CN117058922A - Unmanned aerial vehicle monitoring method and system for road and bridge construction - Google Patents
Unmanned aerial vehicle monitoring method and system for road and bridge construction Download PDFInfo
- Publication number
- CN117058922A CN117058922A CN202311317534.2A CN202311317534A CN117058922A CN 117058922 A CN117058922 A CN 117058922A CN 202311317534 A CN202311317534 A CN 202311317534A CN 117058922 A CN117058922 A CN 117058922A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road
- monitoring
- risk
- area
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 188
- 238000010276 construction Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000008859 change Effects 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 10
- 230000008569 process Effects 0.000 description 13
- 239000003550 marker Substances 0.000 description 7
- 230000004044 response Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 239000000284 extract Substances 0.000 description 5
- 230000000630 rising effect Effects 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 241001330002 Bambuseae Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention is applicable to the technical field of construction monitoring, and particularly relates to an unmanned aerial vehicle monitoring method and system for road and bridge construction, wherein the method comprises the following steps: receiving a temporary monitoring instruction; collecting a road monitoring video, and identifying a road and bridge construction area and a road and bridge passing area based on the road monitoring video; the method comprises the steps of extracting pictures of road monitoring videos, calculating the passing speed of each vehicle, and defining a risk warning area according to the safety monitoring grade and the passing speed; and tracking the position of the vehicle in real time, judging whether the vehicle has driving risk or not based on the real-time position of the vehicle, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists. The invention determines a construction area and a warning area based on the positions of the cone and the lane lines, identifies the moving speed of the vehicle, judges whether the risk exists based on the moving speed and the distance of the vehicle, and carries out an audible and visual alarm to prompt the vehicle to decelerate when the risk exists so as to avoid the risk.
Description
Technical Field
The invention belongs to the technical field of construction monitoring, and particularly relates to an unmanned aerial vehicle monitoring method and system for road and bridge construction.
Background
The road bridge is an overhead road with bridge structure to replace embankment, and can raise speed, save land and reduce demolition engineering in dense and heavy urban area.
In the current road bridge maintenance construction process, in order to guarantee the normal traffic of road, adopt the mode of taking part of roads temporarily to construct generally, guide the traffic flow through setting up awl section of thick bamboo and speed limit tablet on the scene, but above-mentioned in-process, often be difficult to guarantee its guide effect through the driver carries out initiative speed reduction, the traffic accident that often appears the vehicle speed reduction and not timely arouses not only influences driver's safety, still influences constructor's safety.
Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle monitoring method for road and bridge construction, which aims to solve the problems that the guiding effect is difficult to ensure when a driver actively decelerates, traffic accidents caused by untimely deceleration of vehicles often occur, the safety of the driver is influenced, and the safety of constructors is also influenced.
The invention is realized in such a way that an unmanned aerial vehicle monitoring method for road and bridge construction comprises the following steps:
receiving a temporary monitoring instruction, wherein the temporary monitoring instruction at least comprises a road speed limit range and a safety monitoring grade;
collecting a road monitoring video, and identifying a road and bridge construction area and a road and bridge passing area based on the road monitoring video;
the method comprises the steps of extracting pictures of road monitoring videos, calculating the passing speed of each vehicle, and defining a risk warning area according to the safety monitoring grade and the passing speed;
and tracking the position of the vehicle in real time, judging whether the vehicle has driving risk or not based on the real-time position of the vehicle, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists.
Preferably, the step of collecting the road monitoring video, identifying the road and bridge construction area and the road and bridge traffic area based on the road monitoring video specifically includes:
the unmanned aerial vehicle is controlled to rise to a preset height, road monitoring video is collected at the position, and a starting position calibration point is identified;
performing Hough transformation on the picture, converting the picture into a line image, and identifying lane lines contained in the picture based on the line image;
and (3) carrying out image recognition on the picture, determining the position of the cone in the picture, and defining a road and bridge construction area and a road and bridge passing area based on the position of the cone and the position of the lane line.
Preferably, the step of calculating the traffic speed of each vehicle by extracting the picture of the road monitoring video and defining the risk warning area according to the safety monitoring level and the traffic speed specifically includes:
extracting a monitoring picture from a road monitoring video based on a preset time step to form a monitoring picture sequence, wherein the monitoring picture sequence comprises a time sequence;
determining the position of a vehicle in a picture through image recognition, and calculating the passing speed of the vehicle by comparing the positions of the vehicles in two adjacent frames of monitoring pictures;
and calculating the safe deceleration distance of the vehicle based on a preset braking distance formula, and defining a risk warning area based on the safe deceleration distance and the safety monitoring level.
Preferably, the step of tracking the vehicle position in real time, determining whether the vehicle has a driving risk based on the real-time position of the vehicle, and performing an acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists specifically includes:
constructing a two-dimensional coordinate system, and generating a vehicle movement track curve based on the real-time position of each vehicle;
collecting a plurality of track coordinates based on a vehicle movement track curve, generating a running track function based on the track coordinates, and generating predicted coordinates according to the running track function;
and judging whether the driving risk exists or not based on the relative position relation between the predicted coordinates and the risk warning area, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists.
Preferably, the starting position calibration point coincides with the position of the first cone.
Preferably, the risk warning area is a circular area taking the starting position calibration point as the center of a circle and L as the radius,wherein->For the real-time speed of the vehicle>For a desired speed of the vehicle,afor the deceleration of the vehicle,Kfor the early warning distance coefficient, < >>For the longitudinal distance of the cone array of the vehicle, < >>Is the lateral distance of the cone array of the vehicle.
