A non-embedded deep learning-based concrete and workability detection method

Abstract

The application relates to the technical field of concrete construction monitoring, and discloses a non-embedded concrete workability detection method based on deep learning, which uses an image acquisition device to shoot images of concrete flowing from a mixer truck chute, analyzes image data, combines concrete mix data, hydration reaction time and the angle of the mixer truck chute, and outputs the concrete viscosity value and the slump degree. The method combines computer vision algorithms, deep learning and machine learning to complete the capture of the concrete features flowing out of the mixer truck in steps, and makes machine learning based on all the captured characteristic values to output the concrete slump degree. The algorithm involved in the scheme supports an edge computing device carrying a network communication module to complete data acquisition and analysis, and uses the communication module to transmit the acquired and analyzed data to a cloud server, so that the concrete mix of a commercial mixing station can be accurately adjusted according to different engineering actual conditions.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of concrete construction monitoring, in particular to a non-embedded concrete workability detection method based on deep learning. BACKGROUND

[0002] In recent years, China's overall economy has entered a high-quality development stage, and the economic growth rate has slowed down. The current construction planning land approval is increasingly tight, and the era of real estate and municipal engineering driving investment has passed. The profit space is reduced, and the market raw material price is rising. The necessity of whole-cycle quality control of building materials is increasingly prominent. The use of commercial concrete has been on the rise, but the digital scale popularization rate of commercial mixing stations is low. At present, the production relationship between the construction site and the commercial mixing station leads to a data gap. However, if there is a problem with concrete pouring, the accident will cause huge personnel safety and indirect or direct economic losses. Therefore, the digital link between commercial mixing and intelligent construction management centered on the concrete expert system is imminent.

[0003] The workability of concrete is a basic physical property for evaluating its construction performance. The workability detection of fresh concrete mixture (hereinafter referred to as fresh concrete) before construction is an essential process link in the construction quality control process. Workability refers to the ability of concrete mixture to flow and uniformly fill the corners of the form under the action of gravity or construction mechanical vibration. It reflects the workability of fresh concrete. The size of the workability reflects the dilution degree of the concrete mixture, which can affect the difficulty of construction and the quality of pouring. At present, the detection method of concrete workability in the construction site is still to use the slump cone detection, which is complicated to operate. In the actual construction process, workers and site management personnel do not detect the slump of each truck of concrete because the operation is too complex, which leads to inaccurate construction record data and poor management. And the interpretation of the test results by slump cannot perfectly explain the physical meaning of the fluidity of the mixture. Slump can only represent the fluid tension. The rheological properties of fresh concrete are represented by the function relationship between shear rate and shear stress, i.e. the rheological model. However, the shear stress and shear rate of fresh concrete cannot be directly measured. At present, the test results of the concrete rheometer (i.e. torque-speed data) are fitted by the conversion equation of the rheological model, and the rheological curve is established according to the calculated model parameter value to represent its rheological properties. With the maturity of computer vision and digital image processing technology, it is possible to identify flowing concrete.

[0004] The method for testing the workability of concrete at the construction site is still to use the slump cone test, which is cumbersome to operate. During the actual construction process on site, workers and on-site managers do not perform slump tests on every truck of concrete because the operation is too complicated. This leads to inaccurate construction record data and inadequate management during the process. The construction site's response to the quality of freshly mixed concrete is too rough. Most of them use the dry and wet conditions of concrete to respond to the mixing station. The commercial concrete mixing station lacks a basis for judgment, resulting in a large difference between the quality of the next batch of freshly mixed concrete and the previous batch. Therefore, there is a need for a digital control mechanism for concrete quality between the construction site and the commercial concrete mixing station. Related research inventions are as follows:

[0005] Taisei Co., Ltd. (President: Yoshiyuki Murata) has announced the release of its T-CIM®*1 system, which manages and shares construction-related information. This system digitizes and centrally manages the various information required for cast-in-place concrete work, thereby improving productivity and quality. "T-CIM® / Concrete" digitizes ready-mixed concrete information, from kneading at the ready-mix concrete plant to pouring completion. This information can be viewed in real time on a web server connected to the internet. This system enables information sharing among relevant parties and supports shipping management, transportation management, acceptance management, placement management, and quality control, aiming to improve productivity and quality in cast-in-place concrete work.

