CN108198417A - A kind of road cruising inspection system based on unmanned plane - Google Patents
A kind of road cruising inspection system based on unmanned plane Download PDFInfo
- Publication number
- CN108198417A CN108198417A CN201711471859.0A CN201711471859A CN108198417A CN 108198417 A CN108198417 A CN 108198417A CN 201711471859 A CN201711471859 A CN 201711471859A CN 108198417 A CN108198417 A CN 108198417A
- Authority
- CN
- China
- Prior art keywords
- road
- image
- unmanned plane
- region
- pixel
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
A kind of road cruising inspection system based on unmanned plane of present invention offer, a kind of road cruising inspection system based on unmanned plane, including：Ground control centre and unmanned plane；The unmanned plane includes control module, camera module, wireless transport module and GPS positioning module, wherein：Camera module is used to shoot road image；GPS module is used to carry out precise positioning to unmanned plane, obtains the real-time positioning information of unmanned plane；The wireless transport module is used to the road image and location information are sent to ground control centre, and receive the patrol plan sent from ground control centre；Control module is used to control the flight path of unmanned plane according to the patrol plan；The ground control centre sends patrol plan for receiving the image sent from the unmanned plane and location information to the unmanned plane.The present invention obtains road image by unmanned plane, and road conditions are monitored in real time, and intelligent strong, accuracy is high.
Description
Technical field
The present invention relates to lane detection technology field, particularly a kind of road cruising inspection system based on unmanned plane.
Background technology
In recent years, expressway construction achieves fast development, but at the same time generation is a series of per annual meeting for highway
Traffic accidents problem.Other than road quality problem, vehicle safety problem, also there are overspeed of vehicle, vehicle are illegal
Many human factors such as lane change.
Existing highway inspection be mostly using go on patrol vehicle carry out inspection or using fixed point camera carry out data adopt
Collection.The manpower and materials needed using patrol vehicle inspection are of high cost, while influenced by routing inspection view, can only inspection to cruiser
Traffic around, there are acquisition blind areas, may additionally increase traffic jam；Fixed-point data is carried out using camera
Acquisition is only able to detect the condition of road surface at installation camera, can only collect single speed information in addition, obtained traffic
Condition parameter is less, it is impossible to grasp traffic comprehensively.
Invention content
In view of the above-mentioned problems, a kind of the present invention is intended to provide road cruising inspection system based on unmanned plane.
The purpose of the present invention is realized using following technical scheme：
A kind of road cruising inspection system based on unmanned plane, including：Ground control centre and unmanned plane；
The unmanned plane includes camera module, GPS module, wireless transport module and control module, wherein：
Camera module is used to shoot road image；
GPS module is used to carry out precise positioning to unmanned plane, obtains the real-time positioning information of unmanned plane；
The wireless transport module is used to the road image and location information being sent to ground control centre, and receive
The patrol plan sent from ground control centre；
Control module is used to control the flight path of unmanned plane according to the patrol plan；
The ground control centre for receiving the image sent from the unmanned plane and location information, and to it is described nobody
Machine sends patrol plan.
Preferably, the ground control centre further includes image processing module, for carrying out intelligence to the road image of end
Energy monitoring processing, the automatic road conditions detected in road image.
Preferably, the road conditions include finding smoothly, congestion and traffic accident.
Beneficial effects of the present invention are：The present invention on unmanned plane by carrying camera, by the way of unmanned plane pair
Road is shot, and obtains comprehensive road image, and road image is real-time transmitted to control centre by unmanned plane, and
Control centre carries out intelligent processing to the pavement image of reception, and road conditions are monitored automatically, and intelligent strong, accuracy is high,
Manpower can be effectively saved.
Description of the drawings
Using attached drawing, the invention will be further described, but the embodiment in attached drawing does not form any limit to the present invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the frame construction drawing of the present invention；
Fig. 2 is the frame construction drawing of image processing module of the present invention；
Fig. 3 is the frame construction drawing of image processing module in one embodiment of the invention.
Reference numeral：
Unmanned plane 1, ground control centre 2, camera module 11, GPS module 12, wireless transport module 13, control module
14th, image processing module 21, image pre-processing unit 210, lane segmentation unit 211 and road conditions recognition unit 212
Specific embodiment
With reference to following application scenarios, the invention will be further described.