Another object of the present invention is to provide an unmanned aerial vehicle monitoring system for road and bridge construction, the system comprising:
the instruction receiving module is used for receiving a temporary monitoring instruction, and the temporary monitoring instruction at least comprises a road speed limit range and a safety monitoring grade;
the area dividing module is used for collecting road monitoring videos and identifying road and bridge construction areas and road and bridge passing areas based on the road monitoring videos;
the risk area demarcation module is used for calculating the passing speed of each vehicle by extracting pictures of the road monitoring video and demarcating a risk warning area according to the safety monitoring grade and the passing speed;
and the risk monitoring module is used for tracking the position of the vehicle in real time, judging whether the vehicle has driving risk or not based on the real-time position of the vehicle, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists.
Preferably, the area dividing module includes:
the video acquisition unit is used for controlling the unmanned aerial vehicle to rise to a preset height, acquiring a road monitoring video at the position and identifying a starting position calibration point;
the picture processing unit is used for carrying out Hough transformation on the picture, converting the picture into a line image and identifying lane lines contained in the line image;
and the cone barrel identification unit is used for carrying out image identification on the picture, determining the cone barrel position in the picture and defining a road and bridge construction area and a road and bridge passing area based on the cone barrel position and the position of the lane line.
Preferably, the risk area demarcation module includes:
the image extraction unit is used for extracting a monitoring image from the road monitoring video based on a preset time step to form a monitoring image sequence, wherein the monitoring image sequence comprises a time sequence;
the passing speed calculation unit is used for determining the position of the vehicle in the picture through image recognition and calculating the passing speed of the vehicle by comparing the positions of the vehicles in the two adjacent frames of monitoring pictures;
the area dividing unit is used for calculating the safe deceleration distance of the vehicle based on a preset braking distance formula and dividing a risk warning area based on the safe deceleration distance and the safety monitoring level.
Preferably, the risk monitoring module includes:
the track generation unit is used for constructing a two-dimensional coordinate system and generating a vehicle movement track curve based on the real-time position of each vehicle;
the track prediction unit is used for acquiring a plurality of track coordinates based on a vehicle movement track curve, generating a running track function based on the track coordinates, and generating predicted coordinates according to the running track function;
and the risk identification unit is used for judging whether the driving risk exists or not based on the relative position relation between the prediction coordinates and the risk warning area, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists.
According to the unmanned aerial vehicle monitoring method for road and bridge construction, image acquisition is carried out from high altitude through an unmanned aerial vehicle, positions of a vehicle, a cone and a lane line in a picture are identified through image identification, a construction area and a warning area are determined based on the positions of the cone and the lane line, the moving speed of the vehicle is identified, whether risks exist or not is judged based on the moving speed and the distance of the vehicle, and when the risks exist, an audible and visual alarm is carried out to prompt the vehicle to decelerate, so that the risks are avoided.
Drawings
Fig. 1 is a flowchart of an unmanned aerial vehicle monitoring method for road and bridge construction according to an embodiment of the present invention;
fig. 2 is a flowchart of a step of collecting a road monitoring video, identifying a road and bridge construction area and a road and bridge traffic area based on the road monitoring video according to an embodiment of the present invention;
fig. 3 is a flowchart of a step of calculating a traffic speed of each vehicle by extracting a picture of a road monitoring video and defining a risk warning area according to a security monitoring level and the traffic speed according to an embodiment of the present invention;
FIG. 4 is a flowchart showing steps for tracking the position of a vehicle in real time, determining whether the vehicle has a driving risk based on the real-time position of the vehicle, performing an audible and visual warning when the driving risk exists, and guiding the vehicle to slow down and change lanes according to the embodiment of the present invention;
fig. 5 is a schematic diagram of an unmanned aerial vehicle monitoring system for road and bridge construction according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a region dividing module according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a risk area demarcation module according to an embodiment of the present invention;
FIG. 8 is a block diagram of a risk monitoring module according to an embodiment of the present invention;
FIG. 9 is a schematic view of construction monitoring provided by an embodiment of the present invention;
fig. 10 is a schematic diagram of unmanned aerial vehicle monitoring according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, the method for monitoring an unmanned aerial vehicle for road and bridge construction provided by the embodiment of the invention includes:
s100, receiving a temporary monitoring instruction, wherein the temporary monitoring instruction at least comprises a road speed limit range and a safety monitoring grade.
In this step, a temporary monitoring instruction is received, as shown in fig. 9, when monitoring is required, firstly, a cone is placed based on a construction area, the cone is obliquely arranged along an occupied lane to form an oblique guide line, a marker is placed on the first cone, the marker is placed on the cone, the marker is sleeved on the cone, a take-off platform is arranged at the top of the marker, an identification pattern is drawn on the take-off platform and used for guiding the unmanned aerial vehicle to land, the unmanned aerial vehicle is vertically lifted from the take-off platform and rises to a preset height, the temporary monitoring instruction is received by the unmanned aerial vehicle, the road speed limit range and the safety monitoring grade are included, the road speed limit range is the speed limit value of the current construction section, if the maximum speed of the construction road section is 60 km/h, the safety monitoring grade is divided into low grade, medium grade and high grade, the higher the safety monitoring grade is, the more advanced the time and distance for carrying out acousto-optic warning, the higher the safety monitoring grade can be adopted for roads and bridges on highways, the medium grade safety monitoring grade can be adopted for roads and bridges such as urban express way, and the lower grade safety monitoring grade can be adopted for urban roads.
S200, collecting a road monitoring video, and identifying a road and bridge construction area and a road and bridge passing area based on the road monitoring video.
In this step, after the unmanned aerial vehicle receives the temporary monitoring instruction, the unmanned aerial vehicle rises from the take-off platform by a preset height and hovers, a reference loop line is preset in a picture collected by the unmanned aerial vehicle, as shown in fig. 9, a first connecting line is formed between a point on the loop line and the unmanned aerial vehicle, a second connecting line is formed between the unmanned aerial vehicle and the take-off platform, the included angle between the first connecting line and the second connecting line is known, the actual distance between the adjacent loop lines can be calculated based on the take-off height of the unmanned aerial vehicle, according to the actual distance, a scale between the picture and the actual can be determined, thus the distance can be calculated, the collected picture is converted into a line graph by gray processing and Hough transformation, the position of the lane line is determined, the position of the take-off point can be determined by identifying the identification pattern, the cone in the picture is calibrated, the cone in the picture is identified, the enclosing area formed between the cone line and the cone is used as a construction area, the enclosing area is not enclosed, and the border of the cone line is used as a traffic area except the construction area.