[0006] Zhongshan Ai Shang Zhitong Information Technology Co., Ltd. publicly invented the invention "A method and system for intelligent concrete mixing control" (application publication number: CN109676795A). The present invention provides a method and system for intelligent concrete mixing control, which realizes automatic detection of product rheology and homogeneity during concrete mixing and intelligent regulation of production process. The method is: the monitored mixing data and the physical and chemical properties data of the completed concrete are analyzed by big data to generate the optimal mix ratio and the best mixing scheme under various usage requirements; the mixer automatically calls the optimal material ratio and the best mixing scheme according to the purpose of the concrete or the specific parameter performance requirements, automatically takes materials and measures the performance parameters of the materials, and feeds back the performance parameters to the edge computing platform to determine whether the material performance meets the requirements; after the mixing is completed, the measured physical and chemical properties data of the concrete are compared with the expected data to determine whether to discharge the material or make corrections; the system includes a cloud platform and a mixing terminal, and the mixing terminal includes a human-computer interaction module, a control system, a mixing system, a monitoring system and an edge computer. Summary of the Invention

[0007] (1) Technical problems solved

[0008] In view of the deficiencies of the prior art, the present application provides a non-embedded deep learning-based concrete workability detection method, which can realize non-contact accurate auxiliary commercial mixing station adjustment decision for different engineering actual conditions.

[0009] (II) Technical solutions

[0010] To achieve the above object, the present application provides the following technical solutions: a non-embedded deep learning-based concrete workability detection method, comprising the following steps:

[0011] S1, using an automatic weighing system to record the concrete mix data in each mixing silo of the commercial concrete mixing station, and recording the departure time of the corresponding batch of concrete mixer truck on site;

[0012] S2, a plurality of on-site construction monitoring cameras are arranged in advance at the construction site, and the construction monitoring cameras collect images of the construction site before the mixer truck enters the construction site and starts pouring, and a yolov7 deep learning target detection model is used to identify the on-site concrete mixer truck and pump truck, and to locate the target area;

[0013] S3, according to the positioning of step S2, a site technician is notified to set up an image acquisition device on the mixer truck to acquire images of the concrete in the mixer truck chute, and when the mixer truck starts pouring, the time when the mixer truck starts pouring is recorded, and the time of the newly mixed concrete in the mixer truck is obtained by subtracting the time when the corresponding vehicle departs from the commercial concrete mixing station;

[0014] S4, using the image acquisition device to shoot images of the concrete flowing from the chute, using the GMFlow framework to segment the chute structure and flowing concrete, continuously extracting multiple frames of images, extracting the ROI region of the DIC detection algorithm from the continuous frame images, and then using the feature point capture method of the DIC detection point method to capture the concrete feature points in the ROI region, so as to obtain the Lagrangian flow field image or Euler flow field image of the concrete flow, and mark the displacement vector information on the flow field image;

[0015] S5, using the sift algorithm to determine the angle of the concrete mixer truck chute;

[0016] S6, using KNN network for machine learning, inputting each pixel vector displacement information data of the flowing concrete as input, fitting the concrete mix data, hydration reaction time and mixer truck chute angle to output the concrete viscosity value and slump, feeding the field concrete workability to the background database, improving the mix ratio according to the data of the background database, and the commercial mixing station mixes the new concrete according to the improved mix ratio and delivers it to the construction site, so as to repeat the process to make the work performance of the concrete meet the requirements.

[0017] Preferably, the target detection model using yolov7 deep learning identifies the field concrete mixer truck and pump truck, and locates the target area, specifically comprising: judging the relative positions of the mixer truck, the mixer truck chute and the pump truck in the image, using a material target detection method based on a rotating frame to judge the positions of the concrete mixer truck and the pump truck at different angles in the field, understanding the pouring area, and judging which mixer truck needs to pour concrete.

[0018] Preferably, the image acquisition device acquires images through a camera, and the device is erected with the camera placed vertically to the mixer truck discharge chute.

