CN117011286A - Sewage pipeline defect image identification method, system, terminal and storage medium - Google Patents
Sewage pipeline defect image identification method, system, terminal and storage medium Download PDFInfo
- Publication number
- CN117011286A CN117011286A CN202311131855.3A CN202311131855A CN117011286A CN 117011286 A CN117011286 A CN 117011286A CN 202311131855 A CN202311131855 A CN 202311131855A CN 117011286 A CN117011286 A CN 117011286A
- Authority
- CN
- China
- Prior art keywords
- defect
- sewage pipeline
- video image
- real
- time video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 380
- 239000010865 sewage Substances 0.000 title claims abstract description 212
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 claims description 85
- 230000007849 functional defect Effects 0.000 claims description 17
- 230000007847 structural defect Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 230000010485 coping Effects 0.000 claims description 13
- 230000002950 deficient Effects 0.000 claims description 11
- 230000009286 beneficial effect Effects 0.000 abstract description 8
- 238000012545 processing Methods 0.000 description 12
- 239000013049 sediment Substances 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000008021 deposition Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000009960 carding Methods 0.000 description 1
- 239000003518 caustics Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application relates to the technical field of image recognition, in particular to a sewage pipeline defect image recognition method, a system, a terminal and a storage medium; the method comprises the following steps: acquiring a real-time video image of a sewage pipeline; inputting the real-time video image into a preset defect learning model; judging whether the sewage pipeline has defects or not based on the real-time video image and the defect learning model; if the sewage pipeline has defects, acquiring defect types based on real-time video images; acquiring a defect grade based on the defect type; based on the defect type and the defect level, a defect countermeasure scheme is generated. The application is beneficial to improving the accuracy of detecting the defects of the sewage pipeline.
Description
Technical Field
The present application relates to the field of image recognition technologies, and in particular, to a method, a system, a terminal, and a storage medium for recognizing a sewage pipeline defect image.
Background
The urban drainage pipeline is an indispensable important infrastructure of a modern city, is a backbone engineering for urban water pollution control and urban water drainage, flood drainage and flood control, is one of important marks for measuring the level of the modern city, and is an important link for improving urban investment environment. In the same way, the investigation, carding and detection management of sewage, wastewater, rainwater and the like (hereinafter referred to as drainage) discharged into urban drainage facilities are performed, so that the urban drainage facilities are guaranteed to be normally maintained and safely operated, the paid use management of the urban drainage facilities is enhanced, and necessary and effective means for improving urban water environment are promoted.
In the related art, when defect investigation is performed on a sewage pipeline, a CCTV pipeline endoscopic television camera detection system is generally used for shooting an internal environment of the sewage pipeline, and a detection personnel analyzes the current state of the sewage pipeline by observing a video file and judges whether the sewage pipeline has defects or not.
In view of the above-mentioned related art, the inventors believe that the judgment of whether or not a defect occurs in a sewage pipeline in the related art requires a manual judgment, and a false judgment phenomenon is liable to occur.
Disclosure of Invention
In order to help to improve accuracy of sewage pipeline defect detection, the application provides a sewage pipeline defect image identification method, a system, a terminal and a storage medium.
The first aspect of the application provides a sewage pipeline defect image identification method, which adopts the following technical scheme:
a sewage conduit defect image recognition method, comprising:
acquiring a real-time video image of a sewage pipeline;
inputting the real-time video image into a preset defect learning model;
judging whether the sewage pipeline has defects or not based on the real-time video image and the defect learning model;
if the sewage pipeline has defects, acquiring defect types based on the real-time video images;
acquiring a defect grade based on the defect type;
based on the defect type and the defect level, a defect countermeasure scheme is generated.
By adopting the technical scheme, the real-time video image is firstly input into the defect learning model, then whether the sewage pipeline has defects is judged, if the defects exist, the defect types and the defect grades are sequentially obtained, corresponding defect coping schemes are formulated according to the defect types and the defect grades, and whether the sewage pipeline has defects is judged by comparing and analyzing a large number of pre-stored video images in the real-time video image and the defect learning model, so that the current state of the sewage pipeline is prevented from being analyzed by adopting manual observation, and whether the sewage pipeline has defects is judged, thereby not only being beneficial to improving the accuracy of detecting the defects of the sewage pipeline, but also being beneficial to improving the working efficiency.
Optionally, the specific step of determining whether the sewage pipeline has a defect based on the real-time video image and the defect learning model includes:
judging whether the sewage pipe is an existing sewage pipe or not;
if the sewage pipe is not the existing sewage pipe, comparing the real-time video image with a preset target video image, and generating a first comparison result;
and judging whether the sewage pipeline has defects or not based on the first comparison result.