S300, through extracting pictures of the road monitoring video, the passing speed of each vehicle is calculated, and a risk warning area is defined according to the safety monitoring grade and the passing speed.
In this step, the image is extracted from the road monitoring video, specifically, the image is extracted according to a preset time step, if the interval duration is T, then one frame of image is extracted at a time, the n+1th frame of image is extracted at a+nt, the moving speed of the vehicle is calculated based on the positions of the vehicles in the two frames of images, so that the passing speeds of the vehicles in the images are counted, when the passing speeds of the vehicles are faster, the possibility of risk is indicated to be greater, the corresponding response distance is set based on the passing speeds of the vehicles, the response distance is the response distance of the vehicles after receiving the acousto-optic warning, the whole monitoring area is divided based on the response distance, the road speed limit range and the safety monitoring level, so that the risk warning area is determined, and when the user enters the risk warning area, the acousto-optic warning is started.
S400, tracking the position of the vehicle in real time, judging whether the vehicle has driving risk or not based on the real-time position of the vehicle, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists.
In the step, the positions of vehicles are tracked in real time, the vehicles in a picture are tracked through image recognition, the positions of the vehicles are determined, and because the corresponding risk warning areas are determined based on the speeds of the vehicles, when the vehicles enter the risk warning areas, risks are indicated to occur easily, at the moment, the existence of risks is judged, then the unmanned aerial vehicle can carry out acousto-optic warning, and also the acousto-optic warning devices can be arranged at the two sides of a road to carry out acousto-optic warning, if the judgment that the driving risks do not exist, the acousto-optic warning devices are not started, and the vehicles can drive directly according to the speed limit plate and the guide plate which are arranged on site.
As shown in fig. 2, as a preferred embodiment of the present invention, the step of collecting the road monitoring video, identifying the road and bridge construction area and the road and bridge traffic area based on the road monitoring video specifically includes:
s201, controlling the unmanned aerial vehicle to ascend to a preset height, collecting the road monitoring video at the position, and identifying a starting position calibration point.
In this step, the unmanned aerial vehicle is controlled to rise to a preset height, specifically, the rising height of the unmanned aerial vehicle is determined according to the size of a construction area, when the construction area is large, the inclination of the set cone is smaller, the vehicle is more beneficial to changing the road, the unmanned aerial vehicle needs to rise to a higher height for monitoring, if aiming at a low-speed scene such as a national road, a take-off platform is placed on a first cone placed on the unmanned aerial vehicle, the unmanned aerial vehicle takes off from the take-off platform, the height of the take-off platform is fixed, after the unmanned aerial vehicle takes off, the unmanned aerial vehicle recognizes the identification pattern on the take-off platform according to the acquired video image, because a reference ring is arranged in the video image, as shown in fig. 10, the circle center of the reference ring is always kept to coincide with the identification pattern, and the position is the initial position identification point.
S202, performing Hough transformation on the picture, converting the picture into a line image, and identifying lane lines contained in the line image.
In this step, the frame is subjected to hough transform, and the frame included in the road monitoring video is first subjected to gray processing, and converted into a gray image, so as to reduce the data processing amount, and then subjected to hough transform, so as to obtain an image including only lines, i.e., a line image, and lane lines are identified based on the line image.
And S203, performing image recognition on the picture, determining the position of the cone in the picture, and defining a road and bridge construction area and a road and bridge passing area based on the position of the cone and the position of the lane line.
In the step, image recognition is carried out on a picture, recognition judgment is carried out based on a preset cone top view, the positions of all cones in the picture are determined, the central position of each cone is determined, the central positions of the cones are connected in series according to the extending direction of a lane line, then the lane line and the cone line can form a closed area, namely a construction area, and then areas except the construction area are road and bridge passing areas, and the road and bridge passing areas are limited between the lane lines.
As shown in fig. 3, as a preferred embodiment of the present invention, the steps of calculating the traffic speed of each vehicle by extracting the picture of the road monitoring video, and defining the risk warning area according to the security monitoring level and the traffic speed specifically include:
s301, extracting monitoring pictures from the road monitoring video based on a preset time step to form a monitoring picture sequence, wherein the monitoring picture sequence comprises a time sequence.
In this step, the monitoring frames are extracted from the road monitoring video based on a preset time step, and in the process of monitoring, different warning intervals need to be determined according to the speed setting of the vehicle, specifically, a frame of frames can be extracted according to the rapid measurement requirement according to 100ms, so as to obtain continuous monitoring frames, the continuous monitoring frames are arranged according to the time sequence, and the time intervals between two adjacent monitoring frames are the same.
S302, determining the position of the vehicle in the picture through image recognition, and calculating the passing speed of the vehicle by comparing the positions of the vehicles in the two adjacent frames of monitoring pictures.
In this step, the vehicle position in the frame is determined through image recognition, the vehicle is identified in many ways, specifically, the rectangular area formed by the line enclosing can be determined through processing the line in the line diagram, if the aspect ratio of the rectangular area is within the preset range, the rectangular area is determined to be the vehicle, the rectangular area is used for representing the vehicle, the diagonal intersection point of the rectangular area is used as the vehicle position, then the vehicle position in two adjacent frames of monitoring frames is compared, the moving speed of the vehicle is calculated, in the above process, firstly, the scale between the frame and the actual is required to be determined, specifically, a first connecting line is formed between the point on the reference ring line in the frame acquired by the unmanned aerial vehicle and the unmanned aerial vehicle, a second connecting line is formed between the unmanned aerial vehicle and the take-off platform, the included angle between the first connecting line and the second connecting line is θ, if the rising height of the unmanned aerial vehicle is h, the diameter of the reference ring line is 2h tan θ, and the number of pixels P on any diameter on the reference ring line is counted, and the scale is 1: the distance the vehicle moves in a time step can be determined from the actual length of (2 h tan θ)/P, i.e. one pixel corresponds to (2 h tan θ)/P, and the speed of the vehicle passing in that time step can be calculated since the time step is known.
