CN117935126A - Grouting reinforcement video identification method for soft-flow plastic silt powdery clay stratum - Google Patents
Grouting reinforcement video identification method for soft-flow plastic silt powdery clay stratum Download PDFInfo
- Publication number
- CN117935126A CN117935126A CN202410323481.3A CN202410323481A CN117935126A CN 117935126 A CN117935126 A CN 117935126A CN 202410323481 A CN202410323481 A CN 202410323481A CN 117935126 A CN117935126 A CN 117935126A
- Authority
- CN
- China
- Prior art keywords
- video
- grouting reinforcement
- frame
- monitoring
- foundation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000002787 reinforcement Effects 0.000 title claims abstract description 244
- 238000000034 method Methods 0.000 title claims abstract description 111
- 239000004927 clay Substances 0.000 title claims abstract description 70
- 238000012544 monitoring process Methods 0.000 claims abstract description 295
- 238000007596 consolidation process Methods 0.000 claims abstract description 119
- 230000008569 process Effects 0.000 claims abstract description 68
- 238000006073 displacement reaction Methods 0.000 claims abstract description 39
- 239000012530 fluid Substances 0.000 claims abstract description 24
- 239000000843 powder Substances 0.000 claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 230000000694 effects Effects 0.000 claims abstract description 12
- 230000009471 action Effects 0.000 claims description 47
- 238000011156 evaluation Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 11
- 238000007711 solidification Methods 0.000 claims description 6
- 230000008023 solidification Effects 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 239000002689 soil Substances 0.000 description 21
- 230000009286 beneficial effect Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 10
- 238000005192 partition Methods 0.000 description 8
- 239000002002 slurry Substances 0.000 description 6
- 238000012876 topography Methods 0.000 description 6
- 230000008030 elimination Effects 0.000 description 5
- 238000003379 elimination reaction Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000005553 drilling Methods 0.000 description 2
- 238000005755 formation reaction Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003014 reinforcing effect Effects 0.000 description 2
- ZYPDJSJJXZWZJJ-UHFFFAOYSA-N 2-[4-[2-(2,3-dihydro-1H-inden-2-ylamino)pyrimidin-5-yl]-3-piperidin-4-yloxypyrazol-1-yl]-1-(2,4,6,7-tetrahydrotriazolo[4,5-c]pyridin-5-yl)ethanone Chemical compound C1C(CC2=CC=CC=C12)NC1=NC=C(C=N1)C=1C(=NN(C=1)CC(=O)N1CC2=C(CC1)NN=N2)OC1CCNCC1 ZYPDJSJJXZWZJJ-UHFFFAOYSA-N 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 239000004570 mortar (masonry) Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000012466 permeate Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of video analysis, and particularly discloses a method for grouting reinforcement video identification of a soft-flow plastic silt powdery clay stratum, which comprises the following steps: acquiring grouting reinforcement monitoring videos of a grouting reinforcement process of a soft fluid plastic silt powder clay stratum of a target monitoring foundation and consolidation monitoring videos of the soft fluid plastic silt powder clay stratum in a consolidation process; based on the size and the frame-to-frame displacement of all foundation frame areas in the grouting reinforcement monitoring video, analyzing the land deformation of the target monitoring foundation in the grouting reinforcement process; analyzing the land settlement of the target monitoring foundation in the consolidation process based on the size and the inter-frame displacement of all foundation frame areas in the consolidation monitoring video; determining grouting reinforcement effect of the target monitoring foundation based on the land deformation of the target monitoring foundation in the grouting reinforcement process, the land settlement of the target monitoring foundation in the consolidation process and the weights corresponding to the land deformation and the land settlement; the method is used for evaluating grouting reinforcement effect of the soft-flow plastic silt powdery clay stratum through video identification analysis.
Description
Technical Field
The invention relates to the technical field of video analysis, in particular to a method for reinforcing video identification by grouting in a soft-flow plastic silt powdery clay stratum.
Background
The soft fluid plastic silt powdery clay stratum is a geological term, and the main component in the stratum is soft fluid plastic silt powdery clay. The stratum generally has higher water content and weaker mechanical property, and the problems of foundation settlement and the like are easy to occur. Therefore, in foundation engineering such as construction, bridge, tunnel, etc., special foundation treatment is required to improve the bearing capacity and stability. The formation of soft fluid plastic silt powdery clay stratum is often related to the movement of underground water, and mineral substances dissolved in the underground water can permeate between soil particles so as to moisten the soil, thereby leading to the increase of the compressibility and flowability of the soil. The nature of such formations makes them to some extent more demanding in terms of foundation treatment techniques.
The grouting reinforcement of the soft-flow plastic silt clay stratum is a common foundation treatment method, and is mainly used for improving the bearing capacity and stability of soil and preventing foundation settlement. The following is a brief outline of the grouting reinforcement process of the soft-fluid plastic silt powdery clay stratum:
drilling and grouting: after the position of the grouting holes is determined, special equipment is used for drilling. Grouting materials (such as cement slurry, powdered coal mortar and the like) are injected into the drill holes according to design requirements, and the slurry is injected into foundation soil body through a pressure pump. In the grouting process, the flow speed of the slurry, the deformation condition of the foundation soil body and the like need to be monitored so as to ensure the grouting quality.
Slurry consolidation: after grouting is completed, the slurry needs to be fully solidified in the foundation soil body. This process typically takes hours to days, depending on the nature of the grouting material and the nature of the foundation soil.
And (3) later-stage observation: in order to ensure the safety and stability of the foundation, it is necessary to observe and manage the foundation for a long period of time after grouting reinforcement is completed. This includes periodically checking the displacement and settlement of the foundation soil, and periodically performing strength test of the foundation soil, etc. If abnormal conditions are found, timely measures are needed to be taken for adjustment.
In the later observation step, the grouting reinforcement effect is evaluated mainly through field measurement and calculation of professionals, so that the problems of high labor cost, low efficiency and low accuracy can exist, and the method can only evaluate after the grouting reinforcement and consolidation process is completed, so that the consolidation process or effect is difficult to evaluate from the soil body change condition in the grouting reinforcement process and the consolidation process.
Therefore, the invention provides a grouting reinforcement video identification method for a soft-flow plastic silt powdery clay stratum.
Disclosure of Invention
The invention provides a method for identifying grouting reinforcement videos of a soft-flow-plastic silt-matter glutinous clay stratum, which is used for efficiently and accurately evaluating grouting reinforcement effects of the soft-flow-plastic silt-matter glutinous clay stratum from the condition of soil changes in the grouting reinforcement process and the consolidation process through identification and analysis of a monitoring video of the grouting reinforcement process of the soft-flow-plastic silt-matter glutinous clay stratum and a monitoring video of the consolidation process.
The invention provides a grouting reinforcement video identification method for a soft-flow plastic silt powdery clay stratum, which comprises the following steps:
S1: acquiring grouting reinforcement monitoring videos of a grouting reinforcement process of a soft fluid plastic silt powder clay stratum of a target monitoring foundation and consolidation monitoring videos of the soft fluid plastic silt powder clay stratum in a consolidation process;
S2: extracting a foundation frame area in each video frame in the grouting reinforcement monitoring video, and analyzing the land deformation of the target monitoring foundation in the grouting reinforcement process based on the size and the frame displacement of all the foundation frame areas in the grouting reinforcement monitoring video;
S3: extracting a foundation frame area in each video frame in the consolidation monitoring video, and analyzing land settlement of a target monitoring foundation in the consolidation process based on the size and the frame-to-frame displacement of all the foundation frame areas in the consolidation monitoring video;
S4: and determining the grouting reinforcement effect evaluation value of the target monitoring foundation based on the land deformation and the corresponding weight of the target monitoring foundation in the grouting reinforcement process and the land settlement and the corresponding weight in the consolidation process.
