CN109584176A - Motor vehicle driving vision enhancement system - Google Patents
Motor vehicle driving vision enhancement system Download PDFInfo
- Publication number
- CN109584176A CN109584176A CN201811403887.3A CN201811403887A CN109584176A CN 109584176 A CN109584176 A CN 109584176A CN 201811403887 A CN201811403887 A CN 201811403887A CN 109584176 A CN109584176 A CN 109584176A
- Authority
- CN
- China
- Prior art keywords
- driving vision
- image
- motor vehicle
- driving
- value
- 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
- 238000000034 method Methods 0.000 claims abstract description 32
- 230000002708 enhancing effect Effects 0.000 claims abstract description 16
- 238000003064 k means clustering Methods 0.000 claims abstract description 14
- 239000003595 mist Substances 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 12
- 239000000428 dust Substances 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 7
- 239000011521 glass Substances 0.000 claims description 6
- 239000002245 particle Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 239000004615 ingredient Substances 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 4
- 238000005315 distribution function Methods 0.000 claims description 4
- 239000008187 granular material Substances 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 230000003014 reinforcing effect Effects 0.000 claims 1
- 230000006872 improvement Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000008447 perception Effects 0.000 description 2
- 238000002834 transmittance Methods 0.000 description 2
- 235000008331 Pinus X rigitaeda Nutrition 0.000 description 1
- 235000011613 Pinus brutia Nutrition 0.000 description 1
- 241000018646 Pinus brutia Species 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009102 absorption Effects 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Image Processing (AREA)
- Lighting Device Outwards From Vehicle And Optical Signal (AREA)
Abstract
The invention discloses a kind of motor vehicle driving vision enhancement systems.Motor vehicle driving vision enhancement system, it is characterised in that: enhance equipment including the haze sky driving vision enhancing equipment based on improved dark primary elder generation checking method and the rainy day driving vision based on K-means clustering algorithm.The improved dark primary elder generation checking method is used to handle traffic video image when greasy weather driving, is more clear it.The K-means clustering algorithm is used to handle traffic video image when greasy weather driving, is more clear it.The driving vision enhancing equipment includes the haze sensor, Raindrop sensor, camera module, car light module being set to outside vehicle, and is set to interior main control module and display device.The present invention can be improved driver's misty rain day drive field of front vision clarity, driving conditions avoid because of sight it is unclear caused by vehicle scrape even accidents, improve automobile driver misty rain day driving safety.
Description
Technical field
The present invention relates to safe driving of vehicle technical fields, more particularly to motor vehicle driving vision enhancement system.
Background technique
Motor vehicle driving vision enhancement system is a kind of image processing system applied to during driving path.In haze
Under weather, outdoor object is presented on the image in driver's seat would generally be because of medium muddy in atmosphere (such as solid
Grain, steam etc.) and degrade, because the absorptions such as mist, mist, raindrop in atmosphere or scattering light cause such phenomenon.Due to atmosphere
For the degree and object of scattering to the distance dependent of human eye, image deterioration is with spatial variations.Human eye receives object reflection
The light to come over is through overdamping.In addition, the light that eyes obtain also is mixed with the atmosphere light (ambient enviroment reflected through atmospheric molecule
Light).So the field of front vision that driver gets in the case of the greasy weather is degraded image, picture contrast decline, color mistake
Very.Meanwhile the target object in raindrop meeting shielded image, so that regional area is thickened.
Since the particle in atmosphere causes severe jamming to driver's seat clarity, driver's judgement and reflection are influenced
Speed causes travelling speed to reduce, and traffic accident takes place frequently.Therefore for the sharpening of driver's misty rain day driving vision image
Research is of great significance.
Recently as the continuous development of computer hardware technique, to shot under rain and fog weather the scenic imagery of image into
The processing of row sharpening has become possibility.Image misty rain processing technique is relevant in video monitoring, topographic(al) reconnaissance, urban transportation etc.
Field suffers from extensive utilization, improves the problems such as rain and fog weather whitens caused by image taking, obscures, contrast is low.
But the algorithm does not utilize in driving procedure, combines corresponding hardware device using the technology, provides in real time for driver
Clear picture.