S303, calculating the safe deceleration distance of the vehicle based on a preset braking distance formula, and defining a risk warning area based on the safe deceleration distance and the safety monitoring level.
In this step, the safe deceleration distance of the vehicle is calculated based on a preset braking distance formula, as shown in fig. 9,for warning distance of vehicle (for audible and visual warning of vehicle in this interval, vehicle is required to be decelerated before time B),/the vehicle is provided with a warning device for warning the vehicle in the time zone>For the straight distance that needs to be travelled during deceleration of the vehicle,L=/>the risk warning area takes the starting position calibration point as the center of a circleLIs a circular area with radius +.>Wherein->For the real-time speed of the vehicle>For a desired speed of the vehicle (i.e. for a speed limit),afor the deceleration of the vehicle (the deceleration of the vehicle is more comfortable at a brake deceleration of 1.5-2.5 m/s 2),Kthe distance coefficient is early-warningKThe value is related to the safety monitoring levelThe higher the full monitoring level, the moreKThe greater the value), the>For the longitudinal distance of the cone array of the vehicle, < >>The transverse distance of the cone array of the vehicle is the transverse distance of the cone array of the vehicle, wherein the speed of the vehicle is measured before the vehicle reaches the point A, and the vehicle speed is obtained>Determining a warning distance of the vehicle based on the vehicle speed>And determining the deceleration of the vehicleaThe distance required for deceleration is determined to determine the straight line distance +.>Then the distance over which the audible and visual warning is made can be determinedLWhen the vehicle enters the position A, the distance between the position A and the first cone isLIf the speed of the vehicle entering the point A is lower than +.>Real-time speed +.>Updating to redetermine the warning distance +.>Repeating the above process until +.>Not lower than->。
As shown in fig. 4, as a preferred embodiment of the present invention, the steps of tracking the vehicle position in real time, determining whether the vehicle has a driving risk based on the real-time position of the vehicle, and performing an audible and visual warning when the driving risk exists, and guiding the vehicle to slow down and change lanes specifically include:
s401, constructing a two-dimensional coordinate system, and generating a vehicle movement track curve based on the real-time positions of all vehicles.
In this step, a two-dimensional coordinate system is constructed, specifically, the position where the first cone is located is taken as an origin, the driving direction is taken as an X axis, the driving direction is taken as a Y axis, and the two-dimensional coordinate system is parallel to the road surface, so that the position of the vehicle can be recorded, and in the recording process, the time of the vehicle at each position is recorded.
S402, acquiring a plurality of track coordinates based on a vehicle movement track curve, generating a running track function based on the track coordinates, and generating predicted coordinates according to the running track function.
S403, judging whether the driving risk exists based on the relative position relation between the predicted coordinates and the risk warning area, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists.
In the step, two modes for determining driving risk are provided, wherein the first mode is to judge the risk based on the relation between the current vehicle position and the risk warning area, namely, if the vehicle enters the risk warning area corresponding to the vehicle speed, judging that the risk exists, and starting to carry out acousto-optic warning to prompt the vehicle; the second method is to collect a plurality of track coordinates based on a vehicle moving track curve, perform function fitting of the track curve according to the track coordinates, and predict the position of the vehicle by function fitting, in this embodiment, specifically, the position of the vehicle in the X-axis direction may be taken as an abscissa, the position of the vehicle in the Y-axis direction may be taken as an ordinate, the abscissa and the ordinate corresponding to the same time are combined into a set of track coordinates, in the process of recording the position of the vehicle, the track coordinates are points on the vehicle moving track curve in the history running process, by extracting points on the plurality of vehicle moving track curves (i.e. extracting a plurality of track coordinates), performing function fitting according to the plurality of track coordinates, specifically, mathematical analysis tools such as matlab may be used to perform fitting, the process is not repeated herein, and when the running track function is obtained, the position of the vehicle in the X-axis direction (i.e. the abscissa which is the predicted coordinate) which is not passed by the vehicle is substituted, the position of the vehicle in the X-axis (i.e. the abscissa which is the predicted coordinate) may be calculated, the position of the vehicle moving track corresponding to the position of the X-axis in the history running process may be obtained, the predicted coordinate is predicted coordinate, and the predicted track is predicted in the future risk may be calculated, if the predicted track is predicted, and the predicted is the predicted track is based on the predicted risk of the future risk is detected based on the predicted track.
As shown in fig. 5, an unmanned aerial vehicle monitoring system for road and bridge construction according to an embodiment of the present invention includes:
the instruction receiving module 100 is configured to receive a temporary monitoring instruction, where the temporary monitoring instruction at least includes a road speed limit range and a safety monitoring level.
In the system, the command receiving module 100 receives a temporary monitoring command, as shown in fig. 9, when the monitoring is needed, firstly, a cone is placed on the basis of a construction area, the cone is obliquely arranged along an occupied lane to form an oblique guide line, a marker is placed on the first cone, the marker is placed on the cone, the marker is sleeved on the cone, a take-off platform is arranged at the top of the first cone, an identification pattern is drawn on the take-off platform and used for guiding the unmanned aerial vehicle to land, the unmanned aerial vehicle is vertically lifted from the take-off platform and rises to a preset height, the temporary monitoring command is received by the unmanned aerial vehicle, the temporary monitoring command comprises a road speed limit range and a safety monitoring grade, the road speed limit range is the speed limit value of the current construction section, if the maximum speed of the construction road section is 60 km/h, the safety monitoring grade is divided into low grade, medium grade and high grade, the higher the safety monitoring grade is, the more advanced the time and distance for carrying out acousto-optic warning, the higher the safety monitoring grade can be adopted for roads and bridges on highways, the medium grade safety monitoring grade can be adopted for roads and bridges such as urban express way, and the lower grade safety monitoring grade can be adopted for urban roads.