By adopting the technical scheme, whether the sewage pipeline is the existing sewage pipeline is judged, if not, the sewage pipeline is indicated to be a newly built sewage pipeline, namely, a history detection record does not exist, so that the real-time video image can only be compared with the preset target video image, whether the sewage pipeline has defects is judged, and when judging whether the sewage pipeline has defects, the actual situation of the sewage pipeline is added, thereby being beneficial to improving the accuracy of detecting the defects of the sewage pipeline.
Optionally, the specific step of determining whether the sewage pipeline has a defect based on the real-time video image and the defect learning model further includes:
if the sewage pipe is the existing sewage pipe, judging whether a history detection record of the sewage pipe exists or not;
if the history detection record does not exist, comparing the real-time video image with the target video image, and generating the first comparison result;
and judging whether the sewage pipeline has defects or not based on the first comparison result.
By adopting the technical scheme, if the sewage pipe is the existing sewage pipe, judging whether the history detection record of the sewage pipe exists, if the history detection record does not exist, the sewage pipe is not detected, or the history detection record is not uploaded after the detection, the real-time video image can still be compared with the target video image, and when judging whether the sewage pipe has defects, the actual situation of the sewage pipe is added, so that the accuracy of detecting the defects of the sewage pipe is improved.
Optionally, the specific step of determining whether the sewage pipeline has a defect based on the real-time video image and the defect learning model further includes:
if the history detection record exists, acquiring a last video image based on the history detection record;
comparing the real-time video image with the last video image and generating a second comparison result;
and judging whether the sewage pipeline has defects or not based on the second comparison result.
Through adopting above-mentioned technical scheme, when having history detection record, obtain last video image through history detection record to compare real-time video image and last video image, thereby obtain the change condition in the sewer line in the current time quantum that last video image corresponds time to, judge whether the sewer line exists the defect according to this change condition, laminate actual conditions more, thereby help improving the accuracy to sewer line defect detection.
Optionally, the method further comprises:
judging whether the sewage pipeline has a history defect or not based on the history detection record;
if the sewage pipeline has the historical defect, acquiring a historical defect type based on the historical defect;
acquiring a key detection area based on the historical defect;
acquiring an important video image based on the historical defect type and the important detection area;
and judging whether the sewage pipeline has defects or not based on the key video images.
By adopting the technical scheme, whether the sewage pipeline has the historical defect is judged firstly, if the historical defect exists, the key monitoring area is obtained according to the historical defect, the key video image is obtained according to the key monitoring area, and then the key video image is combined to judge whether the sewage pipeline has the defect, so that the accuracy of detecting the defect of the sewage pipeline is improved.
Optionally, the method further comprises:
acquiring target geographic position information;
acquiring a target detection item based on the target geographic position information;
acquiring target detection data based on the target detection item;
judging whether the target detection data meets a preset data threshold requirement or not;
and if the target detection data does not meet the data threshold requirement, judging that the sewage pipeline has defects.
By adopting the technical scheme, the target geographic position information is firstly obtained, the target detection item and the target detection data are obtained through the target geographic position information, then whether the defect exists in the sewage pipeline is judged by judging whether the target detection data meet the preset data threshold requirement, and when judging whether the defect exists in the sewage pipeline, the accuracy of detecting the defect of the sewage pipeline is improved by combining the geographic position of the sewage pipeline and the actual condition of the geographic position.
Optionally, the defect types include structural defects and functional defects; the specific steps of generating a defect countermeasure scheme based on the defect type and the defect grade include:
judging the defect type as the structural defect or the functional defect;
if the defect type is the structural defect, judging whether the defect grade exceeds a preset defect grade threshold;
if the defect level exceeds the defect level threshold, generating a first scheme as a defect handling scheme;
if the defect level does not exceed the defect level threshold, generating a second scheme as a defect coping scheme;
if the defect type is the functional defect, judging whether the defect grade exceeds a preset defect grade threshold;
if the defect level exceeds the defect level threshold, generating a third scheme as a defect coping scheme;
and if the defect level does not exceed the defect level threshold, generating a fourth scheme as a defect coping scheme.
By adopting the technical scheme, the defect type is firstly judged to be structural defect or functional defect, then whether the defect grade exceeds a preset defect grade threshold value is judged according to different defect grades corresponding to different defect types, and finally a corresponding defect corresponding scheme is generated according to different results, so that the accuracy of detecting the defects of the sewage pipeline is improved.
