CN107463176A - A kind of round-the-clock automated driving system - Google Patents
A kind of round-the-clock automated driving system Download PDFInfo
- Publication number
- CN107463176A CN107463176A CN201710714512.8A CN201710714512A CN107463176A CN 107463176 A CN107463176 A CN 107463176A CN 201710714512 A CN201710714512 A CN 201710714512A CN 107463176 A CN107463176 A CN 107463176A
- Authority
- CN
- China
- Prior art keywords
- image
- misty
- subsystem
- defogging
- round
- 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
- 230000010365 information processing Effects 0.000 claims abstract description 18
- 230000005540 biological transmission Effects 0.000 claims abstract description 13
- 238000011156 evaluation Methods 0.000 claims description 45
- 239000003595 mist Substances 0.000 claims description 20
- 230000008030 elimination Effects 0.000 claims description 19
- 238000003379 elimination reaction Methods 0.000 claims description 19
- 230000000694 effects Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 claims description 2
- 230000014759 maintenance of location Effects 0.000 claims description 2
- 230000035515 penetration Effects 0.000 claims description 2
- 230000000717 retained effect Effects 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000003707 image sharpening Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000005303 weighing Methods 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
- G05D1/0231—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
-
- 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
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- 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
Abstract
The invention provides a kind of round-the-clock automated driving system, including the client on vehicle, information gathering subsystem, information differentiates subsystem, information processing subsystem and message transmission subsystem, described information acquisition subsystem is used to obtain vehicle front image, described information differentiates that subsystem is used to differentiate whether forward image is Misty Image, if Misty Image, then enter information processing subsystem, if it is non-Misty Image, then enter message transmission subsystem, described information processing subsystem is used to carry out sharpening processing to Misty Image, described information transmission subsystem is used to send the Misty Image after processing and non-Misty Image to client, the client is used for according to the image generation automatic Pilot data received, control the traveling of vehicle.Beneficial effects of the present invention are：Realize round-the-clock automatic Pilot.
Description
Technical field
The present invention relates to automatic Pilot technical field, and in particular to a kind of round-the-clock automated driving system.
Background technology
Existing automated driving system can only be carried out in the case of fine, when the evil for meeting with the poor visibilities such as greasy weather
During bad weather, automatic Pilot can not be carried out or automatic Pilot is ineffective.
The content of the invention
A kind of in view of the above-mentioned problems, the present invention is intended to provide round-the-clock automated driving system.
The purpose of the present invention is realized using following technical scheme：
Provide a kind of round-the-clock automated driving system, including client on vehicle, information gathering subsystem,
Information differentiates subsystem, information processing subsystem and message transmission subsystem, and described information acquisition subsystem is used to obtain vehicle
Forward image, described information differentiate that subsystem is used to differentiate whether forward image is Misty Image, if Misty Image, then entered
Information processing subsystem, if being non-Misty Image, into message transmission subsystem, described information processing subsystem is used for mist
Its image carries out sharpening processing, and described information transmission subsystem is used to send the Misty Image after processing and non-Misty Image
To client, the client is used for the traveling for according to the image generation automatic Pilot data received, controlling vehicle.
Beneficial effects of the present invention are：Realize round-the-clock automatic Pilot.
Brief description of the drawings
Using accompanying drawing, the invention will be further described, but the embodiment in accompanying drawing does not form any limit to the present invention
System, for one of ordinary skill in the art, on the premise of not paying creative work, can also be obtained according to the following drawings
Other accompanying drawings.
Fig. 1 is the structural representation of the present invention；
Reference：
Information gathering subsystem 1, information differentiate subsystem 2, information processing subsystem 3, message transmission subsystem 4, client
End 5.
Embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of round-the-clock automated driving system of the present embodiment, including client 5 on vehicle, letter
Cease acquisition subsystem 1, information differentiates subsystem 2, information processing subsystem 3 and message transmission subsystem 4, described information collection
System 1 is used to obtain vehicle front image, and described information differentiates that subsystem 2 is used to differentiate whether forward image is Misty Image,
It is if Misty Image, then described into message transmission subsystem 4 if being non-Misty Image into information processing subsystem 3
Information processing subsystem 3 is used to carry out Misty Image sharpening processing, and described information transmission subsystem 4 is used for after processing
Misty Image and non-Misty Image are sent to client 5, and the client 5 is used for according to the image generation automatic Pilot received
Data, control the traveling of vehicle.
