If the data volume is less than or equal to the preset threshold, information fusion is carried out using the second fusion mode.
The present invention is by obtaining the data volume of information transmission in current network, and it is default to determine whether the data volume is greater than
Threshold value carries out information fusion using the first fusion mode if then the data volume is greater than preset threshold, if last described
When data volume is less than or equal to the preset threshold, then information fusion is carried out using the second fusion mode.The invention also discloses
A kind of information fuse device and computer readable storage medium.The present invention, which is realized, carries out information fusion using both of which, from
And can camera to more vehicles and road camera acquired image information make full use of, and then improve information
Effective rate of utilization.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, Fig. 1 be in hardware running environment that the embodiment of the present invention is related to belonging to information fuse device eventually
The structural schematic diagram at end.
The terminal of that embodiment of the invention can be PC.As shown in Figure 1, the terminal may include:Processor 1001, such as CPU,
Network interface 1004, user interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing this
Connection communication between a little components.User interface 1003 may include display screen (Display), input unit such as keyboard
(Keyboard), optional user interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 is optional
May include standard wireline interface and wireless interface (such as WI-FI interface).Memory 1005 can be high speed RAM memory,
It is also possible to stable memory (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally may be used also
To be independently of the storage device of aforementioned processor 1001.
Optionally, terminal can also include camera, RF (Radio Frequency, radio frequency) circuit, sensor, audio
Circuit, WiFi module etc..Wherein, sensor such as optical sensor, motion sensor and other sensors.Specifically, light
Sensor may include ambient light sensor and proximity sensor, wherein ambient light sensor can according to the light and shade of ambient light come
The brightness of display screen is adjusted, proximity sensor can close display screen and/or backlight when mobile terminal is moved in one's ear.As
One kind of motion sensor, gravity accelerometer can detect the size of (generally three axis) acceleration on direction, when static
Size and the direction that can detect that gravity can be used to identify application (such as the horizontal/vertical screen switching, related trip of mobile terminal posture
Play, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.;Certainly, mobile terminal can also configure
The other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, details are not described herein.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal structure shown in Fig. 1, can wrap
It includes than illustrating more or fewer components, perhaps combines certain components or different component layouts.
As shown in Figure 1, as may include operation server, network in a kind of memory 1005 of computer storage medium
Communication module, Subscriber Interface Module SIM and information merge program.
In terminal shown in Fig. 1, network interface 1004 is mainly used for connecting background server, carries out with background server
Data communication;User interface 1003 is mainly used for connecting client (user terminal), carries out data communication with client;And processor
1001 can be used for that the information stored in memory 1005 is called to merge program.
In the present embodiment, information fuse device includes:Memory 1005, processor 1001 and it is stored in the memory
On 1005 and can be run on the processor 1001 information fusion program, wherein processor 1001 call memory 1005
When the information of middle storage merges program, following operation is executed:
The data volume of information transmission in current network is obtained, and determines whether the data volume is greater than preset threshold;
If the data volume is greater than preset threshold, information fusion is carried out using the first fusion mode;
If the data volume is less than or equal to the preset threshold, information fusion is carried out using the second fusion mode.
Further, processor 1001 can call the information stored in memory 1005 to merge program, also execute following
Operation:
Each camera acquired image is obtained, and described image is pre-processed, to obtain pretreated figure
As information;
Described image information is uploaded to server, wherein server shares described image information to each camera,
Each camera obtains the information of interest in described image information;
Information fusion is carried out based on the information of interest.
Further, processor 1001 can call the information stored in memory 1005 to merge program, also execute following
Operation:
Image perception is carried out to described image, demarcates and identifies target object;
The parameter information for obtaining the target object, using the parameter information as pretreated image information.
Further, processor 1001 can call the information stored in memory 1005 to merge program, also execute following
Operation:
Acquired image is filtered according to preset condition, to obtain filtered described image information
Further, processor 1001 can call the information stored in memory 1005 to merge program, also execute following
Operation:
The collected raw image data of each camera is obtained, and the raw image data is uploaded to server;
Information fusion is carried out based on the raw image data, wherein the server divides the raw image data
It enjoys to each camera.
Based on above-mentioned hardware configuration, each embodiment of information fusion method of the present invention is proposed.
Referring to Fig. 2, information fusion method first embodiment of the present invention provides a kind of information fusion method, the information fusion
Method includes:
Step S10, obtains the data volume of information transmission in current network, and determines whether the data volume is greater than default threshold
Value;
In the present embodiment, image perception is carried out using distributed camera and information merges, between distributed camera
Information fusion include the information fusion between vehicle camera, the information fusion between road camera and vehicle camera with
Between road camera information fusion, wherein information fusion include both of which, the first mode be each camera respectively into
Target object and design parameter information are demarcated and identified to row image perception, and the image perceived is then passed through car networking point
Each camera or road monitoring camera are enjoyed, carries out information fusion for the information that each equipment oneself is most interested in, separately
One mode is that the raw image data that each camera takes directly is distributed sharing in car networking, and each equipment can be with
Directly acquire all detailed original images abundant to go forward side by side row information fusion, be compared to the first mode, second of mode because
For not too many information filtering, available more accurate and detailed fuse information, but can also greatly increase in network
The data volume for needing to transmit, so that bulk redundancy information waste bandwidth, energy consumption resource are caused, so, the present embodiment proposition is being believed
When breath fusion, the data volume of information in current network is detected first, and the data volume detected is judged, is judged
Whether the data volume that information is transmitted in current network information is greater than preset threshold, wherein preset threshold is by technical staff according to reality
Border situation and experiment are set.
Further, video camera is arranged in road roadside according to the landform of road in technical staff, for example, being arranged every 300 meters
One video camera, to guarantee that the field range of the video camera can cover comprehensively this section of road, so that video camera can
Collect the gamut image of this section of road.Network communication can be carried out between each camera, for example, vehicle camera and road
It can establish network communication between camera, then vehicle camera can directly acquire road camera acquired image number
According to, and information fusion is carried out according to the image data.
Step S20 carries out information fusion using the first fusion mode if the data volume is greater than preset threshold;
In the present embodiment, second of mode can be by vehicle camera and the collected original image number of road camera
According to server is sent to, information fusion is carried out for each equipment, so, when carrying out data transmission, required bandwidth and energy
Cost source will greatly increase, so, if the data volume for detecting that information is transmitted in current network is greater than preset threshold, use
The first mode carries out data fusion and specifically obtains each camera acquired image, and camera includes vehicle camera
And road camera, and image is pre-processed, which includes the collected unclear image of filtering camera, mistake
The image information etc. of the collected distant image of camera and filtering containing certain keyword is filtered, by pretreated image
Corresponding image information is sent to server, the image information that each equipment is needed according to respective requirement extract, for example, vehicle
Corresponding control equipment needs the road conditions of certain section of road conditions in front, then can be extracted according to keyword, coordinate etc. interested
Image information, and information fusion is carried out according to itself acquired image.
Step S30 carries out letter using the second fusion mode if the data volume is less than or equal to the preset threshold
Breath fusion.
In the present embodiment, the first mode first pre-processes image, has filtered out parts of images information, but mistake
There may be the valuable information datas that can carry out information fusion in the parts of images information filtered, so the first mode
It not can be carried out detailed fusion, so, if detecting, the data volume that information is transmitted in current network is less than or equal to preset threshold
When, then select second of information fusion mode to carry out information fusion, second of information fusion mode will acquire each camera and adopt
The equipment of the raw image data collected, each vehicle carries out information fusion according to raw image data.
The information fusion method that the present embodiment proposes by obtaining the data volume of information transmission in current network, and determines
Whether the data volume is greater than preset threshold, if then the data volume is greater than preset threshold, uses the first fusion mode
Information fusion is carried out, if the last data volume is less than or equal to the preset threshold, is carried out using the second fusion mode
Information fusion;It realizes and information fusion is carried out using both of which, so as to the camera and road camera to more vehicles
Acquired image information is made full use of, and then improves the effective rate of utilization of information.
Based on first embodiment, the second embodiment of information fusion method of the present invention is proposed, reference Fig. 3, in the present embodiment,
Step S20 includes:
Step S21 obtains each camera acquired image, and pre-processes to described image, to obtain pre- place
Image information after reason;
In the present embodiment, the pretreatment include to image carry out primary image processing, the image include photograph image and
Video image, video camera itself can realize image recognition algorithm, the three-dimensional extraction algorithm according to vision of insertion view-based access control model, know
Not Chu kind of object in video image, shape, location information, camera can carry out image recognition to image, for camera shooting
The image of head acquisition, after the primary images such as image transformation, noise reduction are handled, image recognition algorithm based on deep learning and
The three-dimensional extracting method of view-based access control model obtains the information such as kind of object in video flowing, general shape, position in real time, certainly, can also
To be identified by camera itself, corresponding object (such as vehicle) three-dimensional information is obtained according to itself scene library, and position to it
Tracking, obtains the image information of the object in image, which includes position, shape and the type etc. where object, example
Such as, the coordinate of the object.
Further, which further includes the collected unclear image of filtering camera, filters out camera and adopt
The distant image and filtering that collect do not contain the image information etc. of certain keyword, if camera is carrying out image information collecting
When, institute's acquired image is unclear, the object in image is distant, for example, not in detection zone or in image information
Without the image information etc. of certain keyword.
Described image information is uploaded to server, wherein server shares described image information to each by step S22
A camera, each camera obtain the information of interest in described image information;
Step S23 carries out information fusion based on the information of interest.
In the present embodiment, after each camera acquired image is pre-processed, by pretreated image information
It is uploaded to server, server can be by all pretreated image information analysis to each camera, each camera energy
It enough obtains itself information of interest and carries out information fusion, for example, there are barrier, camera shootings in road camera detection to certain road
Head is demarcated and is identified to the barrier, and the position coordinates, object type and size of the barrier are led to image analysis and are obtained,
And the image information for the barrier that will acquire is sent to server, when certain vehicle need to pass through the road, needing to obtain should
The corresponding road information of road, the road information are then information of interest, then are got according to the road camera of the road
Road information during obstacle information and current driving carries out information fusion, according to the coordinate position of current vehicle, traveling
State determines vehicle heading, speed, acceleration etc., so as to know that road ahead there are barrier, is avoided hindering in advance
Object is hindered to travel.
Information fusion method, device and the computer readable storage medium that the present embodiment proposes realize and obtain each take the photograph
As head acquired image, and described image is pre-processed, to obtain pretreated image information, then by the figure
As information is uploaded to server, wherein server shares described image information to each camera, and each camera obtains institute
The information of interest in image information is stated, information fusion is finally carried out based on the information of interest;It realizes first to image
It is pre-processed, then carries out information fusion further according to information of interest, reduce the data volume in network transmission, to reduce
The pressure of data transmission, accelerates data transmission efficiency, and then improves the efficiency of information fusion.
Based on second embodiment, the 3rd embodiment of information fusion method of the present invention is proposed, reference Fig. 4, in the present embodiment,
Step S21 includes:
Step S211 carries out image perception to described image, demarcates and identify target object;
Step S212 obtains the parameter information of the target object, using the parameter information as pretreated image
Information.
In the present embodiment, each camera acquired image is pre-processed, pretreatment includes carrying out figure to image
As perception, demarcates and identify target object, obtain the parameter information of target object, which includes the position of target object
Information, attribute information etc., the location information include the coordinate of target object, at a distance from vehicle etc., which includes mesh
Type, the shape etc. of object are marked, specifically, video camera itself can realize the image recognition algorithm of insertion view-based access control model, based on view
The three-dimensional extraction algorithm of feel identifies kind of object, shape, location information in video image.Certainly, according to image information
When carrying out information fusion, by obtained information data unification to unification world coordinate system, thus mark of the realization to target object
It is fixed.
The information fusion method that the present embodiment proposes is demarcated by carrying out image perception to described image and identifies target
Then object obtains the parameter information of the target object, using the parameter information as pretreated image information;It realizes
Target object is demarcated and is identified, so as to carry out information fusion to image information.
Based on second embodiment, the fourth embodiment of information fusion method of the present invention is proposed, in the present embodiment, step S21
Further include:
Acquired image is filtered by step S213 according to preset condition, to obtain filtered described image letter
Breath.
In the present embodiment, preset condition is configured by technical staff, and pixel, target object including image are in image
In position etc., the images such as fogging image, target object be unintelligible can be filtered out according to preset condition, for example, to acquisition
To the pixel of image analyzed, the pixel of image is calculated, and judge whether pixel is less than a certain threshold value, if image
Pixel is less than a certain threshold value, then it is assumed that the image is not uploaded to server then by the image filtering by the fogging image, also
Target object can be analyzed, if the feature of target object in image can not be extracted, then it is assumed that the target object is corresponding
Image is invalid image, also will filter out, is not uploaded to server.
The information fusion method that the present embodiment proposes, by the way that acquired image is filtered according to preset condition, with
Obtain filtered described image information;It realizes and acquired image is filtered, to filter out effective image, in turn
Invalid image information transmission bring bandwidth and the wasting of resources are avoided, the speed of data transmission has been further speeded up, has improved
The efficiency of information fusion.
Based on first embodiment, the 5th embodiment of information fusion method of the present invention is proposed, reference Fig. 5, in the present embodiment,
Step S20 further includes:
Step S24 obtains the collected raw image data of each camera, and the raw image data is uploaded to
Server;
Step S25 carries out information fusion based on the raw image data, wherein the server is by the original graph
As data sharing to each camera.
In the present embodiment, the first mode first pre-processes image, has filtered out parts of images information, but mistake
There may be the valuable information data that can carry out information fusion in the parts of images information filtered, the first mode cannot
It is merged in detail, so, if the data volume for detecting that information is transmitted in current network is less than or equal to preset threshold,
Second of information fusion mode is selected to carry out information fusion, it is collected that second of information fusion mode will acquire each camera
The equipment of raw image data, each vehicle carries out information fusion according to raw image data, and each camera is to collected
Raw image data is directly uploaded to server, server is again by the original graph without pretreatment by raw image data
As data sharing to each camera, to realize that each camera can get all image data progress information and melt
Close, can to Face datection, face tracking and identification, vehicle detection, vehicle tracking and identification, suspicious analyte detection, suspicious item with
Track and identification etc., for example, obtaining this when finding suspicious figure in the video in a camera and carrying out mesh to the suspicious figure
Mark not, carries out area-of-interest acquisition and Minutiae extraction, according to the minutia extracted in each of server share
Information fusion is carried out in a collected raw image data of camera can carry out to search and match target person to this
Target person carries out video tracking and extracts new feature, so that the characteristic information of target object is updated, the characteristic information that will be obtained
It is stored, each camera can obtain more accurate and detailed fuse information, improve the accuracy of information fusion.
The information fusion method that the present embodiment proposes, by obtaining each collected raw image data of camera, and
The raw image data is uploaded to server, the raw image data is then based on and carries out information fusion, wherein is described
Server shares the raw image data to each camera;It realizes and utilizes the collected original image of each camera
Data carry out information fusion, and extreme enrichment information content improves the accuracy of information fusion.
In addition, the embodiment of the present invention also proposes a kind of information fuse device.
The data volume of information transmission in current network is obtained, and determines whether the data volume is greater than preset threshold;
If the data volume is greater than preset threshold, information fusion is carried out using the first fusion mode;
If the data volume is less than or equal to the preset threshold, information fusion is carried out using the second fusion mode.
Further, following steps are also realized when the information fusion program is executed by the processor:
Each camera acquired image is obtained, and described image is pre-processed, to obtain pretreated figure
As information;
Described image information is uploaded to server, wherein server shares described image information to each camera,
Each camera obtains the information of interest in described image information;
Information fusion is carried out based on the information of interest.
Further, following steps are also realized when the information fusion program is executed by the processor:
Image perception is carried out to described image, demarcates and identifies target object;
The parameter information for obtaining the target object, using the parameter information as pretreated image information.
Further, following steps are also realized when the information fusion program is executed by the processor:
Acquired image is filtered according to preset condition, to obtain filtered described image information.
Wherein, the specific reality that the information fusion program stored in computer readable storage medium of the present invention is executed by processor
It applies example and each embodiment of above- mentioned information fusion method is essentially identical, therefore not to repeat here.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.