CN110648540A - Expressway emergency lane occupation tracking system and method based on unmanned aerial vehicle - Google Patents
Expressway emergency lane occupation tracking system and method based on unmanned aerial vehicle Download PDFInfo
- Publication number
- CN110648540A CN110648540A CN201910864714.XA CN201910864714A CN110648540A CN 110648540 A CN110648540 A CN 110648540A CN 201910864714 A CN201910864714 A CN 201910864714A CN 110648540 A CN110648540 A CN 110648540A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road surface
- image
- emergency lane
- camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims description 36
- 230000015654 memory Effects 0.000 claims description 36
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention is suitable for the technical field of image processing, and provides a highway emergency lane occupation tracking system and method based on an unmanned aerial vehicle, wherein the method comprises the following steps: s1, tracking and shooting a road surface image of the emergency lane by the first camera; s2, reading the road surface image K currently acquired by the camera in real timen+1The road surface image is RGB color data; s3, displaying the road surface image Kn+1Converts the RGB color data of (1) into grayscale data, i.e., forms a grayscale road surface image K'n+1(ii) a S4, based on two continuous frames of gray level road surface images K'n+1、K′nDetecting the violation vehicles on the emergency lane and the speed of the violation vehicles; and S5, controlling the camera to align the violation vehicle, capturing the violation vehicle, storing the captured image, and recording the shooting position. Based on camera on unmanned aerial vehicle cloud platform comes to track the vehicle that occupies emergency lane violating regulations, based on the difference between two frames to discernThe violation vehicles are distinguished, the violation vehicles are captured and evidence is obtained through the two pairs of cameras, and the recognition is accurate and fast.
Description
Technical Field
The invention belongs to the technical field of image processing, and provides a system and a method for tracking the occupation of an emergency lane of a highway based on an unmanned aerial vehicle.
Background
The existing highway detection mostly adopts manual patrol of road administration vehicles or fixed point photographing for evidence obtaining, the existing detection mode has obvious defects, and the fixed point photographing cannot master the actual situation on the road; the manual inspection consumes large manpower and material resources.
Disclosure of Invention
The unmanned aerial vehicle-based expressway emergency lane occupation tracking system provided by the embodiment of the invention tracks vehicles occupying emergency lanes illegally based on the camera on the unmanned aerial vehicle holder, identifies the vehicles violating the regulations based on the difference between two frames, and takes a snapshot of the vehicles violating the regulations through the camera to obtain evidence, so that the identification is accurate and fast.
In order to achieve the above object, the present invention provides a highway emergency lane occupancy tracking system based on an unmanned aerial vehicle, the system comprising:
the first camera and the second camera are arranged on the cloud deck, the cloud deck is positioned on the unmanned aerial vehicle, the unmanned aerial vehicle flies at a low speed above the emergency lane, and the unmanned aerial vehicle and vehicles on the emergency lane run in opposite directions;
the camera I and the camera II are arranged on the cloud deck, the cloud deck is positioned on the unmanned aerial vehicle, the unmanned aerial vehicle flies at a low speed above the emergency lane, and the flying direction is consistent with the driving direction of the vehicle;
the first camera is connected with the image acquisition unit, the image acquisition unit is connected with the gray level conversion unit, the gray level conversion unit is connected with the first memory, the first memory is connected with the second memory, the first memory and the second memory are connected with the differential calculation unit, the differential calculation unit is connected with the register, the violation judgment unit is connected with the register and the differential calculation unit, the second camera is connected with the violation judgment unit through the android unit, and the cradle head control unit is connected with the violation judgment unit;
the camera I is used for tracking the road surface of the emergency lane; the image acquisition unit extracts a road surface image K currently acquired by the cameran+1The road surface image is an RGB color road surface image; the gray level conversion unit performs gray level processing on the RGB color road surface image; forming a gray-scale road surface image K'n+1(ii) a The gray-scale road surface image K 'in the second memory'n-1Deleting the gray-scale road surface image K 'in the first memory'nStoring the current gray-scale road surface image K 'in a second memory'n+1Storing the data to a first memory; the difference calculation unit is based on the gray-scale road surface image K'nAnd K'n+1Performing pixel difference calculationObtaining a difference image Mn+1(ii) a Register is registered with difference image Mn，MnIs a gray level road surface image K'nAnd K'n-1Difference images formed by the difference calculation; violation judging unit based on difference image Mn+1Detecting whether a suspected violation vehicle exists on the emergency lane and based on the difference image Mn+1And a difference image MnCalculating the speed of the suspected vehicle violating the regulations, and judging whether the suspected vehicle violating the regulations is the vehicle violating the regulations or not; the camera II is used for capturing the violation vehicle; the holder control unit is used for controlling the rotation of the first camera and the second camera on the holder; and the android module is used for starting the camera II to shoot, storing the shot image and shooting the position.
In order to achieve the above object, the present invention provides a method for tracking an emergency lane occupancy of a highway based on an unmanned aerial vehicle, the method specifically comprises the following steps:
s1, tracking and shooting a road surface image of the emergency lane by the first camera;
s2, reading the road surface image K currently acquired by the camera in real timen+1The road surface image is RGB color data;
s3, displaying the road surface image Kn+1Converts the RGB color data of (1) into grayscale data, i.e., forms a grayscale road surface image K'n+1；
S4 based on continuous three-frame gray-scale road surface image K'nAnd K'n-1Detecting the illegal vehicle on the emergency lane and the speed of the illegal vehicle, wherein K'nA gray scale road surface image which is a previous frame of road surface image;
and S5, controlling the camera to align the violation vehicle, capturing the violation vehicle, storing the captured image, and recording the shooting position.
Further, step S4 specifically includes the following steps:
s41, detecting whether a vehicle exists on the emergency lane;
s42, if the vehicle exists on the emergency lane, calculating the driving speed of the vehicle on the emergency lane;
s43, identifying a vehicle state based on the travel speed, the vehicle state including: a parking state and a driving state;
s44, if the vehicle on the emergency lane is in a running state, defining the vehicle as a suspected violation vehicle, and controlling the camera to align the suspected violation vehicle for monitoring;
and S45, if the suspected violation vehicles run in the emergency lane within the set time length, determining that the suspected violation vehicles are violation vehicles.
Further, the vehicle detection method on the emergency lane comprises the following steps:
s411, and gray-scale road surface image K 'of adjacent frames'n+1、K′nCarrying out pixel difference calculation to obtain a difference image Mn+1；
S412, counting the difference image Mn+1And if the number of the pixel points with the middle pixel differential value larger than the differential threshold is larger than the number threshold, judging that the vehicle exists on the emergency lane.
Further, the method for calculating the running speed of the vehicle on the emergency lane comprises the following steps:
s421, for the difference image Mn+1、MnCarrying out binarization to obtain a binarized image Rn、Rn+1，MnIs a difference image of the last pixel difference calculation stored in the register, and the last pixel difference calculation is a gray-scale road surface image K'n-1And K'nCalculating pixel difference between the pixels;
s422, the binary image Rn、Rn+1Carrying out pixel difference calculation again, and recording the line number of the line where the gray value is 255;
s423, calculating the line number difference between the maximum line number and the minimum line number, and calculating the secondary road surface image K based on the line number differencenTo Kn+1The vehicle running distance Δ d;
s424 calculates the vehicle speed of the vehicle in the emergency lane based on the travel distance Δ d.
Further, the detection method of the vehicle state of the emergency lane specifically comprises the following steps:
s431, detecting whether the speed of the vehicle is zero or not;
and S432, if the detection result is positive, determining that the vehicle in the emergency lane is in a parking state, and if the detection result is negative, determining that the vehicle is in a running state.
Further, the gray scale conversion formula is shown as formula (1):
wherein, Grey is gray value, G is green value, R is red value, B is blue value.
The unmanned aerial vehicle-based expressway emergency lane occupation tracking method provided by the invention has the following beneficial effects:
1) the double-camera monitoring is adopted, the data volume of the low-resolution camera is small, the processing equipment adopts an FPGA chip, and due to the characteristic of parallel operation, the processing speed is high, so that the FPGA chip can be used for tracking, and the tracking is to prevent misjudgment; the high-speed camera has high resolution, high frame rate and large data volume and is used for taking pictures and obtaining evidences;
2) in the RGB color-to-gray value part, in order to accelerate the operation speed, the multiplication-division calculation is replaced by the shift operation, and the parallel operation mode is adopted, so that the operation speed is greatly accelerated;
3) the illegal vehicle identification adopts twice two-frame difference method calculation, which can judge whether a vehicle appears in an emergency lane or not, can also judge the vehicle state, and correspondingly processes the two states. And if the time of the vehicle running on the emergency lane is less than the threshold value, judging that the vehicle is wrongly entered, and not recording. If the road occupation state is always in the specified time threshold, recording the road occupation state. For vehicles stopped in the emergency lane, the vehicles are classified, recorded and manually judged to avoid misjudgment, and law enforcement is avoided.
Drawings
Fig. 1 is a schematic structural diagram of a highway emergency lane occupancy tracking system based on an unmanned aerial vehicle according to an embodiment of the present invention;
fig. 2 is a flowchart of a tracking process for an emergency lane occupancy of a highway based on an unmanned aerial vehicle according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Fig. 1 is a schematic structural diagram of an emergency lane occupancy tracking system for a highway based on an unmanned aerial vehicle according to an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown.
The system comprises:
the first camera and the second camera are arranged on the cloud deck, the cloud deck is positioned on the unmanned aerial vehicle, the unmanned aerial vehicle flies at a low speed above the emergency lane, and the unmanned aerial vehicle and vehicles on the emergency lane run in opposite directions;
the first camera is connected with the image acquisition unit, the image acquisition unit is connected with the gray level conversion unit, the gray level conversion unit is connected with the first memory, the first memory is connected with the second memory, the first memory and the second memory are connected with the differential calculation unit, the differential calculation unit is connected with the register, the violation judgment unit is connected with the register and the differential calculation unit, the second camera is connected with the violation judgment unit through the android unit, and the cradle head control unit is connected with the violation judgment unit;
the camera I is used for tracking the road surface of the emergency lane; the image acquisition unit extracts a road surface image K currently acquired by the cameran+1The road surface image is an RGB color road surface image; the gray level conversion unit performs gray level processing on the RGB color road surface image; forming a gray-scale road surface image K'n+1(ii) a The gray-scale road surface image K 'in the second memory'n-1Deleting the gray-scale road surface image K in the first memoryn'store to secondary memory, Current Gray road surface image K'n+1Storing the data to a first memory; the difference calculation unit is based on the gray-scale road surface image K'nAnd K'n+1Carrying out pixel difference calculation to obtain a difference image Mn+1(ii) a Register is registered with difference image Mn，MnIs a gray level road surface image K'nAnd K'n-1Difference images formed by the difference calculation; violation judging unit based on difference image Mn+1Detecting whether a suspected violation vehicle exists on the emergency lane and based on the difference image Mn+1And a difference image MnCalculating the speed of the suspected vehicle violating the regulations, and judging whether the suspected vehicle violating the regulations is the vehicle violating the regulations or not; the camera II is used for capturing the violation vehicle; the holder control unit is used for controlling the rotation of the first camera and the second camera on the holder; and the android module is used for starting the camera II to shoot, storing the shot image and shooting the position.
In the embodiment of the invention, the image acquisition unit, the gray level conversion unit, the difference calculation unit, the violation judgment unit and the holder control unit are all integrated on an FPGA chip, and the Artix-7 series FPGA chip of Xilinx company in America is adopted.
In the embodiment of the invention, the unmanned aerial vehicle flies at a low speed, and the flying speed of the unmanned aerial vehicle is generally lower than 50 kilometers per hour.
Fig. 2 is a flowchart of a flow for tracking an emergency lane occupancy on a highway based on an unmanned aerial vehicle according to an embodiment of the present invention, where the method specifically includes the following steps:
s1, tracking and shooting a road surface image of the emergency lane by the first camera;
s2, extracting the road surface image K currently acquired by the camera in real timen+1The road surface image is RGB color data;
the road surface image read by the image acquisition unit from the first camera is RGB color data and is the road surface image K currently acquired by the first cameran+1The image acquisition unit acquires a road surface image Kn+1Sending the data to a gray level conversion unit;
s3, displaying the road surface image Kn+1Converts the RGB color data of (1) into grayscale data, i.e., forms a grayscale road surface image K'n+1；
The gray level conversion unit converts the road surface image Kn+1The RGB color data in (1) is converted into grayscale data to form a grayscale road surface image K'n+1In order to increase the operation speed of gradation conversion, gradation calculation is performed using the formula (1):
wherein, Grey is gray value, G is green value, R is red value, B is blue value.
Based on a parallel operation circuit in an FPGA, the logic operation of 512 × G, 64 × G, 8 × G, 4 × G and 1 × G is completed simultaneously through the parallel operation circuit, 512 × G is converted into G logic left shift 9 bits, 64 × G is converted into G logic left shift 6 bits, 8 × G is converted into G logic left shift 3 bits, 2 × G is converted into G logic left shift 2 bits, 1G is converted into G logic left shift 1 bit, then addition operation is carried out, and finally 1024 is divided to respectively shift R logic, G logic and G logic right shift 10 bits, so that the operation speed is greatly increased, and the gray value conversion of each pixel point is not a bottleneck.
S4, based on two continuous frames of gray level road surface images K'n+1、K′nTo detect the violation vehicle on the emergency lane and the speed, K'n+1Is a gray scale road surface image of the currently acquired road surface image and is stored in a first memory, K'nThe gray scale road surface image stored in the second memory is the gray scale road surface image of the previous frame of road surface image
In the embodiment of the present invention, the data bit width of the first memory and the data bit width of the second memory are 8 bits, the depth of the first memory is 320 × 240, and the first memory and the second memory are used for storing one frame of data, two adjacent frames of data can be stored in the two memories, and the two memories can respectively store the grayscale road surface image K'n+1And K'nOf which K'nIs a gray level road surface image K'n+1Under the drive of a camera and a clock, two frames of data are written into two memories in a pipeline mode under the coordination of a counter;
in the embodiment of the present invention, step S4 specifically includes the following steps:
s41, detecting whether a vehicle exists on the emergency lane;
whether a vehicle exists on an emergency lane is detected by utilizing an interframe difference method, and the main idea of the interframe difference method is as follows: if the vehicle exists in the emergency lane, the images of several frames continuously shot by the camera have difference, and the vehicle on the emergency lane can be detected through the difference.
S42, if the vehicle exists on the emergency lane, calculating the driving speed of the vehicle on the emergency lane;
the unmanned aerial vehicle and the vehicle travel in the same direction on the highway, even if there is a vehicle in a parking state on an emergency lane, the vehicle still has speed relative to the unmanned aerial vehicle, and considering that the hue of the highway pavement is single, the background is simple, the unmanned aerial vehicle can be realized in fpg in a hardware mode, the response speed is high, and the identification accuracy is high.
S43, detecting vehicle states based on the running speed, wherein the vehicle states comprise a parking state and a running state;
s44, if the vehicle is in a driving state, the vehicle is defined as a suspected violation vehicle, and the camera is controlled to be aligned with the suspected violation vehicle for monitoring;
in the embodiment of the invention, if the vehicle on the emergency lane is in a parking state, the camera is controlled to shoot the vehicle, the vehicle and the android unit are stored, and the shooting position is recorded at the same time, so that manual processing is facilitated.
And S45, if the suspected violation vehicles run in the emergency lane within the set time length, determining that the suspected violation vehicles are violation vehicles.
In the embodiment of the invention, the vehicle detection method on the emergency lane specifically comprises the following steps:
s411, and gray-scale road surface image K 'of adjacent frames'n+1、K′nCarrying out pixel difference calculation to obtain a difference image Mn+1，Mdiff-n+1As a differential image Mn+1The pixel difference value of each pixel point in the image is calculated by adopting a formula (2) in the pixel difference calculation of two adjacent frames of gray level pavement images:
Mdiff(x,y)＝|fk+1(x,y)-fk(x,y)| (2)
wherein M isdiff(x, y) represents the pixel difference value of a pixel point at the coordinate (x, y) in two adjacent frames of images, fk+1(x, y) represents the pixel value of the pixel point at the coordinate (x, y) in the image of the next frame, fk(x, y) represents the pixel value of the pixel point at coordinate (x, y) in the previous frame image.
S412, counting the difference image Mn+1The quantity of the pixel points with the middle pixel differential value larger than the differential threshold value is judged, and if the quantity is larger than the quantity threshold value, the vehicle exists on the emergency lane;
in the embodiment of the invention, the method for calculating the running speed of the vehicle on the emergency lane specifically comprises the following steps:
s421, for the difference image Mn+1、MnCarrying out binarization to obtain a binarized image Rn、Rn+1；
Differential image Mn+1Is a gray level road surface image K'n+1、K′nImage formed after pixel difference calculation, Mdiff-n+1As a differential image Mn+1The pixel differential value of each pixel point in the image; mnIs a difference image calculated from the previous pixel difference stored in the register, i.e., a gray-scale road surface image K'n-1、K′nForming a difference image after pixel difference calculation; the binarization process of the difference image is specifically as the following formula (3):
wherein, R (x, y) represents the binarization result of pixel point at coordinate (x, y) in the differential image, THdiffAnd if the pixel value is the set threshold value, the pixel point with the pixel difference value larger than the threshold value is set to be 255 to represent full black, and the pixel point with the pixel difference value smaller than the threshold value is set to be 0 to represent full white, namely the binarization is completed.
S422, the binary image Rn、Rn+1Carrying out pixel difference calculation again, and recording the line number of the line where the gray value is 255;
s423, calculating the line number difference between the maximum line number and the minimum line number, and calculating the image frame K from the road surface based on the line number differencenTo Kn+1The vehicle running distance Δ d;
s424 calculates the vehicle speed of the vehicle in the emergency lane based on the travel distance Δ d.
In the embodiment of the invention, the detection method of the vehicle state of the emergency lane specifically comprises the following steps:
s431, detecting whether the speed of the vehicle is zero or not;
and S432, if the detection result is positive, determining that the vehicle in the emergency lane is in a parking state, and if the detection result is negative, determining that the vehicle is in a running state.
And S5, controlling the camera to align the violation vehicle, capturing the violation vehicle, storing the captured image, and recording the shooting position.
Every time one frame of road surface image is collected, the position of the lower edge of the current frame of gray road surface image from the center of the image, the running speed of the violation vehicle and the distance of the violation vehicle deviating from the emergency lane line are fed back to the cradle head control unit, the cradle head control unit controls the camera to align the violation vehicle based on the information, the snapshot is facilitated, the rotation control of the camera I is the same as that of the camera II, the emergency lane line adopts a white line as a reference, and the emergency lane line is detected by adopting a Sobel operator edge detection algorithm based on the FPGA.
In order to shoot vehicles violating the regulations, shot photos or screens need to be stored in equipment such as a storage card, and the coding and storage of images are a very complicated process and are difficult to realize through an FPGA (field programmable gate array).
The unmanned aerial vehicle-based expressway emergency lane occupation tracking method provided by the invention has the following beneficial effects:
1) the double-camera monitoring is adopted, the data volume of the low-resolution camera is small, the processing equipment adopts an FPGA chip, and due to the characteristic of parallel operation, the processing speed is high, so that the FPGA chip can be used for tracking, and the tracking is to prevent misjudgment; the high-speed camera has high resolution, high frame rate and large data volume and is used for taking pictures and obtaining evidences;
2) in the RGB color-to-gray value part, in order to accelerate the operation speed, the multiplication-division calculation is replaced by the shift operation, and the parallel operation mode is adopted, so that the operation speed is greatly accelerated;
3) the illegal vehicle identification adopts twice two-frame difference method calculation, which can judge whether a vehicle appears in an emergency lane or not, can also judge the vehicle state, and correspondingly processes the two states. And if the time of the vehicle running on the emergency lane is less than the threshold value, judging that the vehicle is wrongly entered, and not recording. If the road occupation state is always in the specified time threshold, recording the road occupation state. For vehicles stopped in the emergency lane, the vehicles are classified, recorded and manually judged to avoid misjudgment, and law enforcement is avoided.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (7)
1. An unmanned aerial vehicle-based highway emergency lane occupancy tracking system, the system comprising:
the first camera and the second camera are arranged on the cloud deck, the cloud deck is positioned on the unmanned aerial vehicle, the unmanned aerial vehicle flies at a low speed above the emergency lane, and the unmanned aerial vehicle and vehicles on the emergency lane run in opposite directions;
the first camera is connected with the image acquisition unit, the image acquisition unit is connected with the gray level conversion unit, the gray level conversion unit is connected with the first memory, the first memory is connected with the second memory, the first memory and the second memory are connected with the differential calculation unit, the differential calculation unit is connected with the register, the violation judgment unit is connected with the register and the differential calculation unit, the second camera is connected with the violation judgment unit through the android unit, and the cradle head control unit is connected with the violation judgment unit;
the camera I is used for tracking the road surface of the emergency lane; the image acquisition unit extracts a road surface image K currently acquired by the cameran+1The road surface image is an RGB color road surface image; the gray level conversion unit performs gray level processing on the RGB color road surface image; forming a gray-scale road surface image K'n+1(ii) a Will be provided withGrayscale road surface image K 'in secondary memory'n-1Deleting the gray-scale road surface image K 'in the first memory'nStoring the current gray-scale road surface image K 'in a second memory'n+1Storing the data to a first memory; the difference calculation unit is based on the gray-scale road surface image K'nAnd K'n+1Carrying out pixel difference calculation to obtain a difference image Mn+1(ii) a Register is registered with difference image Mn，MnIs a gray level road surface image K'nAnd K'n-1Difference images formed by the difference calculation; violation judging unit based on difference image Mn+1Detecting whether a suspected violation vehicle exists on the emergency lane and based on the difference image Mn+1And a difference image MnCalculating the speed of the suspected vehicle violating the regulations, and judging whether the suspected vehicle violating the regulations is the vehicle violating the regulations or not; the camera II is used for capturing the violation vehicle; the holder control unit is used for controlling the rotation of the first camera and the second camera on the holder; and the android module is used for starting the camera II to shoot, storing the shot image and shooting the position.
2. The method for tracking the occupancy of an emergency highway lane by an unmanned aerial vehicle based on the system for tracking the occupancy of an emergency highway lane by an unmanned aerial vehicle of claim 1, wherein the method specifically comprises the following steps:
s1, tracking and shooting a road surface image of the emergency lane by the first camera;
s2, reading the road surface image K currently acquired by the camera in real timen+1The road surface image is RGB color data;
s3, displaying the road surface image Kn+1Converts the RGB color data of (1) into grayscale data, i.e., forms a grayscale road surface image K'n+1；
S4, based on two continuous frames of gray level road surface images K'n、K′n+1Detecting the illegal vehicle on the emergency lane and the speed of the illegal vehicle, wherein K'nA gray scale road surface image which is a previous frame of road surface image;
and S5, controlling the camera to align the violation vehicle, capturing the violation vehicle, storing the captured image, and recording the shooting position.
3. The method for tracking the emergency lane occupancy of the expressway of claim 2, wherein the step S4 specifically comprises the steps of:
s41, detecting whether a vehicle exists on the emergency lane;
s42, if the vehicle exists on the emergency lane, calculating the driving speed of the vehicle on the emergency lane;
s43, identifying a vehicle state based on the travel speed, the vehicle state including: a parking state and a driving state;
s44, if the vehicle on the emergency lane is in a running state, defining the vehicle as a suspected violation vehicle, and controlling the camera to align the suspected violation vehicle for monitoring;
and S45, if the suspected violation vehicles run in the emergency lane within the set time length, determining that the suspected violation vehicles are violation vehicles.
4. A method for tracking the occupancy of an emergency lane on a highway by a drone according to claim 3, wherein the method for detecting vehicles on the emergency lane comprises the steps of:
s411, and gray-scale road surface image K 'of adjacent frames'n+1、K′nCarrying out pixel difference calculation to obtain a difference image Mn+1；
S412, counting the difference image Mn+1And if the number of the pixel points with the middle pixel differential value larger than the differential threshold is larger than the number threshold, judging that the vehicle exists on the emergency lane.
5. The method for tracking the occupancy of an emergency lane on a highway by an unmanned aerial vehicle as claimed in claim 3, wherein the method for calculating the traveling speed of the vehicle on the emergency lane comprises the steps of:
s421, for the difference image Mn+1、MnCarrying out binarization to obtain a binarized image Rn，MnFor the difference image of the last pixel difference calculation stored in the register, the last pixelThe difference calculation is gray-scale road surface image K'n-1And K'nCalculating pixel difference between the pixels;
s422, the binary image Rn、Rn+1Carrying out pixel difference calculation again, and recording the line number of the line where the gray value is 255;
s423, calculating the line number difference between the maximum line number and the minimum line number, and calculating the secondary road surface image K based on the line number differencenTo Kn+1The vehicle running distance Δ d;
s424 calculates the vehicle speed of the vehicle in the emergency lane based on the travel distance Δ d.
6. The method for tracking the occupancy of the emergency lane of the unmanned aerial vehicle as claimed in claim 3, wherein the detection method of the vehicle state of the emergency lane is as follows:
s431, detecting whether the speed of the vehicle is zero or not;
and S432, if the detection result is positive, determining that the vehicle in the emergency lane is in a parking state, and if the detection result is negative, determining that the vehicle is in a running state.
7. The method for tracking the emergency lane occupancy of the unmanned aerial vehicle as claimed in claim 2, wherein the gray scale conversion formula is shown as formula (1):
wherein, Grey is gray value, G is green value, R is red value, B is blue value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910864714.XA CN110648540B (en) | 2019-09-09 | 2019-09-09 | Expressway emergency lane occupation tracking system and method based on unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910864714.XA CN110648540B (en) | 2019-09-09 | 2019-09-09 | Expressway emergency lane occupation tracking system and method based on unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110648540A true CN110648540A (en) | 2020-01-03 |
| CN110648540B CN110648540B (en) | 2021-07-02 |
Family
ID=69010481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910864714.XA Expired - Fee Related CN110648540B (en) | 2019-09-09 | 2019-09-09 | Expressway emergency lane occupation tracking system and method based on unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110648540B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111432130A (en) * | 2020-04-23 | 2020-07-17 | 西安智文琛软件有限公司 | Automatic tracking focusing snapshot method, snapshot system, unmanned aerial vehicle and application |
| CN112258844A (en) * | 2020-11-05 | 2021-01-22 | 浙江点辰航空科技有限公司 | Method for inspecting expressway emergency lanes by using unmanned aerial vehicle |
| CN112258843A (en) * | 2020-11-05 | 2021-01-22 | 浙江点辰航空科技有限公司 | Image identification method applied to unmanned aerial vehicle inspection of emergency lane of highway |
| 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 |
| CN114512005A (en) * | 2022-02-15 | 2022-05-17 | 复亚智能科技(太仓)有限公司 | Road self-inspection method and device, unmanned aerial 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 (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101097205A (en) * | 2006-06-30 | 2008-01-02 | 宝山钢铁股份有限公司 | Method for automatically detecting aeolotropism in charred coal organization |
| CN101557534A (en) * | 2009-05-19 | 2009-10-14 | 无锡景象数字技术有限公司 | Method for generating disparity map from video close frames |
| CN102024144A (en) * | 2010-11-23 | 2011-04-20 | 上海海事大学 | Container number identification method |
| CN103730015A (en) * | 2013-12-27 | 2014-04-16 | 株洲南车时代电气股份有限公司 | Method and device for detecting traffic flow at intersection |
| CN104392612A (en) * | 2014-11-20 | 2015-03-04 | 东南大学 | Urban traffic state monitoring method based on novel detection vehicles |
| CN104867332A (en) * | 2015-05-26 | 2015-08-26 | 南京通用电器有限公司 | Interval-frame difference method based detection method of driving vehicle in front lane line |
| CN105469604A (en) * | 2015-12-09 | 2016-04-06 | 大连海事大学 | An in-tunnel vehicle detection method based on monitored images |
| CN108877234A (en) * | 2018-07-24 | 2018-11-23 | 河北德冠隆电子科技有限公司 | The rule-breaking vehicle road occupying tracing detection system and method for four-dimensional outdoor scene traffic simulation |
| CN109117702A (en) * | 2018-06-12 | 2019-01-01 | 深圳中兴网信科技有限公司 | The detection and count tracking method and system of target vehicle |
| 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 |
-
2019
- 2019-09-09 CN CN201910864714.XA patent/CN110648540B/en not_active Expired - Fee Related
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101097205A (en) * | 2006-06-30 | 2008-01-02 | 宝山钢铁股份有限公司 | Method for automatically detecting aeolotropism in charred coal organization |
| CN101557534A (en) * | 2009-05-19 | 2009-10-14 | 无锡景象数字技术有限公司 | Method for generating disparity map from video close frames |
| CN102024144A (en) * | 2010-11-23 | 2011-04-20 | 上海海事大学 | Container number identification method |
| CN103730015A (en) * | 2013-12-27 | 2014-04-16 | 株洲南车时代电气股份有限公司 | Method and device for detecting traffic flow at intersection |
| CN104392612A (en) * | 2014-11-20 | 2015-03-04 | 东南大学 | Urban traffic state monitoring method based on novel detection vehicles |
| CN104867332A (en) * | 2015-05-26 | 2015-08-26 | 南京通用电器有限公司 | Interval-frame difference method based detection method of driving vehicle in front lane line |
| CN105469604A (en) * | 2015-12-09 | 2016-04-06 | 大连海事大学 | An in-tunnel vehicle detection method based on monitored images |
| 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 |
| CN109117702A (en) * | 2018-06-12 | 2019-01-01 | 深圳中兴网信科技有限公司 | The detection and count tracking method and system of target vehicle |
| CN108877234A (en) * | 2018-07-24 | 2018-11-23 | 河北德冠隆电子科技有限公司 | The rule-breaking vehicle road occupying tracing detection system and method for four-dimensional outdoor scene traffic simulation |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111432130A (en) * | 2020-04-23 | 2020-07-17 | 西安智文琛软件有限公司 | Automatic tracking focusing snapshot method, snapshot system, unmanned aerial vehicle and application |
| CN112258844A (en) * | 2020-11-05 | 2021-01-22 | 浙江点辰航空科技有限公司 | Method for inspecting expressway emergency lanes by using unmanned aerial vehicle |
| CN112258843A (en) * | 2020-11-05 | 2021-01-22 | 浙江点辰航空科技有限公司 | Image identification method applied to unmanned aerial vehicle inspection of emergency lane of highway |
| CN112258844B (en) * | 2020-11-05 | 2022-05-27 | 浙江点辰航空科技有限公司 | Method for inspecting expressway emergency lanes by using unmanned aerial vehicle |
| 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 |
| CN114512005A (en) * | 2022-02-15 | 2022-05-17 | 复亚智能科技(太仓)有限公司 | Road self-inspection method and device, unmanned aerial 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 |
|---|---|
| CN110648540B (en) | 2021-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110648540B (en) | Expressway emergency lane occupation tracking system and method based on unmanned aerial vehicle | |
| CN110659539B (en) | Information processing method and device and machine-readable storage medium | |
| CN103778786B (en) | A kind of break in traffic rules and regulations detection method based on remarkable vehicle part model | |
| US8798314B2 (en) | Detection of vehicles in images of a night time scene | |
| TWI409718B (en) | Method of locating license plate of moving vehicle | |
| CN106600977B (en) | Multi-feature recognition-based illegal parking detection method and system | |
| CN109299674B (en) | Tunnel illegal lane change detection method based on car lamp | |
| CN104050450A (en) | Vehicle license plate recognition method based on video | |
| CN102880863B (en) | Method for positioning license number and face of driver on basis of deformable part model | |
| CN105005778A (en) | Expressway vehicle detection method based on visual background extraction | |
| Azad et al. | A novel and robust method for automatic license plate recognition system based on pattern recognition | |
| Teutsch et al. | Robust detection of moving vehicles in wide area motion imagery | |
| CN113378690A (en) | In-road irregular parking identification method based on video data | |
| CN105184291A (en) | Method and system for detecting multiple types of license plates | |
| CN113903008A (en) | Ramp exit vehicle violation identification method based on deep learning and trajectory tracking | |
| CN102169583A (en) | Vehicle shielding detection and segmentation method based on vehicle window positioning | |
| CN106340031A (en) | Method and device for detecting moving object | |
| CN116682268A (en) | Portable urban road vehicle violation inspection system and method based on machine vision | |
| CN106447862B (en) | A kind of intelligent gate ticket checking method based on computer vision technique | |
| CN111583341B (en) | Cloud deck camera shift detection method | |
| CN104077566B (en) | Bayonet socket picture method for detecting human face based on color difference | |
| CN113205687A (en) | Drunk driving vehicle track recognition system based on video monitoring | |
| CN202854837U (en) | Vehicle lane mark line detection device | |
| Saha et al. | License plate localization using vertical edge map and hough transform based technique | |
| JPH09288795A (en) | Car number reader |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210702 |