The present embodiment realizes round-the-clock automatic Pilot.
Preferably, differentiate whether forward image is Misty Image in the following ways：When the air visibility of vehicle front
During less than 2 km, then the vehicle front image obtained is Misty Image, is non-Misty Image otherwise.
This preferred embodiment provides the science discriminant approach of Misty Image.
Preferably, described information acquisition subsystem 1 obtains vehicle front image by high-definition camera.
The image that this preferred embodiment obtains is relatively sharp.
Preferably, described information processing subsystem 3 includes the first image processing module and the second performance evaluation module, described
First image processing module is used to carry out Misty Image defogging processing, and the second performance evaluation module is used for described first
The performance of image processing module is evaluated；Described first image processing module includes single treatment unit, after-treatment unit
Processing unit three times, the single treatment unit are used to handle Misty Image according to the first atmospherical scattering model, obtained
To a mist elimination image, the after-treatment unit is used to handle Misty Image according to the second atmospherical scattering model, obtained
To secondary mist elimination image, the processing unit three times is used to carry out fusion treatment to a mist elimination image and secondary mist elimination image,
Obtain defogging picture rich in detail.
This preferred embodiment information processing subsystem realizes the sharpening processing and the evaluation of process performance of Misty Image,
It ensure that the safe driving under the greasy weather.
Preferably, it is described that Misty Image is handled according to the first atmospherical scattering model, be specially：Step 1, establish
One atmospherical scattering model：EH (x)=R1(x) EM (x)+B [1-EM (x)]+1, in above-mentioned formula, EH (x) represents the greasy weather of collection
Image, B represent that atmosphere light is shone, and EM (x) represents Medium Propagation function, for reflecting the penetration capacity of light, R1(x) represent once
Mist elimination image, x represent image pixel space coordinates；Step 2, ask for R1(x) dark primary image： In above-mentioned formula, R1 c(y) R is represented1 da(x) passage in, r, g, b difference
Represent image R1(x) red channel, green channel and blue channel,Represent centered on x, length of side a square region
Domain, a are 2%, the R on image maximum side1 da(x) R is represented1(x) dark primary image；Step 3, to the first atmospheric scattering mould
Type carries out regional area sizeMini-value filtering, and each passage is minimized：
In above-mentioned formula, BcRepresent the passage that atmosphere light is shone, EHc(y) passage in Misty Image is represented；Step
Rapid 4, from dark primary principle, R1 da(x) tend to 0, Medium Propagation function can be obtained：In above-mentioned formula, the journey of fog is retained for adjusting
Degree, δ is fog retention factors；Step 5, according to the first atmospherical scattering model solve a mist elimination image：
This preferred embodiment single treatment unit is simplified to conventional atmospherical scattering model, is favorably improved calculating
Efficiency, when being filtered to the first atmospherical scattering model, filter field is voluntarily adjusted according to image size, ensure that not
With the defog effect of image.
Preferably, it is described that Misty Image is handled according to the second atmospherical scattering model, be specially：Step 1, establish
Two atmospherical scattering models：In above-mentioned formula, EH (x) represents collection
Misty Image, B represent that atmosphere light is shone, and YW (x) represents atmospheric dissipation function, for reflecting influence of the ambient light to scene imaging,
R2(x) secondary mist elimination image is represented, x represents image pixel space coordinates；Step 2, using following formula Misty Image is put down in vain
Weighing apparatus operation：The Minimal color weight of Misty Image is defined as atmospheric dissipation function：In above-mentioned formula, EHc' (x) represents Misty Image in r, and tri- Color Channels of g, b are most
Small color component；Step 3, secondary mist elimination image solved according to atmospheric dissipation function：Institute
State and fusion treatment is carried out to a mist elimination image and secondary mist elimination image, carried out using following formula：In above-mentioned formula, LG (x) represents defogging picture rich in detail.