Preferably, S1: the method for acquiring grouting reinforcement monitoring videos of a soft flow plastic silt powder clay stratum grouting reinforcement process of a target monitoring foundation and consolidation monitoring videos in a consolidation process comprises the following steps:
s101: acquiring a full-time monitoring video of a target monitoring foundation based on a camera, wherein the camera is arranged at a position outside a monitoring range of the target monitoring foundation, and the number of pixels in a video frame shot by the camera needs to reach a preset pixel number threshold;
s102: performing object recognition and action recognition on the full-time monitoring video to obtain object and action recognition results;
s103: and (3) dividing grouting reinforcement monitoring videos of the grouting reinforcement process of the soft fluid plastic silt powdery clay stratum of the target monitoring foundation and consolidation monitoring videos of the consolidation process in the full-time monitoring videos based on object recognition and action recognition results.
Preferably, S102: object recognition and action recognition are carried out on the full-time monitoring video to obtain object and action recognition results, wherein the method comprises the following steps:
S1021: based on the occurrence continuity of any universal object in the full-time monitoring video, primarily removing video frames in the full-time monitoring video to obtain at least one filtered video frame sequence;
S1022: and sequentially identifying the first filtering video frame sequence based on the grouting reinforcement object identification depth model and the grouting reinforcement action identification model, and marking the identification result on the first filtering video frame sequence to obtain an object and action identification result.
Preferably, S103: based on object recognition and action recognition results, a grouting reinforcement monitoring video of a soft flow plastic silt powder clay stratum grouting reinforcement process of a target monitoring foundation and a consolidation monitoring video of a consolidation process are divided in a full-time monitoring video, and the method comprises the following steps:
Based on object recognition and action recognition results, summarizing all video frames which are recognized to contain grouting reinforcement objects and grouting reinforcement actions in the full-time monitoring video, and taking the video frames as grouting reinforcement video frame groups;
Based on the frame sequence distribution characteristics of the grouting reinforcement video frame group in the full-time monitoring video, the grouting reinforcement monitoring video of the grouting reinforcement process of the soft-flow plastic silt powder clay stratum of the target monitoring foundation and the consolidation monitoring video of the consolidation process are divided in the full-time monitoring video.
Preferably, based on the frame sequence distribution characteristics of the grouting reinforcement video frame group in the full-time monitoring video, the grouting reinforcement monitoring video of the grouting reinforcement process of the soft-flow plastic silt matter clay stratum of the target monitoring foundation and the consolidation monitoring video of the consolidation process are divided in the full-time monitoring video, and the method comprises the following steps:
Determining all continuous frame sequences in the grouting reinforcement video frame group based on all grouting reinforcement video frames in the grouting reinforcement video frame group and the frame number in the full-time monitoring video, and determining the ordering positions of all continuous frame sequences in the grouting reinforcement video frame group in the full-time monitoring video;
Determining all adjacent continuous frame sequences based on the ordering positions of all the continuous frame sequences in the full-time surveillance video, and determining the number of interval video frames between the adjacent continuous frame sequences;
When the total number of frames in at least one continuous frame sequence existing in the adjacent continuous frame sequences is smaller than the number of the corresponding interval video frames, the position between the corresponding adjacent continuous frame sequences is regarded as a virtual breakpoint position;
and (3) dividing grouting reinforcement monitoring videos of the grouting reinforcement process of the soft fluid plastic silt powder clay stratum of the target monitoring foundation and consolidation monitoring videos of the consolidation process in the full-time monitoring videos based on all virtual breakpoint positions.
Preferably, based on all virtual breakpoint positions, a grouting reinforcement monitoring video of a grouting reinforcement process of a soft-flow plastic silt powdery clay stratum of a target monitoring foundation and a consolidation monitoring video of a consolidation process are divided in a full-time monitoring video, and the method comprises the following steps:
Determining the number of video frames before a single virtual breakpoint position in the grouting reinforcement video frame group, wherein the number of video frames is used as the number of left video frames corresponding to the virtual breakpoint position, and simultaneously determining the number of video frames after the virtual breakpoint position in the grouting reinforcement video frame group, and the number of right video frames corresponding to the virtual breakpoint position;
Judging whether the number of video frames in at least one virtual breakpoint position is greater than the corresponding left side video frame number and/or the corresponding right side video frame number;
If yes, the corresponding virtual breakpoint position is taken as a true breakpoint position, each video frame sequence in all true breakpoint positions in the grouting reinforcement video frame group and each video frame sequence in the video frame sequence with the preset length after the grouting reinforcement video frame group is taken as a solidification monitoring video of the target monitoring base in the solidification process, and each video frame sequence in the grouting reinforcement video frame group except for the video frame sequences covered by all true breakpoint positions is taken as a grouting reinforcement monitoring video of the grouting reinforcement process of the soft flow plastic silt clay stratum of the target monitoring base;
Otherwise, the video frame sequence covered by the grouting reinforcement video frame group is used as a grouting reinforcement monitoring video of the grouting reinforcement process of the soft-flow plastic silt powdery clay stratum of the target monitoring foundation, and the video frame sequence with the preset length after the grouting reinforcement monitoring video is used as a consolidation monitoring video of the target monitoring foundation in the consolidation process.
Preferably, based on the size and inter-frame displacement of all foundation frame areas in the grouting reinforcement monitoring video, analyzing the land deformation of the target monitoring foundation in the grouting reinforcement process includes:
Determining the size of all foundation frame areas in the grouting reinforcement monitoring video;
Determining the physical center position of each foundation frame area in the grouting reinforcement monitoring video, and regarding the displacement between the physical center positions of adjacent foundation frame areas in the grouting reinforcement monitoring video as the inter-frame displacement of all foundation frame areas in the grouting reinforcement monitoring video;
And inputting the size and the frame-to-frame displacement of all foundation frame areas in the grouting reinforcement monitoring video into a preset land deformation analysis model to obtain the land deformation of the target monitoring foundation in the grouting reinforcement process.
Preferably, the analyzing the land settlement of the target monitoring foundation in the consolidation process based on the size and the inter-frame displacement of all the foundation frame areas in the consolidation monitoring video comprises:
Determining the size of all foundation frame areas in the consolidation monitoring video;
Determining the physical center position of each foundation frame area in the consolidation monitoring video, and taking the displacement between the physical center positions of adjacent foundation frame areas in the consolidation monitoring video as the inter-frame displacement of all foundation frame areas in the consolidation monitoring video;
And inputting the size and the frame-to-frame displacement of all foundation frame areas in the consolidation monitoring video into a preset land settlement analysis model to obtain the land settlement of the target monitoring foundation in the consolidation process.
