CN113533145A - Rockfill particle size identification and monitoring device and method based on camera set three-dimensional reconstruction - Google Patents
Rockfill particle size identification and monitoring device and method based on camera set three-dimensional reconstruction Download PDFInfo
- Publication number
- CN113533145A CN113533145A CN202110779106.6A CN202110779106A CN113533145A CN 113533145 A CN113533145 A CN 113533145A CN 202110779106 A CN202110779106 A CN 202110779106A CN 113533145 A CN113533145 A CN 113533145A
- Authority
- CN
- China
- Prior art keywords
- rockfill
- camera
- particle size
- camera set
- identified
- 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.)
- Pending
Links
- 239000002245 particle Substances 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012806 monitoring device Methods 0.000 title claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 30
- 239000003550 marker Substances 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims abstract description 5
- 230000000007 visual effect Effects 0.000 claims abstract description 4
- 238000012937 correction Methods 0.000 claims description 7
- 230000003287 optical effect Effects 0.000 claims description 2
- 239000004575 stone Substances 0.000 abstract description 6
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 238000010276 construction Methods 0.000 description 9
- 239000004567 concrete Substances 0.000 description 6
- 239000011435 rock Substances 0.000 description 5
- 238000012216 screening Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000011376 self-consolidating concrete Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/02—Investigating particle size or size distribution
- G01N15/0205—Investigating particle size or size distribution by optical means
-
- 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
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/239—Image signal generators using stereoscopic image cameras using two 2D image sensors having a relative position equal to or related to the interocular distance
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/243—Image signal generators using stereoscopic image cameras using three or more 2D image sensors
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Dispersion Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application discloses rockfill particle size discernment and monitoring device and method based on camera unit three-dimensional reconstruction, the device includes: the camera set at least comprises two cameras and is used for acquiring rockfill multi-angle images of the rockfill to be identified at different heights in the rockfill process at different angles; the calibration module is used for placing a marker in the acquisition visual field of the camera set and calibrating the parameters of the camera set; the identification monitoring module is connected with the camera set and used for carrying out image processing on the multi-angle images of the rockfill, determining a classification result of the particle size of each rockfill in the rockfill to be identified according to the multi-angle images of the rockfill, establishing a grading curve of the rockfill to be identified according to the classification result, and identifying and monitoring the rockfill to be identified according to the grading curve; and the result feedback module is used for sending the identification and detection results of the rockfill to be identified to the preset terminal. The device can utilize binocular or many mesh cameras to combine image recognition neural network algorithm to realize the discernment and the control of the heap stone particle size.
Description
Technical Field
The application relates to the technical field of rockfill particle size identification, in particular to a rockfill particle size identification and monitoring device and method based on three-dimensional reconstruction of a camera set.
Background
The particle size distribution of the rockfill is an influence factor influencing the compaction degree of the rockfill concrete. The filling rate of concrete is difficult to ensure due to too small rockfill, the engineering quality is directly influenced, and potential safety hazards are brought; and the excessive rockfill increases the cost for screening the rockfill, and simultaneously, the volume percentage of the concrete is increased, so that the waste of raw materials is caused, and the engineering cost is greatly increased.
In order to enable the construction to be smoothly carried out in the construction process, the minimum particle size of the rockfill is generally required to be not less than 300mm, so that the rockfill gap has enough cross sectional area, and the self-compacting concrete can smoothly pass through the rockfill gap. A common method for controlling the particle size of the rockfill is to screen out rockfill with a particle size of less than 300mm using a steel screen. However, for large-scale engineering rockfill, the screening method is too high in cost, and a method of manual visual inspection by detection personnel is generally adopted in engineering. At present, a method for rapidly acquiring a large amount of particle size information of the rockfill does not exist.