The area dividing module 200 is configured to collect a road monitoring video, and identify a road and bridge construction area and a road and bridge traffic area based on the road monitoring video.
In the system, after the area dividing module 200 collects the road monitoring video, the unmanned aerial vehicle receives the temporary monitoring instruction, the unmanned aerial vehicle ascends from the take-off platform to preset the height and hovers, a reference loop line is preset in a picture collected by the unmanned aerial vehicle, as shown in fig. 9, a first connecting line is formed between a point on the loop line and the unmanned aerial vehicle, a second connecting line is formed between the unmanned aerial vehicle and the take-off platform, the included angle between the first connecting line and the second connecting line is known, the actual distance between the adjacent loop line can be calculated based on the take-off height of the unmanned aerial vehicle, accordingly, the scale between the picture and the actual distance can be determined, the collected picture is converted into a line graph by gray processing and Hough transformation, the position of the lane line is determined, the position of the take-off point can be determined by identifying the identification pattern, the purpose of calibrating the picture is achieved, the cone in the picture is identified, the construction area formed between the lane line and the cone is taken as the construction area, the construction area is taken as the traffic area except the traffic area.
The risk area demarcation module 300 is configured to calculate a traffic speed of each vehicle by extracting a picture of the road monitoring video, and demarcating a risk warning area according to the safety monitoring level and the traffic speed.
In the system, the risk area demarcation module 300 extracts the images of the road monitoring video, specifically, extracts the images according to a preset time step, if the interval duration is T, then extracts one frame of images at a time, and extracts n+1 frames of images at a+nt, calculates the moving speed of the vehicle based on the positions of the vehicles in the two frames of images, thereby counting the passing speed of each vehicle in the images, when the passing speed of the vehicle is faster, the possibility of risk is indicated to be greater, then sets a corresponding response distance based on the passing speed of the vehicle, the response distance is the distance that the vehicle responds after receiving the acousto-optic warning, divides the whole speed limiting monitoring area based on the response distance, the road range and the safety monitoring level, thereby determining the risk warning area, and when the user enters the risk warning area, starts to carry out the acousto-optic warning.
The risk monitoring module 400 is configured to track the position of the vehicle in real time, determine whether the vehicle has a driving risk based on the real-time position of the vehicle, and perform an audible and visual warning to guide the vehicle to slow down and change lanes when the driving risk exists.
In the system, the risk monitoring module 400 tracks the positions of vehicles in real time, tracks each vehicle in a picture through image recognition, determines the position of each vehicle, and because the corresponding risk warning area is determined based on the speed of each vehicle, when the vehicle enters the risk warning area, the risk is indicated to be easy to appear, and at the moment, the risk is judged to exist, then the unmanned aerial vehicle can carry out acousto-optic warning, and also can carry out acousto-optic warning through arranging acousto-optic warning devices at two sides of a road, if the driving risk is judged not to exist, the acousto-optic warning devices are not started, and the vehicle can directly drive according to a speed limit plate and a guide plate which are arranged on site.
As shown in fig. 6, as a preferred embodiment of the present invention, the area dividing module 200 includes:
the video acquisition unit 201 is configured to control the unmanned aerial vehicle to rise to a preset height, perform acquisition of a road monitoring video at the position, and identify a starting position calibration point.
In this module, the video acquisition unit 201 controls unmanned aerial vehicle to rise to preset height, specifically, unmanned aerial vehicle's rising height is determined according to construction area's size, when construction area is great, the inclination of the cone that sets up is littleer, more be favorable to the vehicle to become the way, unmanned aerial vehicle then need rise to higher height and monitor, if to low-speed scene, such as lane such as national road, then adopt can lower height, place take-off platform on the first cone of putting, unmanned aerial vehicle then take-off from take-off platform, take-off platform's height is fixed, after unmanned aerial vehicle takes-off, unmanned aerial vehicle obtains the sign pattern on the video image discernment take-off platform according to gathering, because be provided with the reference ring in the video image, as shown in fig. 10, keep the centre of a circle and the sign pattern coincidence all the time of reference ring, this position is the initial position mark point promptly.
The picture processing unit 202 is configured to perform hough transform on a picture, convert the hough transform into a line image, and identify a lane line included therein based on the line image.
In this module, the frame processing unit 202 performs hough transform on the frame, first performs gray processing on the frame included in the road monitoring video, converts the gray processing into a gray image to reduce the data processing amount, and further performs hough transform to obtain an image including only lines, i.e. a line image, and identifies lane lines based on the line image.
The cone recognition unit 203 is configured to perform image recognition on a screen, determine a cone position in the screen, and define a road and bridge construction area and a road and bridge traffic area based on the cone position and a lane line position.
In this module, the cone recognition unit 203 performs image recognition on the picture, performs recognition determination based on a preset cone top view, determines the positions of all cones in the picture, determines the center position of each cone, and connects the center positions of the cones in series according to the extending direction of the lane lines, so that the lane lines and the cone lines can form a closed area, namely a construction area, and the areas except the construction area are road and bridge traffic areas, wherein the road and bridge traffic areas are limited between the lane lines.
As shown in fig. 7, as a preferred embodiment of the present invention, the risk area demarcation module 300 includes:
the picture extraction unit 301 is configured to extract a monitoring picture from the road monitoring video based on a preset time step, and form a monitoring picture sequence, where the monitoring picture sequence includes a time sequence.
In this module, the picture extracting unit 301 extracts the monitoring pictures from the road monitoring video based on a preset time step, and in the process of monitoring, different warning intervals need to be determined according to the vehicle speed setting of the vehicle, specifically, one frame of picture can be extracted according to the rapid measurement requirement according to 100ms, so as to obtain continuous monitoring pictures, the monitoring picture sequences can be obtained by arranging according to the time sequence, and the time intervals between two adjacent monitoring pictures are the same.
