CN105740837A - Unmanned aerial vehicle-based illegal emergency lane occupancy detection method - Google Patents

Unmanned aerial vehicle-based illegal emergency lane occupancy detection method Download PDF

Info

Publication number
CN105740837A
CN105740837A CN201610083119.9A CN201610083119A CN105740837A CN 105740837 A CN105740837 A CN 105740837A CN 201610083119 A CN201610083119 A CN 201610083119A CN 105740837 A CN105740837 A CN 105740837A
Authority
CN
China
Prior art keywords
unmanned plane
image
road
emergency vehicle
vehicle lane
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
Application number
CN201610083119.9A
Other languages
Chinese (zh)
Other versions
CN105740837B (en
Inventor
张卡
何佳
尼秀明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ANHUI QINGXIN INTERNET INFORMATION TECHNOLOGY Co Ltd
Original Assignee
ANHUI QINGXIN INTERNET INFORMATION TECHNOLOGY Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by ANHUI QINGXIN INTERNET INFORMATION TECHNOLOGY Co Ltd filed Critical ANHUI QINGXIN INTERNET INFORMATION TECHNOLOGY Co Ltd
Priority to CN201610083119.9A priority Critical patent/CN105740837B/en
Publication of CN105740837A publication Critical patent/CN105740837A/en
Application granted granted Critical
Publication of CN105740837B publication Critical patent/CN105740837B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/625—License plates

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides an unmanned aerial vehicle-based illegal emergency lane occupancy detection method. The method comprises the following steps: sending out an unmanned aerial vehicle; positioning a road right edge position; judging whether the road right edge position is positioned; adjusting the orientation of the unmanned aerial vehicle; selecting an emergency lane area; detecting a vehicle position; judging whether the vehicle position is successfully detected; recognizing vehicle license plate characters; storing vehicle information; correcting the fleet angle of the unmanned aerial vehicle; enabling the unmanned aerial vehicle to advance automatically; judging whether the unmanned aerial vehicle flies to an appointed distance; and withdrawing the unmanned aerial vehicle. The method provided by the invention is capable of realizing the automatic flight control of the unmanned aerial vehicle, ignoring any traffic barrier, accurately positioning the emergency lane areas in real time through a video image analysis technology and automatically snapshooting the vehicles in the emergency lane areas, and has the characteristics of realizing all-section snapshooting and being real-time, efficient and accurate in snapshooting and free of barrier.