In a second aspect, the application also discloses a sewage pipeline defect image recognition system, which adopts the following technical scheme:
a sewer line defect image identification system, comprising:
the first acquisition module is used for acquiring real-time video images of the sewage pipeline;
the input module is used for inputting the real-time video image into a preset defect learning model;
the judging module is used for judging whether the sewage pipeline has defects or not based on the real-time video image and the defect learning model;
the second acquisition module is used for acquiring the defect type based on the real-time video image if the sewage pipeline has the defect;
a third obtaining module, configured to obtain a defect level based on the defect type;
and a fourth acquisition module, configured to generate a defect coping scheme based on the defect type and the defect grade.
By adopting the technical scheme, the real-time video image is firstly input into the defect learning model, then whether the sewage pipeline has defects is judged, if the defects exist, the defect types and the defect grades are sequentially obtained, corresponding defect coping schemes are formulated according to the defect types and the defect grades, and whether the sewage pipeline has defects is judged by comparing and analyzing a large number of pre-stored video images in the real-time video image and the defect learning model, so that the current state of the sewage pipeline is prevented from being analyzed by adopting manual observation, and whether the sewage pipeline has defects is judged, thereby not only being beneficial to improving the accuracy of detecting the defects of the sewage pipeline, but also being beneficial to improving the working efficiency.
In a third aspect, the present application provides a computer apparatus, which adopts the following technical scheme:
an intelligent terminal comprising a memory, a processor, wherein the memory is configured to store a computer program capable of running on the processor, and the processor, when loaded with the computer program, performs the method of the first aspect.
By adopting the technical scheme, the computer program is generated based on the method of the first aspect and is stored in the memory to be loaded and executed by the processor, so that the intelligent terminal is manufactured according to the memory and the processor, and the intelligent terminal is convenient for a user to use.
In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:
a computer readable storage medium having stored therein a computer program which, when loaded by a processor, performs the method of the first aspect.
By adopting the technical scheme, the method based on the first aspect generates the computer program, and stores the computer program in the computer readable storage medium to be loaded and executed by the processor, and the computer program is convenient to read and store through the computer readable storage medium.
In summary, the application has the following beneficial technical effects:
firstly inputting a real-time video image into a defect learning model, judging whether the sewage pipeline has defects, if so, acquiring the defect types and the defect grades successively, and formulating corresponding defect coping schemes according to the defect types and the defect grades, and judging whether the sewage pipeline has defects by comparing and analyzing a large number of pre-stored video images in the real-time video image and the defect learning model, thereby avoiding the mode of manually observing the real-time video image, analyzing the current state of the sewage pipeline and judging whether the sewage pipeline has defects, and being beneficial to improving the accuracy of detecting the defects of the sewage pipeline and improving the working efficiency.
Drawings
FIG. 1 is a main flow chart of a defective image recognition method for a sewage pipeline according to an embodiment of the present application;
fig. 2 is a specific step flowchart of steps S201 to S203;
fig. 3 is a specific step flowchart of steps S301 to S303;
fig. 4 is a specific step flowchart of steps S401 to S403;
fig. 5 is a step flowchart of steps S501 to S505;
fig. 6 is a step flowchart of steps S601 to S605;
fig. 7 is a step flowchart of steps S701 to S707;
fig. 8 is a block diagram of a sewage pipeline defect image recognition system according to an embodiment of the present application.
Reference numerals illustrate:
1. a first acquisition module; 2. an input module; 3. a judging module; 4. a second acquisition module; 5. a third acquisition module; 6. and a fourth acquisition module.
Detailed Description
In a first aspect, the application discloses a method for identifying defective images of a sewer line.
Referring to fig. 1, a sewage pipeline defect image recognition method includes steps S101 to S106:
step S101 acquires a real-time video image of the sewer line.
Specifically, in this embodiment, a CCTV pipeline endoscope is used to obtain real-time video images.
Step S102: and inputting the real-time video image into a preset defect learning model.
Specifically, in this embodiment, a large number of defective video images of the sewer line are pre-stored in a preset defect learning model, and are used to analyze and identify whether the sewer line corresponding to the video images input into the defect learning model has defects.
Step S103: and judging whether the sewage pipeline has defects or not based on the real-time video image and the defect learning model.
Specifically, in this embodiment, the real-time video image is compared with the video image in the defect learning model to determine whether the sewage pipeline has a defect.
Step S104: if the sewage pipeline has defects, the defect type is acquired based on the real-time video image.
Specifically, in this embodiment, the defect types include functional defects including deposition, scaling, obstructions, roots, water-holding, dam heads, and scum, and structural defects including cracking, deformation, dislocation, leakage, corrosion, rubber ring detachment, branch pipe darkening, and foreign matter intrusion.
Specifically, in this embodiment, if the sewage pipeline has no defect, no operation is performed.
Step S105: based on the defect type, a defect grade is obtained.
Specifically, in this embodiment, the defect levels may be classified according to the defect types, for example, the defect levels may be equally divided into 1 to 4 levels, or the functional defects may be divided into 1 to 3 levels, and the structural defects may be divided into 1 to 4 levels.
Step S106: based on the defect type and the defect level, a defect countermeasure scheme is generated.
Specifically, in this embodiment, corresponding defect countermeasures are formulated according to different defect types and different defect grades, for example, a small amount of sediment is deposited in the sewage pipeline, the defect grade is determined to be 1 grade, and normal use of the sewage pipeline is not affected, so that the sewage pipeline can be not disposed of; the sediment is deposited in a small amount in the sewage pipeline, the defect grade is judged to be grade 2, the normal use of the sewage pipeline is not affected, the sewage pipeline can be temporarily not treated, but a treatment plan is required to be formulated and the sewage pipeline is treated regularly; the sediment deposition of the medium amount of sediment exists in the sewage pipeline, the defect grade is judged to be grade 3, and the normal use of the sewage pipeline is affected, so that a treatment plan can be formulated and the sewage pipeline can be treated as soon as possible; a large amount of sediment is deposited in the sewage pipeline, the defect grade is judged to be grade 4, the normal use of the sewage pipeline is seriously influenced, and then a treatment plan can be formulated and a treatment is carried out immediately.
According to the sewage pipeline defect image recognition method provided by the embodiment, the real-time video image is input into the defect learning model, whether the sewage pipeline has defects or not is judged, if the defects exist, the defect types and the defect grades are acquired successively, corresponding defect response schemes are formulated according to the defect types and the defect grades, and whether the sewage pipeline has defects or not is judged by comparing and analyzing a large number of pre-stored video images in the real-time video image and the defect learning model, so that the current state of the sewage pipeline is analyzed and whether the sewage pipeline has defects or not is avoided by adopting a mode of manually observing the real-time video image, the defect detection accuracy of the sewage pipeline is improved, and the work efficiency is improved.
Referring to fig. 2, in one implementation manner of the present embodiment, step S103, based on the real-time video image and the defect learning model, the specific steps of determining whether the sewage pipeline has a defect include steps S201 to S203:
step S201: judging whether the sewage pipe is the existing sewage pipe or not.
Specifically, in the present embodiment, the sewage pipes include an existing sewage pipe which is a sewage pipe that has been put into use, and a newly built sewage pipe which is a sewage pipe that has not been put into use formally.
Step S202: if the sewage pipe is not the existing sewage pipe, comparing the real-time video image with a preset target video image, and generating a first comparison result.
Specifically, in this embodiment, the target video image is a video image of the sewage pipe just built in an ideal state; the first comparison result contains distinguishing factors of the real-time video image and the target video image.
Step S203: and judging whether the sewage pipeline has defects or not based on the first comparison result.
Specifically, in this embodiment, a distinguishing factor in the first comparison result is analyzed to determine whether the distinguishing factor meets a condition for forming a defect of the sewage pipe, thereby determining whether the sewage pipe has a defect. Specifically, in this embodiment, the condition constituting the sewage pipe defect may be set according to the relevant sewage pipe defect standard.
According to the sewage pipeline defect image recognition method provided by the embodiment, whether the sewage pipeline is the existing sewage pipeline is judged, if not, the sewage pipeline is indicated to be a newly built sewage pipeline, namely, a history detection record does not exist, so that only a real-time video image can be compared with a preset target video image, whether the sewage pipeline has defects is judged, and when judging whether the sewage pipeline has defects, the actual situation of the sewage pipeline is added, so that the accuracy of detecting the defects of the sewage pipeline is improved.
Referring to fig. 3, in one implementation manner of the present embodiment, step S103, based on the real-time video image and the defect learning model, the specific step of determining whether the sewage pipeline has a defect further includes steps S301 to S303:
step S301: if the sewage pipe is an existing sewage pipe, judging whether a history detection record of the sewage pipe exists.
Specifically, in this embodiment, the history detection record is a detection record before the sewage pipe is detected this time.
Step S302: and if the history detection record does not exist, comparing the real-time video image with the target video image, and generating a first comparison result.
Specifically, in this embodiment, this step is consistent with the manner adopted in step S202.
Step S303: and judging whether the sewage pipeline has defects or not based on the first comparison result.
Specifically, in the present embodiment, this step is identical to the manner adopted in step S203.
According to the sewage pipeline defect image recognition method provided by the embodiment, if the sewage pipeline is the existing sewage pipeline, whether the history detection record of the sewage pipeline exists is judged, if the history detection record does not exist, the sewage pipeline is not detected, or the history detection record is not uploaded after the detection, the real-time video image can still be compared with the target video image, and when judging whether the sewage pipeline has defects, the actual situation of the sewage pipeline is added, so that the accuracy of detecting the defects of the sewage pipeline is improved.
Referring to fig. 4, in one implementation manner of the present embodiment, step S103, based on the real-time video image and the defect learning model, the specific step of determining whether the sewage pipeline has a defect further includes steps S401 to S403:
step S401: and if the history detection record exists, acquiring the last video image based on the history detection record.
Specifically, in this embodiment, the last video image refers to a video image obtained after the last detection of the sewage pipeline and repair if a defect exists.
Step S402: and comparing the real-time video image with the last video image, and generating a second comparison result.
Specifically, in this embodiment, the second comparison result includes a distinguishing factor between the real-time video image and the last video image.
Step S403: and judging whether the sewage pipeline has defects or not based on the second comparison result.
Specifically, in this embodiment, the distinguishing factor in the second comparison result is analyzed to determine whether the distinguishing factor meets the condition for forming a defect of the sewage pipe, thereby determining whether the sewage pipe has a defect.
According to the sewage pipeline defect image identification method, when the history detection record exists, the last video image is obtained through the history detection record, and the real-time video image is compared with the last video image, so that the change condition of the time corresponding to the last video image in the sewage pipeline in the current time period is obtained, whether the defect exists in the sewage pipeline is judged according to the change condition, the actual condition is attached to the sewage pipeline, and the accuracy of detecting the defect of the sewage pipeline is improved.
Referring to fig. 5, in one implementation manner of the present embodiment, steps S501 to S505 are further included:
step S501: and judging whether the sewage pipeline has the history defect or not based on the history detection record.
Specifically, in this embodiment, the history defect is a defect detected in the history inspection record.
Step S502: if the sewage pipeline has the historical defect, acquiring the type of the historical defect based on the historical defect.
Specifically, in this embodiment, the type of the history defect is the type of the history defect.
Step S503: and acquiring a key detection area based on the historical defect.
Specifically, in this embodiment, the key detection area includes an area where a history defect occurs, or an area that is set by itself according to the actual situation of the sewage pipeline, for example, an interface, etc.
Step S504: and acquiring the key video image based on the historical defect type and the key detection area.
Specifically, in this embodiment, the key video image is a real-time video image captured from the key detection area; when the history defect exists, the sewage pipeline at the position is subjected to key detection according to the type of the history defect and the position where the history defect exists, namely a key detection area, for example, when the key detection area exists, the travelling speed of the CCTV pipeline endoscopic television camera shooting is controlled, or the reciprocating camera shooting is performed on the key detection area.
Step S505: and judging whether the sewage pipeline has defects or not based on the key video images.
Specifically, in this embodiment, the key video image and the last video image are compared, and whether the sewage pipeline has a defect is determined.
According to the sewage pipeline defect image recognition method provided by the embodiment, whether the sewage pipeline has the historical defect is judged firstly, if the sewage pipeline has the historical defect, the key monitoring area is obtained according to the historical defect, the key video image is obtained according to the key detection area, and then the key video image is combined to judge whether the sewage pipeline has the defect, so that the accuracy of detecting the defect of the sewage pipeline is improved.
Referring to fig. 6, in one implementation manner of the present embodiment, step S601 to step S605 are further included:
step S601: and obtaining the target geographic position information.
Specifically, in this embodiment, the target geographical location information includes a specific location of the detected sewer pipe, and some specific situations around the location, for example, factory situations around the detected sewer pipe, whether the discharged sewage has substances with stronger corrosiveness or adhesiveness, whether the detected sewer pipe has substances with more sediment or trees around the detected sewer pipe, which easily cause the sewer pipe to be blocked, and whether the detected sewer pipe has a foundation engineering around the sewer pipe, which easily causes the sewer pipe to be broken, and so on.
Step S602: and acquiring a target detection item based on the target geographic position information.
Specifically, in this embodiment, the target detection item is a detection item that is set by itself according to the target geographical location information, for example, when a plant that discharges a more corrosive substance is located near the sewage pipeline, the target detection item may be a corrosive detection, and when a capital construction is located near the sewage pipeline, the target detection item may be a pressure detection or a water seepage detection.