The passing speed calculating unit 302 is configured to determine a vehicle position in the screen through image recognition, and calculate a passing speed of the vehicle by comparing positions of the vehicles in the adjacent two frames of monitoring screens.
In this module, the traffic speed calculating unit 302 determines the vehicle position in the frame through image recognition, and in particular, the traffic speed calculating unit may determine a rectangular area formed by line enclosing by processing lines in the line graph, if the aspect ratio of the rectangular area is within a preset range, it is determined that the rectangular area is a vehicle, the rectangular area is used to characterize the vehicle, a diagonal intersection point of the rectangular area is used as the vehicle position, then the vehicle positions in two adjacent frames of monitoring frames are compared to calculate the moving speed of the vehicle, in the above process, firstly, a scale between the frame and the actual needs to be determined, specifically, a first connection line is formed between a point on a reference loop line in the unmanned aerial vehicle acquisition frame and the unmanned aerial vehicle, a second connection line is formed between the unmanned aerial vehicle and the take-off platform, an included angle between the first connection line and the second connection line is θ, for example, if the rising height of the unmanned aerial vehicle is h, the diameter of the reference loop line is 2h, and the number of pixels P on any diameter of the reference loop line is counted, and the scale is 1: the distance the vehicle moves in a time step can be determined from the actual length of (2 h tan θ)/P, i.e. one pixel corresponds to (2 h tan θ)/P, and the speed of the vehicle passing in that time step can be calculated since the time step is known.
The area dividing unit 303 is configured to calculate a safe deceleration distance of the vehicle based on a preset braking distance formula, and define a risk warning area based on the safe deceleration distance and the safety monitoring level.
In this module, the region dividing unit 303 calculates a safe deceleration distance of the vehicle based on a preset braking distance formula, as shown in fig. 9,for warning distance of vehicle (for audible and visual warning of vehicle in this interval, vehicle is required to be decelerated before time B),/the vehicle is provided with a warning device for warning the vehicle in the time zone>For the straight distance that needs to be travelled during deceleration of the vehicle,L=/>the risk warning area takes the starting position calibration point as the center of a circleLIs a circular region of radius,wherein->For the real-time speed of the vehicle>For a desired speed of the vehicle (i.e. for a speed limit),afor the deceleration of the vehicle (the deceleration of the vehicle is more comfortable at a brake deceleration of 1.5-2.5 m/s 2),Kthe distance coefficient is early-warningKThe value is related to the security monitoring level, the higher the security monitoring level isKThe greater the value), the>For the longitudinal distance of the cone array of the vehicle, < >>For a vehicleThe transverse distance of the cone array of the vehicle, wherein the speed of the vehicle is measured before the vehicle reaches the point A, so as to obtain the vehicle speed +.>Determining a warning distance of the vehicle based on the vehicle speed>And determining the deceleration of the vehicleaThe distance required for deceleration is determined to determine the straight line distance +.>Then the distance over which the audible and visual warning is made can be determinedLWhen the vehicle enters the position A, the distance between the position A and the first cone isLIf the speed of the vehicle entering the point A is lower than +.>Real-time speed +.>Updating to redetermine the warning distance +.>Repeating the above process until +.>Not lower than。
As shown in fig. 8, as a preferred embodiment of the present invention, the risk monitoring module 400 includes:
the track generation unit 401 is configured to construct a two-dimensional coordinate system, and generate a vehicle movement track curve based on the real-time positions of the respective vehicles.
In this module, the track generating unit 401 constructs a two-dimensional coordinate system, specifically, the position where the first cone is located may be taken as an origin, the driving direction is taken as an X axis, and the direction perpendicular to the driving direction is taken as a Y axis, and the two-dimensional coordinate system is parallel to the road surface, so that the position of the vehicle may be recorded, and in the recording process, the time of the vehicle at each position may be recorded.
The track prediction unit 402 is configured to collect a plurality of track coordinates based on a vehicle movement track curve, generate a running track function based on the track coordinates, and generate predicted coordinates according to the running track function.
The risk recognition unit 403 is configured to determine whether there is a driving risk based on a relative positional relationship between the prediction coordinates and the risk warning area, and perform an audible and visual warning to guide the vehicle to slow down and change lanes when there is a driving risk.
In the module, two modes for determining driving risk are provided, wherein the first mode is to judge the risk based on the relation between the current vehicle position and the risk warning area, namely, if the vehicle enters the risk warning area corresponding to the vehicle speed, the risk is judged to exist, and then sound and light warning is started to prompt the vehicle; and secondly, acquiring a plurality of track coordinates based on a vehicle movement track curve, performing function fitting of the track curve according to the track coordinates, predicting the position of the vehicle through the function fitting, and judging that the risk exists and performing acousto-optic warning if the vehicle speed exceeds a preset value and the predicted coordinates generated based on the running track function are located in a risk warning area.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
1. An unmanned aerial vehicle monitoring method for road and bridge construction, the method comprising:
receiving a temporary monitoring instruction, wherein the temporary monitoring instruction at least comprises a road speed limit range and a safety monitoring grade;
collecting a road monitoring video, and identifying a road and bridge construction area and a road and bridge passing area based on the road monitoring video;
the method comprises the steps of extracting pictures of road monitoring videos, calculating the passing speed of each vehicle, and defining a risk warning area according to the safety monitoring grade and the passing speed;
and tracking the position of the vehicle in real time, judging whether the vehicle has driving risk or not based on the real-time position of the vehicle, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists.
2. The unmanned aerial vehicle monitoring method for road and bridge construction according to claim 1, wherein the step of collecting road monitoring video and identifying road and bridge construction areas and road and bridge traffic areas based on the road monitoring video specifically comprises the following steps:
the unmanned aerial vehicle is controlled to rise to a preset height, road monitoring video is collected at the position, and a starting position calibration point is identified;
performing Hough transformation on the picture, converting the picture into a line image, and identifying lane lines contained in the picture based on the line image;
and (3) carrying out image recognition on the picture, determining the position of the cone in the picture, and defining a road and bridge construction area and a road and bridge passing area based on the position of the cone and the position of the lane line.
3. The unmanned aerial vehicle monitoring method for road and bridge construction of claim 2, wherein the starting position calibration point coincides with the position of the first cone.
4. The unmanned aerial vehicle monitoring method for road and bridge construction according to claim 3, wherein the risk warning area is a circular area with a starting position calibration point as a center and L as a radius,wherein->For the real-time speed of the vehicle>For a desired speed of the vehicle,afor the deceleration of the vehicle,Kfor the early warning distance coefficient, < >>For the longitudinal distance of the cone array of the vehicle, < >>Is the lateral distance of the cone array of the vehicle.
5. The unmanned aerial vehicle monitoring method for road and bridge construction according to claim 1, wherein the step of calculating the traffic speed of each vehicle by extracting the picture of the road monitoring video and defining the risk warning area according to the safety monitoring level and the traffic speed comprises the following steps:
extracting a monitoring picture from a road monitoring video based on a preset time step to form a monitoring picture sequence, wherein the monitoring picture sequence comprises a time sequence;
determining the position of a vehicle in a picture through image recognition, and calculating the passing speed of the vehicle by comparing the positions of the vehicles in two adjacent frames of monitoring pictures;
and calculating the safe deceleration distance of the vehicle based on a preset braking distance formula, and defining a risk warning area based on the safe deceleration distance and the safety monitoring level.
6. The unmanned aerial vehicle monitoring method for road and bridge construction according to claim 1, wherein the steps of tracking the vehicle position in real time, determining whether the vehicle has a driving risk based on the real-time position of the vehicle, performing an acousto-optic warning when the driving risk exists, and guiding the vehicle to slow down and change lanes specifically comprise:
constructing a two-dimensional coordinate system, and generating a vehicle movement track curve based on the real-time position of each vehicle;
collecting a plurality of track coordinates based on a vehicle movement track curve, generating a running track function based on the track coordinates, and generating predicted coordinates according to the running track function;
and judging whether the driving risk exists or not based on the relative position relation between the predicted coordinates and the risk warning area, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists.
7. An unmanned aerial vehicle monitoring system for road and bridge construction, the system comprising:
the instruction receiving module is used for receiving a temporary monitoring instruction, and the temporary monitoring instruction at least comprises a road speed limit range and a safety monitoring grade;
the area dividing module is used for collecting road monitoring videos and identifying road and bridge construction areas and road and bridge passing areas based on the road monitoring videos;
the risk area demarcation module is used for calculating the passing speed of each vehicle by extracting pictures of the road monitoring video and demarcating a risk warning area according to the safety monitoring grade and the passing speed;
and the risk monitoring module is used for tracking the position of the vehicle in real time, judging whether the vehicle has driving risk or not based on the real-time position of the vehicle, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists.
8. The unmanned aerial vehicle monitoring system for road and bridge construction of claim 7, wherein the area dividing module comprises:
the video acquisition unit is used for controlling the unmanned aerial vehicle to rise to a preset height, acquiring a road monitoring video at the position and identifying a starting position calibration point;
the picture processing unit is used for carrying out Hough transformation on the picture, converting the picture into a line image and identifying lane lines contained in the line image;
and the cone barrel identification unit is used for carrying out image identification on the picture, determining the cone barrel position in the picture and defining a road and bridge construction area and a road and bridge passing area based on the cone barrel position and the position of the lane line.
9. The unmanned aerial vehicle monitoring system for road and bridge construction of claim 7, wherein the risk zone delineating module comprises:
the image extraction unit is used for extracting a monitoring image from the road monitoring video based on a preset time step to form a monitoring image sequence, wherein the monitoring image sequence comprises a time sequence;
the passing speed calculation unit is used for determining the position of the vehicle in the picture through image recognition and calculating the passing speed of the vehicle by comparing the positions of the vehicles in the two adjacent frames of monitoring pictures;
the area dividing unit is used for calculating the safe deceleration distance of the vehicle based on a preset braking distance formula and dividing a risk warning area based on the safe deceleration distance and the safety monitoring level.