Description

A kind of take Emergency Vehicle Lane detection method based on the illegal of unmanned plane
Technical field
The present invention relates to intelligent traffic monitoring technical field, specifically a kind of take Emergency Vehicle Lane detection method based on the illegal of unmanned plane.
Background technology
Highway Emergency Vehicle Lane is the rescue passage set up exclusively for the public, at stake the life passage of an enforcement emergency relief especially.Pertinent regulations according to " People's Republic of China's law on road traffic safety " and " People's Republic of China's law on road traffic safety implementing regulations ": except the police car carried out an urgent task, fire fighting truck, breakdown lorry, ambulance, other motor vehicles must not enter and travel in Emergency Vehicle Lane or stop.But, quick growth along with China's automobile pollution, increasing driver, when blocking up occurs in highway, likes illegally occupying Emergency Vehicle Lane and travels or wait, even some drivers when having a good transport and communication network also with being intended in Emergency Vehicle Lane to overtake other vehicles or temporary parking, this is breakneck behavior, once vehicle accident occurs in front, frequently can lead to police car and breakdown lorry cannot quickly be reached the spot, extend the time of traffic congestion, cause rescue difficulty, increase the weight of accident Factual Damage.
In recent years, illegal Emergency Vehicle Lane behavior is taken in order to administer, traffic has carried out corresponding treatment action, utilize the video camera that highway monitoring system and people's police are equipped with, the illegal infringement taking Emergency Vehicle Lane is carried out capturing evidence obtaining by photographing unit, but this mode but has great limitation, first highway monitoring system cannot be carried out the monitoring of system-wide section, secondly people's police are manually captured by video camera and photographing unit, although system-wide section can be realized captures, but it is inefficient, when running into traffic congestion, front illegal road occupation vehicle cannot be captured equally, therefore, in the urgent need to a kind of system-wide section, efficiently, clog-free novel candid photograph technological means.
Summary of the invention
It is an object of the invention to provide and a kind of take Emergency Vehicle Lane detection method based on the illegal of unmanned plane, it is possible to realize system-wide section, vehicle that real-time high-efficiency, candid photograph accurate, accessible occur in Emergency Vehicle Lane.
The technical scheme is that
A kind of take Emergency Vehicle Lane detection method based on the illegal of unmanned plane, comprise the following steps:
(1) release unmanned plane, record GPS location when unmanned plane takes off simultaneously；
(2) unmanned plane climbs certain altitude, the video capture highway image on unmanned plane, positions road right hand edge linear position；
(3) judge whether to navigate to road right hand edge linear position, if so, then enter step (4), if not, then it represents that unmanned plane cannot find express highway pavement, jump to step (13)；
(4) based on the angle of inclination of the road right hand edge straight line obtained and its position in the picture, adjust unmanned plane orientation, make road right hand edge straight line parallel in the vertical direction of image, control unmanned plane and be lowered vertically into the height that can capture characters on license plate along present level, the shooting angle of fine setting video camera and the right position of unmanned plane so that road right hand edge straight line is positioned at a certain fixed position place of picture traverse；
(5) Emergency Vehicle Lane width range on image is obtained, further according to road right hand edge straight line fixed position on picture traverse, it is determined that the Emergency Vehicle Lane regional location on image；
(6) adopt car plate grader, in Emergency Vehicle Lane region, carry out car plate detection；
(7) judge whether car plate to be detected, if so, then record car plate center point coordinate, enter step (8), if it is not, then jump to step (11)；
(8) Recognition of License Plate Characters is carried out；
(9) storage characters on license plate information and corresponding vehicle raw video image；
(10) the center point coordinate position according to several car plates of record, revises the flight angle of unmanned plane；
(11) unmanned plane heading along up-to-date correction, the distance of one parking stall of flight forward are controlled；
(12) judge that whether unmanned plane flies distance to a declared goal, if so, then enters step (13), if it is not, then return step (6)；
(13) control unmanned plane and return to the GPS location place of record when taking off, regain unmanned plane.
