CN110362071A - Artificial Intelligence Control and device based on multi-optical spectrum imaging technology - Google Patents
Artificial Intelligence Control and device based on multi-optical spectrum imaging technology Download PDFInfo
- Publication number
- CN110362071A CN110362071A CN201910443489.2A CN201910443489A CN110362071A CN 110362071 A CN110362071 A CN 110362071A CN 201910443489 A CN201910443489 A CN 201910443489A CN 110362071 A CN110362071 A CN 110362071A
- Authority
- CN
- China
- Prior art keywords
- image information
- vehicle
- surrounding objects
- information
- image
- 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
- 238000001228 spectrum Methods 0.000 title claims abstract description 51
- 238000005516 engineering process Methods 0.000 title claims abstract description 47
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 41
- 238000003384 imaging method Methods 0.000 title claims abstract description 38
- 230000003287 optical effect Effects 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000012937 correction Methods 0.000 claims abstract description 7
- 230000010287 polarization Effects 0.000 claims description 38
- 230000008859 change Effects 0.000 claims description 37
- 230000007613 environmental effect Effects 0.000 claims description 16
- 230000003595 spectral effect Effects 0.000 claims description 12
- 230000008521 reorganization Effects 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 6
- 238000011897 real-time detection Methods 0.000 claims description 6
- 230000006798 recombination Effects 0.000 claims 1
- 238000005215 recombination Methods 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 13
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000000701 chemical imaging Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000011514 reflex Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0242—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using non-visible light signals, e.g. IR or UV signals
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0251—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a kind of Artificial Intelligence Control and device based on multi-optical spectrum imaging technology, this method comprises: emitting optical path to surrounding objects with predetermined angle；Reflected light path is handled to obtain the visible images of surrounding objects；It will be seen that the visible light image information that prestores of light image and surrounding objects compares, correction prestores the periphery object image information that the image information of other objects in visible light image information is corrected；Periphery object image information is projected to the real space position of surrounding objects；The rotating image information of periphery object image information and surrounding objects is merged to the image information projected after processing；Obtain vehicle current driving status and surrounding enviroment information；By the current driving status of vehicle and surrounding enviroment information and preset vehicle driving strategy comparison control vehicle automatic running.The present invention can accurately obtain the real-time image information of vehicle-surroundings environment, and then Vehicular intelligent control analysis real-time image information is combined to carry out automatic Pilot.
Description
Technical field
This application involves the technical field of intelligent control more particularly to a kind of artificial intelligence based on multi-optical spectrum imaging technology
Control method and device.
Background technique
Vehicle already becomes the important vehicles of modern people's life, provides greatly for the life and work of people
Convenience.But everyone driving technology is not identical, in addition road vehicles situation is also more and more multiple as vehicle is more and more
It is miscellaneous, rely solely on the purpose that driver's subjective judgement is extremely difficult to safety and comfort driving.Therefore, automatic Pilot technology becomes row
The key issues studied in the industry, automatic Pilot, also known as pilotless automobile, computer driving or wheeled mobile robot are
One kind realizing unpiloted intelligent driving technology by computer system.
The control of Vehicular automatic driving is dependent on the monitoring system to vehicle driving surrounding enviroment, by vehicle-surroundings ring
The accurate measurements in border realize the automatic Pilot of vehicle in conjunction with intelligent control technology.Normally, environmental monitoring system generally includes to take the photograph
Camera, millimetre-wave radar and other various sensors, wherein video camera for shoot surrounding enviroment for vehicle control center into
Row analysis.But single camera can only obtain the image information of vehicle-surroundings two-dimensional space in existing environmental monitoring system,
Image information only by two-dimensional space is the driving condition that cannot accurately obtain vehicle-surroundings.It can only be by sensing more
The environmental aspect of the available vehicle-surroundings of device combined application, is otherwise difficult to ensure accurately controlling for vehicle, but multiple sensings
It is complicated that device combined application makes vehicle structure, and cannot neatly cope with the case where different vehicle running environment converts, reliable steady
Qualitative difference, the time difference that multi sensor combination obtains vehicle-surroundings environment is not easy to control, and it is different surely true to obtain each image
Ground reacts the real-time status situation of vehicle, will cause the security risk of control.
Therefore, how to provide that a kind of structure is simple, accuracy is strong and the scheme of reliable and stable automatic Pilot is this field
Technical problem urgently to be resolved.
Summary of the invention
The application's is designed to provide a kind of Artificial Intelligence Control and device based on multi-optical spectrum imaging technology, solution
Certainly the three-dimensional spatial information of vehicle-surroundings environment cannot be accurately obtained in automatic Pilot in the prior art, and then can not achieve standard
The technical issues of true ground automatic Pilot.