10. The unmanned aerial vehicle monitoring system for road and bridge construction of claim 7, wherein the risk monitoring module comprises:
the track generation unit is used for constructing a two-dimensional coordinate system and generating a vehicle movement track curve based on the real-time position of each vehicle;
the track prediction unit is used for acquiring a plurality of track coordinates based on a vehicle movement track curve, generating a running track function based on the track coordinates, and generating predicted coordinates according to the running track function;
and the risk identification unit is used for judging whether the driving risk exists or not based on the relative position relation between the prediction coordinates and the risk warning area, and carrying out acousto-optic warning to guide the vehicle to decelerate and change lanes when the driving risk exists.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311317534.2A CN117058922B (en) | 2023-10-12 | 2023-10-12 | Unmanned aerial vehicle monitoring method and system for road and bridge construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311317534.2A CN117058922B (en) | 2023-10-12 | 2023-10-12 | Unmanned aerial vehicle monitoring method and system for road and bridge construction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117058922A true CN117058922A (en) | 2023-11-14 |
| CN117058922B CN117058922B (en) | 2024-01-09 |
Family
ID=88663110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311317534.2A Active CN117058922B (en) | 2023-10-12 | 2023-10-12 | Unmanned aerial vehicle monitoring method and system for road and bridge construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117058922B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180211179A1 (en) * | 2017-01-23 | 2018-07-26 | DGS Global Systems, Inc. | Systems, methods, and devices for automatic signal detection with temporal feature extraction within a spectrum |
| CN110085045A (en) * | 2019-05-05 | 2019-08-02 | 方星星 | Road and driving Real-time security monitoring, navigation system and safety monitoring method |
| US20200193173A1 (en) * | 2018-12-12 | 2020-06-18 | Here Global B.V. | Methods and systems for determining roadwork zone extension based on lane marking data |
| CN112712244A (en) * | 2020-12-24 | 2021-04-27 | 内蒙古公路交通投资发展有限公司 | Highway construction early warning method, device, system, electronic equipment and medium |
| CN112964265A (en) * | 2021-03-02 | 2021-06-15 | 恒大新能源汽车投资控股集团有限公司 | Obstacle area marking method and device, electronic equipment and storage medium |
| CN213844319U (en) * | 2020-12-28 | 2021-07-30 | 江苏宁靖盐高速公路有限公司 | Early warning device for expressway construction operation area |
| CN113409528A (en) * | 2021-07-07 | 2021-09-17 | 北京市政路桥管理养护集团有限公司 | Road construction area early warning system |
| CN114943941A (en) * | 2021-02-07 | 2022-08-26 | 华为技术有限公司 | Target detection method and device |
| US20230061784A1 (en) * | 2020-01-29 | 2023-03-02 | NetraDyne, Inc. | Combination alerts |
| CN116030631A (en) * | 2023-01-17 | 2023-04-28 | 南京大学 | Real-time traffic jam state assessment method based on unmanned aerial vehicle aerial video |
| CN116564110A (en) * | 2023-05-15 | 2023-08-08 | 淮阴工学院 | Traffic fault early warning device and method based on multi-unmanned aerial vehicle cooperation |
-
2023
- 2023-10-12 CN CN202311317534.2A patent/CN117058922B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180211179A1 (en) * | 2017-01-23 | 2018-07-26 | DGS Global Systems, Inc. | Systems, methods, and devices for automatic signal detection with temporal feature extraction within a spectrum |
| US20200193173A1 (en) * | 2018-12-12 | 2020-06-18 | Here Global B.V. | Methods and systems for determining roadwork zone extension based on lane marking data |
| CN110085045A (en) * | 2019-05-05 | 2019-08-02 | 方星星 | Road and driving Real-time security monitoring, navigation system and safety monitoring method |
| US20230061784A1 (en) * | 2020-01-29 | 2023-03-02 | NetraDyne, Inc. | Combination alerts |
| CN112712244A (en) * | 2020-12-24 | 2021-04-27 | 内蒙古公路交通投资发展有限公司 | Highway construction early warning method, device, system, electronic equipment and medium |
| CN213844319U (en) * | 2020-12-28 | 2021-07-30 | 江苏宁靖盐高速公路有限公司 | Early warning device for expressway construction operation area |
| CN114943941A (en) * | 2021-02-07 | 2022-08-26 | 华为技术有限公司 | Target detection method and device |
| CN112964265A (en) * | 2021-03-02 | 2021-06-15 | 恒大新能源汽车投资控股集团有限公司 | Obstacle area marking method and device, electronic equipment and storage medium |
| CN113409528A (en) * | 2021-07-07 | 2021-09-17 | 北京市政路桥管理养护集团有限公司 | Road construction area early warning system |
| CN116030631A (en) * | 2023-01-17 | 2023-04-28 | 南京大学 | Real-time traffic jam state assessment method based on unmanned aerial vehicle aerial video |
| CN116564110A (en) * | 2023-05-15 | 2023-08-08 | 淮阴工学院 | Traffic fault early warning device and method based on multi-unmanned aerial vehicle cooperation |
Non-Patent Citations (1)
| Title |
|---|
| 王忠宇;贺文雅;杨航;王艳丽;吴兵;: "基于轨迹数据的高速公路养护维修作业区车辆换道特性研究", 东南大学学报(自然科学版), no. 04 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117058922B (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110264783B (en) | Vehicle anti-collision early warning system and method based on vehicle-road cooperation | |
| CN111369831A (en) | Road driving danger early warning method, device and equipment | |
| CN103914688A (en) | Urban road obstacle recognition system | |
| US10699568B1 (en) | Video-based crossroad signal machine control method | |
| CN109598187A (en) | Obstacle recognition method, differentiating obstacle and railcar servomechanism | |
| CN103453892B (en) | A kind of Bridge Crack Real-Time Monitoring and fast prior-warning device | |
| CN102147971A (en) | Traffic information acquisition system based on video image processing technology | |
| CN103617410A (en) | Highway tunnel parking detection method based on video detection technology | |
| CN209168403U (en) | Transfinite high vehicle early warning system | |
| JP4993644B2 (en) | Train operation support device | |
| CN112633722B (en) | Vehicle-mounted road safety risk assessment system and method | |
| KR20110123042A (en) | Apparatus for yielding traffic information of intelligent transport system and method thereof | |
| CN104574993A (en) | Road monitoring method and device | |
| CN114241750A (en) | Vehicle-road cooperative information interaction system and method based on intelligent road traffic risk early warning method | |
| CN112863193B (en) | Monitoring system and method for running vehicles in tunnel | |
| CN117058922B (en) | Unmanned aerial vehicle monitoring method and system for road and bridge construction | |
| CN106600987A (en) | Intersection traffic signal control method and system having multi-dimensional detection function | |
| CN111722617B (en) | Automatic driving automobile performance judgment system and method based on big data | |
| CN116631187B (en) | Intelligent acquisition and analysis system for case on-site investigation information | |
| CN111427063B (en) | Mobile device traffic control method, device, equipment, system and medium | |
| CN112489125A (en) | Automatic detection method and device for storage yard pedestrians | |
| CN114332159A (en) | Early warning method, system and device for pedestrian illegal crossing guardrail based on target tracking algorithm and storage medium | |
| CN212570057U (en) | Road driving danger early warning device and equipment | |
| CN113435277B (en) | Method and system for monitoring vehicle solid line lane change behavior | |
| CN116665440B (en) | Expressway inter-vehicle distance measurement method, system and equipment |
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 |