The described illegal Emergency Vehicle Lane detection method that takies based on unmanned plane, in step (2), described location road right hand edge linear position, specifically include following steps:
Video camera on a, unmanned plane shoots highway image under current angular；
B, the gray level image of highway image to shooting process, and obtain road vertical edge image；
C, acquisition road two-value vertical edge image；
D, obtain all of edge line segment in road two-value vertical edge image based on Hough transform theory；
E, according to the angle of inclination difference between line segment and largest interval distance, the line segment belonging to same edge line is merged；
F, removal Clutter edge straight line；
The number of the edge line that g, statistics remain, it may be judged whether less than 2, if, then it is absent from road edge straight line, enters step h, if not, then will be located in the edge line of the rightmost side as road edge straight line, record its angle of inclination and position in the picture thereof；
H, control video camera rotate according to certain angle；
I, judge that whether the accumulative anglec of rotation of video camera is less than 360 degree, if so, then return step a, if it is not, then terminate.
The described illegal Emergency Vehicle Lane detection method that takies based on unmanned plane, in step (5), described acquisition Emergency Vehicle Lane width range on image, realize especially by below equation:
H f = W w
Wherein, H represents the height of unmanned plane, and f represents the focal length of the video camera on unmanned plane, and W represents the normal width of Emergency Vehicle Lane, and w represents Emergency Vehicle Lane width on image.
The described illegal Emergency Vehicle Lane detection method that takies based on unmanned plane, in step (10), the center point coordinate position of described several car plates according to record, revise the flight angle of unmanned plane, specifically include following steps:
A, according to following least square fitting straight line principle formula, obtain the angle of inclination of car plate central point straight line:
α = arctan ( NΣx i y i - Σx i Σy i NΣx i 2 - ( Σx i ) 2 )
Wherein, α represents the angle of inclination of car plate central point straight line, (xi, yi) representing car plate center point coordinate, N represents car plate central point number；
B, when the angle of described angle of inclination and image vertical direction is more than 10 degree, then the heading of the unmanned plane inner side towards Emergency Vehicle Lane or outside are revised 5 degree.
Described takies Emergency Vehicle Lane detection method based on the illegal of unmanned plane, and in step b, the described gray level image to the highway image of shooting processes, and obtains road vertical edge image, is specifically based on following edge detection convolution template formula and realizes:
K = 0 1 0 - 1 0 1 2 0 - 2 - 1 2 4 0 - 4 - 2 1 2 0 - 2 - 1 0 1 0 - 1 0
Wherein, K represents edge detection convolution template.
Described takies Emergency Vehicle Lane detection method based on the illegal of unmanned plane, in step c, and described acquisition road two-value vertical edge image, it is specifically based on following local binarization algorithmic formula and realizes:
g ( x , y ) = 255 f ( x , y ) &GreaterEqual; T 0 f ( x , y ) < T
T = 1 M * N &Sigma; m = 1 M &Sigma; n = 1 N f ( x m , y n ) + F
Wherein, (x y) represents that (x, y) gray value at place, (x y) represents pixel in road vertical edge image (x, y) gray value at place, f (x to f to pixel in road two-value vertical edge image to gm, yn) represent with pixel in road vertical edge image (x, pixel (x in the M*N neighborhood centered by y)m, yn) gray value at place, M, N represent width and the height of neighborhood respectively, and F represents mean shift amount.
Described takies Emergency Vehicle Lane detection method based on the illegal of unmanned plane, in step e, and the largest interval distance between described line segment, obtain especially by below equation:
max d i s = max { d i s ( 0 ) , d i s ( 1 ) , d i s ( 2 ) } d i s ( i ) = | x i * k - y i + b | 1 + k 2
Wherein, k represents the slope of first line segment, b represents the intercept of first line segment, max{} function representation selects the maximum of all elements, dis (0) represents the top end points distance to first line segment of second line segment, dis (1) represents the midpoint distance to first line segment of second line segment, and dis (2) represents the bottom end points distance to first line segment of second line segment, (xi, yi) denotation coordination value, maxdis represents the largest interval distance between two line segments.
The invention have the benefit that
As shown from the above technical solution, present invention achieves the control of automatically flying of unmanned plane, any traffic obstacle can be ignored, by video image analysis technology, it is accurately positioned Emergency Vehicle Lane region in real time, automatically capturing the vehicle occurring in Emergency Vehicle Lane region, the present invention has system-wide section and captures, captures real-time high-efficiency, captures the features such as accurate, accessible.