In order to achieve the above objectives, the application provides a kind of Artificial Intelligence Control based on multi-optical spectrum imaging technology, packet
It includes:
Optical path is emitted to surrounding objects with predetermined angle in real time by light source；
The reflected light path that the transmitting optical path is reflected through the surrounding objects is received, by the reflected light path through semi-transparent reflection
Mirror handles to obtain the visible images of the surrounding objects；
The visible light image information that prestores of the visible images and the surrounding objects is compared, according to the visible light
Picture position mapping relations between surrounding objects described in image and other objects prestore visible light image information described in correction
In other objects the periphery object image information that is corrected of image information；
Partial mirror transmitting projecting light path is penetrated, the periphery object image information is projected to the ambient
The real space position of body obtains space projection image；
With the polarization direction of the emergent light of light source described in preset angulation change, the rotating image of the surrounding objects is obtained
Information；
It is obtained after the rotating image information of the periphery object image information and the surrounding objects is merged processing
The differential image information of the surrounding objects, by the corresponding projection of the differential image information of the surrounding objects to the space projection
The image information that image is projected；
Projected image information, which is analyzed, using image reorganization obtains the surrounding objects more than or equal to two spectrum
The spatial image information of section or the spectral distribution information of each pixel, based on to the surrounding objects spatial image information or often
The spectral distribution information of a pixel obtains the current driving status and surrounding enviroment information of vehicle；
The current driving status of the vehicle and surrounding enviroment information and preset vehicle driving strategy are compared, institute is obtained
The traveling control instruction of vehicle is stated, and the vehicle automatic running is controlled with the traveling control instruction.
Optionally, wherein with the polarization direction of the emergent light of light source described in preset angulation change, obtain the ambient
The rotating image information of body, are as follows:
The visible images for analyzing the surrounding objects obtain the ambient condition letter that the surrounding objects are presently in
Breath, according to the corresponding relationship of the environmental state information and preset ambient condition and polarization direction change angle obtain it is described go out
Penetrate the change angle of the polarization direction of light；
With the polarization direction of the emergent light of light source described in the change angulation change, the rotation figure of the surrounding objects is obtained
As information.
Optionally, wherein close the periphery object image information and the rotating image information of the surrounding objects
And the differential image information of the surrounding objects is obtained after handling, extremely by the corresponding projection of the differential image information of the surrounding objects
The real space position of the surrounding objects, are as follows:
It carries out the rotating image information of the periphery object image information and the surrounding objects to subtract each other processing and obtains difference
Different image information, by the corresponding projection of the differential image information of the surrounding objects to the real space position of the surrounding objects.
Optionally, wherein this method further include:
The image information of the projection is showed centered on the position of current vehicle, and is showed in institute's projected image
Location information between each object and the vehicle；
When the distance between objects in images and the vehicle reach or are less than preset distance threshold, according to vehicle
Apart from the driving direction of adjustable strategies adjust automatically vehicle between object.
Optionally, wherein this method further include:
The location information of vehicle described in real-time detection, by the image information of the obtained projection and the location information of vehicle
Corresponding storage obtains the projected image library of vehicle driving；
When other vehicle drivings to current position, the image information of the projection is transferred from the projected image library
Traveling projected image as the vehicle.
On the other hand, the present invention also provides a kind of artificial intelligence control device based on multi-optical spectrum imaging technology, comprising: light
Road transmitter, visible images receiver, periphery object image information analyzer, projected image processor, vehicle running state
Analyzer and vehicle travel controller；Wherein,
The optical path transmitter is connected, by light source in real time with predetermined angle with the visible images receiver
Emit optical path to surrounding objects；
The visible images receiver is connected with the optical path transmitter and periphery object image information analyzer,
The reflected light path that the transmitting optical path is reflected through the surrounding objects is received, the reflected light path is handled through partial mirror
To the visible images of the surrounding objects；
The periphery object image information analyzer is connected with the visible images receiver and projected image processor
It connects, the visible light image information that prestores of the visible images and the surrounding objects is compared, according to the visible images
Described in picture position mapping relations between surrounding objects and other objects, prestore in visible light image information described in correction
The periphery object image information that the image information of other objects is corrected；
The projected image processor, with the periphery object image information analyzer and vehicle running state analyzer phase
Connection penetrates partial mirror transmitting projecting light path, the periphery object image information is projected to the surrounding objects
Real space position obtain space projection image；
With the polarization direction of the emergent light of light source described in preset angulation change, the rotating image of the surrounding objects is obtained
Information；
It is obtained after the rotating image information of the periphery object image information and the surrounding objects is merged processing
The differential image information of the surrounding objects, by the corresponding projection of the differential image information of the surrounding objects to the space projection
The image information that image is projected；
The vehicle running state analyzer is connected with the projected image processor and vehicle travel controller, benefit
Projected image information, which is analyzed, with image reorganization obtains the surrounding objects in the space diagram for being greater than or equal to two spectrum segment
As information or the spectral distribution information of each pixel, based on to the surrounding objects spatial image information or each pixel
Spectral distribution information obtains the current driving status and surrounding enviroment information of vehicle；
The vehicle travel controller is connected with the vehicle running state analyzer, by the current row of the vehicle
It sails state and surrounding enviroment information and preset vehicle driving strategy compares, obtain the traveling control instruction of the vehicle, and with
The traveling control instruction controls the vehicle automatic running.
Optionally, wherein the projected image processor penetrates partial mirror transmitting projecting light path, will
The periphery object image information projects to the real space position of the surrounding objects and obtains space projection image；
The visible images for analyzing the surrounding objects obtain the ambient condition letter that the surrounding objects are presently in
Breath, according to the corresponding relationship of the environmental state information and preset ambient condition and polarization direction change angle obtain it is described go out
Penetrate the change angle of the polarization direction of light；
With the polarization direction of the emergent light of light source described in the change angulation change, the rotation figure of the surrounding objects is obtained
As information；
It is obtained after the rotating image information of the periphery object image information and the surrounding objects is merged processing
The differential image information of the surrounding objects, by the corresponding projection of the differential image information of the surrounding objects to the space projection
The image information that image is projected.
Optionally, wherein the projected image processor penetrates partial mirror transmitting projecting light path, will
The periphery object image information projects to the real space position of the surrounding objects and obtains space projection image；
With the polarization direction of the emergent light of light source described in preset angulation change, the rotating image of the surrounding objects is obtained
Information；
It carries out the rotating image information of the periphery object image information and the surrounding objects to subtract each other processing and obtains difference
Different image information, by the corresponding projection of the differential image information of the surrounding objects to the real space position of the surrounding objects.
Optionally, wherein the system further include: vehicle heading adjuster is connected with the vehicle travel controller
It connects, the image information of the projection is showed centered on the position of current vehicle, and show each in institute's projected image
Location information between object and the vehicle；
When the distance between objects in images and the vehicle reach or are less than preset distance threshold, according to vehicle
Apart from the driving direction of adjustable strategies adjust automatically vehicle between object.
Optionally, wherein the system further include: multispectral projected image memory, with the projected image processor phase
It connects, the location information of vehicle described in real-time detection, by the image information of the obtained projection and the location information pair of vehicle
It should store to obtain the projected image library of vehicle driving；
When other vehicle drivings to current position, the image information of the projection is transferred from the projected image library
Traveling projected image as the vehicle.
The Artificial Intelligence Control and device based on multi-optical spectrum imaging technology of the application, the beneficial effect of realization is such as
Under:
(1) Artificial Intelligence Control and device based on multi-optical spectrum imaging technology of the application is based on multispectral camera shooting
The three-dimensional image information of acquisition vehicle surrounding enviroment in real time, the spatial image information of any spectrum segment is obtained in conjunction with image reorganization,
The real-time image information of vehicle-surroundings environment can be accurately obtained, and then combines Vehicular intelligent control analysis real-time image information
Automatic Pilot is carried out, has achieved the purpose that accurate, stable automatic Pilot.
(2) Artificial Intelligence Control and device based on multi-optical spectrum imaging technology of the application, utilizes two kinds of acquisition
The infrared image of the vehicle-surroundings environmental information of different polarization angle, and in computing systems subtract each other the two, by the difference of acquisition
Different image information is directly projected on realistic space or object with visible light, or projects to realistic space or object for correcting
On other images, obtaining inside of human body tissue implies the head-on reflection of infrared ray and irreflexive image difference
Important image information improves the accuracy of acquired vehicle-surroundings environmental information, automatic Pilot control based on this
Also the vision that people can be better adapted to, improves the comfort of automatic Pilot.
(3) Artificial Intelligence Control and device based on multi-optical spectrum imaging technology of the application, to some familiar things
The outgoing light polarization direction of spectrum camera shooting corresponding angle is set, can accurately and rapidly obtain the image letter of familiar things
Breath, while the study memory mechanism to not familiar things outgoing light polarization direction is also set up, further improve automatic Pilot
Accuracy and precision.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application can also be obtained according to these attached drawings other attached for those skilled in the art
Figure.
Fig. 1 is a kind of process signal of the Artificial Intelligence Control based on multi-optical spectrum imaging technology in the embodiment of the present invention
Figure；
Fig. 2 is that the process of Artificial Intelligence Control of the another kind based on multi-optical spectrum imaging technology in the embodiment of the present invention is shown
It is intended to；
Fig. 3 is that the process of another Artificial Intelligence Control based on multi-optical spectrum imaging technology in the embodiment of the present invention is shown
It is intended to；
Fig. 4 is that the process of another Artificial Intelligence Control based on multi-optical spectrum imaging technology in the embodiment of the present invention is shown
It is intended to；
Fig. 5 is that the process of another Artificial Intelligence Control based on multi-optical spectrum imaging technology in the embodiment of the present invention is shown
It is intended to；
Fig. 6 is a kind of structural representation of the artificial intelligence control device based on multi-optical spectrum imaging technology in the embodiment of the present invention
Figure；
Fig. 7 is that the structure of artificial intelligence control device of the another kind based on multi-optical spectrum imaging technology in the embodiment of the present invention is shown
It is intended to；
Fig. 8 is the signal of another artificial intelligence control device based on multi-optical spectrum imaging technology in the embodiment of the present invention
Figure.