This preferred embodiment after-treatment unit is by the way of single treatment unit is different to conventional atmospheric scattering
Model is simplified, and is favorably improved computational efficiency, is obtained fogless picture rich in detail using blending algorithm, is favorably improved fogless
The defog effect of picture rich in detail, obtain the image become apparent from.
Preferably, it is single to include an evaluation unit, second evaluation unit and the 3rd evaluation for the second performance evaluation module
Member, an evaluation unit are used for the first evaluation points for determining defogging picture rich in detail, and the second evaluation unit is used for true
Determine the second evaluation points of defogging picture rich in detail, the 3rd evaluation unit is used for the first evaluation points and the second evaluation points pair
Defogging picture rich in detail is evaluated.
This preferred embodiment the second performance evaluation module merges to multiple evaluation points, realizes at the first image
The accurate evaluation of module performance is managed, ensure that the information processing capability of information processing subsystem.
Preferably, the first evaluation points of defogging picture rich in detail are determined in the following ways：
In above-mentioned formula, n1And n2The number at visible edge in the image and defogging picture rich in detail of collection, CS are represented respectively1Defogging is clear
First evaluation points of image；The second evaluation points of defogging picture rich in detail are determined in the following ways：
In above-mentioned formula, m1And m2Represent that the black pixel point of defogging picture rich in detail and white pixel are counted out respectively, CS2Defogging is clear
Second evaluation points of image；Defogging picture rich in detail is evaluated in the following ways：According to the first evaluation points and second
Evaluation points calculate overall merit factor CS：The overall merit factor is bigger, shows
Fog effect is better, and image is more clear.
Defogging algorithm sharpening effect is quantitatively described this preferred embodiment, realizes the objective of defog effect and comments
Valency, and the evaluation module considers many-sided factor of evaluation, evaluation it is with a high credibility, ensure that the whole day of automated driving system
Wait operation.
Automatic Pilot is carried out using the round-the-clock automated driving system of the present invention, chooses 5 destinations, respectively destination 1,
Destination 2, destination 3, destination 4, destination 5, are counted to automatic Pilot time and automatic Pilot cost, compared with skill
Art is compared, caused to have the beneficial effect that shown in table：
| The automatic Pilot time reduces | Automatic Pilot cost reduces | |
| Destination 1 | 29% | 21% |
| Destination 2 | 27% | 23% |
| Destination 3 | 26% | 25% |
| Destination 4 | 25% | 27% |
| Destination 5 | 24% | 29% |
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of scope is protected, although being explained with reference to preferred embodiment to the present invention, one of ordinary skill in the art should
Work as understanding, technical scheme can be modified or equivalent substitution, without departing from the reality of technical solution of the present invention
Matter and scope.
Claims (8)
1. a kind of round-the-clock automated driving system, it is characterised in that including the client on vehicle, information gathering subsystem
System, information differentiate subsystem, information processing subsystem and message transmission subsystem, and described information acquisition subsystem is used to obtain car
Forward image, described information differentiate that subsystem is used to differentiate whether forward image is Misty Image, if Misty Image, then entered
Enter information processing subsystem, if being non-Misty Image, into message transmission subsystem, described information processing subsystem is used for pair
Misty Image carries out sharpening processing, and described information transmission subsystem is used to send out the Misty Image after processing and non-Misty Image
Client is delivered to, the client is used for the traveling for according to the image generation automatic Pilot data received, controlling vehicle.
2. round-the-clock automated driving system according to claim 1, it is characterised in that differentiate that front is schemed in the following ways
Seem it is no be Misty Image：When the air visibility of vehicle front is less than 2 km, then the vehicle front image obtained is the greasy weather
Image, it is non-Misty Image otherwise.
3. round-the-clock automated driving system according to claim 2, it is characterised in that described information acquisition subsystem passes through
High-definition camera obtains vehicle front image.
4. round-the-clock automated driving system according to claim 3, it is characterised in that described information processing subsystem includes
First image processing module and the second performance evaluation module, described first image processing module are used to carry out defogging to Misty Image
Processing, the second performance evaluation module are used to evaluate the performance of described first image processing module；First figure
As processing module is including single treatment unit, after-treatment unit and processing unit, the single treatment unit are used for root three times
Misty Image is handled according to the first atmospherical scattering model, obtains a mist elimination image, the after-treatment unit is used for root
Misty Image is handled according to the second atmospherical scattering model, obtains secondary mist elimination image, the processing unit three times is used for pair
Mist elimination image and secondary mist elimination image carry out fusion treatment, obtain defogging picture rich in detail.
5. round-the-clock automated driving system according to claim 4, it is characterised in that described according to the first atmospheric scattering mould
Type is handled Misty Image, is specially：Step 1, establish the first atmospherical scattering model：EH (x)=R1(x)EM(x)+B[1-
EM (x)]+1, in above-mentioned formula, EH (x) represents the Misty Image of collection, and B represents that atmosphere light is shone, and EM (x) represents Medium Propagation letter
Number, for reflecting the penetration capacity of light, R1(x) a mist elimination image is represented, x represents image pixel space coordinates；Step 2,
Ask for R1(x) dark primary image：In above-mentioned formula, R1 c(y) table
Show R1 da(x) passage in, r, g, b represent image R respectively1(x) red channel, green channel and blue channel,
Represent centered on x, length of side a square area, a is 2%, the R on image maximum side1 da(x) R is represented1(x) dark original
Color image；Step 3, it is to the first atmospherical scattering model progress regional area sizeMini-value filtering, and to each logical
Minimize in road：Above-mentioned formula
In son, BcRepresent the passage that atmosphere light is shone, EHc(y) passage in Misty Image is represented；It is step 4, former by dark primary
Knowable to reason, R1 da(x) tend to 0, Medium Propagation function can be obtained：On
State in formula, the degree of fog is retained for adjusting, δ is fog retention factors；Step 5, asked according to the first atmospherical scattering model
Solve a mist elimination image：
6. round-the-clock automated driving system according to claim 5, it is characterised in that described according to the second atmospheric scattering mould
Type is handled Misty Image, is specially：Step 1, establish the second atmospherical scattering model： In above-mentioned formula, EH (x) represents the Misty Image of collection, and B represents that atmosphere light is shone, and YW (x) represents atmospheric dissipation
Function, for reflecting influence of the ambient light to scene imaging, R2(x) secondary mist elimination image is represented, x represents that image pixel space is sat
Mark；Step 2, using following formula to Misty Image carry out white balance operation：By Misty Image
Minimal color weight is defined as atmospheric dissipation function：In above-mentioned formula, EHc' (x) is represented
Misty Image is in r, the Minimal color weight of tri- Color Channels of g, b；Step 3, secondary defogging solved according to atmospheric dissipation function
Image：It is described that fusion treatment is carried out to a mist elimination image and secondary mist elimination image, adopt
Carried out with following formula：In above-mentioned formula, LG (x) represents that defogging is clearly schemed
Picture.
7. round-the-clock automated driving system according to claim 6, it is characterised in that the second performance evaluation module bag
An evaluation unit, second evaluation unit and the 3rd evaluation unit are included, an evaluation unit is used to determine that defogging is clearly schemed
First evaluation points of picture, second evaluation points of the second evaluation unit for determining defogging picture rich in detail, the described 3rd
Evaluation unit is used for the first evaluation points and the second evaluation points are evaluated defogging picture rich in detail.