Compared with the prior art, the invention has the following beneficial effects: by means of identification and analysis of the monitoring video of the grouting reinforcement process and the monitoring video of the consolidation process of the soft-flow plastic silt clay stratum, efficient and high-accuracy evaluation of the grouting reinforcement effect of the soft-flow plastic silt clay stratum is achieved from the soil body change condition in the grouting reinforcement process and the consolidation process.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objects and other advantages of the application may be realized and obtained by means of the instrumentalities particularly pointed out in the specification.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a method for identifying grouting reinforcement video of a soft-fluid-plastic silt powdery clay stratum in an embodiment of the invention;
FIG. 2 is a flowchart showing steps for implementing step S1 in an embodiment of the present invention;
Fig. 3 is a flowchart illustrating steps performed in step S102 in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1
The invention provides a method for identifying grouting reinforcement video of a soft-flow plastic silt powdery clay stratum, which comprises the following steps of:
S1: acquiring grouting reinforcement monitoring videos of a grouting reinforcement process of a soft fluid plastic silt powder clay stratum of a target monitoring foundation and consolidation monitoring videos of the soft fluid plastic silt powder clay stratum in a consolidation process;
S2: extracting a foundation frame area in each video frame in the grouting reinforcement monitoring video, and analyzing the land deformation of the target monitoring foundation in the grouting reinforcement process based on the size and the frame displacement of all the foundation frame areas in the grouting reinforcement monitoring video;
S3: extracting a foundation frame area in each video frame in the consolidation monitoring video, and analyzing land settlement of a target monitoring foundation in the consolidation process based on the size and the frame-to-frame displacement of all the foundation frame areas in the consolidation monitoring video;
S4: and determining the grouting reinforcement effect evaluation value of the target monitoring foundation based on the land deformation and the corresponding weight of the target monitoring foundation in the grouting reinforcement process and the land settlement and the corresponding weight in the consolidation process.
In this embodiment, the target monitoring foundation is a foundation which needs to be monitored and identified by using the grouting reinforcement video identification method of the soft fluid plastic silt powdery clay stratum in this embodiment.
In this embodiment, the grouting reinforcement process of the soft-fluid-plastic muddy silty clay stratum is the grouting reinforcement process of the soft-fluid-plastic muddy silty clay stratum in the target monitoring foundation.
In the embodiment, the grouting reinforcement monitoring video is a monitoring video of the whole grouting reinforcement process of a soft fluid plastic silt clay stratum recorded with a target monitoring foundation.
In the embodiment, the consolidation process is a process of fully consolidating slurry in a foundation soil body after grouting and reinforcing a soft fluid plastic silt powdery clay stratum of a target monitoring foundation.
In the embodiment, the consolidation monitoring video is a monitoring video of the whole consolidation process after the soft fluid plastic silt powdery clay stratum with the target monitoring foundation is grouting and reinforced.
In this embodiment, the foundation frame area is a frame area representing the appearance of the foundation, for example, in the grouting reinforcement monitor video and the video frame in the consolidation monitor video: foundation surfaces, etc.
In this embodiment, the size is the size of the foundation frame area.
In this embodiment, the inter-frame displacement is a displacement generated in the adjacent video frame by the foundation soil body corresponding to the foundation frame area.
In this embodiment, the deformation of the land of the foundation during grouting reinforcement is a value of the deformation of the land of the foundation, for example: the size of the deformation area of the foundation surface and the elevation of the foundation surface.
In this embodiment, the land settlement amount of the target monitoring foundation in the consolidation process is the settlement height of the soil mass of the target monitoring foundation generated in the consolidation process.
In this embodiment, the weight of the land deformation amount and the weight of the land settlement amount are both preset, and the sum of the weights is 1, for example, the weight of the land deformation amount and the weight of the land settlement amount may be 0.5.
In this embodiment, based on the land deformation and the corresponding weight of the target monitoring base in the grouting reinforcement process, and the land settlement and the corresponding weight in the consolidation process, the grouting reinforcement effect evaluation value of the target monitoring base is determined, and is:
Taking the difference value of the land topography variable and the standard land topography variable and the ratio of the standard land topography variable as a first evaluation value;
taking the difference between the land settlement amount and the standard land settlement amount and the ratio of the standard land settlement amount as a second evaluation value;
Taking the product of the first evaluation value and the land topography variable and the product of the second evaluation value and the land settlement amount as the evaluation value of the grouting reinforcement effect of the target monitoring foundation.
The beneficial effects of the technology are as follows: by means of identification and analysis of the monitoring video of the grouting reinforcement process and the monitoring video of the consolidation process of the soft-flow plastic silt clay stratum, efficient and high-accuracy evaluation of the grouting reinforcement effect of the soft-flow plastic silt clay stratum is achieved from the soil body change condition in the grouting reinforcement process and the consolidation process.
Example 2
Based on example 1, S1: acquiring grouting reinforcement monitoring videos of a grouting reinforcement process of a soft-flow plastic silt clay stratum of a target monitoring foundation and consolidation monitoring videos of the consolidation process, referring to fig. 2, comprising:
S101: acquiring a full-time monitoring video of a target monitoring foundation based on a camera, wherein the camera is arranged at a (random) position outside the monitoring range of the target monitoring foundation, and the number of pixels in a video frame shot by the camera needs to reach a preset pixel number threshold;
s102: performing object recognition and action recognition on the full-time monitoring video to obtain object and action recognition results;
s103: and (3) dividing grouting reinforcement monitoring videos of the grouting reinforcement process of the soft fluid plastic silt powdery clay stratum of the target monitoring foundation and consolidation monitoring videos of the consolidation process in the full-time monitoring videos based on object recognition and action recognition results.
In this embodiment, the full-time monitoring video is a monitoring video of a foundation monitored by an online monitoring target of the camera device for 24 hours.
In the embodiment, the monitoring range is the geographical range which needs to be detected by the target monitoring foundation and is consistent with the soil range which can be stabilized by grouting reinforcement.
In this embodiment, the number of pixels in the video frame is the total number of all pixels contained in the video frame.
In this embodiment, the preset pixel number threshold is a preset minimum number that needs to be reached by the number of pixels included in the video frame acquired by the image capturing apparatus.
In this embodiment, the object recognition and motion recognition is a process of recognizing a video frame containing a grouting reinforcement object and/or a grouting reinforcement motion in the full-time surveillance video.
In this embodiment, the object and the action recognition result are video frames marked with a grouting reinforcement object and/or a grouting reinforcement action, where the grouting reinforcement object is an equipment object or an operator object involved in a grouting reinforcement process, and the grouting reinforcement action is an action generated by a grouting reinforcement equipment or an action generated by a grouting reinforcement operator.
The beneficial effects of the technology are as follows: the full-time monitoring video of the target monitoring foundation is obtained, and the grouting reinforcement video and the consolidation monitoring video are accurately extracted from the full-time monitoring video through the object identification and the action identification results of the full-time monitoring video.
Example 3
Based on example 2, S102: object recognition and action recognition are performed on the full-time surveillance video, and object and action recognition results are obtained, and referring to fig. 3, the method includes:
S1021: based on the occurrence continuity of any universal object in the full-time monitoring video, primarily removing video frames in the full-time monitoring video to obtain at least one filtered video frame sequence;
S1022: and sequentially identifying the first filtering video frame sequence based on the grouting reinforcement object identification depth model and the grouting reinforcement action identification model, and marking the identification result on the first filtering video frame sequence to obtain an object and action identification result.
In this embodiment, a generic object is any object that can be photographed by an image pickup device, for example: objects such as biological objects or static objects which appear on the target monitoring foundation.
In this embodiment, the occurrence continuity is continuity of video frames in which a pervasive object appears in the full-time surveillance video.
In this embodiment, the filtered video frame sequence is a video frame sequence obtained after preliminary removal of video frames in the full-time surveillance video.
In this embodiment, the grouting reinforcement object recognition depth model is a depth learning algorithm, and uses a large number of video frames marked with different grouting reinforcement objects as training samples, and the trained depth model can recognize an image area where the grouting reinforcement object is located in the input video frames.
In this embodiment, the grouting reinforcement action recognition model is a depth model trained by using a depth learning algorithm in advance and taking a large number of video frames marked with different grouting reinforcement actions as training samples, and the grouting reinforcement action recognition depth model can recognize an image area forming the grouting reinforcement action in the input video frames.
In this embodiment, based on the grouting reinforcement object recognition depth model and the grouting reinforcement action recognition model, the first filtered video frame sequence is sequentially recognized, and an image area where the grouting reinforcement object is located and an image area where the grouting reinforcement action is formed in the first frame, the second frame, and … … in the first filtered video frame sequence are sequentially recognized.
In this embodiment, the recognition result includes an image area where the grouting reinforcement object included in each video frame in the first filtered video frame sequence is located and an image area where the grouting reinforcement action is formed.
The beneficial effects of the technology are as follows: the preliminary elimination and filtration of the full-time monitoring video are realized based on the occurrence continuity of the universal object, and the identification of the grouting reinforcement object and the action in the first filtering video frame sequence obtained after the preliminary elimination and filtration is further realized, so that the video frames of the grouting reinforcement process determined subsequently are carried out on the basis of the double identification based on the object and the action, and the division accuracy of the grouting reinforcement monitoring video and the consolidation monitoring video which are divided subsequently is ensured.
Example 4
Based on example 3, S1021: based on the occurrence continuity of any universal object in the full-time monitoring video, primarily excluding the video frames in the full-time monitoring video to obtain at least one filtered video frame sequence, comprising:
Extracting a video frame containing at least any pervasive object from the full-time monitoring video based on the pervasive object identification model, and taking the video frame as a pervasive object video frame;
dividing all universal object video frames in the full-time monitoring video into object frame groups of each fuzzy dividing population;
Based on each object frame group of fuzzy partition group, analyzing appearance continuity of appearance objects in the full-schedule monitoring video, and primarily removing video frames in the full-schedule monitoring video to obtain at least one filtered video frame sequence.
In this embodiment, the generic object recognition model is a depth model trained by using a machine learning algorithm in advance and taking a large number of video frames marked with the image areas of different generic objects as training samples, where the generic object recognition model can recognize the image areas of the generic objects included in the input video frames.
In this embodiment, the fuzzy partition population is a partition population that may be included in the generic object, for example: equipment, humans, plants, animals.
In this embodiment, the object frame group is a video frame group formed by all video frames of a pervasive object including a single fuzzy partition group in the full-time surveillance video.
In this embodiment, the appearance object is a pervasive object that appears in the full-time surveillance video.
The beneficial effects of the technology are as follows: based on the universal object recognition model, recognizing video frames containing universal objects in the full-time monitoring video, classifying all kinds of the video frames containing the universal objects based on fuzzy classification populations of the universal objects, and based on object frame groups of different fuzzy classification populations in a classification result, analyzing appearance continuity of appearance objects in the full-time monitoring objects is facilitated, and based on continuous lines of the appearance objects, preliminary elimination and filtration of the full-time monitoring video are achieved.
Example 5
Based on embodiment 4, based on each object frame group of fuzzy partition group, analyzing appearance continuity of appearance objects in the full-schedule monitoring video, and performing preliminary elimination on video frames in the full-schedule monitoring video to obtain at least one filtered video frame sequence, including:
Determining a video frame blurring interval threshold value of each object frame group based on the total number of video frames contained in the object frame groups of each blurring division group;
Determining a frame interval value between every two adjacent video frames in the corresponding object frame group based on the frame number of each video frame in the object frame group of each fuzzy partition group in the full-time surveillance video;
Taking the inter-frame position between adjacent video frames with frame interval values exceeding the corresponding video frame fuzzy interval threshold value in each object frame group as the non-continuous inter-frame position of the corresponding object frame group;
Determining all continuous frame sequences of each object frame group based on all non-continuous inter-frame positions in each object frame group, and screening out continuous frame sequences with the total number of frames exceeding a total number threshold of continuous frames from all continuous frame sequences of each object frame group, wherein the continuous frame sequences are used as excellent continuous frame sequences of corresponding object frame groups;
And preliminarily removing all the video frames in the full-time monitoring video except all the excellent continuous frame sequences of all the object frame groups to obtain at least one filtered video frame sequence.
In this embodiment, the video frame blurring interval threshold is a value that needs to be exceeded by the frame interval value between corresponding adjacent video frames when the inter-frame position of the adjacent video frames in the determination target frame group, which is determined by using the total number of video frames included in the single target frame group, is a discontinuous video frame.
In this embodiment, based on the total number of video frames contained in the object frame groups of each fuzzy partition group, the video frame fuzzy interval threshold value of each object frame group is determined as: the product of the total number of video frames contained in the object frame group of each fuzzy partition group and a preset proportion is taken as a video frame fuzzy interval threshold value of each object frame group, wherein the preset proportion is 0.3 for example.
In this embodiment, the frame interval value is the difference between ordinal numbers of adjacent video frames in the object frame group in the full-time surveillance video.
In this embodiment, all continuous frame sequences of each object frame group are determined based on all inter-discontinuous frame positions in each object frame group, which is:
taking the inter-position of the discontinuous frames as a dividing limit, dividing the frame sequences of all video frames in each object frame group from small to large based on the frame number of the video frames in the full-time monitoring video, obtaining at least two frame sequences, and taking all the frame sequences obtained by dividing as all the continuous frame sequences of the object frame group.
In this embodiment, the total number of consecutive frames threshold is a value that needs to be exceeded by the total number of frames that the consecutive frame sequence contains when it is determined to be a good consecutive frame.
In this embodiment, the total number of frames is the total number of all video frames contained in the sequence of consecutive frames.
The beneficial effects of the technology are as follows: the method and the device have the advantages that the video frame fuzzy interval threshold value of the object frame group is reasonably determined based on the total number of frames of the object frame group, the position between discontinuous frames of the object frame group is determined based on the frame interval number and the video frame fuzzy interval threshold value between adjacent video frames in the object frame group, the further screening of the continuity of the continuous frame sequence is realized based on the total number of frames and the total number of continuity frame threshold value in all continuous frame sequences in the object frame group which are divided by utilizing the position between the discontinuous frames, the excellent continuous frame sequence is obtained, and the preliminary filtering elimination of the full-time monitoring video is realized based on all the excellent continuous frame sequences of all the object frame groups.