Specific embodiment
Below with reference to the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Ground description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on the application
In embodiment, those skilled in the art's every other embodiment obtained without making creative work, all
Belong to the range of the application protection.
Embodiment
As shown in Figure 1, for a kind of process of the Artificial Intelligence Control based on multi-optical spectrum imaging technology in the present embodiment
Schematic diagram.The three-dimensional image information of acquisition vehicle surrounding enviroment in real time, the space diagram of any spectrum segment is obtained in conjunction with image reorganization
As information, the real-time image information of vehicle-surroundings environment can be accurately obtained, and then combines Vehicular intelligent control analysis real-time
Image information carries out automatic Pilot.This method comprises the following steps:
Step 101 emits optical path to surrounding objects with predetermined angle in real time by light source.
Step 102, surrounding objects receive transmitting light, reflect to form reflected light for light is emitted by oneself reflex
Road.
Step 103 receives the reflected light path that reflects through surrounding objects of transmitting optical path, by reflected light path through partial mirror at
Reason obtains the visible images of surrounding objects.
Step 104 will be seen that the visible light image information that prestores of light image and surrounding objects compares, according to visible images
Picture position mapping relations between middle surrounding objects and other objects, correction prestore other objects in visible light image information
The periphery object image information that is corrected of image information.
Step 105 penetrates partial mirror transmitting projecting light path, and periphery object image information is projected to surrounding objects
Real space position obtains space projection image.
Step 106, with the polarization direction of the emergent light of preset angulation change light source, obtain the rotating image of surrounding objects
Information.
Step 107 obtains after the rotating image information of periphery object image information and surrounding objects is merged processing
The differential image information of surrounding objects is projected the corresponding projection of the differential image information of surrounding objects to space projection image
Image information.
Step 108 analyzes projected image information acquisition surrounding objects more than or equal to two using image reorganization
The spectral distribution information of the spatial image information of spectrum segment or each pixel, based on to surrounding objects spatial image information or often
The spectral distribution information of a pixel obtains the current driving status and surrounding enviroment information of vehicle.
In the present embodiment, two kinds of different polarization angles can be obtained by rotation polaroid or the polarization angle of light source
Multispectral infrared image, the two is handled into (subtracting each other) in computer systems, the two is subtracted each other and by figure after treatment
Picture is projected directly on real space or object, or the information for being included with subtraction image strengthens the image of other classes
Or abundant processing.In other words, in order to obtain inside of human body tissue for the head-on reflection and irreflexive image difference of infrared ray
The important image letter that imply, obtains differential image information and is directly projected with visible light to realistic space or object, is used to
Amendment projects to other images on realistic space or object.The spatial image of any spectrum segment is obtained using image reorganization technology
The spectral distribution information of information or any pixel.Spatial image information and spectral distribution information of the vehicle control center to acquisition
It is handled, in conjunction with the i.e. exportable control instruction to Vehicular automatic driving of the current vehicle condition obtained from vehicle ECU.
Step 109 compares the current driving status of vehicle and surrounding enviroment information and preset vehicle driving strategy, obtains
To the traveling control instruction of vehicle, and to travel control instruction control vehicle automatic running.
It in some alternative embodiments, as depicted in figs. 1 and 2, is that multi-optical spectrum imaging technology is separately based in the present embodiment
Artificial Intelligence Control flow diagram.Fig. 2 is unlike Fig. 1, step 106, with preset angulation change light
The polarization direction of the emergent light in source obtains the rotating image information of surrounding objects, are as follows:
Step 201, the visible images for analyzing surrounding objects obtain the environmental state information that surrounding objects are presently in, root
The polarization side of emergent light is obtained according to the corresponding relationship of environmental state information and preset ambient condition and polarization direction change angle
To change angle.
The polarization direction of step 202, emergent light to change angulation change light source obtains the rotating image letter of surrounding objects
Breath.
In some alternative embodiments, as shown in figures 1 and 3, multispectral imaging is based on for another in the present embodiment
The flow diagram of the Artificial Intelligence Control of technology.Fig. 3 is unlike Fig. 1, step 107, by periphery subject image
Information and the rotating image information of surrounding objects obtain the differential image information of surrounding objects after merging processing, by ambient
The differential image information of body is corresponding to be projected to the real space position of surrounding objects, are as follows:
Step 301 carries out the rotating image information of periphery object image information and surrounding objects to subtract each other processing and obtains difference
Different image information.
The differential image information of surrounding objects is corresponded to projection to the real space position of surrounding objects by step 302.
In some alternative embodiments, as shown in Figure 1 and Figure 4, multispectral imaging is based on for another in the present embodiment
The flow diagram of the Artificial Intelligence Control of technology.Fig. 4 is unlike Fig. 1, further includes:
Step 401 shows the image information of projection centered on the position of current vehicle, and shows institute's perspective view
Location information as between each object and vehicle.
Step 402, when the distance between objects in images and vehicle reach or be less than preset distance threshold when, according to
Apart from the driving direction of adjustable strategies adjust automatically vehicle between vehicle and object.