Accompanying drawing explanation
Fig. 1 is the method flow diagram of the present invention；
Fig. 2 is the right edge position flow chart of location road；
Fig. 3 is the gray-scale map of highway Aerial Images；
Fig. 4 is highway edge line Detection results figure.
Detailed description of the invention
The present invention is further illustrated below in conjunction with the drawings and specific embodiments.
The present invention is directed highway Emergency Vehicle Lane, its lane line meets the specification standard of country, and the difference in brightness in lane line region and region, road surface is bigger.
Emergency Vehicle Lane detection method is taken based on the illegal of unmanned plane, including the step of following sequence as it is shown in figure 1, a kind of:
S1, releasing unmanned plane, the people's police being mainly responsible for capturing have debugged the relevant parameter of unmanned plane, let unmanned plane fly away, record GPS location when taking off simultaneously, when unmanned plane take off stable after, automatic climbing is to certain altitude；
S2, location road right edge position, as it is shown on figure 3, according on the Aerial Images of certain altitude, the road surface of highway can become narrower banding, there is obvious demarcation line with the vegetation clump in roadside.Therefore, the present invention takes photo by plane the feature of figure according to highway, detects feature based on edge line, is automatically positioned out the right hand edge of road, as in figure 2 it is shown, specifically include following steps:
S21, unmanned plane video camera shoot highway image under current angular；
S22, acquisition road vertical edge image, according to designing requirement, road edge straight line should be parallel to the vertical direction of image, therefore, the gray level image of the highway image of shooting is processed by the present invention based on edge detection convolution template formula (1), obtain road vertical edge image, complete the detection of road vertical edge:
K = 0 1 0 - 1 0 1 2 0 - 2 - 1 2 4 0 - 4 - 2 1 2 0 - 2 - 1 0 1 0 - 1 0 - - - ( 1 )
Wherein, K represents edge detection convolution template.
S23, acquisition road two-value vertical edge image, based on local binarization algorithmic formula (2), formula (3), complete the binaryzation of road vertical edge image:
g ( x , y ) = 255 f ( x , y ) &GreaterEqual; T 0 f ( x , y ) < T - - - ( 2 )
T = 1 M * N &Sigma; m = 1 M &Sigma; n = 1 N f ( x m , y n ) + F - - - ( 3 )
Wherein, (x is y) that (x, y) gray value at place, (x y) is (x, y) gray value at place, the f (x of pixel in road vertical edge image to f to pixel in road two-value vertical edge image to gm, yn) it is with pixel in road vertical edge image (x, pixel (x in the M*N neighborhood centered by y)m, yn) gray value at place, M, N are width and the height of neighborhood respectively, and F is mean shift amount.
S24, detection edge line, be mainly based upon Hough transform theory and obtain all of edge line in road two-value vertical edge image.
S25, merging edge line, the straight line obtained due to Hough transform is all line segment, it is understood that there may be an edge line is detected as multiple line segment, accordingly, it would be desirable to line segment is merged, obtains complete straight line.Concrete grammar is for two different line segments, angle of inclination difference and largest interval Joint according to the two judge whether to belong to same straight line, wherein, largest interval distance is based on formula (4) and completes, and is merged by the line segment belonging to same straight line:
max d i s = max { d i s ( 0 ) , d i s ( 1 ) , d i s ( 2 ) } d i s ( i ) = | x i * k - y i + b | 1 + k 2 - - - ( 4 )
Wherein, k represents the slope of first line segment, b represents the intercept of first line segment, max{} function representation selects the maximum of all elements, dis (0) represents the top end points distance to first line segment of second line segment, dis (1) represents the midpoint distance to first line segment of second line segment, and dis (2) represents the bottom end points distance to first line segment of second line segment.
S26, removal interference straight line, mainly remove the straight line that the shorter straight line of length, angle of inclination and phase quadrature are bigger, and effect is as shown in Figure 4.
S27, judge whether road edge straight line, first the number of the edge line remained is added up, if number is less than 2, illustrates that the deviation of current Aerial Images shooting angle is relatively big, be absent from road edge straight line, enter step S28, if number is more than or equal to 2, illustrate that current Aerial Images shooting angle is within allowed band, exists road edge straight line, record angle of inclination and the position in the picture thereof of rightmost side road edge straight line, exit current procedures.
