CN108566523A - A kind of vehicle-mounted obstacle identification optical projection system - Google Patents
A kind of vehicle-mounted obstacle identification optical projection system Download PDFInfo
- Publication number
- CN108566523A CN108566523A CN201810467829.0A CN201810467829A CN108566523A CN 108566523 A CN108566523 A CN 108566523A CN 201810467829 A CN201810467829 A CN 201810467829A CN 108566523 A CN108566523 A CN 108566523A
- Authority
- CN
- China
- Prior art keywords
- module
- color
- short
- vehicle
- laser
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/30—Transforming light or analogous information into electric information
- H04N5/33—Transforming infrared radiation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/10—Cameras or camera modules comprising electronic image sensors; Control thereof for generating image signals from different wavelengths
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/12—Picture reproducers
- H04N9/31—Projection devices for colour picture display, e.g. using electronic spatial light modulators [ESLM]
- H04N9/3141—Constructional details thereof
- H04N9/315—Modulator illumination systems
- H04N9/3161—Modulator illumination systems using laser light sources
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/12—Picture reproducers
- H04N9/31—Projection devices for colour picture display, e.g. using electronic spatial light modulators [ESLM]
- H04N9/3179—Video signal processing therefor
- H04N9/3182—Colour adjustment, e.g. white balance, shading or gamut
Abstract
The invention discloses a kind of vehicle-mounted obstacle identification optical projection system, including short-wave infrared image-forming module, modulated signal module and laser projection module, the vehicle-mounted obstacle identification optical projection system further includes color processing module；The laser projection module further includes mist panel module；The color processing module passes through object described in contour of object in the short infrared imaging data and feature recognition, the converting colors of the object are determined as object color, and the short infrared imaging data is converted into visual light imaging data, the visual light imaging data are output to the modulated signal module；The laser projection module shows full color by the mist panel module, display device can be made to be not take up larger space, it can carry out large-area displays obstacle image, the visual color that imaging shows color close to people recognizes custom, motorist is effectively improved to obstacle recognition ability, effective use is on vehicle.
Description
Technical field
The present invention relates to technical field of imaging more particularly to a kind of vehicle-mounted obstacle identification optical projection systems.
Background technology
Currently, vehicle in the case of greasy weather, sleet sky or other environment low visibility when driving, driver's seat by
Limit declines distant place road environment observation ability, is easy to happen traffic accident.Short-wave infrared be operated in just go out visible-range it
Outside, because short-wave infrared similar with visible light uses catoptric imaging, thus imaging is very similar to visible images, profile
Clear, details is abundant.Short-wave infrared can still keep good in the environment of the low visibility such as haze, mist, rain, snow simultaneously
Picture contrast, short-wave infrared can be most as low as the night even for having starlight in addition, thus short-wave infrared imaging can conduct
One of night vision means.
But it is larger with the projecting apparatus occupied space of short-wave infrared camera carrying at present, display area is smaller, is unfavorable for
Driver observes barrier, and short infrared imaging effect is imaged for black and white, poor to the image restoring ability of barrier, but also
Motorist cannot effectively identify barrier.
Invention content
The present invention may be implemented in order to solve the above technical problems, a kind of vehicle-mounted obstacle identification optical projection system of offer by black and white
Image is converted to coloured image, improves the resolution of user.
A kind of vehicle-mounted obstacle identification optical projection system of first aspect present invention offer, the vehicle-mounted obstacle identification optical projection system,
Including short-wave infrared image-forming module, modulated signal module and laser projection module, the vehicle-mounted obstacle identification optical projection system is also wrapped
Include color processing module；The laser projection module further includes mist panel module；
The short-wave infrared light received is converted to short-wave infrared imaging data and is output to by the short-wave infrared image-forming module
The color processing module；The color processing module passes through the contour of object and feature in the short infrared imaging data
It identifies the object, the converting colors of the object is determined as object color, and the short infrared imaging data is turned
It changes visual light imaging data into, the visual light imaging data is output to the modulated signal module；The modulated signal mould
The visual light imaging data are converted to Red light data control signal, green light data controlling signal and blue light data control letter by block
It number is output to the input terminal of the laser projection module, the laser projection module, which controls the Red light data received, to be believed
Number, the green light data controlling signal and the blue light data controlling signal be converted into full color and carried out by the mist panel module
Display.