In some alternative embodiments, as shown in Figure 1 and Figure 5, multispectral imaging is based on for another in the present embodiment
The flow diagram of the Artificial Intelligence Control of technology.Fig. 5 is unlike Fig. 1, further includes:
The location information of step 501, real-time detection vehicle, by the image information of obtained projection and the location information of vehicle
Corresponding storage obtains the projected image library of vehicle driving.
Step 502, when other vehicle drivings to current position, the image information of projection is transferred from projected image library
Traveling projected image as the vehicle.
Fig. 6 is a kind of structural representation of the artificial intelligence control device 600 based on multi-optical spectrum imaging technology in the present embodiment
Figure, the method which is used to implement the above-mentioned automatic Pilot based on multispectral camera shooting, which includes: optical path transmitter
601, visible images receiver 602, periphery object image information analyzer 603, projected image processor 604, vehicle driving
State analyzer 605 and vehicle travel controller 606.
Wherein, optical path transmitter 601 is connected with visible images receiver 602, by light source in real time with preset angle
It spends to surrounding objects and emits optical path.
Visible images receiver 602 is connected with optical path transmitter 601 and periphery object image information analyzer 603,
The reflected light path that transmitting optical path is reflected through surrounding objects is received, reflected light path is handled to obtain surrounding objects through partial mirror
Visible images.
Periphery object image information analyzer 603, with 604 phase of visible images receiver 602 and projected image processor
Connection, it will be seen that the visible light image information that prestores of light image and surrounding objects compares, according to surrounding objects in visible images
Picture position mapping relations between other objects, correction prestore the image information of other objects in visible light image information
The periphery object image information corrected.
Projected image processor 604, with periphery object image information analyzer 603 and vehicle running state analyzer 605
It is connected, penetrates partial mirror transmitting projecting light path, periphery object image information is projected to the real space of surrounding objects
Position obtains space projection image；With the polarization direction of the emergent light of preset angulation change light source, turning for surrounding objects is obtained
Moving picture information；Ambient is obtained after the rotating image information of periphery object image information and surrounding objects is merged processing
The differential image information of body, the image that the corresponding projection of the differential image information of surrounding objects is projected to space projection image
Information.
Optionally, wherein projected image processor can also penetrate partial mirror transmitting projecting light path, by periphery object
The real space position of body visual information projection to surrounding objects obtains space projection image；
The visible images of analysis surrounding objects obtain the environmental state information that surrounding objects are presently in, according to environment shape
State information and preset ambient condition and the corresponding relationship of polarization direction change angle obtain the change of the polarization direction of emergent light
Angle；
To change the polarization direction of the emergent light of angulation change light source, the rotating image information of surrounding objects is obtained；It will be all
Side object image information and the rotating image information of surrounding objects obtain the differential image letter of surrounding objects after merging processing
Breath, the image information that the corresponding projection of the differential image information of surrounding objects is projected to space projection image.
Optionally, wherein projected image processor can also penetrate partial mirror transmitting projecting light path, by periphery object
The real space position of body visual information projection to surrounding objects obtains space projection image；
With the polarization direction of the emergent light of preset angulation change light source, the rotating image information of surrounding objects is obtained；It will
Periphery object image information and the rotating image information of surrounding objects, which carry out subtracting each other processing, obtains differential image information, by ambient
The differential image information of body is corresponding to be projected to the real space position of surrounding objects.
Vehicle running state analyzer 605 is connected with projected image processor 604 and vehicle travel controller 606, benefit
Projected image information, which is analyzed, with image reorganization obtains surrounding objects in the spatial image letter for being greater than or equal to two spectrum segments
The spectral distribution information of breath or each pixel, based on the spatial distribution to surrounding objects spatial image information or each pixel
The current driving status of acquisition of information vehicle and surrounding enviroment information.
Vehicle travel controller 606 is connected with vehicle running state analyzer 605, by the current driving status of vehicle
And surrounding enviroment information and preset vehicle driving strategy compare, and obtain the traveling control instruction of vehicle, and refer to traveling control
Enable control vehicle automatic running.
In some alternative embodiments, as shown in fig. 7, being another kind in the present embodiment based on multi-optical spectrum imaging technology
The structural schematic diagram of artificial intelligence control device 700, unlike Fig. 6, further includes: vehicle heading adjuster 701, with
Vehicle travel controller 606 is connected, and the image information of projection is showed centered on the position of current vehicle, and shows
Location information in institute's projected image between each object and vehicle；Reach when the distance between objects in images and vehicle or
When less than preset distance threshold, according to the driving direction between vehicle and object apart from adjustable strategies adjust automatically vehicle.
In some alternative embodiments, as shown in figure 8, being another kind in the present embodiment based on multi-optical spectrum imaging technology
The structural schematic diagram of artificial intelligence control device 800, unlike Fig. 6, further includes: multispectral projected image memory 801,
It is connected with projected image processor 604, the location information of real-time detection vehicle, by the image information and vehicle of obtained projection
The corresponding storage of location information obtain the projected image library of vehicle driving；When other vehicle drivings to current position, from throwing
Traveling projected image of the image information as the vehicle of projection is transferred in shadow image library.
The beneficial effect that Artificial Intelligence Control and device in the present embodiment based on multi-optical spectrum imaging technology are realized is such as
Under:
(1) Artificial Intelligence Control and device based on multi-optical spectrum imaging technology of the application is based on multispectral camera shooting
The three-dimensional image information of acquisition vehicle surrounding enviroment in real time, the spatial image information of any spectrum segment is obtained in conjunction with image reorganization,
The real-time image information of vehicle-surroundings environment can be accurately obtained, and then combines Vehicular intelligent control analysis real-time image information
Automatic Pilot is carried out, has achieved the purpose that accurate, stable automatic Pilot.
(2) Artificial Intelligence Control and device based on multi-optical spectrum imaging technology of the application, utilizes two kinds of acquisition
The infrared image of the vehicle-surroundings environmental information of different polarization angle, and in computing systems subtract each other the two, by the difference of acquisition
Different image information is directly projected on realistic space or object with visible light, or projects to realistic space or object for correcting
On other images, obtaining inside of human body tissue implies the head-on reflection of infrared ray and irreflexive image difference
Important image information improves the accuracy of acquired vehicle-surroundings environmental information, automatic Pilot control based on this
Also the vision that people can be better adapted to, improves the comfort of automatic Pilot.
(3) Artificial Intelligence Control and device based on multi-optical spectrum imaging technology of the application, to some familiar things
The outgoing light polarization direction of spectrum camera shooting corresponding angle is set, can accurately and rapidly obtain the image letter of familiar things
Breath, while the study memory mechanism to not familiar things outgoing light polarization direction is also set up, further improve automatic Pilot
Accuracy and precision.
Although the preferred embodiment of the application has been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the application range.Obviously, those skilled in the art can be to the application
Various modification and variations are carried out without departing from spirit and scope.If in this way, these modifications and variations of the application
Belong within the scope of the claim of this application and its equivalent technologies, then the application is also intended to encompass these modification and variations and exists
It is interior.
Claims (10)
1. a kind of Artificial Intelligence Control based on multi-optical spectrum imaging technology characterized by comprising
Optical path is emitted to surrounding objects with predetermined angle in real time by light source；
Receive the reflected light path that reflects through the surrounding objects of transmitting optical path, by the reflected light path through partial mirror at
Reason obtains the visible images of the surrounding objects；
The visible light image information that prestores of the visible images and the surrounding objects is compared, according to the visible images
Described in picture position mapping relations between surrounding objects and other objects, prestore in visible light image information described in correction
The periphery object image information that the image information of other objects is corrected；
Partial mirror transmitting projecting light path is penetrated, the periphery object image information is projected to the surrounding objects
Real space position obtains space projection image；
With the polarization direction of the emergent light of light source described in preset angulation change, the rotating image letter of the surrounding objects is obtained
Breath；
The rotating image information of the periphery object image information and the surrounding objects is merged described in being obtained after handling
The differential image information of surrounding objects, by the corresponding projection of the differential image information of the surrounding objects to the space projection image
The image information projected；
The surrounding objects, which are obtained, using the projected image information of image reorganization analysis is being greater than or equal to two spectrum segments
The spectral distribution information of spatial image information or each pixel, based on to the surrounding objects spatial image information or each picture
The spectral distribution information of vegetarian refreshments obtains the current driving status and surrounding enviroment information of vehicle；
The current driving status of the vehicle and surrounding enviroment information and preset vehicle driving strategy are compared, the vehicle is obtained
Traveling control instruction, and the vehicle automatic running is controlled with the traveling control instruction.
2. the Artificial Intelligence Control according to claim 1 based on multi-optical spectrum imaging technology, which is characterized in that with pre-
If angulation change described in light source emergent light polarization direction, obtain the rotating image information of the surrounding objects, are as follows:
The visible images for analyzing the surrounding objects obtain the environmental state information that the surrounding objects are presently in, root
The emergent light is obtained according to the corresponding relationship of the environmental state information and preset ambient condition and polarization direction change angle
Polarization direction change angle；
With the polarization direction of the emergent light of light source described in the change angulation change, the rotating image letter of the surrounding objects is obtained
Breath.
3. the Artificial Intelligence Control according to claim 1 based on multi-optical spectrum imaging technology, which is characterized in that by institute
State periphery object image information and the surrounding objects rotating image information merge processing after obtain the surrounding objects
Differential image information, by the corresponding projection of the differential image information of the surrounding objects to the real space position of the surrounding objects
It sets, are as follows:
It carries out the rotating image information of the periphery object image information and the surrounding objects to subtract each other processing and obtains disparity map
As information, by the corresponding projection of the differential image information of the surrounding objects to the real space position of the surrounding objects.
4. the Artificial Intelligence Control according to claim 1 based on multi-optical spectrum imaging technology, which is characterized in that also wrap
It includes:
The image information of the projection is showed centered on the position of current vehicle, and is showed each in institute's projected image
Location information between object and the vehicle；
When the distance between objects in images and the vehicle reach or are less than preset distance threshold, according to vehicle and object
Apart from the driving direction of adjustable strategies adjust automatically vehicle between body.
5. the Artificial Intelligence Control according to claim 1 based on multi-optical spectrum imaging technology, which is characterized in that also wrap
It includes:
The location information of vehicle described in real-time detection, the location information of the image information of the obtained projection and vehicle is corresponding
Storage obtains the projected image library of vehicle driving；
When other vehicle drivings to current position, the image information conduct of the projection is transferred from the projected image library
The traveling projected image of the vehicle.
6. a kind of artificial intelligence control device based on multi-optical spectrum imaging technology characterized by comprising optical path transmitter, can
Light-exposed picture receiver, periphery object image information analyzer, projected image processor, vehicle running state analyzer and vehicle
Travel controller；Wherein,
The optical path transmitter is connected with the visible images receiver, by light source in real time with predetermined angle to week
Enclose object emission optical path；
The visible images receiver is connected with the optical path transmitter and periphery object image information analyzer, receives
The reflected light path that the transmitting optical path is reflected through the surrounding objects, the reflected light path is handled to obtain institute through partial mirror
State the visible images of surrounding objects；
The periphery object image information analyzer is connected with the visible images receiver and projected image processor,
The visible light image information that prestores of the visible images and the surrounding objects is compared, according to institute in the visible images
The picture position mapping relations between surrounding objects and other objects are stated, are prestored described in correction described in visible light image information
The periphery object image information that the image information of other objects is corrected；
The projected image processor is connected with the periphery object image information analyzer and vehicle running state analyzer
It connects, penetrates partial mirror transmitting projecting light path, the periphery object image information is projected to the surrounding objects
Real space position obtains space projection image；
With the polarization direction of the emergent light of light source described in preset angulation change, the rotating image letter of the surrounding objects is obtained
Breath；
The rotating image information of the periphery object image information and the surrounding objects is merged described in being obtained after handling
The differential image information of surrounding objects, by the corresponding projection of the differential image information of the surrounding objects to the space projection image
The image information projected；
The vehicle running state analyzer is connected with the projected image processor and vehicle travel controller, utilizes figure
The image information projected as recombination analysis obtains the surrounding objects in the spatial image letter for being greater than or equal to two spectrum segments
The spectral distribution information of breath or each pixel, based on the spectrum to the surrounding objects spatial image information or each pixel
Distributed intelligence obtains the current driving status and surrounding enviroment information of vehicle；
The vehicle travel controller is connected with the vehicle running state analyzer, by the current traveling shape of the vehicle
State and surrounding enviroment information and preset vehicle driving strategy compare, and obtain the traveling control instruction of the vehicle, and with described
It travels control instruction and controls the vehicle automatic running.
7. the artificial intelligence control device according to claim 6 based on multi-optical spectrum imaging technology, which is characterized in that described
The projected image processor penetrates partial mirror transmitting projecting light path, the periphery object image information is projected
Space projection image is obtained to the real space position of the surrounding objects；
The visible images for analyzing the surrounding objects obtain the environmental state information that the surrounding objects are presently in, root
The emergent light is obtained according to the corresponding relationship of the environmental state information and preset ambient condition and polarization direction change angle
Polarization direction change angle；
With the polarization direction of the emergent light of light source described in the change angulation change, the rotating image letter of the surrounding objects is obtained
Breath；
The rotating image information of the periphery object image information and the surrounding objects is merged described in being obtained after handling
The differential image information of surrounding objects, by the corresponding projection of the differential image information of the surrounding objects to the space projection image
The image information projected.
8. the artificial intelligence control device according to claim 6 based on multi-optical spectrum imaging technology, which is characterized in that described
The projected image processor penetrates partial mirror transmitting projecting light path, the periphery object image information is projected
Space projection image is obtained to the real space position of the surrounding objects；
With the polarization direction of the emergent light of light source described in preset angulation change, the rotating image letter of the surrounding objects is obtained
Breath；
It carries out the rotating image information of the periphery object image information and the surrounding objects to subtract each other processing and obtains disparity map
As information, by the corresponding projection of the differential image information of the surrounding objects to the real space position of the surrounding objects.
9. the artificial intelligence control device according to claim 6 based on multi-optical spectrum imaging technology, which is characterized in that also wrap
Include: vehicle heading adjuster is connected with the vehicle travel controller, by the image information of the projection to work as front truck
Position centered on showed, and show the location information in institute's projected image between each object and the vehicle；
When the distance between objects in images and the vehicle reach or are less than preset distance threshold, according to vehicle and object
Apart from the driving direction of adjustable strategies adjust automatically vehicle between body.
10. the artificial intelligence control device according to claim 6 based on multi-optical spectrum imaging technology, which is characterized in that also
Include: multispectral projected image memory, is connected with the projected image processor, the position letter of vehicle described in real-time detection
The corresponding storage of the location information of the image information of the obtained projection and vehicle is obtained the projected image of vehicle driving by breath
Library；
When other vehicle drivings to current position, the image information conduct of the projection is transferred from the projected image library
The traveling projected image of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910443489.2A CN110362071B (en) | 2019-05-24 | 2019-05-24 | Artificial intelligence control method and device based on multispectral imaging technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910443489.2A CN110362071B (en) | 2019-05-24 | 2019-05-24 | Artificial intelligence control method and device based on multispectral imaging technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110362071A true CN110362071A (en) | 2019-10-22 |
| CN110362071B CN110362071B (en) | 2022-07-22 |
Family
ID=68215271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910443489.2A Active CN110362071B (en) | 2019-05-24 | 2019-05-24 | Artificial intelligence control method and device based on multispectral imaging technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110362071B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111427331A (en) * | 2020-03-24 | 2020-07-17 | 新石器慧通（北京）科技有限公司 | Perception information display method and device of unmanned vehicle and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101107556A (en) * | 2005-02-11 | 2008-01-16 | 宝马股份公司 | Method and device for visualising the surroundings of a vehicle by merging an infrared image and a visual image |
| CN102013174A (en) * | 2010-11-18 | 2011-04-13 | 华东理工大学 | Vehicle collision warning system based on optical communication |
| CN102745135A (en) * | 2012-07-24 | 2012-10-24 | 苏州工业园区七星电子有限公司 | Active vehicle infrared night vision system |
| US20170270375A1 (en) * | 2014-12-07 | 2017-09-21 | Brightway Vision, Ltd. | Object Detection Enhancement of Reflection-Based Imaging Unit |
| CN107411706A (en) * | 2017-04-07 | 2017-12-01 | 展谱光电科技（上海）有限公司 | Multispectral projection arrangement and projecting method, multispectral camera device and image capture method |
-
2019
- 2019-05-24 CN CN201910443489.2A patent/CN110362071B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101107556A (en) * | 2005-02-11 | 2008-01-16 | 宝马股份公司 | Method and device for visualising the surroundings of a vehicle by merging an infrared image and a visual image |
| CN102013174A (en) * | 2010-11-18 | 2011-04-13 | 华东理工大学 | Vehicle collision warning system based on optical communication |
| CN102745135A (en) * | 2012-07-24 | 2012-10-24 | 苏州工业园区七星电子有限公司 | Active vehicle infrared night vision system |
| US20170270375A1 (en) * | 2014-12-07 | 2017-09-21 | Brightway Vision, Ltd. | Object Detection Enhancement of Reflection-Based Imaging Unit |
| CN107411706A (en) * | 2017-04-07 | 2017-12-01 | 展谱光电科技（上海）有限公司 | Multispectral projection arrangement and projecting method, multispectral camera device and image capture method |
Non-Patent Citations (1)
| Title |
|---|
| 辛海升等: "主动式车辆夜视系统技术问题及解决方案", 《中国农机化》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111427331A (en) * | 2020-03-24 | 2020-07-17 | 新石器慧通（北京）科技有限公司 | Perception information display method and device of unmanned vehicle and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110362071B (en) | 2022-07-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108572663B (en) | Target tracking | |
| CN111448591B (en) | System and method for locating a vehicle in poor lighting conditions | |
| KR101949358B1 (en) | Apparatus for providing around view and Vehicle including the same | |
| US7684894B2 (en) | Autonomously moving robot | |
| KR101579100B1 (en) | Apparatus for providing around view and Vehicle including the same | |
| KR102516326B1 (en) | Camera extrinsic parameters estimation from image lines | |
| US10776636B2 (en) | Stereo camera-based detection of objects proximate to a vehicle | |
| US10949679B2 (en) | Nighttime sensing | |
| US8982191B2 (en) | Divergence ratio distance mapping camera | |
| US20150288948A1 (en) | System and method for night vision object detection and driver assistance | |
| US10643342B2 (en) | Group optimization depth information method and system for constructing a 3D feature map | |
| US20190080481A1 (en) | Image processing apparatus and ranging apparatus | |
| AU2015238768A1 (en) | Motion estimation in real-time visual odometry system | |
| US10503989B2 (en) | Image processing apparatus, imaging apparatus, camera monitor system, and image processing method | |
| US20240153122A1 (en) | Binocular vision-based environment sensing method and apparatus, and unmanned aerial vehicle | |
| CN109444916A (en) | The unmanned travelable area determining device of one kind and method | |
| CN109521780B (en) | Control system and control method for remote control work vehicle | |
| WO2020137110A1 (en) | Movement amount estimation device | |
| CN110362071A (en) | Artificial Intelligence Control and device based on multi-optical spectrum imaging technology | |
| CN209991983U (en) | Obstacle detection equipment and unmanned aerial vehicle | |
| US20210147077A1 (en) | Localization Device and Localization Method for Unmanned Aerial Vehicle | |
| US11360552B1 (en) | High assurance headtracking via structured light projection for head worn display (HWD) | |
| JP7056379B2 (en) | Vehicle driving control device | |
| CN113486836B (en) | Automatic driving control method for low-pass obstacle | |
| EP2919150A1 (en) | Safety system for vehicles |
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 |