Defogging processing is carried out to image at present and mainly realizes that the algorithm is by right using dark primary priori defogging algorithm
Statistical law that a large amount of fog free images are observed and obtain.Dark primary priori defogging algorithm is succinctly effective, to various types of
The image containing mist of type is attained by a degree of defog effect.Improved dark primary elder generation checking method is more suitable in driving procedure
Sky is left white more situation, therefore the algorithm can be applied in traffic video.Otherwise for rainy weather, then video is based on
The time domain specification of middle raindrop and the global property of pixel histogram restore rainy day image by K-means clustering algorithm.
Summary of the invention
In order to solve the problems, such as the reduction of misty rain day driver's seat clarity, the present invention provides a kind of motor vehicle driving vision
Enhancing system is more suitable for catching in processing traffic driving procedure using improved dark primary priori algorithm process greasy weather video
The image obtained improves the effect of video defogging processing.Rainy day image is handled using K-means clustering algorithm, it is clear to restore
Rainy day image.Sensor technology and image processing techniques are blended simultaneously, so that rain and fog weather detection more automates, it is quasi-
Really complete the unlatching of system.System can be effectively improved the safety issue in driving path field under rain and fog weather at this stage, be
Up to this purpose, the present invention provides a kind of motor vehicle driving vision enhancement system, and the motor vehicle driving vision enhancement system includes
Haze sky driving vision enhancing system based on improved dark primary elder generation checking method and the rainy day based on K-means clustering algorithm drive
Sail vision enhancement system, the improved dark primary of the haze sky driving vision enhancing system of the improved dark primary elder generation checking method
First checking method is used to handle traffic video image when greasy weather driving, and the rainy day based on K-means clustering algorithm drives view
Feel the traffic video image when K-means clustering algorithm of enhancing system is used to handle rainy day driving, the motor vehicle driving view
Feel that enhancing system support driving vision enhances equipment, the driving vision enhancing equipment includes the haze sensing being set to outside vehicle
Device, Raindrop sensor, camera module, car light module and the main control module and display device that are set to car, the haze pass
The lower section of car body front glass is arranged in sensor, and the top of car body front glass is arranged in the camera module,
The Raindrop sensor is arranged at the top of car body, and there are two before two side lights of car body are respectively set for the car light module
In square car light, the haze sensor connects the unlatching of warning device and the unlatching control of fog lamp, institute for detecting greasy weather weather
Raindrop sensor is stated for detecting rainy weather, connects the unlatching of warning device and the unlatching control of headlight.
Further improvement of the present invention, the improved dark primary elder generation checking method utilize pool by estimation transmissivity distribution
The stingy nomography of pine obtains fine transmissivity, restores object light to handle video image, finally realizes the enhancing to driving vision
Effect, the specific steps are as follows:
Step 1: estimation transmissivity；
In computer vision, iconic model containing mist is as follows:
I (x)=J (x) t (x)+A (1-t (x))
Wherein, for I (x) to mist elimination image, J (x) is fog free images to be restored, and A is atmosphere light ingredient, and t (x) is transmission
Rate；According to dark primary priori theoretical, the dark primary of fog free images is always gloomy, and the dark primary of the image containing mist is with higher strong
Angle value, it is assumed that in each window internal transmission factor t (x) be constant, minimum value twice is carried out to above formula and handles available following formula:
In above formula, J is fog free images to be asked, and dark primary priori theoretical has:
Therefore:
Iteration can obtain:
This is transmissivityDiscreet value because air is there are particle, therefore need pairIt is modified, draws in formula
Enter a coefficient between [0,1], by experimental verification, the coefficient desirable 0.95, then above formula can be corrected are as follows:
Step 2: transmissivity distribution function is improved
Stingy figure equation on mist image formation model equation and computer graphical is similar in form, the distribution of transmissivity its
Real is exactly the distribution of Alpha, therefore, applies Poisson and scratches nomography to improve transmissivity distribution function, to iconic model containing mist
It carries out that partial derivative is taken to handle, can obtain:
In the case where background is smooth,Relative toVery little, therefore
Have:
Nomography principle is scratched according to Poisson, available:
Wherein, Δ is Laplace operator, and div is divergence operator, then can be asked using Gauss-Sidel iterative algorithm
Take t (x)；
Step 3: object light is restored；
In practice, A value can be obtained from foggy image by means of dark channel diagram, first from dark channel diagram according to
The size of brightness takes preceding 0.1% pixel, in these positions, finds in original foggy image I corresponding with most highlighted
The value of the point of degree, as A value.To this step, so that it may carry out the recovery of fog free images；
When the value very little of projection figure t, the value that will lead to J is bigger than normal, to keep image whole excessive to white field therefore general
Settable threshold value T0, when t value is less than T0, enable t=T0, all effect pictures are with T0=0.1 is criterion calculation, and final is extensive
Multiple formula is as follows:
Further improvement of the present invention obtains fine transmittance figure using Steerable filter by estimation transmissivity distribution, multiple
Original light handles the non-sky area in video image, utilizes histogram equalization algorithm process sky areas.