At present, some equipment and instruments for identifying the particle size are available, but due to the large rock-fill volume and the complex structure, no proper method is available for identifying the particle size. In the existing particle size identification methods, for example, a concrete rock-fill grade identification and regulation device, the sand particle size is identified by using equipment combining a small box and a conveyor belt. For gravels with uniform sizes, the particle size of the piled stones is larger, and the piled stones are not suitable for experiments and checks of indoor box dimensions; on the other hand, when the stone piling operation is carried out on a construction site, the stone is directly conveyed to a warehouse surface by a forklift to be paved, and the mode of the conveyor belt causes additional operation and equipment cost, so that the method is not suitable. Also, as a device and a method for in-situ real-time measurement of silt concentration gradation in a natural river, the device calculates the silt particle size corresponding to each silt particle spot by using a formula based on identification of the silt particle spots. The particle size form of the rockfill is wider in change range, a unified calculation formula is not provided, and accurate identification under more environment backgrounds is required along with influences of factors such as light shadow, block stone edges and corners and the like. Accordingly, rockfill particle size identification places higher demands on the process and corresponding equipment.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, one objective of the present application is to provide a rockfill particle size identification and monitoring device based on three-dimensional reconstruction of a camera set, which utilizes a binocular or multi-view camera in combination with an image recognition neural network algorithm to realize identification and monitoring of rockfill particle size.
Another objective of the present application is to provide a rockfill particle size identification and monitoring method based on three-dimensional reconstruction of a camera set.
In order to achieve the above object, an embodiment of the present application provides a rockfill particle size identification and monitoring device based on three-dimensional reconstruction of a camera set, including:
the camera set is fixed around the surface of the rockfill bin through a camera support and at least comprises two cameras and is used for acquiring rockfill multi-angle images of rockfill to be identified at different heights in the rockfill process at different angles;
the calibration module is used for placing a marker in the acquisition visual field of the camera set and calibrating the parameters of the camera set;
the identification monitoring module is connected with the camera set and used for carrying out image processing on the multi-angle images of the rockfill, determining a classification result of the particle size of each rockfill in the rockfill to be identified according to the multi-angle images of the rockfill, establishing a grading curve of the rockfill to be identified according to the classification result, and identifying and monitoring the rockfill to be identified according to the grading curve;
and the result feedback module is used for sending the identification and detection results of the rockfill to be identified to a preset terminal.
In order to achieve the above object, another embodiment of the present application provides a rockfill particle size identification and monitoring method based on three-dimensional reconstruction of a camera set, including the following steps:
s1, adjusting the position of the camera group: placing the selected marker in the center of a rockfill bin surface area of the rockfill to be identified, adjusting each camera of the camera set to enable each camera to acquire the marker, wherein the marker is located in the center of a rockfill multi-angle image acquired by the cameras;
s2, camera set attitude calibration: measuring the actual distance from the marker to the rock-fill warehouse surface, and calculating a camera attitude parameter according to the position information of the camera set;
s3, collecting a rockfill photo: collecting the multi-angle rockfill images at different heights of the rockfill bin surface, and acquiring the multi-angle rockfill images shot from different angles at different heights in the rockfill process;
s4, correcting the picture distortion of the camera group: calculating and correcting the rockfill multi-angle image by combining the internal and external parameter information of the camera set acquired in S1 and S2 through a camera distortion correction algorithm;
s5, selecting characteristic points: selecting feature points in the rockfill to be identified, finding corresponding positions of the feature points on different angle pictures, and measuring pixel distances of the feature points on the rockfill multi-angle image;
s6, three-dimensional reconstruction: analyzing rockfill photos of different angles acquired by a camera set, calculating the actual distance of the characteristic points by a stereoscopic vision reconstruction method, and measuring the scale of each rockfill multi-angle image according to the actual distance;
s7, identifying the particle size of the rockfill: and identifying the rockfill particle size in the rockfill multi-angle image by using an image identification algorithm, wherein the rockfill particle size data is calculated by the scale calculated in the step S6.
The rockfill particle size identification and monitoring device and method based on camera set three-dimensional reconstruction in the embodiment of the application have the following beneficial effects:
1. the engineering practicability is good: based on the stereoscopic vision method, the method is not influenced by external light, can ensure the precision of the later image processing result, and is suitable for the rock-fill concrete construction site. The accuracy of the angle that has realized remote monitoring rockfill particle diameter, multiunit camera shooting and the degree of accuracy of result, further assurance the precision of shooting and the degree of accuracy of result can effectively promote the speed and the accuracy that the rockfill particle size gradation calculated, promoted the monitoring precision to mixing the rockfill particle size in the work progress.
2. Simple equipment and good stability: the camera set-based three-dimensional reconstruction technology does not need to add other light sources, and is suitable for a rock-fill concrete construction site with complex illumination conditions; on the other hand, the stereoscopic vision method has a mature algorithm for monocular or monocular cameras, and even if one or more cameras in a camera group are damaged or data errors are large, the final result can still be obtained by adjusting the algorithm.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic structural diagram of a rockfill particle size identification and monitoring device based on three-dimensional reconstruction of a camera set according to an embodiment of the present application;
FIG. 2 is a block diagram of a camera cluster according to one embodiment of the present application;
FIG. 3 is a flow chart of a rockfill particle size identification and monitoring method based on three-dimensional reconstruction of a camera set according to an embodiment of the present application;
fig. 4 is a flow chart of a rockfill particle size identification and monitoring method based on three-dimensional reconstruction of a camera set according to an embodiment of the present application.
Reference numerals: the system comprises a camera set, a camera module and a control module, wherein the camera set comprises a camera, a height-adjustable bracket, 2-bolts, 3-rockfill bin surfaces, 4-markers, 5-identification monitoring modules and 6-result feedback modules; 7 a-camera, 7 b-laser range finder, 7 c-level, 7 d-movable wheel disc of support.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The rockfill grain size identification and monitoring device and method based on camera set three-dimensional reconstruction according to the embodiment of the application are described below with reference to the accompanying drawings.
The rockfill grain size identification and monitoring device based on the three-dimensional reconstruction of the camera set according to the embodiment of the present application will be described with reference to the accompanying drawings.
Fig. 1 is a schematic structural diagram of a rockfill particle size identification and monitoring device based on three-dimensional reconstruction of a camera set according to an embodiment of the present application.
As shown in fig. 1, the rockfill particle size identification and monitoring device based on camera set three-dimensional reconstruction includes:
the camera set 1 is fixed on the periphery of the rockfill bin surface and used for acquiring rockfill multi-angle images of the rockfill to be identified at different heights in the rockfill process at different angles.
Specifically, the position of the camera group is known, and the camera group comprises a camera which can rotate horizontally and in a pitching mode, a camera support with the height adjustable through a bolt 2 and a marker for calibrating the camera group. The camera set is fixed around the rock-fill storehouse surface through the telescopic bracket.
And the calibration module is used for placing a marker in the acquisition visual field of the camera set and calibrating the parameters of the camera set.
And the identification monitoring module is connected with the camera set and used for carrying out image processing on the multi-angle images of the rockfill, determining the classification result of the particle size of each rockfill in the rockfill to be identified according to the multi-angle images of the rockfill, establishing a grading curve of the rockfill to be identified according to the classification result, and identifying and monitoring the rockfill to be identified according to the grading curve.
And the result feedback module is used for sending the identification and detection results of the rockfill to be identified to the preset terminal.
Optionally, in an embodiment of the present application, the method further includes: a position adjustable camera mount; for fixed and mobile camera groups
Optionally, in an embodiment of the present application, the camera support includes: a telescoping support; and moving the roller disc.
Optionally, in an embodiment of the present application, as shown in fig. 2, the telescopic bracket further comprises a level, and the level is disposed on a side wall of the camera head.
Optionally, in an embodiment of the present application, the telescopic bracket further includes a screw telescopic rod or an adjusting bolt, and the screw telescopic rod includes a thick thread portion, a thin thread portion, and a smooth portion in sequence from bottom to top.
Optionally, in an embodiment of the present application, the telescoping support further comprises a coarse adjustment screw and a fine adjustment screw.
Optionally, in an embodiment of the present application, as shown in fig. 2, the camera group includes: and the laser range finder is used for confirming the positions of the characteristic points in the rockfill in the multi-angle image of the rockfill collected by the camera.
Optionally, in an embodiment of the present application, a laser range finder is installed on a top wall of each camera for measuring an actual distance between the camera and the feature point and an optical axis direction.
In the embodiment of the application, the marker can be a reference object with obvious color and proper size, and is placed in each camera in the rockfill area to be capable of shooting, so as to calibrate parameters inside and outside the camera.
The camera set comprises a plurality of cameras with known relative positions, wherein the cameras can rotate horizontally and vertically and are mounted on a height-adjustable support, and the height of the support can be adjusted through bolts, so that a target rockfill identification area and a marker can be shot by each camera.
The camera in the camera group can shoot the image of the rockfill on the bin surface according to a certain time interval, namely the image of the rockfill layer with different heights in the rockfill process.
The identification monitoring module can also display the rockfill photos shot by the camera set, calibrate the corresponding positions of the characteristic points or the characteristic block rocks at the rockfill photos at different angles, and perform distortion correction and proportion conversion on the rockfill photos shot in the same area according to the internal and external parameters of the camera set.
It should be noted that the algorithm is a three-dimensional reconstruction method by a stereo vision method: when only two cameras are arranged, three-dimensional information is presumed through two images to carry out binocular stereo vision reconstruction; and when a plurality of cameras exist, recovering three-dimensional information by using a multi-image multi-view ranging algorithm, and combining the calibrated characteristic points to obtain the actual size of the rockfill in the target area. And acquires range information by directly using the range finder.
The result feedback module feeds the rockfill particle size information acquired by the identification and monitoring module back to field workers and related supervision personnel so as to adjust the rockfill process of a construction field.
According to the rockfill particle size identification and monitoring device based on camera set three-dimensional reconstruction provided by the embodiment of the application, the camera set is adopted to realize acquisition of multi-angle images of the rockfill, the three-dimensional characteristic of the rockfill to be identified is fully considered, the camera set calibration device is arranged, the camera set can be rapidly calibrated before shooting, the simple and rapid calibration method is suitable for the situations of construction site personnel and mechanical complexity, and the stability and the engineering practicability of the whole set of equipment are guaranteed. The device can acquire the multi-angle images of the rockfill by combining a three-dimensional reconstruction algorithm, determines the particle size result in the rockfill to be identified according to the multi-angle images, further establishes the grading curve of the rockfill to be identified, realizes digital identification and monitoring of the rockfill to be identified, and feeds the monitoring result back to a field engineer. Compared with the existing manual or mechanical screening method, the device of the invention improves the grading efficiency and precision and realizes the digital identification and monitoring of the rock stacking grading.
Next, a rockfill grain size identification and monitoring method based on three-dimensional reconstruction of a camera set according to an embodiment of the present application is described with reference to the drawings.
Fig. 3 is a flowchart of a rockfill grain size identification and monitoring method based on three-dimensional reconstruction of a camera set according to an embodiment of the present application.
FIG. 4 is a flow chart of a rockfill particle size identification and monitoring method based on three-dimensional reconstruction of a camera set according to an embodiment of the present application
As shown in fig. 3 and 4, the rockfill particle size identification and monitoring method based on three-dimensional reconstruction of camera group includes the following steps:
s1, adjusting the position of the camera group: and placing the selected marker in the center of the rockfill bin surface area of the rockfill to be identified, adjusting each camera of the camera set to enable the camera set to acquire the marker, wherein the marker is located in the center of the rockfill multi-angle image acquired by the camera.
S2, camera set attitude calibration: and measuring the actual distance from the marker to the rock stacking bin surface, and calculating the attitude parameter of the camera according to the position information of the camera set.
S3, collecting a rockfill photo: and (4) collecting the rockfill multi-angle images at different heights of the rockfill bin surface, and acquiring the rockfill multi-angle images shot at different heights from different angles in the rockfill process.
It is to be understood that at the time of acquisition, the acquisition may be performed at certain time intervals. But not limited to taking pictures at regular intervals, the frequency of taking pictures is adjusted according to the face update state of the rockfill in the target rockfill area.
S4, correcting the picture distortion of the camera group: and calculating and correcting the multi-angle image of the rockfill by combining the internal and external parameter information of the camera set acquired in the S1 and S2 through a camera distortion correction algorithm.
The method for correcting the distortion of the pictures of the camera group comprises but is not limited to a traditional camera calibration method for calibrating the camera, a camera self-calibration method and the like, a non-measurement distortion correction method and the like.
S5, selecting characteristic points: and selecting the characteristic points in the rockfill to be identified, finding the corresponding positions of the characteristic points on the photos with different angles, and measuring the pixel distance of the characteristic points on the multi-angle image of the rockfill.
S6, three-dimensional reconstruction: and analyzing the rockfill pictures of different angles acquired by the camera set, calculating the actual distance of the characteristic points by a stereoscopic vision reconstruction method, and measuring the scale of each rockfill multi-angle image according to the actual distance.
S7, identifying the particle size of the rockfill: and (4) identifying the rockfill particle size in the rockfill multi-angle image by using an image identification algorithm, wherein the rockfill particle size data is calculated by the scale calculated in the step S6.
Optionally, in an embodiment of the present application, S6 includes:
when the images of the cross sections of the rockfill are collected by the two cameras, the three-dimensional information of the rockfill is presumed according to the images of the cross sections of the rockfill collected by the two cameras, and binocular vision reconstruction is carried out; when the rockfill section images are collected through the at least three cameras, the rockfill section images collected through the at least three cameras are used for recovering three-dimensional information of the rockfill, the actual size of each rockfill in the rockfill section images is obtained through combination of the calibrated characteristic points, and the scale of each rockfill multi-angle image is calculated through combination of the characteristic points in the step S5.
The key point of identifying the particle size of the rockfill is that the contour of the rockfill in the picture is accurately identified through an image identification algorithm, and the contour of the rockfill can also be identified through other algorithms without specific limitation.
In the embodiment of the application, the digital image of the rockfill is acquired by using the camera group acquisition device with known relative position or capable of calculating the relative position, and the acquisition of the digital image from different angles can be completed as long as the method capable of acquiring the particle digital image with better quality can be realized.
Acquiring a plurality of high-quality target images by using markers arranged in a target area of a bin surface, and resolving the relative position between camera sets on the one hand based on accurate coordinates of three-dimensional scene points of the markers; and on the other hand, calibrating the camera by using a calibration method of the planar target of Zhangyingyou, solving a distortion coefficient and a distortion center, and correcting the rockfill photo by using a calibration result.
Acquiring a plurality of high-quality rockfill images by using the adjusted camera set, performing three-dimensional reconstruction by using feature points of which corresponding points can be found in pictures shot by the multi-angle camera, and calculating the actual distance between the feature points; and software is used for obtaining the pixel distance of the characteristic points, and the pixel scale of the rockfill picture is calculated according to the pixel distance.
Writing the contour of the rock block in the corrected rock-fill digital image divided by the neural network algorithm for target detection, acquiring the particle size information of the rock block, and calculating the actual particle size of the rock-fill in the region by combining the pixel scale of the image so as to determine the grading curve of the rock-fill. Different image recognition algorithms can extract the geometrical information of the rockfill particles in the picture.
The four steps of operation are repeatedly carried out on the whole bin surface, the calculation result is statistically processed, and the particle size condition of the rockfill on the whole bin surface can be determined, so that whether the rockfill on a construction site meets the standard requirement or not is monitored.
It should be noted that the foregoing explanation of the embodiment of the apparatus is also applicable to the method of the embodiment, and is not repeated herein.
According to the rockfill particle size identification and monitoring method based on the three-dimensional reconstruction of the camera set, the camera set is adopted to achieve the acquisition of multi-angle images of the rockfill to be identified, the three-dimensional characteristics of the rockfill to be identified are fully considered, target calibration is carried out, the camera set can be quickly calibrated before shooting, the simple and quick calibration method is suitable for the situations of construction site personnel and mechanical complexity, the stability and engineering practicability of the whole set of equipment are guaranteed, the particle size result of each rockfill in the rockfill to be identified is determined according to the acquired multi-angle images of the multi-layer rockfill, the grading curve of the rockfill to be identified is further established, the digital identification and monitoring of the rockfill to be identified are achieved, and the monitoring result is fed back to a site engineer. Compared with the existing manual or mechanical screening method, the grading efficiency and precision are improved, and the digital identification and monitoring of the rockfill grading are realized.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. The utility model provides a rockfill particle size discernment and monitoring device based on camera unit three-dimensional reconstruction which characterized in that includes:
the camera set is fixed around the surface of the rockfill bin through a camera support and at least comprises two cameras and is used for acquiring rockfill multi-angle images of rockfill to be identified at different heights in the rockfill process at different angles;
the calibration module is used for placing a marker in the acquisition visual field of the camera set and calibrating the parameters of the camera set;
the identification monitoring module is connected with the camera set and used for carrying out image processing on the multi-angle images of the rockfill, determining a classification result of the particle size of each rockfill in the rockfill to be identified according to the multi-angle images of the rockfill, establishing a grading curve of the rockfill to be identified according to the classification result, and identifying and monitoring the rockfill to be identified according to the grading curve;
and the result feedback module is used for sending the identification and detection results of the rockfill to be identified to a preset terminal.
2. The apparatus of claim 1, wherein the camera mount is configured to hold and move the set of cameras, comprising:
a telescoping support;
and moving the roller disc.
3. The apparatus of claim 2, wherein the telescoping legs further comprise a level disposed on a side wall of the camera head.
4. The device of claim 2, wherein the telescopic bracket further comprises a screw telescopic rod or an adjusting bolt, and the screw telescopic rod comprises a thick thread part, a thin thread part and a smooth part from bottom to top.
5. The device of claim 2, wherein the telescoping support further comprises a coarse adjustment screw and a fine adjustment screw.
6. The apparatus of claim 1, wherein the set of cameras comprises:
and the laser range finder is used for confirming the positions of the characteristic points in the rockfill in the multi-angle image of the rockfill collected by the camera.
7. The apparatus of claim 6, wherein the laser range finder is mounted on the top wall of each camera for measuring the actual distance from the camera to the feature point and the optical axis direction.
8. A rockfill particle size identification and monitoring method based on camera set three-dimensional reconstruction is suitable for the rockfill particle size identification and monitoring device based on camera set three-dimensional reconstruction as claimed in claim 1, and is characterized by comprising the following steps:
s1, adjusting the position of the camera group: placing the selected marker in the center of a rockfill bin surface area of the rockfill to be identified, adjusting each camera of the camera set to enable each camera to acquire the marker, wherein the marker is located in the center of a rockfill multi-angle image acquired by the cameras;
s2, camera set attitude calibration: measuring the actual distance from the marker to the rock-fill warehouse surface, and calculating a camera attitude parameter according to the position information of the camera set;
s3, collecting a rockfill photo: collecting the multi-angle rockfill images at different heights of the rockfill bin surface, and acquiring the multi-angle rockfill images shot from different angles at different heights in the rockfill process;
s4, correcting the picture distortion of the camera group: calculating and correcting the rockfill multi-angle image by combining the internal and external parameter information of the camera set acquired in S1 and S2 through a camera distortion correction algorithm;
s5, selecting characteristic points: selecting feature points in the rockfill to be identified, finding corresponding positions of the feature points on different angle pictures, and measuring pixel distances of the feature points on the rockfill multi-angle image;
s6, three-dimensional reconstruction: analyzing rockfill photos of different angles acquired by a camera set, calculating the actual distance of the characteristic points by a stereoscopic vision reconstruction method, and measuring the scale of each rockfill multi-angle image according to the actual distance;
s7, identifying the particle size of the rockfill: and identifying the rockfill particle size in the rockfill multi-angle image by using an image identification algorithm, wherein the rockfill particle size data is calculated by the scale calculated in the step S6.
9. The method according to claim 8, wherein the S6 includes:
when the images of the cross sections of the rockfill are collected through the two cameras, the three-dimensional information of the rockfill is presumed according to the images of the cross sections of the rockfill collected by the two cameras, and binocular vision reconstruction is carried out; when the rockfill section images are collected through at least three cameras, three-dimensional information of the rockfill is recovered by using the rockfill section images collected through the at least three cameras, the actual size of each rockfill in the rockfill section images is obtained by combining calibrated characteristic points, and the scale of each rockfill multi-angle image is calculated by combining the characteristic points in the step S5.
10. The method of claim 8, wherein the camera distortion correction algorithm comprises a conventional camera calibration method, a camera self-calibration method, and a non-measured distortion correction method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110779106.6A CN113533145A (en) | 2021-07-09 | 2021-07-09 | Rockfill particle size identification and monitoring device and method based on camera set three-dimensional reconstruction |
PCT/CN2022/104605 WO2023280300A1 (en) | 2021-07-09 | 2022-07-08 | Rockfill particle size identification and monitoring apparatus and method based on three-dimensional reconstruction of camera group |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110779106.6A CN113533145A (en) | 2021-07-09 | 2021-07-09 | Rockfill particle size identification and monitoring device and method based on camera set three-dimensional reconstruction |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113533145A true CN113533145A (en) | 2021-10-22 |
Family
ID=78098274
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110779106.6A Pending CN113533145A (en) | 2021-07-09 | 2021-07-09 | Rockfill particle size identification and monitoring device and method based on camera set three-dimensional reconstruction |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113533145A (en) |
WO (1) | WO2023280300A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113792715A (en) * | 2021-11-16 | 2021-12-14 | 山东金钟科技集团股份有限公司 | Granary pest monitoring and early warning method, device, equipment and storage medium |
WO2023280300A1 (en) * | 2021-07-09 | 2023-01-12 | 清华大学 | Rockfill particle size identification and monitoring apparatus and method based on three-dimensional reconstruction of camera group |
CN115711836A (en) * | 2022-11-17 | 2023-02-24 | 上海勘测设计研究院有限公司 | Scanning particle size grading method and system |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117237303B (en) * | 2023-09-19 | 2024-05-03 | 中南大学 | Non-contact rock-fill grain grading detection method and device based on machine vision |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101936761B (en) * | 2009-06-30 | 2012-02-15 | 宝山钢铁股份有限公司 | Visual measuring method of stockpile in large-scale stock ground |
CN103047942B (en) * | 2012-12-26 | 2014-05-21 | 浙江大学 | Visual acquisition system and method for geometrical characteristics of graded crushed rocks of railway and road beds |
FI20155908A (en) * | 2015-12-01 | 2017-06-02 | Outotec Finland Oy | Process and arrangement for controlling a atomization process comprising a grinding circuit |
CN106018441A (en) * | 2016-05-10 | 2016-10-12 | 东南大学 | Method for detecting internal structure of cement graded crushed stones for high-speed rail roadbed |
CN108053449A (en) * | 2017-12-25 | 2018-05-18 | 北京工业大学 | Three-dimensional rebuilding method, device and the binocular vision system of binocular vision system |
CN210730212U (en) * | 2019-08-15 | 2020-06-12 | 中国水利水电科学研究院 | Concrete aggregate grading identification and regulation device |
CN216870297U (en) * | 2021-07-09 | 2022-07-01 | 清华大学 | Rockfill particle size identification and monitoring device based on three-dimensional reconstruction of camera set |
CN113533145A (en) * | 2021-07-09 | 2021-10-22 | 清华大学 | Rockfill particle size identification and monitoring device and method based on camera set three-dimensional reconstruction |
-
2021
- 2021-07-09 CN CN202110779106.6A patent/CN113533145A/en active Pending
-
2022
- 2022-07-08 WO PCT/CN2022/104605 patent/WO2023280300A1/en active Application Filing
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023280300A1 (en) * | 2021-07-09 | 2023-01-12 | 清华大学 | Rockfill particle size identification and monitoring apparatus and method based on three-dimensional reconstruction of camera group |
CN113792715A (en) * | 2021-11-16 | 2021-12-14 | 山东金钟科技集团股份有限公司 | Granary pest monitoring and early warning method, device, equipment and storage medium |
CN115711836A (en) * | 2022-11-17 | 2023-02-24 | 上海勘测设计研究院有限公司 | Scanning particle size grading method and system |
Also Published As
Publication number | Publication date |
---|---|
WO2023280300A1 (en) | 2023-01-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113533145A (en) | Rockfill particle size identification and monitoring device and method based on camera set three-dimensional reconstruction | |
CN110044289B (en) | Automatic zooming-based tunnel multi-section convergence deformation video monitoring device and method | |
Fassi et al. | Comparison between laser scanning and automated 3d modelling techniques to reconstruct complex and extensive cultural heritage areas | |
CN104766302B (en) | A kind of method and system using unmanned plane image optimization Point Cloud of Laser Scanner | |
CN110285827B (en) | Distance-constrained photogrammetry high-precision target positioning method | |
CN101226057B (en) | Digital close range photogrammetry method | |
CN106978774B (en) | A kind of road surface pit slot automatic testing method | |
CN108534760A (en) | A kind of image measurement method based on binocular camera and laser range sensor | |
CN111091076B (en) | Tunnel limit data measuring method based on stereoscopic vision | |
CN102589529B (en) | Scanning close-range photogrammetry method | |
CN216870297U (en) | Rockfill particle size identification and monitoring device based on three-dimensional reconstruction of camera set | |
CN112288848A (en) | Method for calculating engineering quantity through three-dimensional modeling of unmanned aerial vehicle aerial photography | |
CN111383174A (en) | Pile bursting data acquisition method for photogrammetry | |
CN113971768A (en) | Unmanned aerial vehicle-based three-dimensional dynamic detection method for power transmission line illegal building | |
CN114998399B (en) | Heterogeneous optical remote sensing satellite image stereopair preprocessing method | |
CN113340241A (en) | Binocular vision concrete joint surface roughness measurement method and system | |
CN109813221A (en) | The measurement Error Compensation method of heavy steel plate based on controlling filed | |
CN114943890A (en) | Transformer substation field flatness identification method adopting unmanned aerial vehicle-mounted laser point cloud | |
Rieke-Zapp et al. | Digital photogrammetry for measuring soil surface roughness | |
CN104180794A (en) | Method for treating texture distortion area of digital orthoimage | |
JP6281014B1 (en) | Particle size measurement method for granular materials | |
Cardenal et al. | Close range digital photogrammetry techniques applied to landslide monitoring | |
CN116839539A (en) | Automatic monitoring and measuring system for tunnel engineering construction | |
Tian et al. | Pavement macrotexture determination using multi-view smartphone images | |
CN116468621A (en) | One-key digital aviation image data processing method |
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 |