S28, rotation unmanned plane video camera, mainly according to certain fixed angle, rotate unmanned plane video camera；
S29, judge that whether unmanned plane camera status is effective, if the accumulative anglec of rotation is more than 360 degree, illustrate to have been rotated through one week currently without man-machine video camera, without continuing to repeat to rotate, exit current procedures, if the accumulative anglec of rotation is less than 360 degree, illustrates to belong to normal rotation angle range currently without man-machine video camera, continue executing with step S21 to step S29.
S3, judging whether to navigate to the right edge position of road, if successfully positioned, entering step S4, without the right edge position navigating to road, illustrates to find express highway pavement, entrance step S13 currently without man-machine position；
S4, adjustment unmanned plane orientation, it is mainly based upon angle of inclination and its position in the picture of the road right hand edge straight line of acquisition in step S2, unmanned plane is carried out orientation adjustment, make road right hand edge straight line parallel in the vertical direction of image, then, it is lowered vertically into certain altitude along current location, this height is as the criterion can see characters on license plate clearly, finally, the shooting angle of fine setting unmanned plane video camera and the right position of unmanned plane so that road right hand edge straight line is positioned at 3/4 position of picture traverse.
S5, selection Emergency Vehicle Lane region, owing to the height of unmanned plane and the focal length of unmanned plane video camera are known, the width of Emergency Vehicle Lane also has fixed standard simultaneously, therefore, image-forming principle formula (5) based on video camera, Emergency Vehicle Lane width range on image can be obtained, and then determine Emergency Vehicle Lane regional location:
H f = W w - - - ( 5 )
Wherein, H represents the height of unmanned plane, and f represents the focal length of unmanned plane video camera, and W represents the normal width of Emergency Vehicle Lane, and w represents Emergency Vehicle Lane width on image.
S6, detection vehicle location, mainly in Emergency Vehicle Lane region, detect whether there is vehicle, and car plate is unique mark of vehicle, therefore, the present invention adopts car plate grader, car plate detection is carried out in Emergency Vehicle Lane region, and then determine occur with or without vehicle, wherein, car plate grader is based on harr feature and the training of adaboost theory obtains.
S7, judge whether to successfully be detected vehicle location, if successfully be detected vehicle location, recording current car plate center point coordinate, entering step S8, without vehicle location being detected, enter step S11.
S8, Recognition of License Plate Characters.
S9, storage information of vehicles, mainly characters on license plate information and vehicle raw video image, or remote transmission information of vehicles.
S10, revise unmanned plane flight angle, several car plate center point coordinate positions according to record, based on least square fitting straight line principle formula (6), obtain the angle of inclination of car plate central point straight line, if the angle of this angle of inclination and image vertical direction is more than 10 degree, then the heading of unmanned plane needs inside Emergency Vehicle Lane or outside correction 5 degree:
&alpha; = arctan ( N&Sigma;x i y i - &Sigma;x i &Sigma;y i N&Sigma;x i 2 - ( &Sigma;x i ) 2 ) - - - ( 6 )
Wherein, α represents the angle of inclination of car plate central point straight line, (xi, yi) representing car plate center point coordinate, N represents car plate central point number.
S11, unmanned plane move ahead automatically, and primarily along the heading of up-to-date correction, the distance of one parking stall of flight forward, this distance is determined based on the length of typical case parking stall in actual environment.
S12, judging that whether unmanned plane flies distance to a declared goal, arrives without flight, continues executing with step S6, if flown, performing step S13.
S13, withdrawal unmanned plane, after mainly unmanned plane arrives distance to a declared goal or when cannot find express highway pavement, automatically return to the GPS location place of record when taking off, work people's police regained.
The above embodiment is only that the preferred embodiment of the present invention is described; not the scope of the present invention is defined; under the premise designing spirit without departing from the present invention; various deformation that technical scheme is made by those of ordinary skill in the art and improvement, all should fall in the protection domain that claims of the present invention are determined.

Claims (7)

1. one kind takies Emergency Vehicle Lane detection method based on the illegal of unmanned plane, it is characterised in that comprise the following steps:
(1) release unmanned plane, record GPS location when unmanned plane takes off simultaneously；
(2) unmanned plane climbs certain altitude, the video capture highway image on unmanned plane, positions road right hand edge linear position；
(3) judge whether to navigate to road right hand edge linear position, if so, then enter step (4), if not, then it represents that unmanned plane cannot find express highway pavement, jump to step (13)；
(4) based on the angle of inclination of the road right hand edge straight line obtained and its position in the picture, adjust unmanned plane orientation, make road right hand edge straight line parallel in the vertical direction of image, control unmanned plane and be lowered vertically into the height that can capture characters on license plate along present level, the shooting angle of fine setting video camera and the right position of unmanned plane so that road right hand edge straight line is positioned at a certain fixed position place of picture traverse；
(5) Emergency Vehicle Lane width range on image is obtained, further according to road right hand edge straight line fixed position on picture traverse, it is determined that the Emergency Vehicle Lane regional location on image；
(6) adopt car plate grader, in Emergency Vehicle Lane region, carry out car plate detection；
(7) judge whether car plate to be detected, if so, then record car plate center point coordinate, enter step (8), if it is not, then jump to step (11)；
(8) Recognition of License Plate Characters is carried out；
(9) storage characters on license plate information and corresponding vehicle raw video image；
(10) the center point coordinate position according to several car plates of record, revises the flight angle of unmanned plane；
(11) unmanned plane heading along up-to-date correction, the distance of one parking stall of flight forward are controlled；
(12) judge that whether unmanned plane flies distance to a declared goal, if so, then enters step (13), if it is not, then return step (6)；
(13) control unmanned plane and return to the GPS location place of record when taking off, regain unmanned plane.
2. according to claim 1 take Emergency Vehicle Lane detection method based on the illegal of unmanned plane, it is characterised in that in step (2), described location road right hand edge linear position, specifically include following steps:
Video camera on a, unmanned plane shoots highway image under current angular；
B, the gray level image of highway image to shooting process, and obtain road vertical edge image；
C, acquisition road two-value vertical edge image；
D, obtain all of edge line segment in road two-value vertical edge image based on Hough transform theory；
E, according to the angle of inclination difference between line segment and largest interval distance, the line segment belonging to same edge line is merged；
F, removal Clutter edge straight line；
The number of the edge line that g, statistics remain, it may be judged whether less than 2, if, then it is absent from road edge straight line, enters step h, if not, then will be located in the edge line of the rightmost side as road edge straight line, record its angle of inclination and position in the picture thereof；
H, control video camera rotate according to certain angle；
I, judge that whether the accumulative anglec of rotation of video camera is less than 360 degree, if so, then return step a, if it is not, then terminate.
3. according to claim 1 take Emergency Vehicle Lane detection method based on the illegal of unmanned plane, it is characterised in that in step (5), described acquisition Emergency Vehicle Lane width range on image, realize especially by below equation:
H f = W w
Wherein, H represents the height of unmanned plane, and f represents the focal length of the video camera on unmanned plane, and W represents the normal width of Emergency Vehicle Lane, and w represents Emergency Vehicle Lane width on image.
4. according to claim 1 take Emergency Vehicle Lane detection method based on the illegal of unmanned plane, it is characterized in that, in step (10), the center point coordinate position of described several car plates according to record, revise the flight angle of unmanned plane, specifically include following steps:
A, according to following least square fitting straight line principle formula, obtain the angle of inclination of car plate central point straight line:
&alpha; = arctan ( N&Sigma;x i y i - &Sigma;x i &Sigma;y i N&Sigma;x i 2 - ( &Sigma;x i ) 2 )
Wherein, α represents the angle of inclination of car plate central point straight line, (xi, yi) representing car plate center point coordinate, N represents car plate central point number；
B, when the angle of described angle of inclination and image vertical direction is more than 10 degree, then the heading of the unmanned plane inner side towards Emergency Vehicle Lane or outside are revised 5 degree.
5. according to claim 2 take Emergency Vehicle Lane detection method based on the illegal of unmanned plane, it is characterized in that, in step b, the described gray level image to the highway image of shooting processes, obtain road vertical edge image, be specifically based on following edge detection convolution template formula and realize:
K = 0 1 0 - 1 0 1 2 0 - 2 - 1 2 4 0 - 4 - 2 1 2 0 - 2 - 1 0 1 0 - 1 0
Wherein, K represents edge detection convolution template.
6. according to claim 2 take Emergency Vehicle Lane detection method based on the illegal of unmanned plane, it is characterised in that in step c, described acquisition road two-value vertical edge image, it is specifically based on following local binarization algorithmic formula and realizes:
g ( x , y ) = 255 f ( x , y ) &GreaterEqual; T 0 f ( x , y ) < T
T = 1 M * N &Sigma; m = 1 M &Sigma; n = 1 N f ( x m , y n ) + F
Wherein, (x y) represents that (x, y) gray value at place, (x y) represents pixel in road vertical edge image (x, y) gray value at place, f (x to f to pixel in road two-value vertical edge image to gm, yn) represent with pixel in road vertical edge image (x, pixel (x in the M*N neighborhood centered by y)m, yn) gray value at place, M, N represent the width drenching territory and height respectively, and F represents mean shift amount.
7. according to claim 2 take Emergency Vehicle Lane detection method based on the illegal of unmanned plane, it is characterised in that in step e, the largest interval distance between described line segment, obtain especially by below equation:
max d i s = max { d i s ( 0 ) , d i s ( 1 ) , d i s ( 2 ) } d i s ( i ) = | x i * k - y i + b | 1 + k 2
Wherein, k represents the slope of first line segment, b represents the intercept of first line segment, max{} function representation selects the maximum of all elements, dis (0) represents the top end points distance to first line segment of second line segment, dis (1) represents the midpoint distance to first line segment of second line segment, and dis (2) represents the bottom end points distance to first line segment of second line segment, (xi, yi) denotation coordination value, maxdid represents the largest interval distance between two line segments.
CN201610083119.9A 2016-02-03 2016-02-03 A kind of illegal occupancy Emergency Vehicle Lane detection method based on unmanned plane Active CN105740837B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610083119.9A CN105740837B (en) 2016-02-03 2016-02-03 A kind of illegal occupancy Emergency Vehicle Lane detection method based on unmanned plane

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610083119.9A CN105740837B (en) 2016-02-03 2016-02-03 A kind of illegal occupancy Emergency Vehicle Lane detection method based on unmanned plane

Publications (2)

Publication Number Publication Date
CN105740837A true CN105740837A (en) 2016-07-06
CN105740837B CN105740837B (en) 2019-04-30

Family

ID=56245066

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610083119.9A Active CN105740837B (en) 2016-02-03 2016-02-03 A kind of illegal occupancy Emergency Vehicle Lane detection method based on unmanned plane

Country Status (1)

Country Link
CN (1) CN105740837B (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108510745A (en) * 2018-03-20 2018-09-07 北方工业大学 Air-ground cooperation-based police aircraft detection method and device
CN108573259A (en) * 2018-03-10 2018-09-25 王洁 Unmanned plane during flying Orientation system and method
CN109308807A (en) * 2017-07-28 2019-02-05 南京模幻天空航空科技有限公司 Road violation snap-shooting system based on unmanned plane aerial photography technology
CN110033622A (en) * 2018-01-12 2019-07-19 南京模幻天空航空科技有限公司 Violation snap-shooting based on unmanned plane aerial photography technology occupies Emergency Vehicle Lane method
CN110045736A (en) * 2019-04-12 2019-07-23 淮安信息职业技术学院 A kind of curve barrier preventing collision method and its system based on unmanned plane
CN110192232A (en) * 2019-04-18 2019-08-30 京东方科技集团股份有限公司 Traffic information processing equipment, system and method
CN110210303A (en) * 2019-04-29 2019-09-06 山东大学 A kind of accurate lane of Beidou vision fusion recognizes and localization method and its realization device
CN113763719A (en) * 2021-10-13 2021-12-07 深圳联和智慧科技有限公司 Unmanned aerial vehicle-based illegal emergency lane occupation detection method and system
CN113807125A (en) * 2020-06-12 2021-12-17 深圳市丰驰顺行信息技术有限公司 Emergency lane occupation detection method and device, computer equipment and storage medium
CN113920736A (en) * 2021-10-25 2022-01-11 桂林长海发展有限责任公司 Method and device for detecting emergency lane occupation of motor vehicle and storage medium
CN114566054A (en) * 2022-04-29 2022-05-31 深圳联和智慧科技有限公司 Method and system for capturing emergency lane by law violation based on unmanned aerial vehicle aerial photography technology

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100002911A1 (en) * 2008-07-06 2010-01-07 Jui-Hung Wu Method for detecting lane departure and apparatus thereof
CN104573655A (en) * 2015-01-09 2015-04-29 安徽清新互联信息科技有限公司 Blind sidewalk direction detection method based on video
CN104657727A (en) * 2015-03-18 2015-05-27 厦门麦克玛视电子信息技术有限公司 Lane line detection method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100002911A1 (en) * 2008-07-06 2010-01-07 Jui-Hung Wu Method for detecting lane departure and apparatus thereof
CN104573655A (en) * 2015-01-09 2015-04-29 安徽清新互联信息科技有限公司 Blind sidewalk direction detection method based on video
CN104657727A (en) * 2015-03-18 2015-05-27 厦门麦克玛视电子信息技术有限公司 Lane line detection method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
刘国荣: "基于图像的车道线检测与跟踪算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
张浩 等: "无人机航测技术在高速公路勘测及辅助选线中的应用", 《工程勘察》 *
董建成 等: "小型无人机交通辅助系统", 《电子产品世界》 *

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109308807A (en) * 2017-07-28 2019-02-05 南京模幻天空航空科技有限公司 Road violation snap-shooting system based on unmanned plane aerial photography technology
CN110033622A (en) * 2018-01-12 2019-07-19 南京模幻天空航空科技有限公司 Violation snap-shooting based on unmanned plane aerial photography technology occupies Emergency Vehicle Lane method
CN108573259A (en) * 2018-03-10 2018-09-25 王洁 Unmanned plane during flying Orientation system and method
CN108573259B (en) * 2018-03-10 2019-06-25 东营市远信电器与技术有限责任公司 Unmanned plane during flying Orientation system and method
CN108510745A (en) * 2018-03-20 2018-09-07 北方工业大学 Air-ground cooperation-based police aircraft detection method and device
CN110045736B (en) * 2019-04-12 2022-02-15 淮安信息职业技术学院 Bend obstacle avoiding method based on unmanned aerial vehicle
CN110045736A (en) * 2019-04-12 2019-07-23 淮安信息职业技术学院 A kind of curve barrier preventing collision method and its system based on unmanned plane
CN110192232A (en) * 2019-04-18 2019-08-30 京东方科技集团股份有限公司 Traffic information processing equipment, system and method
WO2020211047A1 (en) * 2019-04-18 2020-10-22 京东方科技集团股份有限公司 Traffic information processing device, system and method
US11535376B2 (en) 2019-04-18 2022-12-27 Beijing Boe Technology Development Co., Ltd. Traffic information processing equipment, system and method
CN110210303A (en) * 2019-04-29 2019-09-06 山东大学 A kind of accurate lane of Beidou vision fusion recognizes and localization method and its realization device
CN113807125A (en) * 2020-06-12 2021-12-17 深圳市丰驰顺行信息技术有限公司 Emergency lane occupation detection method and device, computer equipment and storage medium
CN113763719A (en) * 2021-10-13 2021-12-07 深圳联和智慧科技有限公司 Unmanned aerial vehicle-based illegal emergency lane occupation detection method and system
CN113763719B (en) * 2021-10-13 2022-06-14 深圳联和智慧科技有限公司 Unmanned aerial vehicle-based illegal emergency lane occupation detection method and system
CN113920736A (en) * 2021-10-25 2022-01-11 桂林长海发展有限责任公司 Method and device for detecting emergency lane occupation of motor vehicle and storage medium
CN114566054A (en) * 2022-04-29 2022-05-31 深圳联和智慧科技有限公司 Method and system for capturing emergency lane by law violation based on unmanned aerial vehicle aerial photography technology

Also Published As

Publication number Publication date
CN105740837B (en) 2019-04-30

Similar Documents

Publication Publication Date Title
CN105740837A (en) Unmanned aerial vehicle-based illegal emergency lane occupancy detection method
KR101671428B1 (en) Intelligent Monitoring System For Violation Vehicles in crossroads
DE112020004931T5 (en) SYSTEMS AND METHODS FOR DETERMINING ROAD SAFETY
US20170010612A1 (en) Vehicle controller, vehicle control method, and vehicle control program
DE102019100559A1 (en) METHOD AND SYSTEMS FOR SUPPORTING THE OPERATION OF A ROAD VEHICLE WITH A FLIGHT DROME
CN110782673A (en) Vehicle violation identification and detection system based on unmanned aerial vehicle shooting cloud computing
US10839680B2 (en) Vehicle control device, vehicle control method, and storage medium
EP1930863A2 (en) Detecting and recognizing traffic signs
US11639174B2 (en) Automated speed control system
DE102016217645A1 (en) A method for providing information about a probable driving intention of a vehicle
CN106340180A (en) Vehicle-mounted illegal lane occupation behavior detecting method and device
CN105741559A (en) Emergency vehicle lane illegal occupation detection method based on lane line model
EP3500974B1 (en) Method and device for supporting a driver assistance system in a motor vehicle
CN110164182B (en) Vehicle awareness data collection system and method
DE112020004949T5 (en) VEHICLE ONBOARD DEVICE AND DRIVING ASSISTANCE METHOD
CN105740836A (en) Illegal emergency lane occupancy detection method
CN110033622A (en) Violation snap-shooting based on unmanned plane aerial photography technology occupies Emergency Vehicle Lane method
US7068154B2 (en) Stop marker recognition apparatus of vehicle drive assist system
WO2019233777A1 (en) Driving assistance system
DE112021003340T5 (en) OBSTACLE INFORMATION MANAGEMENT DEVICE, OBSTACLE INFORMATION MANAGEMENT METHOD AND DEVICE FOR VEHICLE
DE102014221675A1 (en) Method and control and detection device for plausibility of a wrong-way drive of a motor vehicle
CN110580809B (en) Expressway rescue lane occupation snapshot method
US20210114611A1 (en) System for performing effective identification of vehicle line pressing and giving early prompt
CN114419885A (en) Vehicle violation snapshot method and system based on high-precision positioning and vehicle-mounted sensing capability
KR102158169B1 (en) Lane detection apparatus

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant