Process identification method, device and equipment and computer readable storage medium
By acquiring and analyzing the images of the construction site, and using preset models to identify the types and processes of equipment, the problem of complex and low efficiency of process identification in the existing technology is solved, and the accurate identification and progress monitoring of construction processes are realized, and the construction efficiency and Security.
Patent Information
- Application Number
- CN202411228210.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2025-01-14
AI Technical Summary
In bridge construction, the existing manual inspection methods are complex, cumbersome, time-consuming and inefficient, resulting in inaccurate process identification and affecting construction quality and safety.
By obtaining the construction picture images of the construction site, using the preset area constraint model and equipment identification model, identifying the types of equipment in the target area, and determining the current construction process and progress based on multiple consecutive images, determining whether it is abnormal, and outputting a prompt signal .
Accurate identification and progress monitoring of construction processes are realized, interference without identification of areas is reduced, accuracy and efficiency of construction processes are improved, and construction processes are ensured to be carried out in accordance with standards.
Smart Images
Figure CN119313049A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of construction monitoring, and in particular to a process identification method, device, equipment and computer-readable storage medium. Background Art
[0002] The importance of bridge construction projects is not only reflected in connecting cities and promoting economic development, but also in its key infrastructure status. Bridges are an important part of the transportation network. In bridge construction, process identification tasks are the core of ensuring project quality and safety. Through intelligent monitoring and identification, precise control of the construction process is achieved to ensure that the construction is carried out in an orderly manner according to standards and plans. Therefore, bridge construction projects are not only the pillars of urban development, but also require the support of advanced process identification technology to ensure their quality, efficiency and safety, laying a solid foundation for the sustainable development of cities.
[0003] In the current field of bridge construction, accurate identification and monitoring of each process in the construction of bridges is crucial to ensure the high-quality production of prefabricated beams. The original manual inspection method is complicated, tedious, time-consuming and inefficient. Summary of the invention
[0004] The present application provides a process identification method, device, equipment and computer-readable storage medium, which can solve the related technical problems existing in the above-mentioned prior art.
[0005] In a first aspect, the present application provides a process identification method, which adopts the following technical solution:
[0006] A process identification method, the process identification method comprising:
[0007] Acquire construction scene images of the construction site;
[0008] Determining a target area in the construction scene image according to a preset area constraint model;
[0009] Identify the type of equipment in the target area of the construction picture image according to a preset equipment identification model;
[0010] The current construction process at the construction site is determined according to the equipment types in a plurality of consecutive construction scene images.
[0011] In combination with the first aspect, in one implementation, determining the current construction process at the construction site according to the equipment types in a plurality of consecutive construction scene images comprises the following steps:
[0012] Determine the construction process corresponding to the construction picture image according to the type of equipment in the target area;
[0013] If the number of the construction picture images continuously corresponding to the same construction process exceeds a preset number threshold, it is determined that the construction site is currently.
[0014] In combination with the first aspect, in one implementation, if the number of the construction picture images corresponding to the same construction process continuously exceeds a preset number threshold, it is determined that the construction site is currently in
[0015] The quantity threshold is determined according to the construction process.
[0016] In combination with the first aspect, in one embodiment, after determining the current construction process at the construction site according to the equipment types in the continuous plurality of construction scene images, the following steps are further included:
[0017] The progress of the current construction process is determined according to the number of construction scene images in the current construction process.
[0018] In combination with the first aspect, in one implementation, the target area in the construction scene image is determined according to a preset area constraint model.
[0019] Determine an operation platform area map of a target area in the construction picture image;
[0020] A spatial area map of a target area including the operating platform area map is determined based on the operating platform area map.
[0021] In combination with the first aspect, in one embodiment, after determining the current construction process at the construction site according to the equipment types in the plurality of consecutive construction scene images, the following steps are included:
[0022] According to a preset process constraint model, determining whether the current construction process is abnormal;
[0023] If abnormal, a prompt signal is output to the receiving end.
[0024] In combination with the first aspect, in one implementation, the process constraint model is used to determine whether the current construction process is abnormal.
[0025] Whether the current construction process is abnormal is determined based on whether the current construction process conforms to a preset arrangement order of multiple process types.
[0026] In a second aspect, the embodiment of the present application provides a process identification device, which adopts the following technical solution:
[0027] A process identification device, comprising:
[0028] An acquisition module, which is configured to acquire a construction scene image of the construction site;
[0029] A region constraint module, configured to determine a target region in the construction scene image according to a preset region constraint model;
[0030] The process identification module is configured to identify the type of equipment in the target area of the construction picture image according to a preset equipment identification model; and determine the current construction process of the construction site according to the type of equipment in a plurality of consecutive construction picture images.
[0031] In a third aspect, the embodiment of the present application provides a process identification device, which adopts the following technical solution:
[0032] A process identification device comprises a processor, a memory, and a process identification program stored in the memory and executable by the processor, wherein when the process identification program is executed by the processor, the steps of the process identification method described above are implemented.
[0033] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which adopts the following technical solution:
[0034] A computer-readable storage medium stores a process identification program, wherein when the process identification program is executed by a processor, the steps of the process identification method described above are implemented.
[0035] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:
[0036] After acquiring the construction picture image of the construction site, the target area that needs to be analyzed in the construction picture image is first determined according to the preset area constraint model, so as to effectively reduce the interference of other areas that do not need to be identified, and further use the equipment recognition model to identify the equipment type of related equipment in the target area, and finally determine the current construction process of the construction site according to the equipment type in multiple consecutive construction picture images, so as to effectively ensure the recognition accuracy of the construction process. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 This is a flow chart of an embodiment of a process identification method of the present application;
[0038] Figure 2 This is a functional module diagram of an embodiment of a process identification device of the present application;
[0039] Figure 3 This is a schematic diagram of the hardware structure of the process identification device involved in the embodiment of the present application. DETAILED DESCRIPTION
[0040] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0041] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0042] In a first aspect, an embodiment of the present application provides a process identification method.
[0043] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the process identification method of this application. Figure 1 As shown, the process identification method includes:
[0044] S100, obtaining a construction scene image of the construction site;
[0045] S200, determining a target area in the construction scene image according to a preset area constraint model;
[0046] S300, identifying the type of equipment in the target area of the construction picture image according to a preset equipment recognition model;
[0047] S400: Determine the current construction process at the construction site according to the equipment types in a plurality of consecutive construction scene images.
[0048] Among them, when calibrating the target area in step S200, the workbench where the construction is located is mainly calibrated. The regional constraint model used in this process can be an artificial model that requires manual intervention to manually calibrate each image, or it can be an automatic model that automatically calibrates the workbench area to extract the target area corresponding to the workbench.
[0049] After the calibration is completed, the construction equipment in the target area will be monitored and identified, and the current construction process of the construction site will be determined based on the identification results. Among them, for different construction processes, the types of equipment involved and other relevant requirements are different. This application does not limit this, and it can be formulated by technical personnel according to specific construction requirements. For example, for the binding process, it is necessary to first identify the presence of bellows in the image in step S300, and after the bellows are present in the construction picture image acquired for 5 minutes, it is determined whether the appearance of the cage is monitored in the target area of the image. If the cage is successfully monitored after the former is met, it can be determined that the current construction process of the construction site at this time is the binding process. The equipment recognition model used in step S300 is pre-trained and can identify a variety of different types of equipment according to specific needs.
[0050] In this embodiment, in step S400, in the process of judging whether each construction scene image belongs to the preset multiple construction processes, the preset multiple construction processes specifically include binding process, formwork installation process, pouring process, tensioning process and grouting process, etc. For these processes, step S400 will be executed according to the specific judgment requirements of each of the following processes.
[0051] Binding process: after the corrugated pipe is identified in the image and the corrugated pipe is present in the construction images acquired for 5 consecutive minutes, it is determined whether the cage is detected in the target area of the image. If the cage is successfully detected after the former is satisfied, it can be determined that the current construction process at the construction site is the binding process;
[0052] Template installation process: If the suspended ceiling is identified in the target area and the identification result is stable for 1 minute, the template installation start time is uploaded and the target is tracked; until the suspended ceiling target disappears in the target area, the template installation end time is uploaded;
[0053] Casting process: If a funnel is identified in the pedestal area and the identification result is stable for 10 minutes, the casting start time is uploaded and the target is tracked; until the funnel target disappears in the pedestal area, the casting end time is uploaded;
[0054] Tensioning process: If the anchor is detected and identified in the pedestal area, and the identification result is stable for 10 minutes, the tensioning start time is uploaded and the target is tracked; until the anchor target disappears in the pedestal area, the tensioning end time is uploaded;
[0055] Grouting process: If the bellows is detected and identified in the pedestal area, and the identification result is stable for 10 minutes, the grouting start time is uploaded and the target is tracked; until the bellows target disappears in the pedestal area, the grouting end time is uploaded;
[0056] Finally, after acquiring the construction scene image of the construction site, the target area that needs to be analyzed in the construction scene image is first determined according to the preset regional constraint model, so as to effectively reduce the interference of other areas that do not need to be identified, and further use the equipment recognition model to identify the equipment type of the relevant equipment in the target area, and finally determine the current construction process of the construction site according to the equipment type in multiple consecutive construction scene images, so as to effectively ensure the recognition accuracy of the construction process.
[0057] Further, in one embodiment, the step S400, determining the current construction process at the construction site according to the equipment types in the continuous plurality of construction scene images, comprises the following steps:
[0058] S410, determining the construction process corresponding to the construction picture image according to the type of equipment in the target area;
[0059] S420: If the number of the construction picture images that continuously correspond to the same construction process exceeds a preset number threshold, determine the current construction process at the construction site, wherein the number threshold is determined according to the construction process.
[0060] Specifically, for different construction processes, since the construction time may vary greatly, the quantity thresholds adopted may be different. With this setting, only when multiple construction scene images are continuously identified as belonging to a certain construction process and the number exceeds the corresponding quantity threshold, the current construction process of the construction site can be judged, thereby effectively ensuring the recognition accuracy.
[0061] Furthermore, after determining the current construction process at the construction site according to the equipment types in the plurality of consecutive construction scene images in S400, the following steps are further included:
[0062] S500: Determine the progress of the current construction process according to the number of construction scene images in the current construction process.
[0063] Specifically, the acquired status of each process is transmitted to the efficacy statistics system for efficacy statistics;
[0064] The incoming process start time, that is, the acquisition time of the first construction picture image corresponding to the current construction process, is subtracted from the acquisition time of the latest construction picture image, and the time difference between the two is compared with the duration required for the preset construction process. The ratio result can be regarded as the process completion degree; then the process completion degree result is uploaded to the interface for subsequent processing and management.
[0065] Further, in one embodiment, the step S200, determining the target area in the construction scene image according to a preset area constraint model, comprises the following steps:
[0066] S210, determining an operation platform area map of a target area in the construction picture image;
[0067] S220. Determine, based on the operation platform area map, a spatial area map of the target area including the operation platform area map.
[0068] In this embodiment, the operating platform area map is the two-dimensional boundary area of the operating platform in the target area on the image, but in practice, the relevant equipment is placed on the operating platform, and there are many equipment screens that exceed the operating platform area map in the vertical direction. Therefore, it is necessary to include part of the space above the operating platform area map to improve the recognition accuracy. Then, in step S220, the operating platform area map is used to further obtain a space area map including the appropriate space above it and the operating platform area map.
[0069] Furthermore, since some problems may be encountered at the acquisition end of the construction scene image, resulting in unsuccessful acquisition in the middle part of the time, the intermediate construction stage in this embodiment cannot be smoothly grasped. In order to enable the staff to grasp this situation, in some embodiments, the step S400, after determining the current construction process of the construction site according to the equipment types in the continuous plurality of the construction scene images, includes the following steps:
[0070] S600, judging whether the current construction process is abnormal according to a preset process constraint model;
[0071] S610: If abnormal, output a prompt signal to the receiving end.
[0072] Specifically, in determining whether the current construction process is abnormal according to a preset process constraint model,
[0073] Whether the current construction process is abnormal is determined based on whether the current construction process conforms to a preset arrangement order of multiple process types.
[0074] In this way, through the pre-set sequence constraints, that is, using the process constraint model to determine whether the current construction process conforms to the preset arrangement order of multiple process types, it is possible to understand whether the sequence of the current construction process in the overall construction process is abnormal. When an abnormal situation occurs, a prompt signal will be sent to the receiving end, so that the relevant personnel at the receiving end can understand the abnormal situation of the construction image acquisition, and then be able to make timely adjustments to the relevant equipment, and at the same time, the abnormalities that occur in the relevant equipment can also be recorded.
[0075] In a second aspect, an embodiment of the present application also provides a process identification device.