Referring to Fig. 1, a kind of road cruising inspection system based on unmanned plane, which is characterized in that including：2 He of ground control centre
Unmanned plane 1；
The unmanned plane 1 includes camera module 11, GPS module 12, wireless transport module 13 and control module 14,
In：
Camera module 11 is used to shoot road image；
GPS module 12 is used to carry out precise positioning to unmanned plane 1, obtains the real-time positioning information of unmanned plane 1；
The wireless transport module 13 is used to the road image and location information being sent to ground control centre 2, and
Receive the patrol plan sent from ground control centre 2；
Control module 14 is used to control the flight path of unmanned plane 1 according to the patrol plan；
The ground control centre 2 is for receiving the image sent from the unmanned plane 1 and location information, and to the nothing
Man-machine 1 sends patrol plan.
Preferably, the ground control centre 2 further includes image processing module 21, for being carried out to the road image of end
Intellectual monitoring processing, the automatic road conditions detected in road image.
Preferably, the road conditions include finding smoothly, congestion and traffic accident.
Above preferred embodiment of the present invention, by carrying camera on unmanned plane, to road by the way of unmanned plane
It is shot, obtains comprehensive road image, road image is real-time transmitted to, and controlling by control centre by unmanned plane
Center carries out intelligent processing to the pavement image of reception, and road conditions are monitored automatically, and intelligent strong, accuracy is high, can
It is effectively saved manpower.
Preferably, referring to Fig. 2, described image processing module 21 includes image pre-processing unit 210, lane segmentation unit
211 and road conditions recognition unit 212, wherein：
Image pre-processing unit 210 obtains pretreated mileage chart for being pre-processed to the road image of reception
Picture；
Lane segmentation unit 211 to pretreated road image for being split processing, by the roadway area in image
Regional partition comes out；
Road conditions recognition unit 212 identifies the traffic feelings in road area for the road area being identified processing
Condition.
This preferred embodiment by handling the road image shot from unmanned plane, is partitioned into specific from figure
Then road area is identified the road conditions of road further according to the vehicle distribution situation in road area, obtain traffic information,
Cruising inspection system is contributed to obtain the real-time traffic condition of road.
Preferably, described image pretreatment unit 210, specifically includes：
(1) dark channel image of road image is obtained；
(2) obtain the propagation parameter of road image, wherein the propagation parameter that uses obtain function for：
In formula, C (y) represents the propagation parameter of road image pixel y, and wherein the value of C (y) is smaller represents that distance is adopted as setting
Standby more remote, bigger expression distance is adopted as equipment is nearer, and H represents the brightness of road image, and T represents the bright of object in road image
Degree, u ∈ r, g, b represented under r, g, b channel, and E represents the brightness of atmosphere light in road image, τ (y) represent using pixel y as
The rectangular area at center；Preferably, the rectangular area size selection 15 × 15；
Wherein, the acquisition methods of the brightness of atmosphere light are：In dark channel image by the brightness of each pixel from high to low
It is arranged, chooses highest preceding 1/1000 pixel of brightness, and these pixels are found out with highest in road image
Brightness of the value of brightness as atmosphere light；
(3) obtain the scale parameter of each pixel in road image, wherein the scale parameter function used for：
In formula, D (y) represents the scale parameter of pixel y in road image, and C (y) represents pixel y in road image
Propagation parameter, μ represent the rescaling factor, and γ represents scale threshold factor；
(4) to road image different zones, different single scale Retinex algorithms pair is used according to the scale parameter of acquisition
Image carries out enhancing processing, obtains pretreated road image.
In the prior art, enhancing processing is carried out to image using traditional Retinex algorithm, wherein using single scale
The feature that Retinex algorithm cannot be well adapted for image is enhanced, and multi-Scale Retinex Algorithm is used to exist and is calculated
The problem of complexity is higher；Therefore, this preferred embodiment pre-processes road image using the above method, first basis
The characteristic of road image obtains the scale parameter of different zones, and then image is carried out at enhancing according to different scale parameters
Reason, makes image more adapt to eye-observation characteristic, and enhancing effect is good, and complexity is low, can efficiently solve the figure of unmanned plane shooting
Because weather effect leads to the atomization of image and unsharp problem as in, can adapt to various bad weather circumstances leads to image not
The problem of clear, to lay a good foundation after system to being further processed for road image.
Preferably, the lane segmentation unit 211 specifically includes：
(1) K mean cluster processing is carried out to image, divides an image into different region rm, wherein representing all strokes with R
Region r after pointmSet；
(2) obtain any two adjacent area similarity, wherein the similarity function used for：
In formula, Sd(rm,rn) represent region rmWith region rnSimilarity, Pα(rm,rn) represent region rmWith region rnClass
Between difference, obtained by the distance of the RGB of interregional RGB histograms, Pβ(rm) and Pβ(rn) region r is represented respectivelymAnd region
rnClass in difference, by obtaining in region the brightness of neighborhood territory pixel point and the maximum value of gray difference in pixel and its region
It obtains, specially：Wherein ML(x) and MH(x) represent pixel x with it in region respectively
Neighborhood territory pixel point brightness and gray scale difference maximum value, b (rn) represent the threshold function table set, wherein|r
| represent the number of different pixels point in the r of region, v represents the segmentation controlling elements of setting；
(3) similarity of each region and adjacent area in image is obtained successively, if the similarity S obtainedd(rm,rn)=
1, two regions are merged；If Sd(rm,rn)=0, then the boundary in two regions of label is as road edge；
(4) all areas in image are traversed, obtain road-edge detection as a result, and being partitioned into roadway area according to the result
Domain.
This preferred embodiment adopts and road image is handled with the aforedescribed process, obtains the boundary of road in image, so
Accurate road area is split further according to road boundary afterwards；Image is subjected to primary segmentation first, is divided the image into
Multiple regions, then merge the high region of similarity by comparing the similarity of adjacent area, retain distinguish larger region and its
Boundary is as final lane segmentation edge, and adaptable, accuracy is high, can accurately extract the road edge in image, be
It lays a good foundation later to road area segmentation and monitoring.
Preferably, in actual treatment, the testing result of road edge is there are unsharp problem, by target in image
Form and noise interference, cause road edge that can all carry burr different in size.Therefore, the road in image is obtained
It after Road Edge, needs to be further processed road edge the extra burr of removal, for this purpose, the lane segmentation unit 211 is also
Deburring processing is carried out to the road edge of acquisition using following method, specially：
(1) setting is as T (x, y)=0, it is believed that the pixel is road edge, otherwise it is assumed that being background dot；
(2) for pixel n, if meeting T (xn,yn)=0 counts T (x in its 8 neighborhoodn+zx,yn+zyThe pixel of)=0
The number of point is simultaneously included in SnIn, wherein zx,zy=-1,0,1；If Sn=1, then the pixel is vertex JnIf Sn>3, by this
Pixel is denoted as lines branch point Kn；
(3) the branch point K of label is deleted in original image T (x, y)nAfterwards, the edge of connection is marked, obtains label figure Tp(x,
y)；
(4) in TpIn (x, y), J is calculated since each vertexnThe length at place edge, and use NnTo represent；
(5) to carry out burr elimination, then set length threshold asTake minimum length min (Nn), ifThen by min (Nn) it is corresponding connection edge labelling be T (x, y)=1；
(6) the lines branch point K to undeleten, and it is jagged until eliminating to repeat step (1)-(5).
This preferred embodiment adopts and the image after segmentation is post-processed with the aforedescribed process, can effectively remove
The burr of road boundary, raising road area segmentation precision in the image segmentation of road are system further to the monitoring of road area
It lays a good foundation with road conditions extraction.