[0019] Preferably, the GMFlow framework is composed of three main parts:

[0020] A, a Transformer for feature enhancement;

[0021] B, a correlation and softmax layer for global matching;

[0022] C, a self-attention layer for optical flow propagation.

[0023] Preferably, the feature point capture method using the DIC detection point-free method for concrete feature point capture specifically comprises:

[0024] The results obtained by optical flow estimation separate the region of interest of the flowing concrete, extract the key points of the flowing concrete, obtain a one-to-one correspondence between the material points in the reference (initial undeformed image) and current (subsequent deformed image) configurations by obtaining a pixel subset of the reference image, obtain a grid containing displacement and strain information related to the reference configuration, and divide it into Euler grid and Lagrangian grid.

[0025] Preferably, the use of the sift algorithm to determine the angle of the concrete mixer truck chute includes scale space extreme value detection, key point positioning, direction determination and key point description, a chute reference is set at a fixed place in the field, and the inclination angle of the real chute is calculated by comparing the reference with the real chute.

[0026] Preferably, in step S6, the relevant data collected from S1 to S5 can be used to collect the real viscosity and slump of the measured flow rate concrete, create a training set, and use the KNN network to perform machine learning on the displacement vector information of the concrete flow pixel set, the main factors affecting viscosity in the mix ratio parameters, the hydration reaction time, and the inclination angle of the mixer truck chute as inputs to output the concrete viscosity and slump.

[0027] Preferably, the image acquisition device includes:

[0028] The data acquisition and processing unit includes a camera, a central processing unit, a network communication module, and an edge computing module. The image data collected by the camera is transmitted to the central processing unit for processing through the edge computing module. The network communication module transmits the processed data to the cloud server.

[0029] Digital display controller, used to display and control image acquisition equipment;

[0030] A power supply unit, which is a lithium battery, is used to provide power to the image acquisition device;

[0031] The external device unit includes a fixing clip for adjusting the camera angle and an aluminum alloy shell for carrying the entire device.

[0032] Another technical problem to be solved by the present invention is to provide a computable and readable storage medium, which implements the above-mentioned monitoring method when the program is executed by a processor.

[0033] (3) Beneficial effects

[0034] Compared with the prior art, the present invention provides a non-embedded method for concrete workability detection based on deep learning, which has the following beneficial effects:

[0035] This method combines computer vision algorithms, deep learning, and machine learning to capture the characteristics of concrete flowing out of mixer trucks in steps, and uses machine learning based on all captured feature values ​​to output the slump of concrete. The algorithm involved in this solution supports edge computing devices equipped with network communication modules to complete data collection and analysis, and uses the communication module to transmit the collected and analyzed data to the cloud server, accurately assisting commercial concrete mixing stations to make adjustments to the concrete mix ratio based on the actual conditions of different projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic diagram illustrating the process of the present invention;

[0037] Figure 2 It is a schematic diagram of the process of the present invention;

[0038] Figure 3 This is a structural diagram of the algorithm training method of the present invention;

[0039] Figure 4 The algorithm training mode flowchart of the application;

[0040] Figure 5 The system control schematic diagram of the image acquisition device of the application;

[0041] Figure 6 The on-site installation schematic diagram of the image acquisition device of the application;

[0042] Figure 7 The effect diagram of the flow concrete identification of the application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the application.

[0044] Please refer to Figures 1-4 The application provides a non-embedded concrete and workability detection method based on deep learning, which uses an image acquisition device to shoot images of the flowing concrete from the chute of a mixer truck, analyzes image data, combines concrete mix data, hydration reaction time and chute angle of the mixer truck, and outputs concrete viscosity value and slump.

[0045] Specifically, the concrete mix data and hydration reaction time can be obtained by recording the concrete mix data in each mixing silo of the commercial concrete mixing station by using an automatic weighing system, confirming the departure time of the mixer truck carrying the corresponding batch of concrete by using license plate recognition, recording the departure time of the mixer truck carrying the corresponding batch of concrete, and then arranging multiple on-site construction monitoring cameras at the construction site in advance. After the mixer truck enters the construction site, the construction monitoring cameras start image acquisition before the mixer truck starts pouring. The yolov7 deep learning target detection model is used to identify the on-site concrete mixer truck and pump truck, and to locate the target area. According to the positioning, the on-site technical personnel are notified to set up image acquisition devices on the mixer truck to collect images of the concrete in the chute of the mixer truck. When the mixer truck starts pouring, the time when the mixer truck starts pouring is recorded. The time when the mixer truck starts pouring is subtracted from the time when the corresponding vehicle departs from the commercial concrete mixing station to obtain the hydration reaction time of the freshly mixed concrete in the mixer truck.

[0046] Among them, the yolov7 deep learning target detection model is used to identify on-site concrete mixer trucks and pump trucks, and locate the target area, specifically including: judging the relative positions of the mixer truck, mixer truck chute and pump truck in the image, and using the material target detection method based on rotating frame positioning to judge the location of concrete mixer trucks and pump trucks at different angles on site, understand the pouring area, and determine which mixer truck needs to pour concrete.

[0047] See also Figures 5-6 The image acquisition device collects images through a camera. The camera is a depth camera. When the equipment is set up, the camera is placed perpendicular to the mixer truck's unloading chute. It should be noted that when shooting the flowing concrete in the mixer truck's chute, the camera's illumination angle must be fixed (preferably perpendicular to the ground or perpendicular to the chute). The coordinate points of the four corners of the entire chute on the camera's projection must be fixed, paving the way for subsequent machine learning data analysis of the vectorized image information.

[0048] The image acquisition device includes a data acquisition and processing unit, a digital display controller, a power supply unit and an external device unit. Among them, the data acquisition and processing unit includes a camera, a central processing unit, a network communication module and an edge computing module. The image data collected by the camera is transmitted to the central processing unit for processing through the edge computing module, and the network communication module transmits the processing structure to the cloud server; the digital display controller is used to display and control the image acquisition device; the power supply unit is a lithium battery, which is used to provide power to the image acquisition device; the external device unit includes a fixed clamp with adjustable camera angle, which is installed on the funnel of the concrete mixer truck and an aluminum alloy shell for carrying the entire device.

[0049] An image acquisition device is used to capture images of concrete flowing through the chute. The chute structure and the flowing concrete are segmented using the GMFlow framework, and multiple frames of images are continuously extracted. The ROI area of ​​the DIC detection algorithm is extracted from the continuous frame images. Then, the feature point capture method of the DIC detection without punctuation is used to capture the concrete feature points in the ROI area, thereby obtaining a Lagrangian flow field image or an Eulerian flow field image of the concrete flow, and the displacement vector information is marked on the flow field image.

[0050] The GMFlow framework segments the chute structure and flowing concrete. Its purpose is to extract the semantic segmentation results and use them as regions of interest (ROIs) for DIC detection. Unlike traditional semantic segmentation models that classify and identify single images, the GMFlow framework consists of three main components: a Transformer for feature enhancement, correlation and softmax layers for global matching, and a self-attention layer for optical flow propagation. Because the optical flow features of flowing concrete are relatively prominent, optical flow estimation is used to segment and identify flowing fresh concrete.

[0051] Among them, it is configured to use the semantic segmentation results to select the ROI region of interest for DIC detection, and to infer the pixel motion vector information of the flowing concrete based on the pixel interpolation of the ROI region of interest in the previous and next frames, thereby obtaining the Euler motion field.

[0052] The results of optical flow estimation are used to segment the area of ​​interest of concrete flow, and key points of the flowing concrete are extracted. By obtaining a subset of reference image pixels, a one-to-one correspondence is obtained between the material points in the reference (initial undeformed image) and current (subsequent deformed image) configurations. The resulting grid contains displacement and strain information related to the reference configuration, which is divided into Eulerian grids and Lagrangian grids.

[0053] Specifically, the changing curve of the concrete's motion state in the chute is used to identify the flow characteristics of different slumps at the same chute angle, record the displacement vector information, form a unique Euler vector pixel field for the flowing concrete, and use a fresh concrete viscometer to record the viscosity of the truck's concrete to carry out data collection.

[0054] The SIFT algorithm is used to determine the angle of the concrete mixer truck chute, including scale space extreme value detection, key point positioning, direction determination and key point description. A chute reference object is set at a fixed location on site, and the inclination angle of the actual chute is calculated by comparing the reference object with the actual chute.

[0055] Using the KNN network for machine learning, the vector displacement information of each pixel of flowing concrete is input as input, and the concrete mix ratio data, hydration reaction time, and mixer truck chute angle are fitted to output the concrete viscosity value and slump. The workability of the on-site concrete is fed back to the backend database, and the mix ratio is improved based on the data in the backend database. The Internet of Things technology is used to notify the mixing station to adjust the concrete mix ratio. The commercial concrete mixing station mixes the fresh concrete according to the mix ratio improved by the backend database and delivers it to the construction site. This process is repeated to ensure that the working performance of the concrete meets the requirements.

[0056] See also Figure 7 , Figure 7This is the effect diagram of the flow concrete identification of the present invention. It needs to be further explained that the movement state of the flow concrete in 10 consecutive frames shows a certain pattern, which is a representation of the rheological properties of the concrete. From this, its motion vector information can be used for machine learning to obtain its fixed rheological parameters, so that concrete with different rheological characteristics can be observed and recorded, and included in the cloud database. As the data accumulates, its cloud algorithm model becomes more accurate, and its upgraded content can be remotely delivered to the edge.

[0057] Since concrete mix design is determined based on concrete mix strength, concrete design strength, and concrete strength standard deviation, the values ​​that have the greatest impact on fresh concrete workability are the water-cement ratio, cement type, admixture quantity and type, sand content, and aggregate particle size and proportion. Using the aforementioned method, we collected relevant data, including the actual viscosity and slump of the measured concrete flow rate, to create a training set. A KNN network was then used to perform machine learning on the displacement vector information of the concrete flow pixel set, the main viscosity-influencing factors of the mix parameters, the hydration reaction time, and the inclination angle of the mixer truck chute as inputs, outputting concrete viscosity and slump. This dataset takes concrete mix data, hydration reaction time data within the mixer truck, and concrete flow rate vector data as inputs, and outputs concrete viscosity. The KNN network was used for machine learning on this data, focusing on accurate data on the concrete batching plant mix ratio and the accurate recording of the mixing time in the commercial concrete plant's mixing silo, combined with the transportation time within the mixer truck during transportation.

[0058] In order to establish a weighted relationship between the change in viscosity of freshly mixed concrete and the change in the amount of aggregate corresponding to different gradations, the predicted value of the concrete's working performance in the mixing image is used to determine whether the amount of aggregate used in the concrete mixing process needs to be adjusted. The amount of aggregate used in the concrete mixing process is adjusted based on the predicted value of the concrete's working performance, the gradation of the aggregate in the concrete mixing process, and the weighted relationship. The above operation is repeated to estimate the concrete viscosity until the concrete's working performance meets the requirements.

[0059] This method combines computer vision algorithms, deep learning, and machine learning to capture the characteristics of concrete flowing out of mixer trucks in steps, and uses machine learning based on all captured feature values ​​to output the slump of concrete. The algorithm involved in this solution supports edge computing devices equipped with network communication modules to complete data collection and analysis, and uses the communication module to transmit the collected and analyzed data to the cloud server, accurately assisting commercial concrete mixing stations to make adjustments to the concrete mix ratio based on the actual conditions of different projects.

[0060] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0061] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0064] The foregoing description of specific exemplary embodiments of the application has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the application to the precise forms disclosed, and obviously many modifications and variations are possible in light of the above teaching. It is intended that the scope of the application be limited not with this detailed description, but rather by the claims appended hereto.

Claims

1. A non-embedded method for concrete workability detection based on deep learning, characterized in that: The following steps are involved: S1. Use the automatic weighing system to record the concrete mix ratio data in each mixing silo of the commercial concrete mixing station and record the departure time of the mixer truck transporting the corresponding batch of concrete on site; S2. Pre-deploy multiple on-site construction monitoring cameras at the construction site. After the concrete mixer truck enters the construction site and before pouring begins, the construction monitoring cameras collect images of the construction site situation. The yolov7 deep learning target detection model is used to identify the on-site concrete mixer truck and pump truck, and locate the target area. S3. Based on the positioning in step S2, the on-site technician is notified to set up an image acquisition device on the mixer truck to capture images of the concrete in the mixer truck chute. When the mixer truck starts pouring, the time when the mixer truck starts pouring is recorded. The time when the corresponding vehicle departs from the commercial concrete mixing plant is subtracted from the time to obtain the hydration reaction time of the fresh concrete in the mixer truck. S4. Using an image acquisition device, capture images of concrete flowing through the chute, segment the chute structure and the flowing concrete using the GMFlow framework, continuously extract multiple frames of images, extract the ROI region of interest (ROI) of the DIC detection algorithm from the continuous frame images, and then use the feature point capture method of the DIC detection method without punctuation to capture concrete feature points in the ROI region, thereby obtaining a Lagrangian flow field image or an Eulerian flow field image of the concrete flow, and marking the displacement vector information on the flow field image. S5. Using SIFT algorithm to determine the angle of the concrete mixer truck chute; S6. Use the KNN network for machine learning. Input the vector displacement information data of each pixel of the flowing concrete as input. Fit the concrete mix ratio data, hydration reaction time, and mixer truck chute angle to output the concrete viscosity value and slump. Feedback the on-site concrete workability status to the backend database. Improve the mix ratio based on the data in the backend database. The commercial concrete mixing station mixes the fresh concrete according to the mix ratio improved by the backend database and delivers it to the construction site. Repeat this process until the working performance of the concrete meets the requirements.

2. The method for detecting concrete workability without embedded deep learning according to claim 1, characterized in that: In step S2, the target detection model of yolov7 deep learning is used to identify the on-site concrete mixer trucks and pump trucks, and the target area is located, specifically including: judging the relative positions of the mixer truck, mixer truck chute and pump truck in the image, and using the material target detection method based on rotating frame positioning to judge the positions of the concrete mixer trucks and pump trucks at different angles on site, understand the pouring area, and judge which mixer truck needs to pour concrete.

3. The method for detecting concrete workability without embedded deep learning according to claim 1, characterized in that: The image acquisition device in step S3 acquires images through a camera, and when the device is set up, the camera is placed perpendicular to the unloading chute of the mixer truck.

4. The method for detecting concrete workability without embedded deep learning according to claim 1, characterized in that: The GMFlow framework in step S4 consists of three main parts: A. Transformer for feature enhancement; B. Correlation and softmax layers for global matching; C. Self-attention layer for optical flow propagation.

5. The method for detecting concrete workability without embedded deep learning according to claim 4 is characterized in that: The method for capturing concrete feature points using the feature point capture method without punctuation method using DIC detection in step S4 specifically includes: The results of optical flow estimation are used to segment the area of ​​interest of concrete flow, and key points of the flowing concrete are extracted. By obtaining a subset of reference image pixels, a one-to-one correspondence is obtained between the material points in the initial undeformed image and the subsequent deformed image configuration, and a grid containing displacement and strain information related to the reference configuration is obtained, which is divided into Eulerian grid or Lagrangian grid.

6. The method for detecting concrete workability without embedded deep learning according to claim 1, characterized in that: In step S5, the angle of the concrete mixer truck chute is determined by using the SIFT algorithm, which includes scale space extreme value detection, key point positioning, direction determination, and key point description. A chute reference object is set at a fixed place on site, and the inclination angle of the actual chute is calculated by comparing the reference object with the actual chute.

7. The method for detecting concrete workability without embedded deep learning according to claim 1, characterized in that: The image acquisition device comprises: The data acquisition and processing unit includes a camera, a central processing unit, a network communication module, and an edge computing module. The image data collected by the camera is transmitted to the central processing unit for processing through the edge computing module. The network communication module transmits the processed data to the cloud server. Digital display controller, used to display and control image acquisition equipment; A power supply unit, which is a lithium battery, is used to provide power to the image acquisition device; The external device unit includes a fixing clip for adjusting the camera angle and an aluminum alloy shell for carrying the entire device.

8. A computable and readable storage medium, characterized in that: When the program included in the storage medium is executed by a processor, the detection method according to any one of claims 1 to 6 is implemented.

Images