[0076] In one embodiment, referring to Figure 2 , Figure 2 This is a functional module diagram of an embodiment of the process identification device of the present application. Figure 2 As shown, the process identification device includes:
[0077] An acquisition module, which is configured to acquire a construction scene image of the construction site;
[0078] A region constraint module, configured to determine a target region in the construction scene image according to a preset region constraint model;
[0079] The process identification module is configured to identify the type of equipment in the target area of the construction picture image according to a preset equipment identification model; and determine the current construction process of the construction site according to the type of equipment in a plurality of consecutive construction picture images.
[0080] Among them, the functional implementation of each module in the above-mentioned process identification device corresponds to each step in the above-mentioned process identification method embodiment, and its functions and implementation processes will not be repeated here one by one.
[0081] In a third aspect, an embodiment of the present application provides a process identification device, which may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.
[0082] Reference Figure 3 , Figure 3 Schematic diagram of the hardware structure of the process identification device involved in the embodiment of the present application. In the embodiment of the present application, the process identification device may include a processor, a memory, a communication interface and a communication bus.
[0083] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.
[0084] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the process identification device, and the interface used to realize the interconnection between the process identification device and other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.
[0085] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.
[0086] The processor may be a general-purpose processor, which may call the process identification program stored in the memory and execute the process identification method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the process identification program is called may refer to the various embodiments of the process identification method of the present application, which will not be described in detail here.
[0087] Those skilled in the art will understand that Figure 3 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0088] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.
[0089] The computer-readable storage medium of the present application stores a process identification program, wherein when the process identification program is executed by a processor, the steps of the process identification method as described above are implemented.
[0090] Among them, the method implemented when the process identification program is executed can refer to the various embodiments of the process identification method of the present application, and will not be repeated here.
[0091] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.
[0092] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.
[0093] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.
[0094] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.
[0095] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.
[0096] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.
[0097] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A process identification method, characterized in that: The process identification method comprises: Acquire construction scene images of the construction site; Determining a target area in the construction scene image according to a preset area constraint model; Identify the type of equipment in the target area of the construction picture image according to a preset equipment identification model; The current construction process at the construction site is determined according to the equipment types in a plurality of consecutive construction scene images.
2. The process identification method according to claim 1, characterized in that: Determining the current construction process at the construction site according to the equipment types in the continuous plurality of construction scene images comprises the following steps: Determine the construction process corresponding to the construction picture image according to the type of equipment in the target area; If the number of the construction picture images that continuously correspond to the same construction process exceeds a preset number threshold, the current construction process at the construction site is determined.
3. The process identification method according to claim 2, characterized in that: If the number of the construction scene images corresponding to the same construction process continuously exceeds the preset number threshold, it is determined that the construction site is currently in The quantity threshold is determined according to the construction process.
4. The process identification method according to claim 2, characterized in that: After determining the current construction process at the construction site according to the equipment types in the continuous plurality of construction scene images, the following steps are also included: The progress of the current construction process is determined according to the number of construction scene images in the current construction process.
5. The process identification method according to claim 1, characterized in that: Determining the target area in the construction picture image according to the preset area constraint model includes the following steps: Determine an operation platform area map of a target area in the construction picture image; A spatial area map of a target area including the operating platform area map is determined based on the operating platform area map.
6. The process identification method according to claim 1, characterized in that: After determining the current construction process at the construction site according to the equipment types in the continuous plurality of construction scene images, the following steps are included: According to a preset process constraint model, determining whether the current construction process is abnormal; If abnormal, a prompt signal is output to the receiving end.
7. The process identification method according to claim 6, characterized in that: The method determines whether the current construction process is abnormal according to the preset process constraint model. Whether the current construction process is abnormal is determined based on whether the current construction process conforms to a preset arrangement order of multiple process types.
8. A process identification device, characterized in that: The process identification device comprises: An acquisition module, which is configured to acquire a construction scene image of the construction site; A region constraint module, configured to determine a target region in the construction scene image according to a preset region constraint model; The process identification module is configured to identify the type of equipment in the target area of the construction picture image according to a preset equipment identification model; and determine the current construction process of the construction site according to the type of equipment in a plurality of consecutive construction picture images.
9. A process identification device, characterized in that: The process identification device includes a processor, a memory, and a process identification program stored in the memory and executable by the processor, wherein when the process identification program is executed by the processor, the steps of the process identification method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a process identification program, wherein when the process identification program is executed by a processor, the steps of the process identification method according to any one of claims 1 to 7 are implemented.