Step S603: based on the target detection item, target detection data is acquired.
Specifically, in this embodiment, the target detection data is data obtained after the detection of the target detection item is completed, for example, ph value or pressure value.
Step S604: and judging whether the target detection data meets the preset data threshold requirement.
Specifically, in this embodiment, the data threshold is required to be set according to the corresponding target detection data, and the specific standard refers to the relevant acceptance or detection standard.
Step S605: and if the target detection data does not meet the data threshold requirement, judging that the sewage pipeline has defects.
Specifically, in this embodiment, if the target detection data meets the data threshold requirement, factors such as image recognition are combined to comprehensively determine whether the sewage pipeline has a defect.
According to the sewage pipeline defect image identification method, the target geographic position information is firstly obtained, the target detection item and the target detection data are obtained through the target geographic position information, whether the defect exists in the sewage pipeline is judged by judging whether the target detection data meet the preset data threshold requirement, and when judging whether the defect exists in the sewage pipeline, the accuracy of detecting the defect of the sewage pipeline is improved by combining the geographic position of the sewage pipeline and the actual condition of the geographic position.
Referring to fig. 7, in one implementation of the present embodiment, step S106 includes specific steps of generating a defect countermeasure scheme based on the defect type and the defect level, including steps S701 to S707:
step S701: judging the defect type as structural defect or functional defect.
Specifically, in the present embodiment, the defect types include structural defects and functional defects.
Step S702: if the defect type is structural defect, judging whether the defect grade exceeds a preset defect grade threshold.
Specifically, in this embodiment, when the defect type is a structural defect, the defect level threshold may be 1 level.
Step S703: if the defect level exceeds the defect level threshold, a first scheme is generated as a defect handling scheme.
Specifically, in the present embodiment, the first scheme includes timing processing, fast processing, and immediate processing of the defect, and the processing schemes respectively correspond to the stages 2 to 4 of the defect class when the defect type is a structural defect.
Step S704: if the defect level does not exceed the defect level threshold, a second scheme is generated as a defect coping scheme.
Specifically, in this embodiment, the second scheme is to perform no processing, or perform processing according to actual situations.
Step S705: if the defect type is a functional defect, judging whether the defect level exceeds a preset defect level threshold.
Specifically, in this embodiment, when the defect type is a functional defect, the defect level threshold may be level 2.
Step S706: if the defect level exceeds the defect level threshold, a third scheme is generated as a defect coping scheme.
Specifically, in the present embodiment, the third scheme includes a fast processing and an immediate processing, and the processing schemes respectively correspond to the 3 to 4 stages of the defect level when the defect type is a functional defect.
Step S707: if the defect level does not exceed the defect level threshold, a fourth scheme is generated as a defect coping scheme.
Specifically, in the present embodiment, the fourth aspect includes temporary non-processing and processing according to actual conditions, the processing schemes respectively correspond to 1 to 2 levels of defect levels when the defect type is a functional defect.
It is noted that in the present embodiment, when the defect type of the sewage pipe is a structural defect, the treatment means maintenance or repair, and when the defect type of the sewage pipe is a functional defect, the treatment means maintenance or care.
According to the sewage pipeline defect image identification method provided by the embodiment, firstly, the defect type is judged to be structural defect or functional defect, then, whether the defect level exceeds a preset defect level threshold is judged according to different defect levels corresponding to different defect types, and finally, a corresponding defect corresponding scheme is generated according to different results, so that the accuracy of detecting the defects of the sewage pipeline is improved.
The implementation principle of the sewage pipeline defect image identification method provided by the embodiment of the application is as follows: acquiring a real-time video image of a sewage pipeline; inputting the real-time video image into a preset defect learning model; judging whether the sewage pipeline has defects or not based on the real-time video image and the defect learning model; if the sewage pipeline has defects, acquiring defect types based on real-time video images; acquiring a defect grade based on the defect type; based on the defect type and the defect level, a defect countermeasure scheme is generated.
In a second aspect, the application also discloses a sewage pipeline defect image recognition system.
Referring to fig. 8, a sewage pipeline defect image recognition system includes:
a first acquisition module 1, configured to acquire a real-time video image of a sewage pipeline;
the input module 2 is used for inputting the real-time video image into a preset defect learning model;
a judging module 3, configured to judge whether the sewage pipeline has a defect based on the real-time video image and the defect learning model;
the second acquisition module 4 is used for acquiring the defect type based on the real-time video image if the sewage pipeline has the defect;
a third obtaining module 5, configured to obtain a defect level based on the defect type;
a fourth acquisition module 6 for generating a defect countermeasure scheme based on the defect type and the defect level.
The implementation principle of the sewage pipeline defect image recognition system provided by the embodiment of the application is as follows: the method comprises the steps that a first acquisition module 1 acquires a real-time video image of a sewage pipeline, the real-time video image is sent to an input module 2, and the input module 2 inputs the real-time video image into a preset defect learning model; the judging module 3 judges whether the sewage pipeline has defects based on the real-time video image and the defect learning model, when the sewage pipeline has defects, the judging module 3 sends the judging result to the second acquiring module 4, the second acquiring module 4 acquires the defect type based on the real-time video image and sends the defect type to the third acquiring module 5, the third acquiring module 5 acquires the defect grade based on the defect type and sends the defect grade to the fourth acquiring module 6, and the fourth acquiring module 6 generates a defect response scheme based on the defect type and the defect grade, so that the technical effect similar to that of the sewage pipeline defect image identifying method is achieved.
In a third aspect, an embodiment of the present application discloses an intelligent terminal, including a memory, and a processor, where the memory is configured to store a computer program capable of running on the processor, and when the processor loads the computer program, execute a method for identifying a defective image of a sewer line according to the above embodiment.
In a fourth aspect, an embodiment of the present application discloses a computer readable storage medium, and a computer program is stored in the computer readable storage medium, wherein the computer program, when loaded by a processor, performs a sewer line defect image identifying method of the above embodiment.
The above embodiments are not intended to limit the scope of the present application, so: all equivalent changes in structure, shape and principle of the application should be covered in the scope of protection of the application.
Claims (10)
1. A method for identifying a defective image of a sewer line, comprising:
acquiring a real-time video image of a sewage pipeline;
inputting the real-time video image into a preset defect learning model;
judging whether the sewage pipeline has defects or not based on the real-time video image and the defect learning model;
if the sewage pipeline has defects, acquiring defect types based on the real-time video images;
acquiring a defect grade based on the defect type;
based on the defect type and the defect level, a defect countermeasure scheme is generated.
2. The method for identifying a defective image of a sewer line according to claim 1, wherein said determining whether a defect exists in said sewer line based on said real-time video image and said defect learning model comprises:
judging whether the sewage pipe is an existing sewage pipe or not;
if the sewage pipe is not the existing sewage pipe, comparing the real-time video image with a preset target video image, and generating a first comparison result;
and judging whether the sewage pipeline has defects or not based on the first comparison result.
3. The method for identifying a defective image of a sewer line according to claim 2, wherein said step of determining whether a defect exists in said sewer line based on said real-time video image and said defect learning model further comprises:
if the sewage pipe is the existing sewage pipe, judging whether a history detection record of the sewage pipe exists or not;
if the history detection record does not exist, comparing the real-time video image with the target video image, and generating the first comparison result;
and judging whether the sewage pipeline has defects or not based on the first comparison result.
4. A method for identifying a defective image of a sewer line according to claim 3, wherein said step of determining whether said sewer line is defective based on said real-time video image and said defect learning model further comprises:
if the history detection record exists, acquiring a last video image based on the history detection record;
comparing the real-time video image with the last video image and generating a second comparison result;
and judging whether the sewage pipeline has defects or not based on the second comparison result.
5. The method for identifying a defective image of a sewer line according to claim 4, further comprising:
judging whether the sewage pipeline has a history defect or not based on the history detection record;
if the sewage pipeline has the historical defect, acquiring a historical defect type based on the historical defect;
acquiring a key detection area based on the historical defect;
acquiring an important video image based on the historical defect type and the important detection area;
and judging whether the sewage pipeline has defects or not based on the key video images.
6. The method for identifying a defective image of a sewer line according to claim 1, further comprising:
acquiring target geographic position information;
acquiring a target detection item based on the target geographic position information;
acquiring target detection data based on the target detection item;
judging whether the target detection data meets a preset data threshold requirement or not;
and if the target detection data does not meet the data threshold requirement, judging that the sewage pipeline has defects.
7. A sewer pipe defect image identification method according to claim 1, wherein the defect types include structural defects and functional defects; the specific steps of generating a defect countermeasure scheme based on the defect type and the defect grade include:
judging the defect type as the structural defect or the functional defect;
if the defect type is the structural defect, judging whether the defect grade exceeds a preset defect grade threshold;
if the defect level exceeds the defect level threshold, generating a first scheme as a defect handling scheme;
if the defect level does not exceed the defect level threshold, generating a second scheme as a defect coping scheme;
if the defect type is the functional defect, judging whether the defect grade exceeds a preset defect grade threshold;
if the defect level exceeds the defect level threshold, generating a third scheme as a defect coping scheme;
and if the defect level does not exceed the defect level threshold, generating a fourth scheme as a defect coping scheme.
8. A sewer line defect image recognition system, comprising:
a first acquisition module (1) for acquiring real-time video images of a sewer line;
the input module (2) is used for inputting the real-time video image into a preset defect learning model;
a judging module (3) for judging whether the sewage pipeline has a defect or not based on the real-time video image and the defect learning model;
a second acquisition module (4), if the sewage pipeline has a defect, the second acquisition module (4) is used for acquiring a defect type based on the real-time video image;
a third acquisition module (5) for acquiring a defect level based on the defect type;
a fourth acquisition module (6) for generating a defect countermeasure scheme based on the defect type and the defect level.
9. A smart terminal comprising a memory, a processor, wherein the memory is configured to store a computer program capable of running on the processor, and wherein the processor, when loaded with the computer program, performs the method of any of claims 1-7.
10. A computer readable storage medium having a computer program stored therein, characterized in that the computer program, when loaded by a processor, performs the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311131855.3A CN117011286A (en) | 2023-09-02 | 2023-09-02 | Sewage pipeline defect image identification method, system, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311131855.3A CN117011286A (en) | 2023-09-02 | 2023-09-02 | Sewage pipeline defect image identification method, system, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117011286A true CN117011286A (en) | 2023-11-07 |
Family
ID=88572813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311131855.3A Pending CN117011286A (en) | 2023-09-02 | 2023-09-02 | Sewage pipeline defect image identification method, system, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117011286A (en) |
-
2023
- 2023-09-02 CN CN202311131855.3A patent/CN117011286A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102008973B1 (en) | Apparatus and Method for Detection defect of sewer pipe based on Deep Learning | |
| CN109492708B (en) | LS-KNN-based pipeline magnetic flux leakage internal detection missing data interpolation method | |
| CN112883538B (en) | Corrosion prediction system and method for buried crude oil pipeline | |
| CN112857471B (en) | Industrial Internet of things chemical wastewater treatment emission on-line monitoring and early warning management cloud platform | |
| CN115435245A (en) | Method for quickly identifying defects of high-water-level operation pipeline | |
| CN111289526B (en) | Method and system for detecting defects on inner surface of gas conveying pipeline | |
| CN109035202A (en) | A kind of drainage pipeline defect diagonsis appraisal procedure based on CCTV video image multivariate analysis | |
| CN114778684A (en) | Steel pipe performance evaluation method and system based on service scene | |
| CN117235672B (en) | Comprehensive pipe gallery fault diagnosis method and device based on multi-source data | |
| CN115075341A (en) | Regional water leakage pipeline detection method and system, storage medium and intelligent terminal | |
| CN117011286A (en) | Sewage pipeline defect image identification method, system, terminal and storage medium | |
| JP7396944B2 (en) | Pipe damage identification device, pipe damage identification method, and pipe damage identification program | |
| JP2022082294A (en) | Pipe channel abnormality detection system, estimation device, learning model generation device, pipe channel abnormality detector, method for detecting abnormality in pipe channel, method for estimation, and method for generating learning model | |
| KR101213251B1 (en) | Method and system for monitoring sewer drainage pipes using chloride ion concentrations | |
| CN114495019B (en) | Real-time monitoring and dynamic feedback method for leakage diseases of pipe gallery | |
| Myrans et al. | Using Automatic Anomaly Detection to Identify Faults in Sewers:(027) | |
| CN115356260A (en) | High-water-level running pipeline health condition efficient detection method | |
| CN110780316B (en) | Basement drainage detection method | |
| CN112097125B (en) | Water supply pipe network pipe burst detection and positioning method based on self-adaptive checking | |
| CN113238234A (en) | Underwater sewage outlet identification method based on underwater sonar identification | |
| Elkmann et al. | Fully automatic inspection systems for large underground concrete pipes partially filled with wastewater | |
| CN116975767B (en) | Intelligent water affair monitoring system and disaster deduction method based on big data analysis | |
| CN114943884B (en) | Equipment protection method based on deep learning | |
| CN117094594B (en) | Intelligent detection, analysis and evaluation system for water seepage and water leakage of building engineering wall | |
| CN116704734B (en) | Monitoring and early warning method and system for preventing underground pipeline from being excavated based on Internet of things technology |
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 |