The invention discloses a kind of vehicle-mounted obstacle identification optical projection systems, including short-wave infrared image-forming module, modulated signal mould
Block and laser projection module, vehicle-mounted obstacle identification optical projection system further includes color processing module；Laser projection module further includes mist
Panel module；The short-wave infrared light received is converted to short-wave infrared imaging data and is output at color by short-wave infrared image-forming module
Manage module；Color processing module is by the contour of object and feature recognition object in short infrared imaging data, by object
Converting colors are determined as object color, and short infrared imaging data is converted into visual light imaging data, will be described visible
Light imaging data is output to the modulated signal module；Modulated signal module will be seen that light imaging data is converted to Red light data control
Signal, green light data controlling signal and blue light data controlling signal processed are output to the input terminal of the laser projection module, laser
The Red light data received is controlled signal, green light data controlling signal and the conversion of blue light data controlling signal and helped by projection module
Colour shown by mist panel module, can be with large-area displays obstacle image by the way that mist panel module is arranged, and passes through setting
Color processing module, modulated signal module and laser projection module, realize black white image being converted to coloured image, effectively carry
High motorist is to obstacle recognition ability.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description be only the present invention some
Embodiment for those of ordinary skill in the art without having to pay creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the structure chart of vehicle-mounted obstacle identification optical projection system provided in an embodiment of the present invention；
Fig. 2 is the color processing module structure chart of vehicle-mounted obstacle identification optical projection system provided in an embodiment of the present invention；
Fig. 3 is the color processing module structure chart of another vehicle-mounted obstacle identification optical projection system provided in an embodiment of the present invention；
Fig. 4 is the structure chart of another vehicle-mounted obstacle identification optical projection system provided in an embodiment of the present invention；
Fig. 5 is the structure chart of another vehicle-mounted obstacle identification optical projection system provided in an embodiment of the present invention.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
The embodiment of the present invention provides a kind of vehicle-mounted obstacle identification optical projection system, as shown in Figure 1, being imaged mould including short-wave infrared
Block 10, modulated signal module 30 and laser projection module 40, the vehicle-mounted obstacle identification optical projection system further includes colors countenance mould
Block 20；The laser projection module 40 further includes mist panel module 411；
The short-wave infrared light received is converted to the output of short-wave infrared imaging data by the short-wave infrared image-forming module 10
To the color processing module 20；The color processing module 20 passes through the contour of object in the short infrared imaging data
And object described in feature recognition, the converting colors of the object are determined as object color, and by the short-wave infrared line imaging
Data conversion is output to the modulated signal module 30 at visual light imaging data, by the visual light imaging data；The tune
The visual light imaging data are converted to Red light data control signal, green light data controlling signal and blue light by signaling module 30 processed
Data controlling signal is output to the input terminal of the laser projection module 40, and the laser projection module is described red by what is received
Light data control signal, the green light data controlling signal and the blue light data controlling signal are converted into full color described in
Mist panel module 40 is shown.
Then color processing module 20 will by the contour of object and feature recognition object in short infrared imaging data
Converting colors are determined as the color of object, and converting colors are artificially defined colors herein, for example, passing through short-wave infrared line imaging
Contour of object and feature recognition object in data go out object be road surface when, definition object converting colors be grey；Identify object
When body is bear, definition object converting colors are brown, and the short infrared imaging data is converted into turning for corresponding object
Change the visual light imaging data of color, it will be seen that light imaging data is output to modulated signal module 30；Modulated signal module 30 will
Visual light imaging data are converted to Red light data control signal, green light data controlling signal and blue light data controlling signal and are output to
The Red light data received is controlled signal, institute by the input terminal of the laser projection module 40, the laser projection module
It states green light data controlling signal and the blue light data controlling signal is converted into full color and is shown by the mist panel module.
As an embodiment of the present embodiment, the short-wave infrared image-forming module 10 includes：Short-wave infrared optical mode
Block 101, short-wave infrared detector 102 and signal processing module 103；
The output end of the short-wave infrared optical module 101 is connect with the input terminal of the short-wave infrared detector 102, institute
The output end for stating short-wave infrared detector 102 is connect with the input terminal of the signal processing module 103, the signal processing module
103 output end is connect with the input terminal of the color processing module 20；
The short-wave infrared light received is focused on the short-wave infrared detector by the short-wave infrared optical module 101
On 102 focal plane；
The short-wave infrared light received is completed photoelectric signal transformation with the short-wave infrared detector 102 and signal amplifies
Afterwards, it is output to the signal processing module 103；
The electric signal received by analog-to-digital conversion, is converted electrical signals to short-wave infrared by the signal processing module 103
Imaging data is output to the color processing module 20.