Further improvement of the present invention, the K-means clustering algorithm are the cluster sides K-means based on objective function
Method detects raindrop region and removes, restored image.
Further improvement of the present invention, the haze sensor use optics dust sensor, the optics dust sensing
Device model GP2Y1010AU0F for detecting diameter greater than 0.8 μm of dust granule concentration, and is greater than the set value in detectable concentration
Shi Kaiqi haze sky vision enhancement system.
Further improvement of the present invention, the main control module use TSM320DSP chip carrying video processnig algorithms.
Further improvement of the present invention, the display device are taken the photograph using 7 cun of LCD displays by dsp chip and vehicle-borne CCD
As head connection, and show the live video stream after image defogging algorithm process.
Further improvement of the present invention, the car light module are connected to control mainboard by CAN bus.
Motor vehicle driving vision enhancement system of the present invention, compared with prior art, the invention has the following advantages:
(1) improved dark primary elder generation checking method used in the present invention, for there are the characteristics that sky areas is done in driving vision
It improves out, can effectively avoid after image procossing there are transitional region and color distortion phenomenon, restore clearly driving video figure
Picture.
(2) present invention utilizes sensor automatic identification Changes in weather, and realizes that system communication, system are opened by CAN bus
Open automatic convenience.
(3) image processing algorithm is applied to driving field by the present invention, greatly improves drive safety.
Detailed description of the invention
Fig. 1 is present system structure composition figure；
Fig. 2 is present system flow chart；
Fig. 3 is the present device location drawing；
Label declaration:
1, haze sensor；2, camera module；3, Raindrop sensor；4, car light module.
Specific embodiment
Present invention is further described in detail with specific embodiment with reference to the accompanying drawing:
The present invention provides a kind of motor vehicle driving vision enhancement system, using the improved dark primary priori algorithm process greasy weather
Video, the captured image being more suitable in processing traffic driving procedure, improves the effect of video defogging processing.Using K-
Means clustering algorithm handles rainy day image, restores clearly rainy day image.Simultaneously by sensor technology and image processing techniques
It blends, so that rain and fog weather detection more automates, is accurately finished the unlatching of system.System can be effectively improved rain at this stage
The safety issue in driving path field under greasy weather gas.
Present system structure composition figure as shown in Figure 1, system flow chart as shown in Fig. 2, device location figure such as Fig. 3 institute
Show wherein there is haze sensor 1 below car body front glass, there is camera mould above car body front glass
Block, car body top are provided with Raindrop sensor 3, and car light respectively has a car light module 4 in front of two side lights of car body, this
Application system main body consists of two parts, and is divided into detection and photographing module outside enhancing system car display module and vehicle.
Wherein greasy weather vision increases using the particle concentration in haze sensor perception ambient enviroment, using Sharp optics
Dust sensor (GP2Y1010AU0F), for detecting diameter greater than 0.8 μm of dust granule concentration.When particle concentration reaches shape
At haze grade when, by CAN bus to dsp chip, open system video dehazing function, while car light flashing warning drives
Member simultaneously opens fog lamp.
Wherein rainy day vision increases is fallen using haze sensor perception raindrop, using Sharp optics dust sensor
(GP2Y1010AU0F), for detecting diameter greater than 0.8 μm of dust granule concentration.When particle concentration reach to be formed haze etc.
When grade, by CAN bus to dsp chip, open system video dehazing function, while car light flashing warning driver.
System installs the camera of 13,000,000 pixels above vehicle outside vehicle window, it can be achieved that road environment real-time video
Shooting.Vehicle interior has the live video stream defogging system based on dark primary elder generation checking method, at TSM320DSP chip defogging
Reason will clearly video be shown on 7 cun of LCD displays.
Image defogging is realized using dark primary elder generation checking method.The general top half of driving vision image is sky portion, is answered
It is separately handled with object parts.Histogram equalization algorithm process is used for the sky portion of image.Furthermore to the object of image
Body portion calculates full figure dark primary figure, after calculating atmosphere light ingredient according to the dark primary figure, judges described calculated
Whether each channel value of atmosphere light ingredient is more than preset value, if then substituting the corresponding of calculated atmosphere light ingredient with preset value
Channel value；It calculates typical traffic scene image and estimates transmittance figure；Calculate Steerable filter figure；It calculates and obtains fine transmissivity
Figure；It eventually forms model equation and calculates fog free images.
The raindrop detection and removal of rainy day image are realized using K-means clustering algorithm.After successfully detecting rain belt, lead to
It crosses and replaces the pixel of the raindrop detected to reach removal effect with the mixed number of raindrop and background colour asked.
The above described is only a preferred embodiment of the present invention, being not the limit for making any other form to the present invention
System, and made any modification or equivalent variations according to the technical essence of the invention, still fall within present invention model claimed
It encloses.
Claims (7)
1. motor vehicle driving vision enhancement system, which is characterized in that the motor vehicle driving vision enhancement system includes being based on changing
Into dark primary elder generation checking method haze sky driving vision enhancing system and based on the rainy day driving vision of K-means clustering algorithm
The improved dark primary of enhancing system, the haze sky driving vision enhancing system based on improved dark primary elder generation checking method is first
Checking method is used to handle traffic video image when greasy weather driving, the rainy day driving vision based on K-means clustering algorithm
The K-means clustering algorithm of enhancing system is used to handle traffic video image when rainy day driving, the motor vehicle driving vision
Enhancing system support driving vision enhances equipment, driving vision enhancing equipment include the haze sensor being set to outside vehicle,
Raindrop sensor, camera module, car light module, and it is set to interior main control module and display device, the haze passes
The lower section of car body front glass is arranged in sensor, and the top of car body front glass is arranged in the camera module,
The Raindrop sensor is arranged at the top of car body, and there are two before two side lights of car body are respectively set for the car light module
In square car light, for the haze sensor for detecting greasy weather weather, the Raindrop sensor is described for detecting rainy weather
Main control module is responsible for the control of the acquisition of data, the unlatching of warning device and fog lamp headlight.
2. motor vehicle driving vision enhancement system according to claim 1, it is characterised in that: the improved dark primary is first
Checking method scratches nomography using Poisson and obtains fine transmissivity by estimation transmissivity distribution, restores object light to handle view
Frequency image, the final reinforcing effect realized to driving vision, the specific steps are as follows:
Step 1: estimation transmissivity；
In computer vision, iconic model containing mist is as follows:
I (x)=J (x) t (x)+A (1-t (x))
Wherein, for I (x) to mist elimination image, J (x) is fog free images to be restored, and A is atmosphere light ingredient, and t (x) is transmissivity；
According to dark primary priori theoretical, the dark primary of fog free images is always gloomy, and the dark primary of the image containing mist is with higher
Intensity value, it is assumed that each window internal transmission factor t (x) be constant, to above formula carry out twice minimum value processing it is available under
Formula:
In above formula, J is fog free images to be asked, and dark primary priori theoretical has:
Therefore:
Iteration can obtain:
This is transmissivityDiscreet value because air is there are particle, therefore need pairIt is modified, one is introduced in formula
A coefficient between [0,1], by experimental verification, the coefficient desirable 0.95, then above formula can be corrected are as follows:
Step 2: transmissivity distribution function is improved
Stingy figure equation on mist image formation model equation and computer graphical is similar in form, and the distribution of transmissivity is in fact
It is the distribution of Alpha, therefore, applies Poisson and scratch nomography to improve transmissivity distribution function, iconic model containing mist is carried out
It takes partial derivative to handle, can obtain:
In the case where background is smooth,Relative toVery little, therefore have:
Nomography principle is scratched according to Poisson, available:
Wherein, Δ is Laplace operator, and div is divergence operator, then can seek t using Gauss-Sidel iterative algorithm
(x)；
Step 3: object light is restored；
In practice, A value can be obtained from foggy image by means of dark channel diagram, first according to brightness from dark channel diagram
Size take preceding 0.1% pixel to find in original foggy image I corresponding with maximum brightness in these positions
The value of point, as A value.To this step, so that it may carry out the recovery of fog free images；
When the value very little of projection figure t, the value that will lead to J is bigger than normal, so that it is whole excessive to white field to make image, therefore can generally set
Set a threshold value T0, when t value is less than T0, enable t=T0, all effect pictures are with T0=0.1 is criterion calculation, and final recovery is public
Formula is as follows:
3. motor vehicle driving vision enhancement system according to claim 1, it is characterised in that: the K-means cluster is calculated
Method is the K-means clustering method based on objective function, detects raindrop region and removes, restored image.
4. motor vehicle driving vision enhancement system according to claim 1, it is characterised in that: the haze sensor uses
Optics dust sensor, the optics dust sensor model GP2Y1010AU0F, for detecting diameter greater than 0.8 μm of dust
Granule density, and haze sky vision enhancement system is opened when detectable concentration is greater than the set value.
5. motor vehicle driving vision enhancement system according to claim 1, it is characterised in that: the main control module uses
TSM320DSP chip carrying video processnig algorithms.
6. motor vehicle driving vision enhancement system according to claim 1, it is characterised in that: the display device uses 7
Very little LCD display is connect by dsp chip with vehicle-borne CCD camera, and shows the real-time video after image defogging algorithm process
Stream.
7. motor vehicle driving vision enhancement system according to claim 1, it is characterised in that: the car light module passes through
CAN bus is connected to control mainboard.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811403887.3A CN109584176B (en) | 2018-11-23 | 2018-11-23 | Vision enhancement system for motor vehicle driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811403887.3A CN109584176B (en) | 2018-11-23 | 2018-11-23 | Vision enhancement system for motor vehicle driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109584176A true CN109584176A (en) | 2019-04-05 |
| CN109584176B CN109584176B (en) | 2021-07-23 |
Family
ID=65924153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811403887.3A Active CN109584176B (en) | 2018-11-23 | 2018-11-23 | Vision enhancement system for motor vehicle driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109584176B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112140998A (en) * | 2020-10-12 | 2020-12-29 | 华南师范大学 | Vision enhancement defogging system for assisting motor vehicle driving |
| CN113364937A (en) * | 2021-05-13 | 2021-09-07 | 西安交通大学 | Method and system for acquiring supervised video real defogging data set |
| US11124173B2 (en) * | 2018-07-17 | 2021-09-21 | Jaguar Land Rover Limited | Method and apparatus for outputting a control signal |
| CN113487882A (en) * | 2021-06-16 | 2021-10-08 | 东风柳州汽车有限公司 | Driving warning method, device, equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101783012A (en) * | 2010-04-06 | 2010-07-21 | 中南大学 | Automatic image defogging method based on dark primary colour |
| CN102510482A (en) * | 2011-11-29 | 2012-06-20 | 蔡棽 | Image splicing reconstruction and overall monitoring method for improving visibility and visual distance |
| US8340461B2 (en) * | 2010-02-01 | 2012-12-25 | Microsoft Corporation | Single image haze removal using dark channel priors |
| CN103077501A (en) * | 2012-12-30 | 2013-05-01 | 信帧电子技术（北京）有限公司 | Road target marking method and device |
| CN103700070A (en) * | 2013-12-12 | 2014-04-02 | 中国科学院深圳先进技术研究院 | Video raindrop-removing algorithm based on rain-tendency scale |
| KR101448164B1 (en) * | 2013-04-22 | 2014-10-14 | 금오공과대학교 산학협력단 | Method for Image Haze Removal Using Parameter Optimization |
| CN105512623A (en) * | 2015-12-02 | 2016-04-20 | 吉林大学 | Foggy-day driving visual enhancement and visibility early warning system and method based on multiple sensors |
| CN106991663A (en) * | 2017-04-05 | 2017-07-28 | 淮海工学院 | A kind of under water colour-image reinforcing method theoretical based on dark |
| CN107516295A (en) * | 2016-06-15 | 2017-12-26 | 诺基亚技术有限公司 | The method and apparatus for removing the noise in image |
-
2018
- 2018-11-23 CN CN201811403887.3A patent/CN109584176B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8340461B2 (en) * | 2010-02-01 | 2012-12-25 | Microsoft Corporation | Single image haze removal using dark channel priors |
| CN101783012A (en) * | 2010-04-06 | 2010-07-21 | 中南大学 | Automatic image defogging method based on dark primary colour |
| CN102510482A (en) * | 2011-11-29 | 2012-06-20 | 蔡棽 | Image splicing reconstruction and overall monitoring method for improving visibility and visual distance |
| CN103077501A (en) * | 2012-12-30 | 2013-05-01 | 信帧电子技术（北京）有限公司 | Road target marking method and device |
| KR101448164B1 (en) * | 2013-04-22 | 2014-10-14 | 금오공과대학교 산학협력단 | Method for Image Haze Removal Using Parameter Optimization |
| CN103700070A (en) * | 2013-12-12 | 2014-04-02 | 中国科学院深圳先进技术研究院 | Video raindrop-removing algorithm based on rain-tendency scale |
| CN105512623A (en) * | 2015-12-02 | 2016-04-20 | 吉林大学 | Foggy-day driving visual enhancement and visibility early warning system and method based on multiple sensors |
| CN107516295A (en) * | 2016-06-15 | 2017-12-26 | 诺基亚技术有限公司 | The method and apparatus for removing the noise in image |
| CN106991663A (en) * | 2017-04-05 | 2017-07-28 | 淮海工学院 | A kind of under water colour-image reinforcing method theoretical based on dark |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11124173B2 (en) * | 2018-07-17 | 2021-09-21 | Jaguar Land Rover Limited | Method and apparatus for outputting a control signal |
| CN112140998A (en) * | 2020-10-12 | 2020-12-29 | 华南师范大学 | Vision enhancement defogging system for assisting motor vehicle driving |
| CN113364937A (en) * | 2021-05-13 | 2021-09-07 | 西安交通大学 | Method and system for acquiring supervised video real defogging data set |
| CN113364937B (en) * | 2021-05-13 | 2022-10-25 | 西安交通大学 | Method and system for acquiring supervised video real defogging data set |
| CN113487882A (en) * | 2021-06-16 | 2021-10-08 | 东风柳州汽车有限公司 | Driving warning method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109584176B (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108515909B (en) | Automobile head-up display system and obstacle prompting method thereof | |
| CN109584176A (en) | Motor vehicle driving vision enhancement system | |
| CN107862290B (en) | Lane line detection method and system | |
| CN111829549B (en) | Snow pavement virtual lane line projection method based on high-precision map | |
| CN105354806B (en) | Rapid defogging method and system based on dark | |
| US20110184895A1 (en) | Traffic object recognition system, method for recognizing a traffic object, and method for setting up a traffic object recognition system | |
| TW201716266A (en) | Image inpainting system area and method using the same | |
| CN111860120B (en) | Automatic shielding detection method and device for vehicle-mounted camera | |
| CN105844595B (en) | The method for building model recovery night traffic video car light based on atmospheric reflectance-scattering principle | |
| US20120162425A1 (en) | Device and method for securing visibility for driver | |
| TWI749030B (en) | Driving assistance system and driving assistance method | |
| CN104766286A (en) | Image defogging device and method based on pilotless automobile | |
| CN105701783A (en) | Single image defogging method based on ambient light model and apparatus thereof | |
| CN106780362B (en) | Road video defogging method based on dichromatic reflection model and bilateral filtering | |
| KR20230093471A (en) | Correction of omnidirectional camera system images with rain, light smear and dust | |
| CN111815556A (en) | Vehicle-mounted fisheye camera self-diagnosis method based on texture extraction and wavelet transformation | |
| KR101998027B1 (en) | Method and System for synthesizing fog and rain image based on machine learning of road object detection in bad weather | |
| CN112465720B (en) | Image defogging method and device based on image sky segmentation and storage medium | |
| CN107316284A (en) | Intense light source hypograph defogging method and device | |
| CN110341602A (en) | A kind of automobile front and rear windshield auxiliary display system and display methods | |
| CN111800586B (en) | Virtual exposure processing method for vehicle-mounted image, vehicle-mounted image splicing processing method and image processing device | |
| CN112140998A (en) | Vision enhancement defogging system for assisting motor vehicle driving | |
| CN113840123B (en) | Image processing device of vehicle-mounted image and automobile | |
| KR102115579B1 (en) | Vehicle side view system | |
| CN113538311A (en) | Image fusion method based on human eye subjective visual effect vehicle-mounted redundant camera |
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 |