CN115546717A - Concrete pumpability type identification method and device and electronic equipment - Google Patents
Concrete pumpability type identification method and device and electronic equipment Download PDFInfo
- Publication number
- CN115546717A CN115546717A CN202211174178.9A CN202211174178A CN115546717A CN 115546717 A CN115546717 A CN 115546717A CN 202211174178 A CN202211174178 A CN 202211174178A CN 115546717 A CN115546717 A CN 115546717A
- Authority
- CN
- China
- Prior art keywords
- concrete
- image
- pumpability
- blanking
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a concrete pumpability type identification method, a concrete pumpability type identification device and electronic equipment, wherein the concrete pumpability type identification method comprises the following steps: the concrete pumpability category is obtained by obtaining a blanking image of the concrete blanking process, determining a concrete area image in the blanking image and calculating the concrete area image by using a trained classification model, so that the pumpability of the concrete is obtained before the pump truck is constructed, and the risk in the pump truck construction process can be avoided.
Description
Technical Field
The invention relates to the technical field of material management of constructional engineering, in particular to a concrete pumpability type identification method, a concrete pumpability type identification device and electronic equipment.
Background
At present, can not learn the pumpability of concrete in advance in pump truck work progress, but if can just know the risk in the pump truck work progress in advance just can knowing the pumpability of concrete before the pump truck construction, for example stifled pipe can take place the anti-pump, and the segregation can cause and gets rid of the pipe.
The invention patent application with application publication number CN109784436A discloses an intelligent concrete control method and system, the system comprises: the system comprises an acquirer client, a supplier client, a server, a first electronic tag, a second electronic tag, a third electronic tag, a first electronic tag reader, a second electronic tag reader, a weighing management system and a positioning device. The method and the system realize the automatic operation of the whole process of material weighing through an informatization means, and realize the association between the BIM sub-model and the test block detection report information, the concrete information and the concrete pouring area information in the BIM system, thereby dynamically reflecting the project progress and the related information; and whether the information of the concrete pouring position is matched with the information of the pump truck pouring position is judged, so that the concrete with wrong performance can be prevented from being poured by the building component. However, the method cannot know the pumpability of the concrete in advance in the pump truck construction process, so that the risk in the pump truck construction process is avoided.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for identifying a concrete pumpability category, so as to avoid risks in a pump truck construction process.
According to a first aspect, an embodiment of the present invention provides a concrete pumpability category identification method, including the following steps: obtaining a blanking image in the concrete blanking process; determining a concrete area image in the blanking image; and calculating the concrete area image by using the trained classification model to obtain the pumpability category of the concrete.
With reference to the first aspect, in a first implementation manner of the first aspect, the determining a concrete area image in the blanking image includes: inputting the blanking image into a trained target detection model for recognition to obtain a concrete area positioning frame; and cutting the blanking image by using the concrete area positioning frame to obtain the concrete area image.
With reference to the first embodiment of the first aspect, in a second embodiment of the first aspect, the obtaining the concrete area image by cutting the blanking image with the concrete area positioning frame includes: when the number of the concrete area positioning frames is one, cutting the blanking image by using the concrete area positioning frames to obtain a cut image, and taking the cut image as the concrete area image; when the number of the concrete area positioning frames is multiple, cutting the blanking image by using the concrete area positioning frame to obtain a cut image corresponding to the concrete area positioning frame aiming at any concrete area positioning frame; traversing each concrete area positioning frame to obtain a cutting image corresponding to each concrete area positioning frame; and fusing the plurality of cutting images to obtain the concrete area image.
With reference to the first implementation manner of the first aspect, in a third implementation manner of the first aspect, the obtaining the trained target detection model includes: acquiring a training image set, wherein training images in the training image set comprise at least one of: the system comprises a training image containing a blanking concrete area, a training image containing a stacking concrete area and a training image containing a concrete area below a screen surface; and training the target detection model by using the training image set to obtain the trained target detection model.
With reference to the first aspect, in a fourth implementation manner of the first aspect, the step of obtaining the trained classification model includes: acquiring a plurality of images corresponding to each pumpability category in a preset pumpability category set; training the classification model using a plurality of images corresponding to each pumpability class to obtain a trained classification model.
With reference to the fourth implementation manner of the first aspect, in the fifth implementation manner of the first aspect, the pumpability category in the pumpability category set includes: normal hydrous concrete with the water content less than or equal to a preset first threshold, semi-hydrous concrete with the water content greater than the first threshold and less than or equal to a preset second threshold, and full hydrous concrete with the water content greater than the second threshold; the normal hydrous concrete comprises low-coarse aggregate content concrete with coarse aggregate content less than or equal to a preset third threshold, medium-coarse aggregate content concrete with coarse aggregate content greater than the third threshold and less than or equal to a preset fourth threshold, and high-coarse aggregate content bulk concrete with coarse aggregate content greater than the fourth threshold; wherein the low coarse aggregate content concrete comprises first pebble concrete, first crushed stone concrete and first mixed concrete; the concrete with the medium coarse aggregate content comprises second pebble concrete, second crushed stone concrete and second mixed concrete; the concrete with high coarse aggregate content comprises third pebble concrete, third crushed stone concrete and third mixed concrete.
With reference to the first aspect, in a sixth implementation manner of the first aspect, after the calculating the concrete area image by using the trained classification model to obtain the pumpability category of the concrete, the method further includes: and when the pumpability category of the concrete belongs to a preset alarm range, giving an alarm.
According to a second aspect, an embodiment of the present invention further provides a concrete pumpability category identification apparatus, including an obtaining module, a first processing module, and a second processing module, where the obtaining module is configured to obtain a blanking image of a concrete blanking process; the first processing module is used for determining a concrete area image in the blanking image; the second processing module is used for calculating the concrete area image by using the trained classification model to obtain the pumpability category of the concrete.
According to a third aspect, an embodiment of the present invention further provides an electronic device, including a camera and a processor, where the camera is configured to capture a blanking image of a concrete blanking process; the image capturing device is communicatively connected to the processor, and the processor stores therein computer instructions, and executes the computer instructions to execute the method for identifying the pumpability category of concrete according to the first aspect or any one of the embodiments of the first aspect.
With reference to the third aspect, in a first implementation manner of the third aspect, the electronic device further includes a controller and an alarm device, the controller is communicatively connected with the processor, and the alarm device is communicatively connected with the controller.
According to the concrete pumpability type identification method, the concrete pumpability type identification device and the electronic equipment, the concrete regional image in the blanking image is determined by obtaining the blanking image in the concrete blanking process, the concrete regional image is calculated by using the trained classification model, and the pumpability type of the concrete is obtained, so that the pumpability of the concrete is known before the pump truck is constructed, and the risk in the pump truck construction process can be avoided.
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are schematic and are not to be understood as limiting the invention in any way, and in which:
FIG. 1 is a schematic flow chart showing a concrete pumpability class identification method according to embodiment 1 of the invention;
FIG. 2 is a schematic view of a first concrete area positioning frame and a second concrete area positioning frame;
fig. 3 is a schematic structural view of a concrete pumpability category identification device in embodiment 2 of the invention;
the method comprises the following steps of 1, positioning a first concrete area frame; 2. a second concrete area positioning frame; 3. and (7) a mesh surface.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Example 1
The embodiment 1 of the invention provides a concrete pumpability category identification method. Fig. 1 is a schematic flowchart of a concrete pumpability category identification method in embodiment 1 of the present invention, and as shown in fig. 1, the concrete pumpability category identification method in embodiment 1 of the present invention includes the following steps:
s101: and acquiring a blanking image in the concrete blanking process.
Specifically, the blanking process can be that the concrete is blanked from the mixer truck to the pump truck. That is, a discharge image of the concrete discharged from the mixer truck to the pump truck is obtained. For example, a feeding image of concrete fed from a mixer truck to a pump truck can be obtained by a camera device arranged at a lamp pole of the hopper or right above the hopper. Wherein, the blanking image can be an RGB image.
S102: and determining a concrete area image in the blanking image.
Specifically, the following steps may be adopted to determine the concrete area image in the blanking image: inputting the blanking image into a trained target detection model for recognition to obtain a concrete area positioning frame; and cutting the blanking image by using the concrete area positioning frame to obtain the concrete area image. For example, the target detection model may be a model established based on the YOLO algorithm or the SSD algorithm, so that the target detection accuracy is good and the operation speed is fast.
More specifically, the obtaining of the concrete area image by cutting the blanking image with the concrete area positioning frame includes the following two situations.
The first situation is that when the number of the concrete area positioning frames is one, the blanking image is cut by using the concrete area positioning frames to obtain a cut image, and the concrete area image is obtained according to the cut image.
The second situation is that when the number of the concrete area positioning frames is multiple, the blanking image is cut by using the concrete area positioning frame to obtain a cut image corresponding to the concrete area positioning frame aiming at any concrete area positioning frame; traversing each concrete area positioning frame to obtain a cutting image corresponding to each concrete area positioning frame; and fusing the plurality of cutting images to obtain the concrete area image.
For example, as shown in fig. 2, a blanking image is input into a trained target detection model to obtain two concrete area location boxes, i.e., a first concrete area location box 1 and a second concrete area location box 2.
Cutting the blanking image by using the first concrete area positioning frame 1 to obtain a first cutting image corresponding to the first concrete area positioning frame 1, wherein the first cutting image corresponds to a blanking concrete area in the blanking process; and cutting the blanking image by using the second concrete area positioning frame 2 to obtain a second cutting image corresponding to the second concrete area positioning frame 2, wherein the second cutting image corresponds to the accumulated concrete area in the blanking process.
And fusing the first cutting image and the second cutting image to obtain a concrete area. Further, the following method can be adopted to train the target detection model: acquiring a training image set, wherein the training image set comprises at least one of the following: the system comprises a training image containing a blanking concrete area, a training image containing a stacking concrete area and a training image containing a concrete area below a net surface; and training the target detection model by using the training image set to obtain the trained target detection model. Specifically, the net surface is an intercepting surface used for intercepting impurities in concrete in the concrete blanking process. Further, before determining the concrete area image in the blanking image, the method further includes: and preprocessing the blanking image, wherein the preprocessing comprises but is not limited to noise reduction processing, gray scale image generation and the like.
S103: and calculating the concrete area image by using the trained classification model to obtain the pumpability category of the concrete. Specifically, the classification model may be trained by the following method: acquiring a plurality of images corresponding to each pumpability category in a preset pumpability category set; training the classification model using a plurality of images corresponding to each pumpability category to obtain the trained classification model. For example, the classification model may be a model established based on the FCN algorithm.
Specifically, the pumpability categories in the pumpability category set include: normal hydrous concrete with the water content less than or equal to a preset first threshold, semi-hydrous concrete with the water content greater than the first threshold and less than or equal to a preset second threshold, and full hydrous concrete with the water content greater than the second threshold; the normal water-containing concrete comprises low-coarse aggregate content concrete with coarse aggregate content less than or equal to a preset third threshold value, medium-coarse aggregate content concrete with coarse aggregate content more than the third threshold value and less than or equal to a preset fourth threshold value, and high-coarse aggregate content material concrete with coarse aggregate content more than the fourth threshold value.
This is because, as shown in table 1, concrete can be classified into normal water-containing concrete, semi-water-containing concrete, and full water-containing concrete according to the difference in water content. Specifically, the normal hydrous concrete is concrete without obvious water in the concrete area image, that is, concrete with a ratio (also referred to as water content) of the area occupied by water in the concrete area image to the total area of the concrete area image being less than or equal to a preset first threshold; the semi-hydrated concrete is concrete with obvious water but less water in the concrete area image, namely the ratio of the area occupied by the water in the concrete area image to the total area of the concrete area image is larger than the first threshold value and smaller than or equal to a preset second threshold value; the fully hydrated concrete is concrete with obvious water and much water in the concrete area image, namely the ratio of the area occupied by the water in the concrete area image to the total area of the concrete area image is greater than the second threshold value. For example, the first threshold may be 30%, that is, the ratio of the area occupied by water in the concrete area image to the total area of the concrete area image is 30%; the second threshold value may be 70%, that is, the ratio of the area occupied by water in the concrete region image to the total area of the concrete region image is 70%.
TABLE 1 pumpability classes obtained by classifying concrete according to different water contents
Further, as shown in Table 2, the normal aqueous concrete can be classified into low-coarse-aggregate-content concrete, medium-coarse-aggregate-content concrete and high-coarse-aggregate-content concrete according to the difference in coarse aggregate content. Specifically, the concrete with low coarse aggregate content is that the ratio of the area occupied by coarse aggregates in the concrete area image to the total area of the concrete area image (also referred to as coarse aggregate content and coarse aggregate ratio) is less than or equal to a preset third threshold, the concrete with medium coarse aggregate content is that the ratio of the area occupied by coarse aggregates in the concrete area image to the total area of the concrete area image is greater than the third threshold and less than or equal to a preset fourth threshold, and the concrete with high coarse aggregate content is that the ratio of the area occupied by coarse aggregates in the concrete area image to the total area of the concrete area image is greater than the fourth threshold. For example, the third threshold may be 30%, that is, the ratio of the area occupied by the coarse aggregate in the concrete area image to the total area of the concrete area image is 30%; the fourth threshold may be 70%, that is, the ratio of the area occupied by the coarse aggregate in the concrete region image to the total area of the concrete region image is 70%.
TABLE 2 pumpability classes obtained by classifying Normal aqueous concretes
Further, as shown in table 3, the low coarse aggregate content concrete is classified into the first pebble concrete, the first crushed stone concrete and the first mixed concrete according to the kind of the coarse aggregate.
TABLE 3 pumpability classes obtained by classifying low coarse aggregate content concretes according to the class of coarse aggregate
As shown in table 4, the concrete with medium-coarse aggregate content can be further classified into second gravel concrete, second crushed stone concrete and second mixed concrete according to the classification of the coarse aggregate.
TABLE 4 pumpability categories by classifying the medium coarse aggregate content concrete according to the category of the coarse aggregate
As shown in table 5, the high coarse aggregate content concrete was classified according to the type of coarse aggregate, and further classified into third pebble concrete, third crushed stone concrete and third mixed concrete.
| Category label | Pumpability classification |
| Category label 131 | The third pebble concrete, namely pebbles, accounts for more than 70 percent |
| Category label 132 | The third broken stone concrete, namely broken stone, accounts for more than 70 percent |
| Category label 132 | The total ratio of the broken stones and the pebbles in the third mixed concrete is more than 70 percent |
The pebble occupation ratio is the ratio of the area occupied by the pebbles in the concrete area image to the total area of the concrete area image; the broken stone proportion is the ratio of the area occupied by broken stones in the concrete area image to the total area of the concrete area image; the total occupied ratio of the broken stones and the pebbles is the ratio of the area occupied by the broken stones and the pebbles in the concrete area image to the total area of the concrete area image.
Specifically, in the first pebble concrete, the second pebble concrete and the third pebble concrete, the type of the coarse aggregate is mainly pebbles; in the first gravel concrete, the second gravel concrete and the third gravel concrete, the coarse aggregate mainly comprises gravel; in the first mixed concrete, the second mixed concrete and the third mixed concrete, the coarse aggregate is a mixture of pebbles and broken stones. For example, in the coarse aggregate, the ratio of pebbles to crushed stones is 3: 7. 4: 6. 5:5 or the ratio of the crushed stones to the pebbles is 3: 7. 4: 6. 5: and 5, considering the type of the coarse aggregate to belong to the mixture, otherwise, if the amount of pebbles in the coarse aggregate is larger than the amount of broken stones, considering the type of the coarse aggregate to be mainly pebbles, and if the amount of broken stones in the coarse aggregate is larger than the amount of pebbles, considering the type of the coarse aggregate to be mainly broken stones.
Specifically, the pumpability category output by the classification model can be represented by the content of the pumpability category, and can also be represented by a category label. Different pumpability classes have different effects on pumpability.
Further, after inputting the concrete area into the trained classification model to obtain the pumpability category of the concrete, the method further includes: and when the pumpability category of the concrete belongs to a preset alarm range, giving an alarm.
For example, when the pumpability class output by the classification model is the class label 3, namely, the concrete is in a full water-containing state, an alarm is given.
According to the concrete pumpability type identification method, the concrete pumpability type identification device and the electronic equipment in the embodiment 1 of the invention, the concrete pumpability type is obtained by acquiring the blanking image of the concrete when the concrete is blanked from the mixer truck to the pump truck, identifying the concrete area in the blanking image, and inputting the concrete area into the trained classification model, that is, the pumpability type of the concrete can be obtained only through the blanking image, so that the pumpability of the concrete can be known before the pump truck is constructed, and the risk in the pump truck construction process can be avoided.
To explain the concrete pumpability classification identification method of embodiment 1 of the present invention in more detail, a specific example is given, which includes the following steps:
1. the RGB camera acquires the data stream and passes it into the edge computing box device.
2. The RGB image is preprocessed, specifically including but not limited to denoising, generating a gray scale map, etc.
3. And (3) cutting an image data frame by using the deep learning target detection model, specifically, outputting the coordinates of a positioning frame obtained by the model to obtain an image of which most of the occupation ratios in the image are concrete, and conducting the image to a downstream task.
4. And (4) inputting the image obtained in the step (3) into a deep learning classification model to obtain class label numbers.
5. And (5) transmitting the concrete category label number obtained in the step (4) to a pumping truck controller and finally transmitting the concrete category label number back to a database server background.
Therefore, the concrete pumpability type identification method in embodiment 1 of the invention has the following advantages:
(1) Only the classical algorithm of the traditional computer vision is adopted, so that the cost is low; the pumpability analysis can be carried out on the concrete poured into the pump truck, important parameters are obtained, and the pump truck has extremely high application value;
(2) The condition that moisture is too much in can detecting the concrete can carry out early warning to the segregation phenomenon that consequently appears in advance, effectively avoids the pump truck stifled pipe that brings with this.
Example 2
Corresponding to embodiment 1 of the present invention, embodiment 2 of the present invention provides a concrete pumpability category identification device. Fig. 3 is a schematic structural diagram of a concrete pumpability class identification apparatus according to embodiment 2 of the invention, and as shown in fig. 3, the concrete pumpability class identification apparatus according to embodiment 2 of the invention includes an acquisition module 20, a first processing module 21, and a second processing module 22.
The acquiring module 20 is configured to acquire a blanking image in a concrete blanking process;
the first processing module 21 is configured to determine a concrete area image in the blanking image;
and the second processing module 22 is configured to calculate the concrete area image by using the trained classification model, so as to obtain the pumpability category of the concrete.
The first processing module 21 is specifically configured to: inputting the blanking image into a trained target detection model for recognition to obtain a concrete area positioning frame; and cutting the blanking image by using the concrete area positioning frame to obtain the concrete area image.
More specifically, the first processing module 21 is configured to: when the number of the concrete area positioning frames is one, utilizing the concrete area positioning frames to cut the blanking image to obtain a cut image, and obtaining the concrete area image according to the cut image; when the number of the concrete area positioning frames is multiple, the blanking image is cut by utilizing the concrete area positioning frame to obtain a cut image corresponding to the concrete area positioning frame aiming at any concrete area positioning frame; traversing each concrete area positioning frame to obtain a cutting image corresponding to each concrete area positioning frame; and fusing the plurality of cutting images to obtain the concrete area image.
Further, the concrete pumpability category identification apparatus according to embodiment 2 of the present invention further includes a target detection model training module 23. The target detection model training module 23 is specifically configured to: acquiring a training image set, wherein training images in the training image set comprise at least one of: the system comprises a training image containing a blanking concrete area, a training image containing an accumulation concrete area and a training image containing a concrete area below a net surface; and training the target detection model by using the training image set to obtain the trained target detection model.
Further, the concrete pumpability class identification apparatus according to embodiment 2 of the present invention further includes a classification model training module 24. The classification model training module is specifically configured to: acquiring a plurality of images corresponding to each pumpability category in a preset pumpability category set; training the classification model using a plurality of images corresponding to each pumpability category to obtain the trained classification model.
The concrete pumpability type identification device can be understood by referring to the corresponding description and effects in the embodiments shown in fig. 1 to 2, and the details are not repeated herein.
Example 3
Specifically, the camera device is arranged at a lamp pole of the hopper or right above the hopper.
The Processor includes a Processing Unit and a storage Unit, the Processing Unit may adopt a Central Processing Unit (CPU), and may also adopt a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like, or a combination of the above chips.
The memory unit, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the concrete pumpability class identification method in the embodiment of the present invention (for example, the acquisition module 20, the first processing module 21, the second processing module 22, the target detection model training module 23, and the classification model training module 24 shown in fig. 3). The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the storage unit, namely, the concrete pumpability class identification method in the above method embodiment is realized.
The storage unit may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor, and the like. In addition, the storage unit may include a high-speed random access storage unit, and may further include a non-transitory storage unit, such as at least one magnetic disk storage unit, a flash memory device, or other non-transitory solid state storage unit. In some embodiments, the memory unit optionally includes a memory unit located remotely from the processor, and these remote memory units may be connected to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the storage unit and, when executed by the processor, perform the concrete pumpability class identification method as in the embodiment of fig. 1 to 2.
Furthermore, the electronic equipment further comprises a controller and an alarm device, wherein the controller is in communication connection with the processor, and the alarm device is in communication connection with the controller.
The details of the electronic device may be understood by referring to the corresponding descriptions and effects in the embodiments shown in fig. 1 to fig. 3, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory unit (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of storage units of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. A concrete pumpability category identification method is characterized by comprising the following steps:
obtaining a blanking image in the concrete blanking process;
determining a concrete area image in the blanking image;
and calculating the concrete area image by using the trained classification model to obtain the pumpability category of the concrete.
2. The method of claim 1, wherein the determining the concrete area image in the blanking image comprises:
inputting the blanking image into a trained target detection model for recognition to obtain a concrete area positioning frame;
and cutting the blanking image by using the concrete area positioning frame to obtain the concrete area image.
3. The method of claim 2, wherein said cropping the blanking image with the concrete area positioning frame to obtain the concrete area image comprises:
when the number of the concrete area positioning frames is one, cutting the blanking image by using the concrete area positioning frames to obtain a cut image, and taking the cut image as the concrete area image;
when the number of the concrete area positioning frames is multiple, cutting the blanking image by using the concrete area positioning frame to obtain a cut image corresponding to the concrete area positioning frame aiming at any concrete area positioning frame; traversing each concrete area positioning frame to obtain a cutting image corresponding to each concrete area positioning frame; and fusing the plurality of cutting images to obtain the concrete area image.
4. The method of claim 2, wherein obtaining the trained target detection model comprises:
acquiring a training image set, wherein training images in the training image set comprise at least one of: the system comprises a training image containing a blanking concrete area, a training image containing a stacking concrete area and a training image containing a concrete area below a screen surface;
and training the target detection model by using the training image set to obtain the trained target detection model.
5. The method of claim 1, wherein obtaining a trained classification model comprises:
acquiring a plurality of images corresponding to each pumpability category in a preset pumpability category set;
training the classification model using a plurality of images corresponding to each pumpability category to obtain the trained classification model.
6. The method of claim 5, wherein a pumpability category of the set of pumpability categories comprises: normal hydrous concrete with the water content less than or equal to a preset first threshold, semi-hydrous concrete with the water content greater than the first threshold and less than or equal to a preset second threshold, and full hydrous concrete with the water content greater than the second threshold;
the normal hydrous concrete comprises low-coarse aggregate content concrete with coarse aggregate content less than or equal to a preset third threshold, medium-coarse aggregate content concrete with coarse aggregate content greater than the third threshold and less than or equal to a preset fourth threshold, and high-coarse aggregate content bulk concrete with coarse aggregate content greater than the fourth threshold;
wherein the low coarse aggregate content concrete comprises first pebble concrete, first crushed stone concrete and first mixed concrete; the concrete with the medium coarse aggregate content comprises second pebble concrete, second crushed stone concrete and second mixed concrete; the high coarse aggregate content concrete comprises third pebble concrete, third crushed stone concrete and third mixed concrete.
7. The method of claim 1, further comprising, after computing the concrete region image with the trained classification model to obtain the pumpability classification of the concrete:
and when the pumpability category of the concrete belongs to a preset alarm range, alarming.
8. A concrete pumpability class identification device, comprising:
the acquisition module is used for acquiring a blanking image in the concrete blanking process;
the first processing module is used for determining a concrete area image in the blanking image;
and the second processing module is used for calculating the concrete area image by using the trained classification model to obtain the pumpability category of the concrete.
9. An electronic device, comprising:
the camera device is used for shooting a blanking image in the concrete blanking process;
a processor, wherein the image capturing device is communicatively connected to the processor, and wherein the processor stores computer instructions and executes the computer instructions to perform the concrete pumpability category identification method according to any one of claims 1 to 7.
10. The electronic device of claim 9, further comprising a controller communicatively coupled to the processor and an alarm device communicatively coupled to the controller.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211174178.9A CN115546717A (en) | 2022-09-26 | 2022-09-26 | Concrete pumpability type identification method and device and electronic equipment |
| PCT/CN2023/106835 WO2024066664A1 (en) | 2022-09-26 | 2023-07-11 | Concrete pumpability category identification method and apparatus, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211174178.9A CN115546717A (en) | 2022-09-26 | 2022-09-26 | Concrete pumpability type identification method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115546717A true CN115546717A (en) | 2022-12-30 |
Family
ID=84728723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211174178.9A Pending CN115546717A (en) | 2022-09-26 | 2022-09-26 | Concrete pumpability type identification method and device and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115546717A (en) |
| WO (1) | WO2024066664A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024066664A1 (en) * | 2022-09-26 | 2024-04-04 | 三一汽车制造有限公司 | Concrete pumpability category identification method and apparatus, and electronic device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111751253B (en) * | 2020-07-06 | 2022-10-14 | 重庆理工大学 | Forming method and quality detection method of concrete aggregate detection model |
| JP7471178B2 (en) * | 2020-08-31 | 2024-04-19 | 株式会社竹中工務店 | Image region classification model creation device, concrete evaluation device, and concrete evaluation program |
| CN112347985A (en) * | 2020-11-30 | 2021-02-09 | 广联达科技股份有限公司 | Material type detection method and device |
| CN113627293A (en) * | 2021-07-29 | 2021-11-09 | 三一汽车制造有限公司 | Method and device for detecting stirring uniformity of mixture and stirring equipment |
| CN114266989A (en) * | 2021-11-15 | 2022-04-01 | 北京建筑材料科学研究总院有限公司 | Concrete mixture workability determination method and device |
| CN115546717A (en) * | 2022-09-26 | 2022-12-30 | 三一汽车制造有限公司 | Concrete pumpability type identification method and device and electronic equipment |
-
2022
- 2022-09-26 CN CN202211174178.9A patent/CN115546717A/en active Pending
-
2023
- 2023-07-11 WO PCT/CN2023/106835 patent/WO2024066664A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024066664A1 (en) * | 2022-09-26 | 2024-04-04 | 三一汽车制造有限公司 | Concrete pumpability category identification method and apparatus, and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024066664A1 (en) | 2024-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111507958B (en) | Target detection method, training method of detection model and electronic equipment | |
| WO2021135879A1 (en) | Vehicle data monitoring method and apparatus, computer device, and storage medium | |
| CN110889428A (en) | Image recognition method and device, computer equipment and storage medium | |
| CN112528971B (en) | Power transmission line abnormal target detection method and system based on deep learning | |
| CN110956104A (en) | Method, device and system for detecting overflow of garbage can | |
| CN115546717A (en) | Concrete pumpability type identification method and device and electronic equipment | |
| CN112348791A (en) | Intelligent scrap steel detecting and judging method, system, medium and terminal based on machine vision | |
| CN113221804B (en) | Disordered material detection method and device based on monitoring video and application | |
| CN112580542A (en) | Steel bar counting method based on target detection | |
| CN115880260A (en) | Method, device and equipment for detecting base station construction and computer readable storage medium | |
| CN115545058A (en) | Water meter data analysis method and system and readable storage medium | |
| CN115995056A (en) | Automatic bridge disease identification method based on deep learning | |
| CN114926791A (en) | Method and device for detecting abnormal lane change of vehicles at intersection, storage medium and electronic equipment | |
| CN110909674A (en) | Traffic sign identification method, device, equipment and storage medium | |
| CN112784797A (en) | Target image recognition method and device | |
| CN116229396B (en) | High-speed pavement disease identification and warning method | |
| CN115359392A (en) | Roadside construction behavior detection method based on improved YOLOv5 model | |
| CN116012764A (en) | Road disease identification and positioning method and device, electronic equipment and storage medium | |
| Panda et al. | Application of Image Processing In Road Traffic Control | |
| CN112949584A (en) | Image screening method and device, electronic equipment and storage medium | |
| CN113435350A (en) | Traffic marking detection method, device, equipment and medium | |
| CN111881787A (en) | Camera-based store illegal operation behavior identification method and system | |
| CN112395993A (en) | Method and device for detecting ship sheltered based on monitoring video data and electronic equipment | |
| CN115147461A (en) | Disaster real-time early warning method, system and equipment | |
| CN117349734B (en) | Water meter equipment identification method and device, electronic equipment and storage medium |
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 |