As an embodiment of the present embodiment, as shown in Fig. 2, the color processing module 20 includes identification module
201 and color processing module 202；
The identification module 201 divides region to short infrared imaging data, and according to the profile in the region and institute
The object in the relative position identification region in region is stated, and obtains the converting colors of the object in region；
The converting colors of the object are determined as object face by the color conversion 202 according to color conversion pattern
Color, and the short infrared imaging data is converted into visual light imaging data.
Since short-wave infrared line imaging can be good at the profile and details of represented object, identification module 201 can be according to
Short infrared imaging data is divided into multiple regions by short infrared image profiles, such as：Rectangular profile is divided into
Contour area including zebra stripes is divided into crossing region by road surface region；The profile die of familiar object can also be established
Type library, by comparing the region contour of short-wave infrared line imaging and the skeleton pattern in skeleton pattern library, when shortwave is red
When the region contour of outer line imaging reaches certain similarity with the skeleton pattern in skeleton pattern library, you can judge that the region is that
Kind object, for example, the region contour when short-wave infrared line imaging reaches with the vehicle's contour distortion in skeleton pattern library
When 60%, it is determined as that the region object is vehicle；Feature model library can also be established, for example, according to contour of object in region
Relative seat feature, detail textures feature etc. identify object, for example, judging the eyes, nose and mouth of people according to region contour
Bar；The facial relative seat feature model of people is that two-eye area position is symmetric in feature model library, nasal area
Position distribution in middle position, face position distribution is in lower position, if each contour area in the region meets or portion
Divide the facial relative seat feature model for meeting the people in feature model library, then judges the region object for the face of people；It is similar
Ground, the relative position that the four limbs and trunk profile of the four limbs of people and trunk profile and people in region are gone out by outline identification are special
Sign meets or partly meets pedestrian's relative seat feature model in feature model library, judges the region object for pedestrian；It is similar
The vehicle window and tail-light for going out vehicle in region by outline identification, and with the relative position of the vehicle window of vehicle and tail-light spy
Model is levied, meets or partly meets the vehicle relative seat feature model in feature model library, judge the region object for vehicle；
After identifying object, the converting colors of the object are obtained, such as by establishing object color transformation warehouse, eyes converting colors are
Black, lip converting colors are red, vehicle converting colors are yellow, car light converting colors are red；To the finery shoes of pedestrian
Cap can also establish corresponding model in color transformation warehouse according to classifications such as men and women, old and young and distinguish；Color conversion
202 according to color conversion pattern, and according to the recognition result of the object in region, the object color in region is converted to object face
The corresponding converting colors of object in color transformation warehouse；The conversion face of familiar object can also be voluntarily arranged in user by the way that menu is arranged
Color is such as maroon according to the hobby of oneself setting road surface color.The present embodiment is by forming short-wave infrared line imaging itself
Profile be divided into the feature recognitions such as the contour shape of multiple regions calmodulin binding domain CaM and the relative position of profile each region presentation
Be which kind of object respectively, and short infrared imaging data is converted into visual light imaging data, by black and white imaging effect
It is converted into approximate colour imaging effect, the visual color that imaging shows color close to people recognizes custom.
As an embodiment of the present embodiment, the color conversion pattern is basic model；The basic model is
The converting colors of the object are determined as object color.
Further, the color conversion pattern further includes：
Contrast pattern, warm colour pattern and bright mode；
The contrast pattern is to adjust distant view color lightness and close shot color lightness according to default colour table；
The warm colour pattern is that the object color of unrestricted choice is determined as red, orange or yellow；
The bright mode is to adjust integral color brightness according to default colour table.
Basic model is converted directly into the converting colors of object, not further to color to be handled；Contrast pattern will be remote
The color of scape and close shot carries out contrast processing, such as building, mountain range, the trees etc. in distant view are reduced color according to default colour table
Lightness；Vehicle, pedestrian etc. in close shot is improved into color lightness according to default colour table, to improve the color lightness of distant view and close shot
Comparison, makes close shot show more prominent, it is easier to observe；It includes a variety of face such as red, green, blue, purple, Huang, black to preset colour table herein
The color template of multiple lightness grades of color, is such as divided into 9 lightness grades；When reducing color lightness, select than current color
The color of lightness grade bottom one or more lightness grade, when improving color lightness, it is high that selection than current color obviously spends grade
The color of one or more lightness grades.Warm colour pattern is by can be with the color object of unrestricted choice, for example, vehicle color, pedestrian
Clothing color etc., red, orange or yellow is selected when color is converted, image presentation warm tones can be made；Bright mode according to
The color of general image is increased or decreased color lightness and shown by default colour table, to meet the use habit of different user；
User can like selection color conversion pattern according to oneself aesthetic habit or color, to improve the user experience.
Specifically, as shown in figure 3, the color processing module 20 further includes luminance adjustment module 203, when the color turns
When mold changing formula is bright mode, the color conversion 20 drives the luminance adjustment module 203 for adjusting chroma-luminance.
User can by luminance adjustment module 203 adjust bright mode chroma-luminance, so as to environment inside car light
Brightness coordinates, and keeps display effect more preferable.
As an implementation, identification module 201 obtain images to be recognized, images to be recognized be include target area
Image, using region segmentation model to images to be recognized carry out image segmentation, obtain the target area in images to be recognized.This
In embodiment, full convolutional neural networks (Fully Convolutional Networks, FCN) may be used in region segmentation model
It is trained in advance, as an implementation, the training process of region segmentation model can first, be chosen for training
The training sample of region segmentation model, training sample include upper half of human body region, and upper part of the body region does not include interference region.So
Afterwards to including that the training sample of upper half of human body region is labeled, that is, be directed to sample image each pixel whether
Belong to upper part of the body region to be labeled, training sample is finally converted to the two-value including upper part of the body region and non-upper part of the body region
Figure, inputs full convolutional neural networks by binary map and is trained, to obtain region segmentation model.It should be noted that in order to keep away
Exempt from the case where target area is blocked by certain disturbing factors occur, cause the inaccuracy of training sample, by gathering multiple instructions
The target area practiced in sample is trained region segmentation model, and the region segmentation model after training can be to described to be identified
Image carries out image segmentation, to obtain the upper half of human body region in images to be recognized.In detail, region segmentation model
Training process can first, feature extraction be carried out to images to be recognized using full convolutional neural networks, to form multiple convolution
The characteristic pattern of layer.Then, the characteristic pattern of the last one convolutional layer is sampled using warp lamination, this feature figure is restored
To size identical with images to be recognized.
More specifically, in the present embodiment, the feature of the training sample is extracted using the full convolutional neural networks, and
Feature after extraction is subjected to multiple convolution, obtains the characteristic pattern of multiple convolutional layers.In the figure by after multiple convolution, obtaining
As meeting is smaller and smaller.In order to which the rough image of small size to be restored to the picture size of former training sample, deconvolution can be utilized
Layer up-samples the characteristic pattern of the last one convolutional layer, such as after 5 convolution, the size of image reduces successively
2,4,8,16,32 times, therefore for the output characteristic pattern of last layer, then need to carry out 32 times of up-sampling, can be only achieved with
The same picture size of former training sample.
It should be noted that since up-sampling is realized by deconvolution (deconvolution), so to the 5th layer
Output (32 times amplification) deconvolution to artwork size, obtained result or inaccurate, some details can not be restored.So
Output that can be by the 4th layer and the 3rd layer of output also deconvolution successively be respectively necessary for 16 times and 8 times and up-sample, finally by 8 times,
16 times, 32 times up-sample obtained image and carry out image co-registration, and obtained image can be more fine.
Next, the characteristic pattern that above-mentioned fusion obtains is compared structure loss function with training sample image, then
Loss function is minimized by optimization algorithm, and carries out backpropagation and obtains the parameter of the region segmentation model.Specifically, lead to
It crosses and the characteristic pattern after resizing is compared with images to be recognized, a prediction then is generated to each pixel, simultaneously
The spatial information in original input picture is remained, individual element calculates the loss of softmax classification, is equivalent to each pixel
A corresponding training sample.
Then, when obtaining images to be recognized, images to be recognized is input to trained region segmentation model, to divide
Cut out pedestrian's upper part of the body region in the images to be recognized.
It is generated in target area multiple with machine frame, calculates target area in each accounting in machine frame.
The pixel position of preset quantity is generated at random in target area, and is generated in advance centered on each pixel position
If size with machine frame.
In this embodiment, first, the position in target area is randomly selected to generate pixel position, as
Vegetarian refreshments number of positions can be chosen according to actual design demand, such as 50 positions that can be chosen in target area are made
For pixel position, then generated with machine frame centered on each pixel position.It can be according to target area with the size of machine frame
The size in domain is determined, illustratively, three points of the minimum enclosed rectangle for being preferably sized to target area with machine frame
Two sizes.
Identification region is treated using color classification model and carries out color identification, exports color recognition result.
It is alternatively possible to using convolutional neural networks (Convolutional Neural Network, CNN) in advance to institute
Color classification model is stated to be trained.The convolutional neural networks are a kind of neural network model of special deep layer, its spy
Different property is embodied in two aspects, on the one hand its interneuronal connection be it is non-connect entirely, it is certain in another aspect same layer
The weight of connection between neuron is shared.The network structure that its non-full connection and weights are shared is allowed to be more closely similar to give birth to
Object neural network reduces the complexity of network model, reduces the quantity of weights.
The converting colors of the object are determined as object color by color processing module 202, and by the short infrared
Imaging data is converted into visual light imaging data.By RGB tri- color data image to be projected for being decomposed into triple channel, each picture
Element can be decomposed into the data of (R, G, B) format, and be converted into light intensity data control light valve, and use the laser of corresponding color
Transmitter emits the laser of corresponding color respectively, and combination forms projected image on the projection screen.
Specifically, as shown in Figure 1, the laser projection module 40 further includes：Red laser 401, green laser
402, blue laser 403, feux rouges object lens 404, blue light object lens 405, feux rouges light valve 406, green light light valve 407, blue light light valve
408, X prisms 409 and scanning mirror 410；
The red laser 401 projects red laser and projects the feux rouges valve, institute by the feux rouges object lens 404
It states green laser 402 and projects green laser to the green light valve 407, the blue laser 403 projects blue laser warp
It crosses the blue light object lens 405 and projects the blue light valve 408；
The modulated signal module 30 controls the output of feux rouges light valve 406 described in Signal Regulation to institute by the Red light data
The intensity of the red laser of X prisms 409 is stated, the modulated signal module 30 passes through described in green light data controlling signal adjusting
Green light light valve 407 is exported to the intensity of the green laser of the X prisms 409, and the modulated signal module 30 passes through the blue light
Data controlling signal adjusts the intensity of the blue laser of the output of blue light light valve 408 to the X prisms 409；
The red laser, the green laser and the blue laser are mixed into full color simultaneously by the X prisms 409
To the scanning mirror 410, the full color is scanned display by the scanning mirror on mist panel module 411 for output.
The course of work of laser projection module 40 is：The red laser that red laser 401 is sent out passes through feux rouges object lens 404
Feux rouges valve 406 is projected, the green laser that green laser 402 is sent out projects green light valve 407, blue laser 403
The blue laser sent out projects blue light valve 408 by blue light object lens 405；The Red light data control that modulated signal module 30 exports
Signal, green light data controlling signal and three tunnel of blue light data controlling signal control signal processed control feux rouges light valve 406, green light respectively
The intensity that light valve 407 and blue light light valve 408 pass through light；Pass through feux rouges light valve 406, green light light valve 407 and blue light light valve 408
Three road laser are mixed into full-color image by X prisms 409, are scanned using polygonal-mirror by scanning mirror 410 or galvanometer is swept
The scanning for realizing row and field is retouched, projects and is shown on the mist panel module 411；It is occupied when mist panel module 411 uses little
Plane space, and mist screen has penetrability, does not influence other interior objects, is not take up redundant space when not in use；Mist screen
Large-area displays obstacle image can be carried out, effectively improves motorist to obstacle recognition ability.
The invention discloses a kind of vehicle-mounted obstacle identification optical projection systems, including short-wave infrared image-forming module, modulated signal mould
Block and laser projection module, the vehicle-mounted obstacle identification optical projection system further includes color processing module；The laser projection module
It further include mist panel module；The short-wave infrared light received is converted to short-wave infrared imaging data by the short-wave infrared image-forming module
It is output to the color processing module；The color processing module passes through the contour of object in the short infrared imaging data
And object described in feature recognition, the converting colors of the object are determined as object color, and by the short-wave infrared line imaging
Data conversion is output to the modulated signal module at visual light imaging data, by the visual light imaging data；The modulation
The visual light imaging data are converted to Red light data control signal, green light data controlling signal and blue light data by signaling module
Control signal is output to the input terminal of the laser projection module, the Red light data that the laser projection module will receive
Control signal, the green light data controlling signal and the blue light data controlling signal are converted into full color and pass through the mist screen mould
Block is shown, display device can be made to be not take up larger space, can carry out large-area displays obstacle image, imaging display
The visual color of color close to people recognize custom, effectively improve motorist to obstacle recognition ability, effective use is in vehicle
On.
As the another embodiment of the present embodiment, the short-wave infrared image-forming module 10 is set to tailstock position, institute
It states mist panel module 411 and is set to operator seat side vehicle window, operator seat front vehicle window or passenger position side vehicle window.
Due to when driver or passenger, which open the door, to get off, not observing the traffic of rear of vehicle, and frequently result in out
Door moment front vehicle hits the car door opened and causes traffic accident；And in the ring of the low visibility such as haze, mist, rain, snow
Under border, the traffic of rear of vehicle can not be also observed well.By short-wave infrared image-forming module 10 be set to tailstock position with
The traffic for observing vehicle rear, easily observes position when mist panel module 411 is set to door opening, for example, operator seat side vehicle window or
Positions such as the back upper place of vehicle window in front of operator seat, passenger's position side vehicle window or forward seat etc., to facilitate driver or passenger to exist
Before getting off, driver or passenger see whether that the feelings of Vehicular impact car door may occur in lower Chinese herbaceous peony by mist panel module
Condition is determined to open the door again after the traffic conditions safety of vehicle rear and be got off.The present embodiment is set to vehicle by short-wave infrared image-forming module 10
Tail position, the mist panel module 411 easily observe position when being set to door opening, make driver or passenger when visibility is relatively low
It can be good at observing determining vehicle rear traffic conditions, the generation to avoid traffic accident.
Further, as shown in figure 4, the vehicle-mounted obstacle identification optical projection system further includes reminding module 60, wireless switching
Module 70 and power module 80, the wireless switch modules 70 include wireless switching；The reminding module 60 is pressed with car door opening
Key connection, the reminding module 60 detect user whether opening car door；When detecting user's opening car door, the reminding module
60 issue the user with security warning, and user is prompted to open vehicle-mounted obstacle identification optical projection system；The wireless switch modules 70 with
Power module 80 connects, and when wireless switching is closed, powers on module 80 and opens vehicle-mounted obstacle identification optical projection system.
Reminding module 60 is with car door opening by key connection, and to detect user, whether opening car door will get off；Work as detection
When to user's opening car door, security warning can be issued the user with by sound, such as report and " would you please pay attention to observation rear when enabling
Traffic conditions "；And user is prompted to open vehicle-mounted obstacle identification optical projection system, it such as reports and " woulds you please open vehicle-mounted obstacle identification projection
System ".When user thinks to need to observe vehicle rear traffic by vehicle-mounted obstacle identification optical projection system, closure can be passed through
It is set to the wireless switching of the wireless switch modules 70 near car door, module 80 is powered on and is projected with opening vehicle-mounted obstacle identification
System, to observe vehicle rear traffic, the generation to avoid traffic accident.
As the another embodiment of the present embodiment, as shown in figure 5, the vehicle-mounted obstacle identification optical projection system includes moving
Dynamic terminal 50, the mobile terminal 50 are connect with the laser projection module 40, and the mobile terminal 50 sends picture signal
To the laser projection module 40, the described image signal received is converted into full color and passed through by the laser projection module 40
The mist panel module 411 is shown.
Mobile terminal 50, such as smart mobile phone, tablet computer can be connect by user with laser projection module 40, by image
The picture signal of the files such as signal, such as video, PPT, picture, webpage is sent to the laser projection module 40, laser projection
The picture signal received is converted into full color and is shown by the mist panel module 411 by module 40.Due to mist panel module
411 constitute image forming medium using water mist, do not need traditional physical screen, small to place installation requirement, and display area is larger, figure
As clear；After mobile terminal 50 is connect by user with laser projection module 40, is watched by mist panel module 411 and show content, it can
To avoid by bus when see the mobile phone the spinning sensation brought for a long time, can also on the way appreciate program, loosen body and mind, improve user's
It experiences by bus.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each implementation
Technical solution recorded in example is modified or equivalent replacement of some of the technical features；And these modification or
It replaces, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution should all include
Within protection scope of the present invention.
Claims (10)
1. a kind of vehicle-mounted obstacle identification optical projection system, including short-wave infrared image-forming module, modulated signal module and laser projection mould
Block, which is characterized in that the vehicle-mounted obstacle identification optical projection system further includes color processing module；The laser projection module is also wrapped
Include mist panel module；
The short-wave infrared image-forming module by the short-wave infrared light received be converted to short-wave infrared imaging data be output to it is described
Color processing module；The color processing module passes through the contour of object and feature recognition in the short infrared imaging data
The converting colors of the object are determined as object color, and the short infrared imaging data are converted by the object
The visual light imaging data are output to the modulated signal module by visual light imaging data；The modulated signal module will
It is defeated that the visual light imaging data are converted to Red light data control signal, green light data controlling signal and blue light data controlling signal
Go out the input terminal to the laser projection module, the laser projection module by the Red light data received control signal,
The green light data controlling signal and the blue light data controlling signal are converted into full color and are shown by the mist panel module
Show.
2. vehicle-mounted obstacle identification optical projection system as described in claim 1, which is characterized in that the short-wave infrared image-forming module packet
It includes：Short-wave infrared optical module, short-wave infrared detector and signal processing module；
The output end of the short-wave infrared optical module is connect with the input terminal of the short-wave infrared detector, the short-wave infrared
The output end of detector is connect with the input terminal of the signal processing module, the output end of the signal processing module and the color
The input terminal of color processing module connects；
The short-wave infrared light received is focused on the focal plane of the short-wave infrared detector by the short-wave infrared optical module
On；
After the short-wave infrared light received is carried out photoelectric signal transformation and signal amplification by the short-wave infrared detector, it is output to
The signal processing module；
The electric signal received by analog-to-digital conversion, is converted electrical signals to short-wave infrared imaging data by the signal processing module
It is output to the color processing module.
3. vehicle-mounted obstacle identification optical projection system as described in claim 1, which is characterized in that the laser projection module is also wrapped
It includes：Red laser, green laser, blue laser, feux rouges object lens, blue light object lens, feux rouges light valve, green light light valve, blue light
Light valve, X prisms and scanning mirror；
The red laser projection red laser projects the feux rouges valve, the green laser by the feux rouges object lens
Device projects green laser to the green light valve, and the blue laser projection blue laser is projected by the blue light object lens
The blue light valve；
The modulated signal module controls feux rouges light valve described in Signal Regulation by the Red light data and exports to the X prisms
The intensity of red laser, the modulated signal module by the green light data controlling signal adjust the green light light valve export to
The intensity of the green laser of the X prisms, the modulated signal module adjust the indigo plant by the blue light data controlling signal
Light light valve exports the intensity of the blue laser to the X prisms；
The red laser, the green laser and the blue laser are mixed into full color and exported extremely by the X prisms
The full color is scanned display by the scanning mirror, the scanning mirror on mist panel module.
4. vehicle-mounted obstacle identification optical projection system as described in claim 1, which is characterized in that the color processing module includes knowing
Other module and color conversion；
The identification module divides region to short infrared imaging data, and according to the profile in the region and the region
Object in relative position identification region, and obtain the converting colors of the object in region；
The converting colors of the object are determined as object color by the color conversion according to color conversion pattern, and by institute
It states short infrared imaging data and is converted into visual light imaging data.
5. vehicle-mounted obstacle identification optical projection system as claimed in claim 4, which is characterized in that the color conversion pattern is basic
Pattern；
The basic model is that the converting colors of the object are determined as object color.
6. vehicle-mounted obstacle identification optical projection system as claimed in claim 5, which is characterized in that the color conversion pattern further includes
Contrast pattern, warm colour pattern and bright mode；
The contrast pattern is to adjust distant view color lightness and close shot color lightness according to default colour table；
The warm colour pattern is that the object color of unrestricted choice is determined as red, orange or yellow；
The bright mode is to adjust integral color brightness according to default colour table.
7. vehicle-mounted obstacle identification optical projection system as claimed in claim 6, which is characterized in that the color processing module further includes
Luminance adjustment module；
When the color conversion pattern is bright mode, the color conversion drives the luminance adjustment module for adjusting
Save chroma-luminance.
8. vehicle-mounted obstacle identification optical projection system as described in claim 1, which is characterized in that the short-wave infrared image-forming module is set
It is placed in tailstock position, the mist panel module is set to operator seat side vehicle window, operator seat front vehicle window or passenger position side vehicle window.
9. vehicle-mounted obstacle identification optical projection system as described in claim 1, which is characterized in that the vehicle-mounted obstacle identification projection system
System further includes reminding module, wireless switch modules and power module, and the wireless switch modules include wireless switching；The prompting
Module and car door opening by key connection, the reminding module detection user whether opening car door；When detecting user's opening car door
When, the reminding module issues the user with security warning, and user is prompted to open vehicle-mounted obstacle identification optical projection system；It is described wireless
Switch module is connect with power module, when the wireless switching is closed, is powered on module and is opened vehicle-mounted obstacle identification and throw
Shadow system.
10. vehicle-mounted obstacle identification optical projection system as described in claim 1, which is characterized in that the vehicle-mounted obstacle identification projection
System includes mobile terminal, and the mobile terminal is connect with the laser projection module, and the mobile terminal sends out picture signal
It send to the laser projection module, the described image signal received is converted into full color and passes through institute by the laser projection module
Mist panel module is stated to be shown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810467829.0A CN108566523A (en) | 2018-05-16 | 2018-05-16 | A kind of vehicle-mounted obstacle identification optical projection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810467829.0A CN108566523A (en) | 2018-05-16 | 2018-05-16 | A kind of vehicle-mounted obstacle identification optical projection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108566523A true CN108566523A (en) | 2018-09-21 |
Family
ID=63539103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810467829.0A Pending CN108566523A (en) | 2018-05-16 | 2018-05-16 | A kind of vehicle-mounted obstacle identification optical projection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108566523A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882519A (en) * | 2020-06-15 | 2020-11-03 | 上海眼控科技股份有限公司 | Method and device for identifying car lamp |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279938A (en) * | 2013-04-03 | 2013-09-04 | 昆明物理研究所 | Infrared/ glimmer image fusion night vision system |
| CN204367988U (en) * | 2014-12-22 | 2015-06-03 | 深圳市航盛电子股份有限公司 | A kind of on-vehicle safety information presentation device |
| CN204415164U (en) * | 2015-02-02 | 2015-06-24 | 龙泉千成电子科技有限公司 | Multifunctional vehicle mounted HUD telltale |
| CN104751138A (en) * | 2015-03-27 | 2015-07-01 | 东华大学 | Vehicle mounted infrared image colorizing assistant driving system |
| CN104899558A (en) * | 2015-05-25 | 2015-09-09 | 东华大学 | Scene recognition and colorization processing method for vehicle-mounted infrared image |
| CN106464806A (en) * | 2014-03-31 | 2017-02-22 | 谷歌技术控股有限责任公司 | Adaptive low-light identification |
-
2018
- 2018-05-16 CN CN201810467829.0A patent/CN108566523A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279938A (en) * | 2013-04-03 | 2013-09-04 | 昆明物理研究所 | Infrared/ glimmer image fusion night vision system |
| CN106464806A (en) * | 2014-03-31 | 2017-02-22 | 谷歌技术控股有限责任公司 | Adaptive low-light identification |
| CN204367988U (en) * | 2014-12-22 | 2015-06-03 | 深圳市航盛电子股份有限公司 | A kind of on-vehicle safety information presentation device |
| CN204415164U (en) * | 2015-02-02 | 2015-06-24 | 龙泉千成电子科技有限公司 | Multifunctional vehicle mounted HUD telltale |
| CN104751138A (en) * | 2015-03-27 | 2015-07-01 | 东华大学 | Vehicle mounted infrared image colorizing assistant driving system |
| CN104899558A (en) * | 2015-05-25 | 2015-09-09 | 东华大学 | Scene recognition and colorization processing method for vehicle-mounted infrared image |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882519A (en) * | 2020-06-15 | 2020-11-03 | 上海眼控科技股份有限公司 | Method and device for identifying car lamp |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210217212A1 (en) | Method and system for automatically colorizing night-vision images | |
| WO2019192418A1 (en) | Automobile head-up display system and obstacle prompting method thereof | |
| CN108460734B (en) | System and method for image presentation by vehicle driver assistance module | |
| CN101783076B (en) | Method for quick vehicle type recognition under video monitoring mode | |
| US11003931B2 (en) | Vehicle monitoring method and apparatus, processor, and image acquisition device | |
| CN101656023B (en) | Management method of indoor car park in video monitor mode | |
| CN101739827B (en) | Vehicle detecting and tracking method and device | |
| CN109076163A (en) | Imaging control apparatus, image formation control method and imaging device | |
| CN104408424B (en) | A kind of multi signal lamp recognition methods based on image procossing | |
| CN106503707B (en) | Licence plate recognition method and device under a kind of infrared lighting condition | |
| TW201716266A (en) | Image inpainting system area and method using the same | |
| US11117570B1 (en) | Parking assistance using a stereo camera and an added light source | |
| CN208479822U (en) | A kind of automobile-used panoramic looking-around system | |
| WO2003044738A2 (en) | Method and system for improving car safety using image-enhancement | |
| US20220041105A1 (en) | Rearview device simulation | |
| CN105677206A (en) | System and method for controlling head-up display based on vision | |
| CN112116807B (en) | Multifunctional traffic safety guiding device | |
| CN108566523A (en) | A kind of vehicle-mounted obstacle identification optical projection system | |
| CN109410594A (en) | A kind of Vehicle License Plate Recognition System and method | |
| CN106340031A (en) | Method and device for detecting moving object | |
| CN113101155A (en) | Traffic light intersection blind guiding method and blind guiding device based on machine vision | |
| CN112800989A (en) | Method and device for detecting zebra crossing | |
| CN109558872A (en) | A kind of vehicle color identification method | |
| CN109808601A (en) | The implementation method and device of augmented reality head-up-display system for vehicle | |
| CN108608944A (en) | A kind of Intelligent night vision control method and system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180921 |
|
| WD01 | Invention patent application deemed withdrawn after publication |