Example 6
Based on example 3, S103: based on object recognition and action recognition results, a grouting reinforcement monitoring video of a soft flow plastic silt powder clay stratum grouting reinforcement process of a target monitoring foundation and a consolidation monitoring video of a consolidation process are divided in a full-time monitoring video, and the method comprises the following steps:
Based on object recognition and action recognition results, summarizing all video frames which are recognized to contain grouting reinforcement objects and grouting reinforcement actions in the full-time monitoring video, and taking the video frames as grouting reinforcement video frame groups;
Based on the frame sequence distribution characteristics of the grouting reinforcement video frame group in the full-time monitoring video, the grouting reinforcement monitoring video of the grouting reinforcement process of the soft-flow plastic silt powder clay stratum of the target monitoring foundation and the consolidation monitoring video of the consolidation process are divided in the full-time monitoring video.
In this embodiment, the grouting reinforcement video frame group is a video frame set obtained after all video frames including the grouting reinforcement object and the grouting reinforcement action in the full-time surveillance video are summarized.
In this embodiment, the frame sequence distribution feature is the ordering position of the continuous video frames contained in the grouting reinforcement video frame group in the full-time surveillance video frame.
The beneficial effects of the technology are as follows: based on the double recognition results of object recognition and action recognition, the double recognition of the full-time monitoring video is realized, the fact that the screened grouting reinforcement video frame groups must contain a grouting reinforcement process is ensured, and further, based on the frame sequence distribution characteristics of the grouting reinforcement video frame groups in the full-time monitoring video, the division of the full-time monitoring video is realized, namely the accurate division of the grouting reinforcement monitoring video and the consolidation monitoring video is realized.
Example 7
Based on embodiment 6, based on the frame sequence distribution characteristics of the grouting reinforcement video frame group in the full-time monitoring video, a grouting reinforcement monitoring video of a grouting reinforcement process of a soft-flow plastic silt powdery clay stratum of a target monitoring foundation and a consolidation monitoring video of a consolidation process are divided in the full-time monitoring video, and the method comprises the following steps:
Determining all continuous frame sequences in the grouting reinforcement video frame group based on all grouting reinforcement video frames in the grouting reinforcement video frame group and the frame number in the full-time monitoring video, and determining the ordering positions of all continuous frame sequences in the grouting reinforcement video frame group in the full-time monitoring video;
Determining all adjacent continuous frame sequences based on the ordering positions of all the continuous frame sequences in the full-time surveillance video, and determining the number of interval video frames between the adjacent continuous frame sequences;
When the total number of frames in at least one continuous frame sequence existing in the adjacent continuous frame sequences is smaller than the number of the corresponding interval video frames, the position between the corresponding adjacent continuous frame sequences is regarded as a virtual breakpoint position;
and (3) dividing grouting reinforcement monitoring videos of the grouting reinforcement process of the soft fluid plastic silt powder clay stratum of the target monitoring foundation and consolidation monitoring videos of the consolidation process in the full-time monitoring videos based on all virtual breakpoint positions.
In this embodiment, the number of spaced video frames between adjacent consecutive frame sequences is: the difference between the ordinal number in the full-time surveillance video of the last video frame in the earlier sequence of consecutive video frames in the adjacent sequence of consecutive video frames and the ordinal number in the full-time surveillance video of the first video frame in the later sequence of consecutive video frames.
In this embodiment, when there is at least one consecutive frame sequence in the adjacent consecutive frame sequences in which the total number of frames is smaller than the corresponding number of spaced video frames, then the position between the corresponding adjacent consecutive frame sequences is taken as the virtual breakpoint position, for example:
The total number of frames of the adjacent continuous frame sequences a and B is 50, 150, respectively, and the number of interval video frames between the adjacent continuous frame sequences a and B is 100, and the total number of frames 150 of the continuous video frame sequence B is greater than the corresponding number of interval video frames by 100, and the position between the adjacent continuous frame sequences a and B is regarded as a virtual breakpoint position.
The beneficial effects of the technology are as follows: the determination of the video division position (i.e., break point) is achieved with greater accuracy based on a quantitative comparison between the total number of frames of a single continuous frame sequence in each set of adjacent continuous frame sequences in the grouting reinforcement video frame group and the number of frame intervals therebetween.
Example 8
On the basis of embodiment 7, based on all virtual breakpoint positions, a grouting reinforcement monitoring video of a grouting reinforcement process of a soft-flow plastic silt powder clay stratum of a target monitoring foundation and a consolidation monitoring video of a consolidation process are divided in a full-time monitoring video, and the method comprises the following steps:
Determining the number of video frames before a single virtual breakpoint position in the grouting reinforcement video frame group, wherein the number of video frames is used as the number of left video frames corresponding to the virtual breakpoint position, and simultaneously determining the number of video frames after the virtual breakpoint position in the grouting reinforcement video frame group, and the number of right video frames corresponding to the virtual breakpoint position;
Judging whether the number of video frames in at least one virtual breakpoint position is greater than the corresponding left side video frame number and/or the corresponding right side video frame number;
If yes, the corresponding virtual breakpoint position is taken as a true breakpoint position, each video frame sequence in all true breakpoint positions in the grouting reinforcement video frame group and each video frame sequence in the video frame sequence with the preset length after the grouting reinforcement video frame group is taken as a solidification monitoring video of the target monitoring base in the solidification process, and each video frame sequence in the grouting reinforcement video frame group except for the video frame sequences covered by all true breakpoint positions is taken as a grouting reinforcement monitoring video of the grouting reinforcement process of the soft flow plastic silt clay stratum of the target monitoring base;
Otherwise, the video frame sequence covered by the grouting reinforcement video frame group is used as a grouting reinforcement monitoring video of the grouting reinforcement process of the soft-flow plastic silt powdery clay stratum of the target monitoring foundation, and the video frame sequence with the preset length after the grouting reinforcement monitoring video is used as a consolidation monitoring video of the target monitoring foundation in the consolidation process.
In this embodiment, none of the number of video frames preceding (or following) a single virtual breakpoint position contains the number of video frames of the virtual breakpoint position.
In this embodiment, it is determined whether the number of video frames in the at least one virtual breakpoint position is greater than the corresponding number of left side video frames and/or the corresponding number of right side video frames, i.e.:
When the number of video frames in the virtual breakpoint position is greater than the corresponding number of left video frames, or when the number of video frames in the virtual breakpoint position is greater than the corresponding number of right video frames, or when the number of video frames in the virtual breakpoint position is greater than both the corresponding number of left video frames and the corresponding number of right video frames, then the determination result is yes.
In this embodiment, the virtual breakpoint location may contain one or more video frames, so there is a notion of the number of video frames in the virtual breakpoint location.
In this embodiment, the video frame sequence covered by all the true breakpoint positions is a frame sequence obtained by ordering all the video frames in the true breakpoint positions according to the frame numbers in the full-time surveillance video.
In this embodiment, the sequence of video frames of a preset length after grouting to strengthen the video frame group is: in a full-time surveillance video, a sequence of video frames of a preset length, e.g., 10 9 consecutive video frames, immediately follows the last video frame in the group of grouting-reinforced video frames.
In this embodiment, the sequence of video frames with a preset length after grouting reinforcement of the monitoring video is: in a full-time surveillance video, the last video frame in the grouting reinforcement video is followed by a sequence of video frames of a preset length, for example 10 9 consecutive video frames.
The beneficial effects of the technology are as follows: based on the comparison between the number of video frames at the virtual breakpoint position and the number of frames respectively positioned at the left side and the right side of the grouting reinforcement video frame group, the further screening of the true division positions between the grouting reinforcement video and the consolidation video is realized, and the accuracy of the divided grouting reinforcement video and the consolidation video is further ensured.
Example 9
Based on the embodiment 1, based on the size and the inter-frame displacement of all the foundation frame areas in the grouting reinforcement monitoring video, the land deformation of the target monitoring foundation in the grouting reinforcement process is analyzed, which comprises the following steps:
Determining the size of all foundation frame areas in the grouting reinforcement monitoring video;
Determining the physical center position of each foundation frame area in the grouting reinforcement monitoring video, and regarding the displacement between the physical center positions of adjacent foundation frame areas in the grouting reinforcement monitoring video as the inter-frame displacement of all foundation frame areas in the grouting reinforcement monitoring video;
And inputting the size and the frame-to-frame displacement of all foundation frame areas in the grouting reinforcement monitoring video into a preset land deformation analysis model to obtain the land deformation of the target monitoring foundation in the grouting reinforcement process.
In this embodiment, the physical center position of the base frame area is a two-dimensional coordinate corresponding to the average value of two-dimensional coordinates of all pixel points in the base frame area in the video frame, and the two-dimensional coordinates are corresponding to the position in the video frame.
In this embodiment, the displacement between the physical center positions of adjacent foundation frame areas is: and a displacement from the physical center position of the frame region located earlier in the adjacent foundation frame region to the physical center position of the frame region located later in the foundation town region.
In this embodiment, the preset land deformation analysis model is: the method comprises the steps of pre-constructing a model by taking a machine learning algorithm and a plurality of video segments which are determined to be the soil topography variable of the foundation contained in the corresponding video segment in the time span of the corresponding video segment as training samples, wherein the model is constructed, and the pre-set soil deformation analysis model can analyze the soil topography variable of the foundation contained in the input video in the time span of the input video.
The beneficial effects of the technology are as follows: and accurately analyzing the land deformation of the target monitoring foundation in the grouting reinforcement process by using the size and the inter-frame displacement of all the foundation frame areas of the grouting reinforcement monitoring video and the land deformation analysis model.
Example 10:
based on the embodiment 1, the land settlement amount of the target monitoring foundation in the consolidation process is analyzed based on the size and the inter-frame displacement of all the foundation frame areas in the consolidation monitoring video, which comprises the following steps:
Determining the size of all foundation frame areas in the consolidation monitoring video;
Determining the physical center position of each foundation frame area in the consolidation monitoring video, and taking the displacement between the physical center positions of adjacent foundation frame areas in the consolidation monitoring video as the inter-frame displacement of all foundation frame areas in the consolidation monitoring video;
And inputting the size and the frame-to-frame displacement of all foundation frame areas in the consolidation monitoring video into a preset land settlement analysis model to obtain the land settlement of the target monitoring foundation in the consolidation process.
In this embodiment, the preset land settlement amount analysis model is: the method comprises the steps of taking a plurality of video segments, which are determined to correspond to the land settlement amount of the foundation contained in the video segment in the time span of the corresponding video segment, as training samples by means of a machine learning algorithm in advance, building a model, and analyzing the land settlement amount of the foundation contained in the input video in the time span of the input video by means of the preset land settlement amount analysis model.
The beneficial effects of the technology are as follows: and accurately analyzing the land settlement of the target monitoring foundation in the consolidation process by utilizing the size and the inter-frame displacement of all foundation frame areas of the consolidation monitoring video and a land settlement analysis model.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. A method for identifying grouting reinforcement video of a soft-flow plastic silt clay stratum is characterized by comprising the following steps:
S1: acquiring grouting reinforcement monitoring videos of a grouting reinforcement process of a soft fluid plastic silt powder clay stratum of a target monitoring foundation and consolidation monitoring videos of the soft fluid plastic silt powder clay stratum in a consolidation process;
S2: extracting a foundation frame area in each video frame in the grouting reinforcement monitoring video, and analyzing the land deformation of the target monitoring foundation in the grouting reinforcement process based on the size and the frame displacement of all the foundation frame areas in the grouting reinforcement monitoring video;
S3: extracting a foundation frame area in each video frame in the consolidation monitoring video, and analyzing land settlement of a target monitoring foundation in the consolidation process based on the size and the frame-to-frame displacement of all the foundation frame areas in the consolidation monitoring video;
S4: and determining the grouting reinforcement effect evaluation value of the target monitoring foundation based on the land deformation and the corresponding weight of the target monitoring foundation in the grouting reinforcement process and the land settlement and the corresponding weight in the consolidation process.
2. The method for identifying the grouting reinforcement video of the soft-flow plastic silt powdery clay stratum according to claim 1, wherein the method is characterized by comprising the following steps of: the method for acquiring grouting reinforcement monitoring videos of a soft flow plastic silt powder clay stratum grouting reinforcement process of a target monitoring foundation and consolidation monitoring videos in a consolidation process comprises the following steps:
s101: acquiring a full-time monitoring video of a target monitoring foundation based on a camera, wherein the camera is arranged at a position outside a monitoring range of the target monitoring foundation, and the number of pixels in a video frame shot by the camera needs to reach a preset pixel number threshold;
s102: performing object recognition and action recognition on the full-time monitoring video to obtain object and action recognition results;
s103: and (3) dividing grouting reinforcement monitoring videos of the grouting reinforcement process of the soft fluid plastic silt powdery clay stratum of the target monitoring foundation and consolidation monitoring videos of the consolidation process in the full-time monitoring videos based on object recognition and action recognition results.
3. The method for identifying the grouting reinforcement video of the soft-fluid plastic silt powdery clay stratum according to claim 2, wherein the method is characterized by S102: object recognition and action recognition are carried out on the full-time monitoring video to obtain object and action recognition results, wherein the method comprises the following steps:
S1021: based on the occurrence continuity of any universal object in the full-time monitoring video, primarily removing video frames in the full-time monitoring video to obtain at least one filtered video frame sequence;
S1022: and sequentially identifying the first filtering video frame sequence based on the grouting reinforcement object identification depth model and the grouting reinforcement action identification model, and marking the identification result on the first filtering video frame sequence to obtain an object and action identification result.
4. The method for identifying the grouting reinforcement video of the soft-fluid plastic silt powdery clay stratum according to claim 3, wherein the method is characterized by S103: based on object recognition and action recognition results, a grouting reinforcement monitoring video of a soft flow plastic silt powder clay stratum grouting reinforcement process of a target monitoring foundation and a consolidation monitoring video of a consolidation process are divided in a full-time monitoring video, and the method comprises the following steps:
Based on object recognition and action recognition results, summarizing all video frames which are recognized to contain grouting reinforcement objects and grouting reinforcement actions in the full-time monitoring video, and taking the video frames as grouting reinforcement video frame groups;
Based on the frame sequence distribution characteristics of the grouting reinforcement video frame group in the full-time monitoring video, the grouting reinforcement monitoring video of the grouting reinforcement process of the soft-flow plastic silt powder clay stratum of the target monitoring foundation and the consolidation monitoring video of the consolidation process are divided in the full-time monitoring video.
5. The method for identifying grouting reinforcement video of soft-fluid-plastic muddy silty-clay stratum according to claim 4, wherein the grouting reinforcement monitoring video of the grouting reinforcement process of the soft-fluid-plastic muddy silty-clay stratum of the target monitoring foundation and the consolidation monitoring video of the consolidation process are divided in the full-time monitoring video based on the frame sequence distribution characteristics of the grouting reinforcement video frame groups in the full-time monitoring video, and the method comprises the following steps:
Determining all continuous frame sequences in the grouting reinforcement video frame group based on all grouting reinforcement video frames in the grouting reinforcement video frame group and the frame number in the full-time monitoring video, and determining the ordering positions of all continuous frame sequences in the grouting reinforcement video frame group in the full-time monitoring video;
Determining all adjacent continuous frame sequences based on the ordering positions of all the continuous frame sequences in the full-time surveillance video, and determining the number of interval video frames between the adjacent continuous frame sequences;
When the total number of frames in at least one continuous frame sequence existing in the adjacent continuous frame sequences is smaller than the number of the corresponding interval video frames, the position between the corresponding adjacent continuous frame sequences is regarded as a virtual breakpoint position;
and (3) dividing grouting reinforcement monitoring videos of the grouting reinforcement process of the soft fluid plastic silt powder clay stratum of the target monitoring foundation and consolidation monitoring videos of the consolidation process in the full-time monitoring videos based on all virtual breakpoint positions.
6. The method for identifying grouting reinforcement video of soft-fluid-plastic muddy silty-powder clay formation according to claim 5, wherein the grouting reinforcement monitoring video of the grouting reinforcement process of the soft-fluid-plastic muddy silty-powder clay formation of the target monitoring foundation and the consolidation monitoring video of the consolidation process are divided in the full-time monitoring video based on all virtual breakpoint positions, and the method comprises the following steps:
Determining the number of video frames before a single virtual breakpoint position in the grouting reinforcement video frame group, wherein the number of video frames is used as the number of left video frames corresponding to the virtual breakpoint position, and simultaneously determining the number of video frames after the virtual breakpoint position in the grouting reinforcement video frame group, and the number of right video frames corresponding to the virtual breakpoint position;
Judging whether the number of video frames in at least one virtual breakpoint position is greater than the corresponding left side video frame number and/or the corresponding right side video frame number;
If yes, the corresponding virtual breakpoint position is taken as a true breakpoint position, each video frame sequence in all true breakpoint positions in the grouting reinforcement video frame group and each video frame sequence in the video frame sequence with the preset length after the grouting reinforcement video frame group is taken as a solidification monitoring video of the target monitoring base in the solidification process, and each video frame sequence in the grouting reinforcement video frame group except for the video frame sequences covered by all true breakpoint positions is taken as a grouting reinforcement monitoring video of the grouting reinforcement process of the soft flow plastic silt clay stratum of the target monitoring base;
Otherwise, the video frame sequence covered by the grouting reinforcement video frame group is used as a grouting reinforcement monitoring video of the grouting reinforcement process of the soft-flow plastic silt powdery clay stratum of the target monitoring foundation, and the video frame sequence with the preset length after the grouting reinforcement monitoring video is used as a consolidation monitoring video of the target monitoring foundation in the consolidation process.
7. The method for identifying grouting reinforcement video of soft-flow plastic silt powdery clay stratum according to claim 1, wherein the method for analyzing the land deformation of the target monitoring foundation in the grouting reinforcement process based on the size and the inter-frame displacement of all foundation frame areas in the grouting reinforcement monitoring video comprises the following steps:
Determining the size of all foundation frame areas in the grouting reinforcement monitoring video;
Determining the physical center position of each foundation frame area in the grouting reinforcement monitoring video, and regarding the displacement between the physical center positions of adjacent foundation frame areas in the grouting reinforcement monitoring video as the inter-frame displacement of all foundation frame areas in the grouting reinforcement monitoring video;
And inputting the size and the frame-to-frame displacement of all foundation frame areas in the grouting reinforcement monitoring video into a preset land deformation analysis model to obtain the land deformation of the target monitoring foundation in the grouting reinforcement process.
8. The method for identifying the grouting reinforcement video of the soft-flow plastic silt powdery clay stratum according to claim 1, wherein the step of analyzing the land settlement of the target monitoring foundation in the consolidation process based on the size and the inter-frame displacement of all the foundation frame areas in the consolidation monitoring video comprises the following steps:
Determining the size of all foundation frame areas in the consolidation monitoring video;
Determining the physical center position of each foundation frame area in the consolidation monitoring video, and taking the displacement between the physical center positions of adjacent foundation frame areas in the consolidation monitoring video as the inter-frame displacement of all foundation frame areas in the consolidation monitoring video;
And inputting the size and the frame-to-frame displacement of all foundation frame areas in the consolidation monitoring video into a preset land settlement analysis model to obtain the land settlement of the target monitoring foundation in the consolidation process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410323481.3A CN117935126B (en) | 2024-03-21 | 2024-03-21 | Grouting reinforcement video identification method for soft-flow plastic silt powdery clay stratum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410323481.3A CN117935126B (en) | 2024-03-21 | 2024-03-21 | Grouting reinforcement video identification method for soft-flow plastic silt powdery clay stratum |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117935126A true CN117935126A (en) | 2024-04-26 |
| CN117935126B CN117935126B (en) | 2024-07-02 |
Family
ID=90754132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410323481.3A Active CN117935126B (en) | 2024-03-21 | 2024-03-21 | Grouting reinforcement video identification method for soft-flow plastic silt powdery clay stratum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117935126B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104880544A (en) * | 2015-04-02 | 2015-09-02 | 山东大学 | Method for detecting and evaluating reinforcing effect on weak surrounding rock grouting during underground construction |
| CN108252719A (en) * | 2017-12-29 | 2018-07-06 | 中铁隆工程集团有限公司 | Plastic flow modeling shape red clay layer construction method is worn under a kind of urban shallow tunnel |
| CN111350509A (en) * | 2020-01-21 | 2020-06-30 | 中铁二十二局集团轨道工程有限公司 | Muck improvement and grouting method for sandy gravel stratum tunnel shield construction |
| CN111411971A (en) * | 2020-03-25 | 2020-07-14 | 中铁三局集团有限公司 | Settlement control construction method for water-rich silt stratum shield underpass building group |
| KR102150958B1 (en) * | 2019-07-19 | 2020-09-02 | 정재현 | Grouting method for ground reinforcement using quality control system by standardization |
| CN113089394A (en) * | 2021-03-26 | 2021-07-09 | 西南交通大学 | Mechanical lifting and grouting reinforcement rapid repairing method for supporting layer of double-block ballastless track |
| US20210301660A1 (en) * | 2020-03-25 | 2021-09-30 | Bridge & Tunnel Engineering Company of the Third Engineering Group Co. Ltd. of China Railway | Construction method for making water-rich sand layer shield over cross existing line and underneath cross sewage push pipe at close range |
| CN113605933A (en) * | 2021-07-13 | 2021-11-05 | 山东大学 | Grouting reinforcement method for underground excavation channel of close-distance underpass subway station |
| CN113914294A (en) * | 2021-10-15 | 2022-01-11 | 中国化学工程第十四建设有限公司 | Compaction grouting intelligent system for quicksand geology and construction process thereof |
| CN114607418A (en) * | 2022-03-30 | 2022-06-10 | 北京市市政四建设工程有限责任公司 | Fine deformation control grouting process for deep-buried large-section tunnel |
| CN114779316A (en) * | 2022-06-23 | 2022-07-22 | 中铁大桥科学研究院有限公司 | Tunnel flowing water high-osmotic-pressure grouting intelligent monitoring method and related equipment |
| CN114961790A (en) * | 2022-05-27 | 2022-08-30 | 中南大学 | Shield synchronous grouting construction method and construction effect evaluation method thereof |
| CN115730847A (en) * | 2022-11-21 | 2023-03-03 | 中铁二局第二工程有限公司 | Comprehensive evaluation method for surface grouting reinforcement effect |
| CN115853538A (en) * | 2022-10-26 | 2023-03-28 | 中铁七局集团西安铁路工程有限公司 | Method for forming tenon-and-mortise type pipe sheet tunnel in water-rich sandy silt and muddy clay stratum |
| CN116497830A (en) * | 2023-05-19 | 2023-07-28 | 中建二局第一建筑工程有限公司 | Foundation pit engineering construction method |
-
2024
- 2024-03-21 CN CN202410323481.3A patent/CN117935126B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104880544A (en) * | 2015-04-02 | 2015-09-02 | 山东大学 | Method for detecting and evaluating reinforcing effect on weak surrounding rock grouting during underground construction |
| CN108252719A (en) * | 2017-12-29 | 2018-07-06 | 中铁隆工程集团有限公司 | Plastic flow modeling shape red clay layer construction method is worn under a kind of urban shallow tunnel |
| KR102150958B1 (en) * | 2019-07-19 | 2020-09-02 | 정재현 | Grouting method for ground reinforcement using quality control system by standardization |
| CN111350509A (en) * | 2020-01-21 | 2020-06-30 | 中铁二十二局集团轨道工程有限公司 | Muck improvement and grouting method for sandy gravel stratum tunnel shield construction |
| US20210301660A1 (en) * | 2020-03-25 | 2021-09-30 | Bridge & Tunnel Engineering Company of the Third Engineering Group Co. Ltd. of China Railway | Construction method for making water-rich sand layer shield over cross existing line and underneath cross sewage push pipe at close range |
| CN111411971A (en) * | 2020-03-25 | 2020-07-14 | 中铁三局集团有限公司 | Settlement control construction method for water-rich silt stratum shield underpass building group |
| CN113089394A (en) * | 2021-03-26 | 2021-07-09 | 西南交通大学 | Mechanical lifting and grouting reinforcement rapid repairing method for supporting layer of double-block ballastless track |
| CN113605933A (en) * | 2021-07-13 | 2021-11-05 | 山东大学 | Grouting reinforcement method for underground excavation channel of close-distance underpass subway station |
| CN113914294A (en) * | 2021-10-15 | 2022-01-11 | 中国化学工程第十四建设有限公司 | Compaction grouting intelligent system for quicksand geology and construction process thereof |
| CN114607418A (en) * | 2022-03-30 | 2022-06-10 | 北京市市政四建设工程有限责任公司 | Fine deformation control grouting process for deep-buried large-section tunnel |
| CN114961790A (en) * | 2022-05-27 | 2022-08-30 | 中南大学 | Shield synchronous grouting construction method and construction effect evaluation method thereof |
| CN114779316A (en) * | 2022-06-23 | 2022-07-22 | 中铁大桥科学研究院有限公司 | Tunnel flowing water high-osmotic-pressure grouting intelligent monitoring method and related equipment |
| CN115853538A (en) * | 2022-10-26 | 2023-03-28 | 中铁七局集团西安铁路工程有限公司 | Method for forming tenon-and-mortise type pipe sheet tunnel in water-rich sandy silt and muddy clay stratum |
| CN115730847A (en) * | 2022-11-21 | 2023-03-03 | 中铁二局第二工程有限公司 | Comprehensive evaluation method for surface grouting reinforcement effect |
| CN116497830A (en) * | 2023-05-19 | 2023-07-28 | 中建二局第一建筑工程有限公司 | Foundation pit engineering construction method |
Non-Patent Citations (4)
| Title |
|---|
| PARK J ET AL: "Evaluation of reinforcement effects according to reinforcement type and grouting method", JOURNAL OF THE KOREAN GEO-ENVIRONMENTAL SOCIETY, vol. 20, no. 8, 1 August 2019 (2019-08-01), pages 13 - 20 * |
| 段浩然: "地下工程渗漏监测与注浆技术研究", 中国优秀硕士学位论文全文数据库-工程科技Ⅱ辑, no. 2023, 15 March 2023 (2023-03-15), pages 41 - 60 * |
| 汪乐: "秀宁隧道出口段糜棱岩工程特性及其注浆加固技术研究", 中国优秀硕士学位论文全文数据库-工程科技Ⅱ辑, no. 2011, 15 October 2011 (2011-10-15), pages 93 - 97 * |
| 高军: "高铁隧道IV级V级围岩全断面机械化施工掌子面高压注浆工艺试验研究", 铁道技术监督, vol. 48, no. 01, 15 January 2020 (2020-01-15), pages 50 - 55 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117935126B (en) | 2024-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102509087B (en) | Coal-rock identification method based on image gray level co-occurrence matrixes | |
| CN107943823B (en) | Real-time big data processing platform of digital construction | |
| CN101751669B (en) | Static object detection method and device | |
| Wang et al. | Image analysis applications on assessing static stability and flowability of self-consolidating concrete | |
| CN117935126B (en) | Grouting reinforcement video identification method for soft-flow plastic silt powdery clay stratum | |
| CN104992139B (en) | One kind is based on motion vector and the matched falling rock detection method of circularity | |
| CN115629575A (en) | Method for recommending manual regulation and control strategy after automation of hydraulic support | |
| CN105975990A (en) | Reclaimed soil profile fine expression method | |
| CN111860326A (en) | Building site article movement detection method, device, equipment and storage medium | |
| CN116660263A (en) | Grouting effect evaluation method based on digital image processing | |
| CN116796643A (en) | Surface subsidence monitoring method and device, electronic equipment and storage medium | |
| CN111507988A (en) | Broken rock mass modeling and seepage test method based on digital image processing | |
| CN113808128B (en) | Intelligent compaction whole process visualization control method based on relative coordinate positioning algorithm | |
| CN103048257A (en) | Sandy soil type identification and particle component analysis device | |
| Sannakki et al. | Comparison of different leaf edge detection algorithms using fuzzy mathematical morphology | |
| Hofmann et al. | Creep behaviour and remediation concept for a deep‐seated landslide, Navistal, Tyrol, Austria: Kriechverhalten und Sanierungskonzept einer Großhangbewegung, Navistal, Tirol, Österreich | |
| CN114088054A (en) | Automatic monitoring method for longitudinal differential settlement of underground structure | |
| JP7556745B2 (en) | Rolling Compaction Management System | |
| CN108459019B (en) | Landslide slope body broken stone content detection method and intelligent mobile terminal | |
| CN113326812A (en) | Regional burst regulation and storage treatment drainage system based on internet | |
| CN112964192A (en) | Engineering measurement online calibration method and system based on image video | |
| CN117036611B (en) | Three-dimensional scene construction method and system of non-mine safety monitoring platform | |
| Chen et al. | Deep learning based weak inter-layers segmentation and measurement of rock tunnel face | |
| Garzon-Sabogal et al. | Grain portraits: Quantifying heterogeneity of aggregate layers through image analysis | |
| CN102170522B (en) | Method and device for determining abnormal dither of video camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |