CN113033368A - Dynamic monitoring method and system for compaction times of asphalt pavement - Google Patents
Dynamic monitoring method and system for compaction times of asphalt pavement Download PDFInfo
- Publication number
- CN113033368A CN113033368A CN202110292764.2A CN202110292764A CN113033368A CN 113033368 A CN113033368 A CN 113033368A CN 202110292764 A CN202110292764 A CN 202110292764A CN 113033368 A CN113033368 A CN 113033368A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- laser point
- dimensional laser
- different moments
- road roller
- 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 32
- 238000012544 monitoring process Methods 0.000 title claims abstract description 31
- 239000010426 asphalt Substances 0.000 title claims abstract description 29
- 238000005056 compaction Methods 0.000 title claims abstract description 29
- 238000005096 rolling process Methods 0.000 claims abstract description 41
- 230000009471 action Effects 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims description 27
- 238000006073 displacement reaction Methods 0.000 claims description 14
- 238000010191 image analysis Methods 0.000 claims description 7
- 238000007499 fusion processing Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 abstract description 13
- 230000008569 process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 239000011384 asphalt concrete Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 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
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/521—Depth or shape recovery from laser ranging, e.g. using interferometry; from the projection of structured light
-
- 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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Optics & Photonics (AREA)
- Road Paving Machines (AREA)
Abstract
The invention discloses a dynamic monitoring method and a system for the compaction pass of an asphalt pavement, wherein the method comprises the following steps: respectively acquiring a video image and three-dimensional laser point cloud data in a rolling working area in real time by utilizing camera equipment and laser point cloud equipment which are arranged on a paver; establishing a three-dimensional laser point cloud coordinate system with a dynamically changed coordinate origin, and recording three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system to obtain three-dimensional laser point cloud models at different moments; performing machine vision identification and tracking on the video image, and determining the action range of each road roller at different times; and respectively fusing and superposing the video image and the laser point cloud model image at the same moment to obtain data point coordinates in the action range of each road roller at different moments, and counting the times of each coordinate point in the three-dimensional laser point cloud model appearing in the action range of the road roller to obtain the compaction times of each coordinate point. By utilizing the invention, the dynamic monitoring of the rolling construction condition can be realized.
Description
Technical Field
The invention relates to the field of monitoring and detecting of road engineering construction quality, in particular to a dynamic monitoring method and system for compaction pass of an asphalt pavement.
Background
Common asphalt concrete is a typical temperature sensitive material, and the compaction operation performed on the common asphalt concrete at different temperatures leads to different structural characteristics, resulting in different strength and fatigue properties. The asphalt pavement needs to be rolled by a road roller in the construction process, and the compaction frequency under a certain temperature condition is an important index for ensuring the compaction degree of the asphalt pavement, which directly influences the service performance and durability of an asphalt pavement structure in the operation process. At present, the rolling times of the road roller are still difficult to determine in specific construction, the rolling times are counted mainly by subjective judgment of constructors, however, large errors often exist in the construction process, accurate data are difficult to obtain, and the conditions of overvoltage and undervoltage are easy to cause.
With the development of information technology, satellite positioning, image processing and other technologies are also gradually applied to determining the rolling times in the construction process. In the present stage, the detection or monitoring technology for the rolling times of the asphalt pavement mainly depends on collecting and tracking the position information of the road roller, but under the condition that signals such as a GPS (global positioning system) and the like are weak or no signal, obvious position deviation can occur, so that the statistical error of the rolling times is directly caused, and the rolling quality of the asphalt pavement is influenced.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a dynamic monitoring method and a dynamic monitoring system for the compaction pass of an asphalt pavement, which can realize continuous online real-time monitoring on the compaction quality of a road base.
Therefore, the invention provides the following technical scheme:
a method for dynamically monitoring the compaction pass of an asphalt pavement, comprising the following steps of:
respectively acquiring a video image and three-dimensional laser point cloud data in a rolling working area in real time by utilizing camera equipment and laser point cloud equipment which are arranged on a paver;
establishing a three-dimensional laser point cloud coordinate system with a dynamically changed coordinate origin, and recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system to obtain three-dimensional laser point cloud models at different moments;
performing machine vision identification and tracking on the video image, and determining the action range of each road roller at different times;
respectively fusing and superposing the video image and the laser point cloud model image at the same moment to obtain data point coordinates in the action range of each road roller at different moments;
and counting the times of each coordinate point in the three-dimensional laser point cloud model appearing in the working range of the road roller according to the data point coordinates in the working range of the road roller to obtain the compaction pass number of each coordinate point.