8. round-the-clock automated driving system according to claim 7, it is characterised in that determine that defogging is clear in the following ways
First evaluation points of clear image：In above-mentioned formula, n1And n2The figure of collection is represented respectively
The number at visible edge, CS in picture and defogging picture rich in detail1First evaluation points of defogging picture rich in detail；It is true in the following ways
Determine the second evaluation points of defogging picture rich in detail：In above-mentioned formula, m1And m2Represent that defogging is clear respectively
The black pixel point and white pixel of image are counted out, CS2Second evaluation points of defogging picture rich in detail；It is right in the following ways
Defogging picture rich in detail is evaluated：Overall merit factor CS is calculated according to the first evaluation points and the second evaluation points： The overall merit factor is bigger, shows that defog effect is better, image is more clear.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710714512.8A CN107463176A (en) | 2017-08-18 | 2017-08-18 | A kind of round-the-clock automated driving system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710714512.8A CN107463176A (en) | 2017-08-18 | 2017-08-18 | A kind of round-the-clock automated driving system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107463176A true CN107463176A (en) | 2017-12-12 |
Family
ID=60550117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710714512.8A Pending CN107463176A (en) | 2017-08-18 | 2017-08-18 | A kind of round-the-clock automated driving system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107463176A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108237542A (en) * | 2017-12-26 | 2018-07-03 | 韦德永 | A kind of accurate guide service robot of guiding |
| CN108319263A (en) * | 2017-12-26 | 2018-07-24 | 潘荣兰 | A kind of pilotless automobile |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254313A (en) * | 2011-07-14 | 2011-11-23 | 浙江大学 | Image defogging method based on restoration and fusion of images on foggy days |
| CN202872972U (en) * | 2012-08-24 | 2013-04-10 | 中国人民解放军理工大学气象学院 | Image monitoring and processing device |
| CN103955905A (en) * | 2014-05-13 | 2014-07-30 | 北京邮电大学 | Rapid wavelet transformation and weighted image fusion single-image defogging method |
-
2017
- 2017-08-18 CN CN201710714512.8A patent/CN107463176A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254313A (en) * | 2011-07-14 | 2011-11-23 | 浙江大学 | Image defogging method based on restoration and fusion of images on foggy days |
| CN202872972U (en) * | 2012-08-24 | 2013-04-10 | 中国人民解放军理工大学气象学院 | Image monitoring and processing device |
| CN103955905A (en) * | 2014-05-13 | 2014-07-30 | 北京邮电大学 | Rapid wavelet transformation and weighted image fusion single-image defogging method |
Non-Patent Citations (1)
| Title |
|---|
| S.K. NAYAR 等: "Vision in bad weather", 《 PROCEEDINGS OF THE SEVENTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108237542A (en) * | 2017-12-26 | 2018-07-03 | 韦德永 | A kind of accurate guide service robot of guiding |
| CN108319263A (en) * | 2017-12-26 | 2018-07-24 | 潘荣兰 | A kind of pilotless automobile |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11087151B2 (en) | Automobile head-up display system and obstacle prompting method thereof | |
| CN106803008A (en) | A kind of real-time driving behavior methods of marking and system based on ADAS systems | |
| CN106448062A (en) | Fatigue driving detection method and device | |
| CN111829549A (en) | Snow road surface virtual lane line projection method based on high-precision map | |
| CN105023256B (en) | A kind of image defogging method and system | |
| CN107194989A (en) | The scene of a traffic accident three-dimensional reconstruction system and method taken photo by plane based on unmanned plane aircraft | |
| CN103049888A (en) | Image/video demisting method based on combination of dark primary color of atmospheric scattered light | |
| CN102289791B (en) | Method for quickly demisting single image | |
| CN107133927A (en) | Single image to the fog method based on average mean square deviation dark under super-pixel framework | |
| CN107463176A (en) | A kind of round-the-clock automated driving system | |
| CN105139347A (en) | Polarized image defogging method combined with dark channel prior principle | |
| CN106157270A (en) | A kind of single image rapid defogging method and system | |
| CN106355560B (en) | The extracting method and system of air light value in a kind of haze image | |
| EP4011715A1 (en) | Automatic vehicle window cleaning method and apparatus | |
| CN104766286A (en) | Image defogging device and method based on pilotless automobile | |
| CN103258434A (en) | Image border detecting system based on video traffic flow detection and vehicle identification | |
| WO2021164463A1 (en) | Detection method and apparatus, storage medium | |
| CN103077501A (en) | Road target marking method and device | |
| CN103226809B (en) | Image demister and image haze removal method | |
| CN107396053A (en) | A kind of outdoor safety defense monitoring system | |
| CN103778605A (en) | Greasy weather image enhancement method | |
| CN107145824A (en) | A kind of lane line dividing method and system, car-mounted terminal based on significance analysis | |
| CN108230275A (en) | The method of image defogging | |
| CN104134192A (en) | Image defogging method and system | |
| CN110458029A (en) | Vehicle checking method and device in a kind of foggy environment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171212 |
|
| RJ01 | Rejection of invention patent application after publication |