Preferably, referring to Fig. 3, described image processing module 21 further includes image mosaic unit 213, for there is overlapping portion
Point treated, and road image carries out splicing, obtains global road image, including：To treated, road image carries out
Feature point extraction, characteristic matching eliminate parameter transformation and image integration processing between erroneous matching, image；
Wherein, the feature point extraction, specifically includes：
(1) the feature point set S1 of SIFT algorithms extraction image is utilized
(2) obtain image border point set S2, the discriminant function specifically used for：
In formula, p (x, y) is discriminant function, as p (x, y)=0, then pixel (x, y) is included into edge point set S2, G
The Grad of (x, y) expression pixel (x, y), wherein G (x, y)=| cx(x,y)|+|cy(x, y) |, cx(x, y) and cy(x,y)
Respectively represent pixel (x, y) in the horizontal direction with the first differential of vertical direction, ωTRepresent the Grads threshold of setting；
(3) pixel in 3 × 3 neighborhoods of each pixel in edge point set S2 is obtained, it will be in these pixels and S2
The set of each pixel is set as set S3；
(4) the pixel one-to-one correspondence in the pixel and S3 in S1 is compared, if finding the picture of same coordinate
Vegetarian refreshments then removes this pixel from set S1；
(5) using the pixel in set S1 as finally selected characteristic point.
This preferred embodiment is handled the image of acquisition using the above method, all image mosaics to unification
In panorama reference chart, can it is more intuitive, the road image acquired from unmanned plane is shown in more detail.
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 range is protected, although being explained in detail with reference to preferred embodiment to the present invention, those of ordinary skill in the art should
Work as analysis, technical scheme of the present invention can be modified or replaced equivalently, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of road cruising inspection system based on unmanned plane, which is characterized in that including：Ground control centre and unmanned plane；
The unmanned plane includes camera module, GPS module, wireless transport module and control module, wherein：
Camera module is used to shoot road image；
GPS module is used to carry out precise positioning to unmanned plane, obtains the real-time positioning information of unmanned plane；
The wireless transport module is used to the road image and location information are sent to ground control centre, and receive from ground
The patrol plan that face control centre sends；
Control module is used to control the flight path of unmanned plane according to the patrol plan；
It is sent out for receiving the image sent from the unmanned plane and location information to the unmanned plane ground control centre
Send patrol plan.
A kind of 2. road cruising inspection system based on unmanned plane according to claim 1, which is characterized in that the ground control
Center further includes image processing module, for carrying out intellectual monitoring processing to the road image of end, detects road image automatically
In road conditions.
3. a kind of road cruising inspection system based on unmanned plane according to claim 3, which is characterized in that the road conditions include
It was found that smoothly, congestion and traffic accident.
A kind of 4. road cruising inspection system based on unmanned plane according to claim 2, which is characterized in that described image processing
Module includes image pre-processing unit, lane segmentation unit and road conditions recognition unit, wherein：
Image pre-processing unit obtains pretreated road image for being pre-processed to the road image of reception；
Road area in image is partitioned by lane segmentation unit for being split processing to pretreated road image
Come；
Road conditions recognition unit identifies the traffic conditions in road area for the road area being identified processing.
5. a kind of road cruising inspection system based on unmanned plane according to claim 4, which is characterized in that described image is located in advance
Unit is managed, is specifically included：
(1) dark channel image of road image is obtained；
(2) obtain the propagation parameter of road image, wherein the propagation parameter that uses obtain function for：
In formula, C (y) represents the propagation parameter of road image pixel y, and wherein the value of C (y) is smaller represents that distance is adopted as equipment is got over
Far, it is bigger expression distance adopt as equipment it is nearer, H represent road image brightness, T represent road image in object brightness, u ∈
R, g, b represent that under r, g, b channel E represents the brightness of atmosphere light in road image, and τ (y) is represented centered on pixel y
Rectangular area；
Wherein, the acquisition methods of the brightness of atmosphere light are：The brightness of each pixel is carried out from high to low in dark channel image
Highest preceding 1/1000 pixel of brightness is chosen in arrangement, and finds out these pixels with maximum brightness in road image
Brightness of the value as atmosphere light；
(3) obtain the scale parameter of each pixel in road image, wherein the scale parameter function used for：
In formula, D (y) represents the scale parameter of pixel y in road image, and C (y) represents the propagation of pixel y in road image
Parameter, μ represent the rescaling factor, and γ represents scale threshold factor；
(4) to road image different zones, according to the scale parameter of acquisition using different single scale Retinex algorithms to image
Enhancing processing is carried out, obtains pretreated road image.
A kind of 6. road cruising inspection system based on unmanned plane according to claim 5, which is characterized in that the lane segmentation
Unit specifically includes：
(1) K mean cluster processing is carried out to image, divides an image into different region rm, wherein after representing all divisions with R
Region rmSet；
(2) obtain any two adjacent area similarity, wherein the similarity function used for：
In formula, Sd(rm,rn) represent region rmWith region rnSimilarity, Pα(rm,rn) represent region rmWith region rnClass between it is poor
It is different, it is obtained by the distance of the RGB of interregional RGB histograms, Pβ(rm) and Pβ(rn) region r is represented respectivelymWith region rn's
Difference in class is obtained by obtaining pixel in region with the brightness of neighborhood territory pixel point in its region and the maximum value of gray difference
, specially：Wherein ML(x) and MH(x) represent pixel x with it in region respectively
The brightness of neighborhood territory pixel point and the maximum value of the difference of gray scale, b (rn) represent the threshold function table set, wherein|r|
Represent the number of different pixels point in the r of region, v represents the segmentation controlling elements of setting；
(3) similarity of each region and adjacent area in image is obtained successively, if the similarity S obtainedd(rm,rn)=1, will
Two regions merge；If Sd(rm,rn)=0, then the boundary in two regions of label is as road edge；
(4) all areas in image are traversed, obtain road-edge detection as a result, and being partitioned into road area according to the result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711471859.0A CN108198417B (en) | 2017-12-29 | 2017-12-29 | A kind of road cruising inspection system based on unmanned plane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711471859.0A CN108198417B (en) | 2017-12-29 | 2017-12-29 | A kind of road cruising inspection system based on unmanned plane |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108198417A true CN108198417A (en) | 2018-06-22 |
| CN108198417B CN108198417B (en) | 2018-10-12 |
Family
ID=62586370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711471859.0A Active CN108198417B (en) | 2017-12-29 | 2017-12-29 | A kind of road cruising inspection system based on unmanned plane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108198417B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108873901A (en) * | 2018-06-27 | 2018-11-23 | 深圳市创艺工业技术有限公司 | A kind of Unmanned Systems |
| CN109636848A (en) * | 2018-12-17 | 2019-04-16 | 武汉天乾科技有限责任公司 | A kind of oil-gas pipeline method for inspecting based on unmanned plane |
| CN109754485A (en) * | 2018-12-27 | 2019-05-14 | 高戎戎 | A kind of road furniture cruising inspection system based on radio frequency identification |
| CN110046584A (en) * | 2019-04-19 | 2019-07-23 | 上海海事大学 | A kind of road crack detection device and detection method based on unmanned plane inspection |
| CN111309048A (en) * | 2020-02-28 | 2020-06-19 | 重庆邮电大学 | Method for detecting autonomous flight along road by combining multi-rotor unmanned aerial vehicle with road |
| CN112198899A (en) * | 2020-09-30 | 2021-01-08 | 安徽乐道信息科技有限公司 | Road detection method, equipment and storage medium based on unmanned aerial vehicle |
| CN113033301A (en) * | 2021-02-07 | 2021-06-25 | 北京中交创新投资发展有限公司 | Method for collecting road inspection facility data based on AI image recognition technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104332053A (en) * | 2014-11-13 | 2015-02-04 | 深圳大学 | Road traffic inspection system and method based on small unmanned aerial vehicle |
| CN105389988A (en) * | 2015-12-07 | 2016-03-09 | 北京航空航天大学 | Multi-unmanned aerial vehicle cooperation highway intelligent inspection system |
| US20170103265A1 (en) * | 2015-10-07 | 2017-04-13 | Accenture Global Solutions Limited | Border inspection with aerial cameras |
| CN206532417U (en) * | 2017-01-17 | 2017-09-29 | 长安大学 | A kind of highway driving environment automatic Synthesis monitor warning systems based on unmanned plane |
-
2017
- 2017-12-29 CN CN201711471859.0A patent/CN108198417B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104332053A (en) * | 2014-11-13 | 2015-02-04 | 深圳大学 | Road traffic inspection system and method based on small unmanned aerial vehicle |
| US20170103265A1 (en) * | 2015-10-07 | 2017-04-13 | Accenture Global Solutions Limited | Border inspection with aerial cameras |
| CN105389988A (en) * | 2015-12-07 | 2016-03-09 | 北京航空航天大学 | Multi-unmanned aerial vehicle cooperation highway intelligent inspection system |
| CN206532417U (en) * | 2017-01-17 | 2017-09-29 | 长安大学 | A kind of highway driving environment automatic Synthesis monitor warning systems based on unmanned plane |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108873901A (en) * | 2018-06-27 | 2018-11-23 | 深圳市创艺工业技术有限公司 | A kind of Unmanned Systems |
| CN109636848A (en) * | 2018-12-17 | 2019-04-16 | 武汉天乾科技有限责任公司 | A kind of oil-gas pipeline method for inspecting based on unmanned plane |
| CN109636848B (en) * | 2018-12-17 | 2020-12-25 | 武汉天乾科技有限责任公司 | Unmanned aerial vehicle-based oil and gas pipeline inspection method |
| CN109754485A (en) * | 2018-12-27 | 2019-05-14 | 高戎戎 | A kind of road furniture cruising inspection system based on radio frequency identification |
| CN110046584A (en) * | 2019-04-19 | 2019-07-23 | 上海海事大学 | A kind of road crack detection device and detection method based on unmanned plane inspection |
| CN111309048A (en) * | 2020-02-28 | 2020-06-19 | 重庆邮电大学 | Method for detecting autonomous flight along road by combining multi-rotor unmanned aerial vehicle with road |
| CN111309048B (en) * | 2020-02-28 | 2023-05-26 | 重庆邮电大学 | Method for detecting autonomous flight along road by combining multi-rotor unmanned aerial vehicle with road |
| CN112198899A (en) * | 2020-09-30 | 2021-01-08 | 安徽乐道信息科技有限公司 | Road detection method, equipment and storage medium based on unmanned aerial vehicle |
| CN113033301A (en) * | 2021-02-07 | 2021-06-25 | 北京中交创新投资发展有限公司 | Method for collecting road inspection facility data based on AI image recognition technology |
| CN113033301B (en) * | 2021-02-07 | 2024-02-13 | 交信北斗科技有限公司 | Method for acquiring road inspection facility data based on AI image recognition technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108198417B (en) | 2018-10-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108198417B (en) | A kind of road cruising inspection system based on unmanned plane | |
| CN102682292B (en) | Method based on monocular vision for detecting and roughly positioning edge of road | |
| CN101030256B (en) | Method and apparatus for cutting vehicle image | |
| US20200041284A1 (en) | Map road marking and road quality collecting apparatus and method based on adas system | |
| Yan et al. | A method of lane edge detection based on Canny algorithm | |
| CN101334836B (en) | License plate positioning method incorporating color, size and texture characteristic | |
| CN105718872B (en) | Auxiliary method and system for rapidly positioning lanes on two sides and detecting vehicle deflection angle | |
| CN105373135A (en) | Method and system for guiding airplane docking and identifying airplane type based on machine vision | |
| CN110647850A (en) | Automatic lane deviation measuring method based on inverse perspective principle | |
| KR101569919B1 (en) | Apparatus and method for estimating the location of the vehicle | |
| CN107862290A (en) | Method for detecting lane lines and system | |
| CN105203552A (en) | 360-degree tread image detecting system and method | |
| CN102364496A (en) | Method and system for identifying automobile license plates automatically based on image analysis | |
| CN108921076B (en) | Pavement crack disease self-adaptive constant false alarm detection method based on image | |
| CN202134079U (en) | Unmanned vehicle lane marker line identification and alarm device | |
| CN110046584B (en) | Road crack detection device and detection method based on unmanned aerial vehicle inspection | |
| CN108332927A (en) | A kind of bridge surface crack detection device | |
| CN116665080B (en) | Unmanned aerial vehicle deteriorated insulator detection method and system based on target recognition | |
| CN108284793A (en) | A kind of vehicle sub-controlling unit | |
| CN111652033A (en) | Lane line detection method based on OpenCV | |
| CN111144301A (en) | Road pavement defect quick early warning device based on degree of depth learning | |
| CN110276318A (en) | Nighttime road rains recognition methods, device, computer equipment and storage medium | |
| FAN et al. | Robust lane detection and tracking based on machine vision | |
| CN105447431A (en) | Docking airplane tracking and positioning method and system based on machine vision | |
| CN104715250A (en) | Cross laser detection method and device |
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 |