Optionally, the establishing a three-dimensional laser point cloud coordinate system with a dynamically changing coordinate origin, and recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system to obtain three-dimensional laser point cloud models at different times includes:
establishing a three-dimensional laser point cloud coordinate system by taking the position of the laser point cloud equipment as a coordinate origin, and updating the coordinate origin according to the positions of the laser point cloud equipment at different moments;
determining the coordinates of the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the displacement of the paver at different moments;
and recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the coordinates of the three-dimensional laser point cloud data to obtain three-dimensional laser point cloud models at different moments.
Optionally, the method further comprises:
and acquiring the motion parameters of the paver in real time, and determining the displacement of the paver at different moments and the positions of the laser point cloud equipment at different moments according to the motion parameters.
Optionally, the method further comprises: establishing an identification model in advance;
the machine vision recognition and tracking of the video image, and the determination of the action range of each road roller at different times comprises the following steps:
identifying the video image by using the identification model, and tracking an identified object to obtain Mask information of each road roller at different moments;
and determining the action range of the road roller according to Mask information of the road roller at different moments.
Optionally, the image pickup apparatus is a pan-tilt camera with an anti-shake function.
An asphalt pavement compaction pass dynamic monitoring system, the system comprising: the system comprises camera equipment and laser point cloud equipment which are arranged on a paver, and data processing equipment which is respectively connected with the camera equipment and the laser point cloud equipment; the data processing apparatus includes: the system comprises a point cloud model establishing module, an image analyzing module, a fusion processing module and a statistical module;
the camera equipment is used for acquiring video images in a rolling working area in real time and transmitting the acquired video images to the data processing equipment;
the laser point cloud equipment is used for acquiring three-dimensional laser point cloud data in a rolling working area in real time and transmitting the acquired three-dimensional laser point cloud data to the data processing equipment;
the point cloud model establishing module is used for establishing a three-dimensional laser point cloud coordinate system with a dynamically changed coordinate origin and recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system to obtain three-dimensional laser point cloud models at different moments;
the image analysis module is used for carrying out machine vision identification and tracking on the video image and determining the action range of each road roller at different moments;
the fusion processing module is used for respectively fusing and superposing the video image and the laser point cloud model image at the same moment to obtain data point coordinates in the action range of each road roller at different moments;
and the counting module is used for counting the times of each coordinate point in the three-dimensional laser point cloud model appearing in the working range of the road roller according to the data point coordinates in the working range of the road roller to obtain the compaction times of each coordinate point.
Optionally, the point cloud model building module includes:
the coordinate system establishing unit is used for establishing a three-dimensional laser point cloud coordinate system by taking the position of the laser point cloud equipment as a coordinate origin and updating the coordinate origin according to the positions of the laser point cloud equipment at different moments;
the point cloud data coordinate determination unit is used for determining the coordinate of the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the displacement of the paver at different moments;
and the model generation unit is used for recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the coordinates of the three-dimensional laser point cloud data to obtain three-dimensional laser point cloud models at different moments.
Optionally, the system further comprises: an onboard device mounted on the paver; the data processing apparatus further includes: a location determination module;
the vehicle-mounted equipment is used for acquiring the motion parameters of the paver in real time;
and the position determining module is used for determining the displacement of the paver at different moments and the positions of the laser point cloud equipment at different moments according to the motion parameters.
Optionally, the data processing apparatus further comprises: the identification model building module is used for building an identification model in advance;
the image analysis module includes:
the image identification unit is used for identifying the video image by using the identification model and tracking an identification object to obtain Mask information of each road roller at different moments;
and the action range determining unit is used for determining the action range of the road roller according to Mask information of the road roller at different moments.
Optionally, the image pickup apparatus is a pan-tilt camera with an anti-shake function.
The dynamic monitoring method and the system for the compaction pass number of the asphalt pavement, provided by the embodiment of the invention, utilize camera equipment and laser point cloud equipment which are arranged on a paver to respectively acquire video images and three-dimensional laser point cloud data in a rolling working area in real time; the method comprises the steps of forming a mobile three-dimensional laser point cloud data set by using a paver as a mobile coordinate origin, determining the rolling condition of each road roller on the asphalt pavement through image recognition, tracking and data fusion, realizing dynamic monitoring of the rolling construction condition, obtaining an accurate statistical result of the rolling times, ensuring that the rolling times of the asphalt pavement meet the design index requirements, and ensuring the compactness of a pavement structure.
Drawings
In order to more clearly illustrate the embodiments of the present application or technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings can be obtained by those skilled in the art according to the drawings.
FIG. 1 is a flow chart of a method for dynamically monitoring the number of passes through which an asphalt pavement is compacted according to an embodiment of the present invention;
FIG. 2 is a block diagram of a dynamic monitoring system for the compaction pass of an asphalt pavement according to an embodiment of the present invention.
Detailed Description
In order to make the technical field of the invention better understand the scheme of the embodiment of the invention, the embodiment of the invention is further described in detail with reference to the drawings and the implementation mode.
As shown in fig. 1, the method for dynamically monitoring the compaction pass of the asphalt pavement according to the embodiment of the present invention includes the following steps:
Specifically, can set up the professional equipment support of take the altitude on the paver, install high definition surveillance camera equipment and high accuracy laser point cloud equipment respectively on the support top, high definition surveillance camera equipment and high accuracy laser point cloud are pitched at take the altitude with the high accuracy laser point cloud and are rolled the workspace, and the equipment fixing height is with the work area that rolls that the scope of shooing covers to be located behind the paver as the standard. For example, the height of the support can be 5-8 m according to actual conditions, and the shooting range of the equipment can reach at least 100m or cover the range of a rolling construction working area.
The high-definition monitoring camera equipment is used for collecting video images in a rolling working area, and the resolution and the frame number of the high-definition monitoring camera equipment are not lower than 1080P and 30FPS, so that the shot images are clear and effective. In order to reduce the influence of video image quality caused by running jitter of the paver, a pan-tilt camera with an anti-jitter function can be selected for shooting, and the shot video image can be transmitted to a field or remote analysis computer for storage in real time.
The high-precision laser point cloud equipment is used for collecting three-dimensional laser point cloud data in a rolling working area, the collecting speed of the point cloud equipment is not lower than 240000 points per second, and the collected three-dimensional laser point cloud data can be transmitted to a field or remote analysis computer for storage in real time.
It should be noted that the high-definition monitoring camera device and the high-precision laser point cloud device can be arranged at the same point to reduce data errors.
102, establishing a three-dimensional laser point cloud coordinate system with a dynamically changed coordinate origin, and recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system to obtain three-dimensional laser point cloud models at different moments.
That is to say, the three-dimensional laser point cloud data acquired at different times need to be recorded in the three-dimensional laser point cloud coordinate system corresponding to the time.
Specifically, a three-dimensional laser point cloud coordinate system is established by taking the position of the laser point cloud equipment as a coordinate origin, and the coordinate origin is updated according to the positions of the laser point cloud equipment at different moments.
In addition, determining the coordinates of the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the displacement of the paver at different moments; and recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the coordinates of the three-dimensional laser point cloud data to obtain three-dimensional laser point cloud models at different moments.
The displacement of the paver at different moments and the positions of the laser point cloud equipment at different moments can be obtained according to the motion parameters of the paver, wherein the motion parameters comprise: the moving direction and the moving speed. In practical application, the motion parameters of the paver can be acquired in real time through vehicle-mounted equipment of the paver, and are transmitted to the on-site or remote analysis computer in real time.
For each data point in the three-dimensional laser point cloud model at different moments, the data point coordinates belonging to the same point of the actual road surface structure can be determined according to the following method.
Assume that at an initial time, the initial coordinates of the origin of the coordinate system are (0,0,0) and the coordinates of an arbitrary point a in the three-dimensional laser point cloud model are (X)a，Ya，Za). According to the displacement of the paver at the moment t as (l)t，mt，nt) If the coordinate of any point a at that time is (X)a+lt，Ya+mt，Za+nt) Then, the coordinate information of all three-dimensional laser point cloud data points in the rolling working range at different times can be listed as the following table:
TABLE 1 three-dimensional laser point cloud model rolling working range data point coordinates
And 103, performing machine vision identification and tracking on the video image, and determining the action range of each road roller at different moments.
In the embodiment of the invention, the received video data in the rolling working range can be processed in real time by a field or remote computer, the positions of the road rollers at different moments in the video data are identified by an artificial intelligent machine vision technology and are numbered and tracked to form Mask information of the real-time positions of the road rollers, and the action range of the road rollers at the moment can be determined according to the Mask information of the road rollers at different moments.
Specifically, a YOLO V3 algorithm framework can be adopted to establish an identification model in advance, and the identification model is used to identify the road roller in the video image. The position tracking of the road roller can adopt MOT SORT algorithm so as to achieve the aim of dynamically obtaining Mask information of each road roller.
And step 104, respectively fusing and superposing the video image and the laser point cloud model image at the same moment to obtain data point coordinates in the action range of each road roller at different moments.
For example, the identified video image and the three-dimensional laser point cloud model image are respectively extracted at the frequency of 1s, the video image and the three-dimensional laser point cloud model image with the same time are fused and overlapped, laser point cloud data in the three-dimensional laser point cloud model at the corresponding moment are determined through Mask information obtained by identifying the video image at different moments, and therefore data points in the action range of each road roller at different moments are obtained.
And the data points in the action range of the road roller are all data points overlapped with the Mask information in the three-dimensional laser point cloud model image.
Specifically, in practical application, the high-definition monitoring camera and the high-precision laser point cloud equipment can be calibrated to obtain internal parameters and external parameters including parameters such as focal length, pixel size, position and direction, and then three-dimensional point cloud data is projected into the two-dimensional identification video images according to the internal parameters and the external parameters, so that three-dimensional space coordinates corresponding to pixel points in each two-dimensional identification video image can be obtained.
And 105, counting the times of each coordinate point in the three-dimensional laser point cloud model appearing in the working range of the road roller according to the data point coordinates in the working range of the road roller to obtain the compaction times of each coordinate point.
And counting the times of each coordinate point in the three-dimensional laser point cloud model appearing in the working range of the road roller at different moments, wherein the times are the compaction times of the coordinate points.
The dynamic monitoring method for the compaction times of the asphalt pavement, provided by the embodiment of the invention, comprises the steps of respectively acquiring video images and three-dimensional laser point cloud data in a rolling working area in real time by utilizing camera equipment and laser point cloud equipment which are arranged on a paver; the method comprises the steps of forming a mobile three-dimensional laser point cloud data set by using a paver as a mobile coordinate origin, determining the rolling condition of each road roller on the asphalt pavement through image recognition, tracking and data fusion, realizing dynamic monitoring of the rolling construction condition, obtaining an accurate statistical result of the rolling times, ensuring that the rolling times of the asphalt pavement meet the design index requirements, and ensuring the compactness of a pavement structure.
Correspondingly, the embodiment of the invention also provides a dynamic monitoring system for the compaction pass of the asphalt pavement, which is a structural block diagram of the system as shown in fig. 2.
In this embodiment, the system includes: the system comprises an image pickup device 21 and a laser point cloud device 22 which are installed on a paver 20, and a data processing device 30 which is respectively connected with the image pickup device 21 and the laser point cloud device 22. Wherein:
the camera device 21 is configured to collect video images in a rolling work area in real time, and transmit the collected video images to the data processing device 30;
the laser point cloud equipment 22 is configured to collect three-dimensional laser point cloud data in the rolling work area in real time, and transmit the collected three-dimensional laser point cloud data to the data processing equipment 30.
It should be noted that, in practical application, a special device support with a certain height may be disposed on the paver 10, a high-definition monitoring camera device and a high-precision laser point cloud device are respectively mounted at the top end of the support, the high-definition monitoring camera device and the high-precision laser point cloud are taken down at a certain height to roll a rolling working area, and the device mounting height is based on the fact that a shooting range covers the rolling working area located behind the paver. In order to reduce the influence of video image quality caused by the running shake of the paver, the camera device 21 may be a pan-tilt camera with an anti-shake function.
The image capturing device 21 and the laser point cloud device 22 may be connected to the data processing device 30 in a wired manner (for example, a data line), or may be connected to the data processing device in a wireless manner, which is not limited in this embodiment of the present invention. The video images shot by the camera device 21 and the three-dimensional laser point cloud data collected by the laser point cloud device 22 can be transmitted to the data processing device 30 arranged on site or remotely for storage in real time.
It should be noted that the data processing device 30 may be a mobile terminal, a computer, a tablet device, a personal digital assistant, etc. The data processing device 30 may include one or more processors, memories; the memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions so as to realize storage and analysis processing of the video image and the three-dimensional laser point cloud data.
In the embodiment of the present invention, the data processing device 30 includes: a point cloud model establishing module 31, an image analyzing module 32, a fusion processing module 33 and a statistic module 34. Wherein:
the point cloud model establishing module 31 is configured to establish a three-dimensional laser point cloud coordinate system with a dynamically changing coordinate origin, and record the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system to obtain three-dimensional laser point cloud models at different times;
the image analysis module 32 is used for performing machine vision recognition and tracking on the video image and determining the action range of each road roller at different times;
the fusion processing module 33 is configured to fuse and superimpose the video image and the laser point cloud model image at the same time, respectively, to obtain data point coordinates within the action range of each road roller at different times;
and the counting module 34 is configured to count the times of each coordinate point in the three-dimensional laser point cloud model appearing in the working range of the road roller according to the data point coordinates in the working range of the road roller, so as to obtain the compaction pass number of each coordinate point.
The point cloud model building module 31 may specifically include the following units:
the coordinate system establishing unit is used for establishing a three-dimensional laser point cloud coordinate system by taking the position of the laser point cloud equipment as a coordinate origin and updating the coordinate origin according to the positions of the laser point cloud equipment at different moments;
the point cloud data coordinate determination unit is used for determining the coordinate of the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the displacement of the paver at different moments;
and the model generation unit is used for recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the coordinates of the three-dimensional laser point cloud data to obtain three-dimensional laser point cloud models at different moments.
In practical application, the displacement of the paver at different moments and the positions of the laser point cloud equipment at different moments can be obtained according to the motion parameters of the paver, wherein the motion parameters comprise: the moving direction and the moving speed.
Accordingly, an on-board device (not shown) may be mounted on the paving machine 20 to acquire the motion parameters of the paving machine in real time and transmit the motion parameters to the data processing device 30 in real time.
Accordingly, the data processing apparatus 30 may further include: and the position determining module (not shown) is used for determining the displacement of the paver at different moments and the positions of the laser point cloud equipment at different moments according to the motion parameters.
In practical applications, the image analysis module 32 may identify the road roller in the video image by using a pre-established identification model. The position tracking of the road roller can adopt MOT SORT algorithm so as to achieve the aim of dynamically obtaining Mask information of each road roller.
The recognition model may be constructed by a corresponding recognition model construction module (not shown), which may be a part of the data processing apparatus 30 or may be independent of the data processing apparatus 30, and the embodiment of the present invention is not limited thereto.
Correspondingly, the image analysis module may specifically include the following units:
the image identification unit is used for identifying the video image by using the identification model and tracking an identification object to obtain Mask information of each road roller at different moments;
and the action range determining unit is used for determining the action range of the road roller according to Mask information of the road roller at different moments.
The dynamic monitoring system for the compaction times of the asphalt pavement provided by the embodiment of the invention utilizes the camera equipment and the laser point cloud equipment which are arranged on the paver to respectively acquire the video image and the three-dimensional laser point cloud data in the rolling working area in real time; the method comprises the steps of forming a mobile three-dimensional laser point cloud data set by using a paver as a mobile coordinate origin, determining the rolling condition of each road roller on the asphalt pavement through image recognition, tracking and data fusion, realizing dynamic monitoring of the rolling construction condition, obtaining an accurate statistical result of the rolling times, ensuring that the rolling times of the asphalt pavement meet the design index requirements, and ensuring the compactness of a pavement structure.
According to the dynamic monitoring method and system for the compaction pass number of the asphalt pavement, the three-dimensional dynamic model in the construction process is constructed by the aid of the laser point cloud equipment, the acquisition precision of the three-dimensional dynamic model can reach the level of 0.1mm, and the working position of the road roller can be accurately determined; the real-time positioning of the road roller adopts a method of combining video data and laser point cloud, does not need traditional GPS equipment, and is convenient for carrying out asphalt pavement compaction pass analysis in a signal difference or signal-free area; moreover, the laser point cloud model can be used for obtaining three-dimensional data of the rolling condition in the whole construction process, and later-stage display is facilitated.
Those skilled in the art will appreciate that all or part of the steps in the above method embodiments may be implemented by a program to instruct relevant hardware to perform the steps, and the program may be stored in a computer-readable storage medium, referred to herein as a storage medium, such as: ROM/RAM, magnetic disk, optical disk, etc.
The present invention has been described in detail with reference to the embodiments, and the description of the embodiments is provided to facilitate the understanding of the method and apparatus of the present invention, and is intended to be a part of the embodiments of the present invention rather than the whole embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any creative effort shall fall within the protection scope of the present invention, and the content of the present description shall not be construed as limiting the present invention. Therefore, any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A dynamic monitoring method for the compaction pass of an asphalt pavement is characterized by comprising the following steps:
respectively acquiring a video image and three-dimensional laser point cloud data in a rolling working area in real time by utilizing camera equipment and laser point cloud equipment which are arranged on a paver;
establishing a three-dimensional laser point cloud coordinate system with a dynamically changed coordinate origin, and recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system to obtain three-dimensional laser point cloud models at different moments;
performing machine vision identification and tracking on the video image, and determining the action range of each road roller at different times;
respectively fusing and superposing the video image and the laser point cloud model image at the same moment to obtain data point coordinates in the action range of each road roller at different moments;
and counting the times of each coordinate point in the three-dimensional laser point cloud model appearing in the working range of the road roller according to the data point coordinates in the working range of the road roller to obtain the compaction pass number of each coordinate point.
2. The method of claim 1, wherein the establishing a three-dimensional laser point cloud coordinate system with a dynamically changing coordinate origin and recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system to obtain three-dimensional laser point cloud models at different moments comprises:
establishing a three-dimensional laser point cloud coordinate system by taking the position of the laser point cloud equipment as a coordinate origin, and updating the coordinate origin according to the positions of the laser point cloud equipment at different moments;
determining the coordinates of the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the displacement of the paver at different moments;
and recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the coordinates of the three-dimensional laser point cloud data to obtain three-dimensional laser point cloud models at different moments.
3. The method of claim 2, further comprising:
and acquiring the motion parameters of the paver in real time, and determining the displacement of the paver at different moments and the positions of the laser point cloud equipment at different moments according to the motion parameters.
4. The method of claim 1, further comprising: establishing an identification model in advance;
the machine vision recognition and tracking of the video image, and the determination of the action range of each road roller at different times comprises the following steps:
identifying the video image by using the identification model, and tracking an identified object to obtain Mask information of each road roller at different moments;
and determining the action range of the road roller according to Mask information of the road roller at different moments.
5. The method according to any one of claims 1 to 4, wherein the image pickup apparatus is a pan-tilt camera with an anti-shake function.
6. An asphalt pavement compaction pass dynamic monitoring system, the system comprising: the system comprises camera equipment and laser point cloud equipment which are arranged on a paver, and data processing equipment which is respectively connected with the camera equipment and the laser point cloud equipment; the data processing apparatus includes: the system comprises a point cloud model establishing module, an image analyzing module, a fusion processing module and a statistical module;
the camera equipment is used for acquiring video images in a rolling working area in real time and transmitting the acquired video images to the data processing equipment;
the laser point cloud equipment is used for acquiring three-dimensional laser point cloud data in a rolling working area in real time and transmitting the acquired three-dimensional laser point cloud data to the data processing equipment;
the point cloud model establishing module is used for establishing a three-dimensional laser point cloud coordinate system with a dynamically changed coordinate origin and recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system to obtain three-dimensional laser point cloud models at different moments;
the image analysis module is used for carrying out machine vision identification and tracking on the video image and determining the action range of each road roller at different moments;
the fusion processing module is used for respectively fusing and superposing the video image and the laser point cloud model image at the same moment to obtain data point coordinates in the action range of each road roller at different moments;
and the counting module is used for counting the times of each coordinate point in the three-dimensional laser point cloud model appearing in the working range of the road roller according to the data point coordinates in the working range of the road roller to obtain the compaction times of each coordinate point.
7. The system of claim 6, wherein the point cloud model building module comprises:
the coordinate system establishing unit is used for establishing a three-dimensional laser point cloud coordinate system by taking the position of the laser point cloud equipment as a coordinate origin and updating the coordinate origin according to the positions of the laser point cloud equipment at different moments;
the point cloud data coordinate determination unit is used for determining the coordinate of the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the displacement of the paver at different moments;
and the model generation unit is used for recording the three-dimensional laser point cloud data in the three-dimensional laser point cloud coordinate system according to the coordinates of the three-dimensional laser point cloud data to obtain three-dimensional laser point cloud models at different moments.
8. The system of claim 7, further comprising: an onboard device mounted on the paver; the data processing apparatus further includes: a location determination module;
the vehicle-mounted equipment is used for acquiring the motion parameters of the paver in real time;
and the position determining module is used for determining the displacement of the paver at different moments and the positions of the laser point cloud equipment at different moments according to the motion parameters.
9. The system of claim 6, wherein the data processing device further comprises: the identification model building module is used for building an identification model in advance;
the image analysis module includes:
the image identification unit is used for identifying the video image by using the identification model and tracking an identification object to obtain Mask information of each road roller at different moments;
and the action range determining unit is used for determining the action range of the road roller according to Mask information of the road roller at different moments.
10. The system according to any one of claims 6 to 9, wherein the image pickup apparatus is a pan-tilt camera with an anti-shake function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110292764.2A CN113033368B (en) | 2021-03-18 | 2021-03-18 | Dynamic monitoring method and system for compaction pass number of asphalt pavement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110292764.2A CN113033368B (en) | 2021-03-18 | 2021-03-18 | Dynamic monitoring method and system for compaction pass number of asphalt pavement |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113033368A true CN113033368A (en) | 2021-06-25 |
| CN113033368B CN113033368B (en) | 2023-12-08 |
Family
ID=76471483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110292764.2A Active CN113033368B (en) | 2021-03-18 | 2021-03-18 | Dynamic monitoring method and system for compaction pass number of asphalt pavement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033368B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000282448A (en) * | 1999-03-29 | 2000-10-10 | Penta Ocean Constr Co Ltd | Compaction condition measurement method and device with gps and camera |
| JP2001159137A (en) * | 1999-12-02 | 2001-06-12 | Kumagai Gumi Co Ltd | Application-property in-advance investigation device for construction-machinery operating control system using gps |
| JP3421315B2 (en) * | 2000-10-25 | 2003-06-30 | 西松建設株式会社 | Construction work compaction control method |
| JP2011191060A (en) * | 2010-03-11 | 2011-09-29 | Matsue Doken Kk | Rolling compaction control system and rolling compaction control method |
| JP2015052205A (en) * | 2013-09-05 | 2015-03-19 | 鹿島建設株式会社 | Compaction management method and compaction management system |
| KR20150128300A (en) * | 2014-05-09 | 2015-11-18 | 한국건설기술연구원 | method of making three dimension model and defect analysis using camera and laser scanning |
| CN106774069A (en) * | 2016-12-26 | 2017-05-31 | 机械工业勘察设计研究院有限公司 | Supervising device and method are filled in a kind of earthwork based on 3 D laser scanning |
| CN107845093A (en) * | 2017-11-15 | 2018-03-27 | 武汉大学 | A kind of placement grinding pass quick determination method based on image procossing |
| CN110008588A (en) * | 2019-04-04 | 2019-07-12 | 南京林业大学 | Multidimensional integrated highway engineering construction progress msg management system and method |
-
2021
- 2021-03-18 CN CN202110292764.2A patent/CN113033368B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000282448A (en) * | 1999-03-29 | 2000-10-10 | Penta Ocean Constr Co Ltd | Compaction condition measurement method and device with gps and camera |
| JP2001159137A (en) * | 1999-12-02 | 2001-06-12 | Kumagai Gumi Co Ltd | Application-property in-advance investigation device for construction-machinery operating control system using gps |
| JP3421315B2 (en) * | 2000-10-25 | 2003-06-30 | 西松建設株式会社 | Construction work compaction control method |
| JP2011191060A (en) * | 2010-03-11 | 2011-09-29 | Matsue Doken Kk | Rolling compaction control system and rolling compaction control method |
| JP2015052205A (en) * | 2013-09-05 | 2015-03-19 | 鹿島建設株式会社 | Compaction management method and compaction management system |
| KR20150128300A (en) * | 2014-05-09 | 2015-11-18 | 한국건설기술연구원 | method of making three dimension model and defect analysis using camera and laser scanning |
| CN106774069A (en) * | 2016-12-26 | 2017-05-31 | 机械工业勘察设计研究院有限公司 | Supervising device and method are filled in a kind of earthwork based on 3 D laser scanning |
| CN107845093A (en) * | 2017-11-15 | 2018-03-27 | 武汉大学 | A kind of placement grinding pass quick determination method based on image procossing |
| CN110008588A (en) * | 2019-04-04 | 2019-07-12 | 南京林业大学 | Multidimensional integrated highway engineering construction progress msg management system and method |
Non-Patent Citations (4)
| Title |
|---|
| 张嘉明;: "大坝碾压监控的可视化研究与实现", 城市勘测, no. 02 * |
| 张文;黄声享;李洋洋;: "基于测量机器人的碾压施工监控系统设计", 测绘地理信息, no. 02 * |
| 李洋洋: "堆石坝碾压监控数据质量分析及碾压参数可视化实现", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 06 * |
| 王乾坤;陈沁;: "GPS大坝施工碾压质量实时监控方法", 武汉理工大学学报, no. 08 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113033368B (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109870456B (en) | Rapid detection system and method for road surface health condition | |
| US8274571B2 (en) | Image zooming using pre-existing imaging information | |
| CN110830756A (en) | Monitoring method and device | |
| CN105905132A (en) | Intelligent rail state patrolling device and method | |
| CN103874193A (en) | Method and system for positioning mobile terminal | |
| CN109269555A (en) | System and method is monitored based on unmanned plane and the Safety of Tailings Dam of dimensional Modeling Technology | |
| CN109859269B (en) | Shore-based video auxiliary positioning unmanned aerial vehicle large-range flow field measuring method and device | |
| CN107843204A (en) | Side slope three-dimensional deformation monitoring method and system based on monitoring level video camera | |
| CN113850137A (en) | Power transmission line image online monitoring method, system and equipment | |
| CN101510311A (en) | Method for rapidly sorting a large amount of building side elevation images based on GPS information | |
| CN110398760A (en) | Pedestrian's coordinate acquisition equipment and its application method based on image analysis | |
| CN115717867A (en) | Bridge deformation measurement method based on airborne double cameras and target tracking | |
| CN115588040A (en) | System and method for counting and positioning coordinates based on full-view imaging points | |
| CN208984029U (en) | A kind of system for engineering works deformation monitoring | |
| CN113763484A (en) | Ship target positioning and speed estimation method based on video image analysis technology | |
| CN210533296U (en) | Tunnel hole circumferential deformation monitoring system | |
| JP2009052907A (en) | Foreign matter detecting system | |
| CN116309851B (en) | Position and orientation calibration method for intelligent park monitoring camera | |
| Chen et al. | Video camera-based vibration measurement for Condition Assessment of Civil Infrastructure | |
| CN113033368B (en) | Dynamic monitoring method and system for compaction pass number of asphalt pavement | |
| CN103595958A (en) | Video tracking analysis method and system | |
| CN111586303A (en) | Control method and device for dynamically tracking road surface target by camera based on wireless positioning technology | |
| CN111289087A (en) | Remote machine vision vibration measurement method and device | |
| CN106303412A (en) | Refuse dump displacement remote real time monitoring apparatus and method based on monitoring image | |
| CN116297472A (en) | Unmanned aerial vehicle bridge crack detection method and system based on deep learning |
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 |