CN112446870B - Pipeline damage detection method, device, equipment and storage medium - Google Patents
Pipeline damage detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112446870B CN112446870B CN202011385962.5A CN202011385962A CN112446870B CN 112446870 B CN112446870 B CN 112446870B CN 202011385962 A CN202011385962 A CN 202011385962A CN 112446870 B CN112446870 B CN 112446870B
- Authority
- CN
- China
- Prior art keywords
- pipeline
- damage
- detection
- preset
- frame
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 334
- 238000007689 inspection Methods 0.000 claims abstract description 84
- 238000000034 method Methods 0.000 claims abstract description 39
- 239000013598 vector Substances 0.000 claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims description 51
- 238000011156 evaluation Methods 0.000 claims description 40
- 230000010354 integration Effects 0.000 claims description 30
- 238000010586 diagram Methods 0.000 claims description 19
- 230000004927 fusion Effects 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 10
- 238000012423 maintenance Methods 0.000 claims description 7
- 238000012935 Averaging Methods 0.000 claims description 6
- 238000012800 visualization Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 2
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000004718 Panda Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification 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
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the field of artificial intelligence and discloses a pipeline damage detection method, device, equipment and storage medium. The method comprises the following steps: acquiring a pipeline inspection video to be detected; inputting the pipeline inspection video into a preset pipeline damage detection model to detect frame by frame, and outputting a detection result; if the detection result is that the pipeline damage exists in the current video frame, a preset OpenCV interface is called, and the five-dimensional vector in the detection result is visualized as a detection frame; and combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain the pipeline inspection annotation video marked with the damage position and the damage type of the pipeline. The invention performs targeted optimization on the specific task of pipeline damage detection, has better applicability to the pipeline damage detection task, and greatly improves the efficiency of pipeline damage detection.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to a method, apparatus, device, and storage medium for detecting pipeline damage.
Background
With the rapid development of computer technology, computer vision has become an important field of artificial intelligence, playing an increasingly important role in aspects of people's life. The application of the computer vision technology is very wide, and the target object is identified by adopting the target detection method in the computer vision technology, so that the important target in the picture or the video can be effectively extracted, thereby achieving the identification effect.
Traditional pipeline detection mainly relies on manual experience, damage identification is quite easy to make mistakes by using the manual experience, and inspection efficiency is quite low, so that effective and timely maintenance requirements of a large number of sewer pipelines in cities cannot be met.
Disclosure of Invention
The invention mainly aims to solve the technical problem of low detection efficiency of the current pipeline damage.
The first aspect of the invention provides a method for detecting pipeline damage, which comprises the following steps:
acquiring a pipeline inspection video to be detected;
Inputting the pipeline inspection video into a preset pipeline damage detection model to detect frame by frame, and outputting a detection result;
If the detection result is that the pipeline damage exists in the current video frame, a preset OpenCV interface is called, and the five-dimensional vector in the detection result is visualized as a detection frame;
And combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain the pipeline inspection annotation video marked with the damage position and the damage type of the pipeline.
Optionally, in a first implementation manner of the first aspect of the present invention, before the acquiring the sewer pipeline video to be detected, the method further includes:
Obtaining a plurality of pipeline inspection video samples, and marking damage information of the pipeline inspection video samples frame by frame to obtain damaged positive sample images and damaged negative sample images;
inputting the positive sample image and the negative sample image into a preset target detection network for feature extraction to obtain a sample feature map;
according to the sample feature map, invoking a preset AutoFusion algorithm to search an evaluation index of a feature extraction layer connection part of the target detection network, and taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network;
And calling a preset Stacking integration algorithm to integrate the optimal target detection network to obtain a pipeline damage detection model.
Optionally, in a second implementation manner of the first aspect of the present invention, inputting the positive sample image and the negative sample image into a preset target detection network to perform feature extraction, and obtaining a sample feature map includes:
Inputting the positive sample image and the negative sample image into a preset input layer for data enhancement to obtain an enhanced sample picture;
performing size scaling and cutting on the enhanced sample picture to obtain a standard sample picture;
inputting the standard sample picture into a preset CSP network for feature extraction to obtain sample feature information;
And inputting the sample characteristic information into a preset Neck network to perform characteristic fusion, so as to obtain a sample characteristic diagram.
Optionally, in a third implementation manner of the first aspect of the present invention, the invoking a preset AutoFusion algorithm according to the sample feature map to perform evaluation index search on a feature extraction layer connection portion of the target detection network, and taking, as an optimal target detection network, a target detection network corresponding to a combination with a highest evaluation index includes:
Invoking a preset AutoFusion algorithm, and performing unitary operation and maintenance operation on the connection part of the feature extraction layer of the target detection network to obtain a unitary operation value;
Inputting the unary operation value into a preset operation layer to perform amplitude function operation to obtain an operand;
combining the unary operation value and the operand to obtain a combination of evaluation indexes;
And taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the calling a preset Stacking integration algorithm to integrate the optimal target detection network, to obtain a pipeline damage detection model includes:
calling a preset Stacking integration algorithm, and inputting the sample feature map into the optimal target detection network to perform integration operation to obtain a first layer element feature;
Averaging the first layer element characteristics and inputting the average value into the optimal target detection network to perform integrated operation to obtain second layer element characteristics;
And according to the second layer element characteristics, carrying out parameter adjustment on the optimal target detection network until the optimal target detection network converges, and obtaining a pipeline damage detection model.
Optionally, in a fifth implementation manner of the first aspect of the present invention, inputting the pipeline inspection video into a preset pipeline damage detection model to perform frame-by-frame detection, and outputting a detection result includes:
inputting the pipeline inspection video into a CSP network in a preset pipeline damage detection model to perform feature extraction frame by frame to obtain feature information;
Inputting the characteristic information into Neck networks in a preset pipeline damage detection model to perform characteristic fusion, so as to obtain a characteristic diagram;
and analyzing the category information and the position information of the feature map, and outputting a detection result.
Optionally, in a sixth implementation manner of the first aspect of the present invention, after the combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain a pipeline inspection annotation video marked with a pipeline damage position and a damage type, the method further includes:
Playing the pipeline inspection annotation video, and judging whether the pipeline damage exists in the current video frame;
if yes, screenshot is carried out on the current video frame, a pipeline damage picture is obtained, and pipeline damage information in the pipeline damage picture is extracted;
And storing the pipeline damage picture, the pipeline damage information and the current video playing time point in an associated mode, and outputting a CSV format file containing the pipeline damage information.
A second aspect of the present invention provides a pipe damage detection device, comprising:
The acquisition module is used for acquiring a pipeline inspection video to be detected;
The detection module is used for inputting the pipeline inspection video into a preset pipeline damage detection model to carry out frame-by-frame detection and outputting a detection result;
the visualization module is used for calling a preset OpenCV interface if the detection result is that the pipeline damage exists in the current video frame, and visualizing the five-dimensional vector in the detection result into a detection frame;
and the output module is used for combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain the pipeline inspection annotation video marked with the damage position and the damage type of the pipeline.
Optionally, in a first implementation manner of the second aspect of the present invention, the pipe damage detection device further includes:
The marking unit is used for acquiring a plurality of pipeline inspection video samples, and marking damage information on the pipeline inspection video samples frame by frame to obtain damaged positive sample images and damaged negative sample images;
the feature extraction unit is used for inputting the positive sample image and the negative sample image into a preset target detection network to perform feature extraction so as to obtain a sample feature map;
The network optimization unit is used for calling a preset AutoFusion algorithm to search an evaluation index of a feature extraction layer connection part of the target detection network according to the sample feature map, and taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network;
And the model integration unit is used for calling a preset Stacking integration algorithm to integrate the optimal target detection network to obtain a pipeline damage detection model.
Optionally, in a second implementation manner of the second aspect of the present invention, the feature extraction unit is specifically configured to:
Inputting the positive sample image and the negative sample image into a preset input layer for data enhancement to obtain an enhanced sample picture;
performing size scaling and cutting on the enhanced sample picture to obtain a standard sample picture;
inputting the standard sample picture into a preset CSP network for feature extraction to obtain sample feature information;
And inputting the sample characteristic information into a preset Neck network to perform characteristic fusion, so as to obtain a sample characteristic diagram.
Optionally, in a third implementation manner of the second aspect of the present invention, the network optimization unit is specifically configured to:
Invoking a preset AutoFusion algorithm, and performing unitary operation and maintenance operation on the connection part of the feature extraction layer of the target detection network to obtain a unitary operation value;
Inputting the unary operation value into a preset operation layer to perform amplitude function operation to obtain an operand;
combining the unary operation value and the operand to obtain a combination of evaluation indexes;
And taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the model integration unit is specifically configured to:
calling a preset Stacking integration algorithm, and inputting the sample feature map into the optimal target detection network to perform integration operation to obtain a first layer element feature;
Averaging the first layer element characteristics and inputting the average value into the optimal target detection network to perform integrated operation to obtain second layer element characteristics;
And according to the second layer element characteristics, carrying out parameter adjustment on the optimal target detection network until the optimal target detection network converges, and obtaining a pipeline damage detection model.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the detection module is specifically configured to:
inputting the pipeline inspection video into a CSP network in a preset pipeline damage detection model to perform feature extraction frame by frame to obtain feature information;
Inputting the characteristic information into Neck networks in a preset pipeline damage detection model to perform characteristic fusion, so as to obtain a characteristic diagram;
and analyzing the category information and the position information of the feature map, and outputting a detection result.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the pipe damage detection device further includes:
The storage module is used for playing the pipeline inspection annotation video and judging whether the current video frame has pipeline damage or not; if yes, screenshot is carried out on the current video frame, a pipeline damage picture is obtained, and pipeline damage information in the pipeline damage picture is extracted; and storing the pipeline damage picture, the pipeline damage information and the current video playing time point in an associated mode, and outputting a CSV format file containing the pipeline damage information.
A third aspect of the present invention provides a pipe damage detection apparatus comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the pipe damage detection device to perform the pipe damage detection method described above.
A fourth aspect of the present invention provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the above-described pipe damage detection method.
According to the technical scheme provided by the invention, in view of the fact that the existing pipeline detection by means of naked eyes is large in workload and easy to misjudge or miss-detect, a model which can be used for automatically detecting pipeline images is generated by introducing a machine learning mode, pipeline videos to be detected are input into the model for frame-by-frame detection, the model can be used for rapidly detecting damage information on the images, damage positions and types are directly calibrated, then detection results are visualized through an OpenCV interface, detected videos are stored, and a user can rapidly acquire whether damage exists, the damage types and the damage specific positions only by watching the calibrated videos. The invention builds the pipeline damage detection model aiming at pipeline damage detection, and the model has better applicability to pipeline damage detection tasks, thereby greatly improving the efficiency of pipeline damage detection.
Drawings
FIG. 1 is a schematic diagram of a first embodiment of a method for detecting damage to a pipeline according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a second embodiment of a method for detecting damage to a pipeline according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a third embodiment of a method for detecting damage to a pipeline according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a fourth embodiment of a method for detecting a pipe damage according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an embodiment of a pipe damage detection device according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a pipeline damage detection apparatus according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method, a device, equipment and a storage medium for detecting pipeline damage. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For easy understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1, and a first embodiment of a method for detecting a pipeline damage in an embodiment of the present invention includes:
101. acquiring a pipeline inspection video to be detected;
It is to be understood that the execution body of the present invention may be a pipe damage detection device, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
In this embodiment, the video is taken as the pipeline inspection video to be detected by using the pipeline inspection video taken by the camera or other devices.
102. Inputting the pipeline inspection video into a preset pipeline damage detection model to detect frame by frame, and outputting a detection result;
In this embodiment, the pipeline damage detection model detects a network structure by N (N > 1) targets, for example: yoloV5 network structure, yoloV is composed of CSP network, neck network and impairment information analysis layer, and model is built by mainstream deep learning framework Pytorch. The detection result comprises that no damage exists in the current frame, and when damage exists, the position information corresponding to the damage point and the damage type information are generated into a five-dimensional vector and output as the detection result.
In this embodiment, the pipeline inspection video is input into a preset pipeline damage detection model to detect frame by frame, so as to obtain a detection result, where the detection result includes no damage in the current frame, and when there is damage, the position information corresponding to the damage point and the damage type information are generated into a five-dimensional vector and output as the detection result.
Optionally, in an embodiment, inputting the pipeline inspection video into a preset pipeline damage detection model for frame-by-frame detection, and outputting a detection result includes:
inputting the pipeline inspection video into a CSP network in a preset pipeline damage detection model to perform feature extraction frame by frame to obtain feature information;
in this embodiment, the CSP network divides the original input into two branches, performs convolution operation to halve the number of channels, then performs Bottlenneck x N operations on branch one, and then tensors splice branch one and branch two, so that the input and output of the CSP network are the same size, and the CSP network can make the model extract more features.
Inputting the characteristic information into Neck networks in a preset pipeline damage detection model to perform characteristic fusion, so as to obtain a characteristic diagram;
In this embodiment, the key function of the Neck network is to perform feature fusion on feature information extracted from the CSP network, and perform transfer fusion on high-level feature information by using a general convolution operation in an up-sampling manner, so as to obtain a predicted feature map, thereby enhancing the capability of network feature fusion.
And analyzing the category information and the position information of the feature map, and outputting a detection result.
In this embodiment, the CSP network in the preset pipeline damage detection model is inputted with the pipeline inspection video to perform feature extraction frame by frame to obtain feature information, the Neck network in the preset pipeline damage detection model is inputted with the feature information to perform feature fusion to obtain a feature map, and the feature map is analyzed for category information and position information to output a detection result. In this embodiment, if there is damage information in the detected video frame, the detection result is that there is damage, and the coordinates of the damage point and the damage type information are generated into a five-dimensional vector and output.
103. If the detection result is that the pipeline damage exists in the current video frame, a preset OpenCV interface is called, and the five-dimensional vector in the detection result is visualized as a detection frame;
in this embodiment, five-dimensional vectors in the detection result are (c, x, y, w, h), where c is a detection frame type, x is an abscissa, y is an ordinate, w is a width, h is a height, and positions of the damage in the picture and the damage types are marked according to the five-dimensional vectors (c, x, y, w, h).
In this embodiment, if the detection result is that there is a pipeline damage in the current video frame, a preset OpenCV interface is called, and a five-dimensional vector in the detection result is visualized as a detection frame. OpenCV is a cross-platform computer vision and machine learning software library based on BSD license (open source) issues that can run on Linux, windows, android and Mac OS operating systems. OpenCV is lightweight and efficient, provides an interface for Python, ruby, MATLAB languages, and implements multiple general algorithms in terms of image processing and computer vision.
104. And combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain the pipeline inspection annotation video marked with the damage position and the damage type of the pipeline.
In this embodiment, the detection frame is combined with a corresponding video frame in the pipeline inspection video to obtain a pipeline inspection annotation video marked with a pipeline damage position and a damage type. And combining the detection frame with the video frame corresponding to the original video to generate a new video through an OpenCV interface, so as to obtain the marked video containing the marked information. The detection result and the original video are combined, so that a user can effectively classify and store a large amount of video data, and damaged pipeline information is archived, so that the detection and comparison are convenient.
Optionally, in an embodiment, after the combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain a pipeline inspection annotation video marked with a pipeline damage position and a damage type, the method further includes:
Playing the pipeline inspection annotation video, and judging whether the pipeline damage exists in the current video frame;
if yes, screenshot is carried out on the current video frame, a pipeline damage picture is obtained, and pipeline damage information in the pipeline damage picture is extracted;
And storing the pipeline damage picture, the pipeline damage information and the current video playing time point in an associated mode, and outputting a CSV format file containing the pipeline damage information.
In this embodiment, a video frame with damage information in a marked video is captured, the damage information in the captured is extracted, the captured is saved, and damage information corresponding to the captured is called a Panda tool to be saved, so as to obtain a CSV file corresponding to the damage information.
In view of the fact that the existing pipeline detection by means of naked eyes is large in workload and easy to misjudge or miss, a machine learning mode is introduced to generate a model which can be used for automatically detecting pipeline images, pipeline video to be detected is input into the model to be detected frame by frame, the model can be used for rapidly detecting damage information on the images and directly calibrating damage positions and types, then detection results are visualized through an OpenCV interface, detected videos are stored, and a user can rapidly know whether damage exists or not and whether damage types and damage specific positions only by watching calibrated videos. The invention builds the pipeline damage detection model aiming at the specific task of pipeline damage detection, and the model has better applicability to the pipeline damage detection task and can greatly improve the efficiency of pipeline damage detection.
Referring to fig. 2, a second embodiment of a method for detecting damage to a pipeline according to an embodiment of the present invention includes:
201. Obtaining a plurality of pipeline inspection video samples, and marking damage information of the pipeline inspection video samples frame by frame to obtain damaged positive sample images and damaged negative sample images;
In this embodiment, the preset labelme is invoked to inspect the video frame by frame, when there is a damage in the video frame, the coordinates of the damage point in the image are extracted first, the original image is converted into a binary image in the extraction of the damage point in the image, then the coordinates of the connected domain of the damage position are found, and the coordinates corresponding to the connected domain of the damage position in the image are stored as the mat file. And secondly, calling a preset img2json. Py encoder, and encoding and storing the video frame with the current damage as a json file. And fusing the mat file and the json file by adopting a preset imitate _json.py fusion algorithm, and generating an image marked with damage information.
202. Inputting the positive sample image and the negative sample image into a preset target detection network for feature extraction to obtain a sample feature map;
optionally, in an embodiment, inputting the positive sample image and the negative sample image into a preset target detection network to perform feature extraction, and obtaining a sample feature map includes:
Inputting the positive sample image and the negative sample image into a preset input layer for data enhancement to obtain an enhanced sample picture;
performing size scaling and cutting on the enhanced sample picture to obtain a standard sample picture;
inputting the standard sample picture into a preset CSP network for feature extraction to obtain sample feature information;
And inputting the sample characteristic information into a preset Neck network to perform characteristic fusion, so as to obtain a sample characteristic diagram.
In this embodiment, for the positive sample image and the negative sample image, cutMix and the mosaics technique are used to enhance data in addition to classical geometric distortion and illumination distortion, so as to obtain an enhanced sample image. The object detection network needs to adjust the size of the original image for feature recognition, and the image in the model scales to 512 x 512. The CSP network solves the problem of repeated gradient information of network optimization in other large convolutional neural network frameworks, integrates the change of gradients into the feature map from beginning to end, separates the feature map of the base layer, effectively relieves the problem of gradient disappearance, supports feature propagation, encourages network reuse of features, and reduces the number of network parameters. The Neck network is used to generate feature pyramids. The feature pyramid can enhance the detection of the model on objects with different scaling scales, so that the same object with different sizes and scales can be identified, and the features extracted by the CSP network are fused, so that a feature picture is obtained. The detection speed and the detection precision of the target detection network are perfectly coordinated, and the obtained sample feature map has higher accuracy.
203. According to the sample feature map, invoking a preset AutoFusion algorithm to search an evaluation index of a feature extraction layer connection part of the target detection network, and taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network;
In this embodiment, the AutoFusion algorithm performs three steps of spatial search on the feature extraction layer connection portion of the target detection network structure, firstly performs Unary ops operation to obtain op 1、op2,op1、op2 as a unitary operation value, secondly performs amplitude function operation on the unitary operation value to obtain μ 1、μ2,μ1、μ2 as an operand, and finally performs comprehensive operation Δw=λ=b (μ 1(op1),u2(op2)) on the two steps, where Δw is an evaluation index, λ is a custom parameter, b is an addition binary function operation, and when the value of Δw is the highest, the corresponding target detection network is the optimal target detection network.
204. Calling a preset Stacking integration algorithm to integrate the optimal target detection network to obtain a pipeline damage detection model;
In this embodiment, the positive sample image and the negative sample image are input into a preset target detection network to perform feature extraction, so as to obtain a sample feature map; according to the sample feature map, invoking a preset AutoFusion algorithm to search an evaluation index of a feature extraction layer connection part of the target detection network, and taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network; and calling a preset Stacking integration algorithm to integrate the optimal target detection network to obtain a pipeline damage detection model.
In this embodiment, the traditional computing learning method includes three major parts of feature extraction, model design and parameter tuning, and the automatic machine learning AutoFusion algorithm, so that the whole machine learning process is automatically completed, and only data needs to be input to obtain output. In this embodiment, the neural network structure search technique refers to performing a spatial search on the connection of the feature extraction layers of the target detection network by using AutoFusion algorithm, searching for an optimal evaluation index combination, and taking the target detection network with the highest evaluation index as the optimal target detection network.
In this embodiment, the AutoFusion algorithm searches local maxima, suppresses non-maxima, finds a binding box with higher confidence according to the score matrix and the coordinate information of region, sorts all the detection frames in descending order, then selects the detection frame with highest confidence, judges whether the detection frame with highest confidence is correct, calculates the IOU value of the detection frame with highest confidence and other detection frames if the detection frame is correct, removes the IOU value with high overlap according to the IOU value, removes the corresponding detection frame if the IOU value is greater than threshold, and continues the sorting of confidence of the remaining detection frames after removing the detection frame with high overlap until the redundant detection frame is eliminated, and finds the optimal damage detection position.
The Stacking integrated algorithm in this embodiment trains a multi-layer learner structure, the first layer uses N YoloV models to obtain a prediction result of the first layer, the prediction result of the first layer is combined into a new feature input image, the new feature input image is input into the learned YoloV model, and a final prediction result of the pipeline damage model is obtained through output of the second prediction process.
205. Acquiring a pipeline inspection video to be detected;
206. inputting the pipeline inspection video into a preset pipeline damage detection model to detect frame by frame, and outputting a detection result;
207. If the detection result is that the pipeline damage exists in the current video frame, a preset OpenCV interface is called, and the five-dimensional vector in the detection result is visualized as a detection frame;
208. and combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain the pipeline inspection annotation video marked with the damage position and the damage type of the pipeline.
In the embodiment of the invention, a AutoFusion algorithm is adopted to optimize a target network structure to obtain an optimal target network structure, and a Stacking integration algorithm is adopted to integrate the optimal target network structure to obtain a final pipeline damage detection model. And a AutoFusion optimization algorithm is adopted to optimize the network structure, so that the obtained pipeline damage detection model is more suitable for the specific task of pipeline damage detection.
Referring to fig. 3, a third embodiment of a method for detecting damage to a pipeline according to an embodiment of the present invention includes:
301. obtaining a plurality of pipeline inspection video samples, and marking damage information of the pipeline inspection video samples frame by frame to obtain damaged positive sample images and damaged negative sample images;
302. Inputting the positive sample image and the negative sample image into a preset target detection network for feature extraction to obtain a sample feature map;
303. invoking a preset AutoFusion algorithm, and performing unitary operation and maintenance operation on the connection part of the feature extraction layer of the target detection network to obtain a unitary operation value;
304. Inputting the unary operation value into a preset operation layer to perform amplitude function operation to obtain an operand;
305. Combining the unary operation value and the operand to obtain a combination of evaluation indexes;
306. Taking a target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network;
In this embodiment, three steps are taken in optimizing the target detection network structure by adopting AutoFusion algorithm, firstly, operation is performed on the operation to obtain op 1、op2,op1、op2 as a unitary operation value, secondly, operation is performed on the unitary operation value to obtain mu 1、μ2,μ1、μ2 as an operand, finally, an evaluation index combination is obtained by combining the two steps, and finally, comprehensive operation Δw=λ×b (mu 1(op1),u2(op2) of the two steps is performed, wherein Δw is an evaluation index, λ is a custom parameter, b is an addition binary function operation, and when Δw is highest, the corresponding target detection network is the optimal target detection network. The target detection network with the highest evaluation index is selected from the search space to serve as the target detection network, so that a neural architecture with good performance is generated, the target detection network corresponding to the highest evaluation index in the evaluation index combination is used as the optimal target detection network, the detection speed of the optimal target detection network is improved, and the damage detection is more accurate.
307. Acquiring a pipeline inspection video to be detected;
308. inputting the pipeline inspection video into a preset pipeline damage detection model to detect frame by frame, and outputting a detection result;
309. if the detection result is that the pipeline damage exists in the current video frame, a preset OpenCV interface is called, and the five-dimensional vector in the detection result is visualized as a detection frame;
310. and combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain the pipeline inspection annotation video marked with the damage position and the damage type of the pipeline.
In the embodiment of the invention, the AutoFusion algorithm is adopted to optimize the target detection network structure, so that the target detection network structure can be automatically optimized without external assistance, and a network architecture and a model which are close to the optimal and aim at pipeline damage detection can be still obtained.
Referring to fig. 4, a fourth embodiment of a method for detecting damage to a pipeline according to an embodiment of the present invention includes:
401. obtaining a plurality of pipeline inspection video samples, and marking damage information of the pipeline inspection video samples frame by frame to obtain damaged positive sample images and damaged negative sample images;
402. Inputting the positive sample image and the negative sample image into a preset target detection network for feature extraction to obtain a sample feature map;
403. according to the sample feature map, invoking a preset AutoFusion algorithm to search an evaluation index of a feature extraction layer connection part of the target detection network, and taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network;
404. calling a preset Stacking integration algorithm, and inputting the sample feature map into the optimal target detection network to perform integration operation to obtain a first layer element feature;
405. averaging the first layer element characteristics and inputting the average value into the optimal target detection network to perform integrated operation to obtain second layer element characteristics;
406. According to the second layer element characteristics, parameter adjustment is carried out on the optimal target detection network until the optimal target detection network converges, and a pipeline damage detection model is obtained;
in this embodiment, a meta-model is trained by using a Stacking method, and the model generates a final output according to an output result returned by the weak learner at a lower layer. In the Stacking method, the first layer uses N YoloV models to obtain a prediction result of the first layer, the prediction result of the first layer is combined into a new feature input image, the new feature input image is input into a YoloV model after learning, the N YoloV models are integrated into one pipeline detection model through the output of the second prediction process as a final detection result of the system, and the advantages of a plurality of network structures can be integrated, so that the detection speed of the integrated pipeline damage model is faster, and the accuracy is higher. Performing cross validation by using YoloV as a basic model, wherein the cross validation comprises two processes, namely training the model based on the feature map; and secondly, predicting the feature map based on a model generated by feature map training. And obtaining a predicted value about the current feature map after the cross verification is completed, and carrying out the two steps twice to finally generate a detection result. And carrying out parameter adjustment on the optimal target detection network by adopting binary cross entropy until the optimal target detection network converges, so as to obtain a pipeline damage detection model.
407. Acquiring a pipeline inspection video to be detected;
408. inputting the pipeline inspection video into a preset pipeline damage detection model to detect frame by frame, and outputting a detection result;
409. If the detection result is that the pipeline damage exists in the current video frame, a preset OpenCV interface is called, and the five-dimensional vector in the detection result is visualized as a detection frame;
410. And combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain the pipeline inspection annotation video marked with the damage position and the damage type of the pipeline.
In the embodiment of the invention, the Stacking integration method combines the two meta models by training one meta model, and outputs a final prediction result according to the prediction results of different weak models, so that the frame can integrate the advantages of various frames, has better applicability to pipeline damage detection tasks, and the pipeline damage detection model obtained by Stacking integration is more accurate in identifying the position information and the category information of damage.
The method for detecting the damage to the pipe in the embodiment of the present invention is described above, and the apparatus for detecting the damage to the pipe in the embodiment of the present invention is described below, referring to fig. 5, where an embodiment of the apparatus for detecting the damage to the pipe in the embodiment of the present invention includes:
the acquisition module 501 is used for acquiring a pipeline inspection video to be detected;
The detection module 502 is configured to input the pipeline inspection video into a preset pipeline damage detection model to perform frame-by-frame detection, and output a detection result;
a visualization module 503, configured to invoke a preset OpenCV interface if the detection result indicates that there is a pipeline damage in the current video frame, and visualize a five-dimensional vector in the detection result as a detection frame;
and the output module 504 is configured to combine the detection frame with a corresponding video frame in the pipeline inspection video to obtain a pipeline inspection annotation video marked with a pipeline damage position and a damage type.
Optionally, in an embodiment, the device for detecting a damage to a pipe further includes:
The marking unit is used for acquiring a plurality of pipeline inspection video samples, and marking damage information on the pipeline inspection video samples frame by frame to obtain damaged positive sample images and damaged negative sample images;
the feature extraction unit is used for inputting the positive sample image and the negative sample image into a preset target detection network to perform feature extraction so as to obtain a sample feature map;
The network optimization unit is used for calling a preset AutoFusion algorithm to search an evaluation index of a feature extraction layer connection part of the target detection network according to the sample feature map, and taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network;
And the model integration unit is used for calling a preset Stacking integration algorithm to integrate the optimal target detection network to obtain a pipeline damage detection model.
Optionally, in an embodiment, the feature extraction unit is specifically configured to:
Inputting the positive sample image and the negative sample image into a preset input layer for data enhancement to obtain an enhanced sample picture;
performing size scaling and cutting on the enhanced sample picture to obtain a standard sample picture;
inputting the standard sample picture into a preset CSP network for feature extraction to obtain sample feature information;
And inputting the sample characteristic information into a preset Neck network to perform characteristic fusion, so as to obtain a sample characteristic diagram.
Optionally, in an embodiment, the network optimization unit is specifically configured to:
Invoking a preset AutoFusion algorithm, and performing unitary operation and maintenance operation on the connection part of the feature extraction layer of the target detection network to obtain a unitary operation value;
Inputting the unary operation value into a preset operation layer to perform amplitude function operation to obtain an operand;
combining the unary operation value and the operand to obtain a combination of evaluation indexes;
And taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network.
Optionally, in an embodiment, the model integration unit is specifically configured to:
calling a preset Stacking integration algorithm, and inputting the sample feature map into the optimal target detection network to perform integration operation to obtain a first layer element feature;
Averaging the first layer element characteristics and inputting the average value into the optimal target detection network to perform integrated operation to obtain second layer element characteristics;
And according to the second layer element characteristics, carrying out parameter adjustment on the optimal target detection network until the optimal target detection network converges, and obtaining a pipeline damage detection model.
Optionally, in an embodiment, the detection module 502 is specifically configured to:
inputting the pipeline inspection video into a CSP network in a preset pipeline damage detection model to perform feature extraction frame by frame to obtain feature information;
Inputting the characteristic information into Neck networks in a preset pipeline damage detection model to perform characteristic fusion, so as to obtain a characteristic diagram;
and analyzing the category information and the position information of the feature map, and outputting a detection result.
Optionally, in an embodiment, the device for detecting a damage to a pipe further includes:
The storage module is used for playing the pipeline inspection annotation video and judging whether the current video frame has pipeline damage or not; if yes, screenshot is carried out on the current video frame, a pipeline damage picture is obtained, and pipeline damage information in the pipeline damage picture is extracted; and storing the pipeline damage picture, the pipeline damage information and the current video playing time point in an associated mode, and outputting a CSV format file containing the pipeline damage information.
In view of the fact that the existing pipeline detection by means of naked eyes is large in workload and easy to misjudge or miss, a machine learning mode is introduced to generate a model which can be used for automatically detecting pipeline images, pipeline video to be detected is input into the model to be detected frame by frame, the model can be used for rapidly detecting damage information on the images and directly calibrating damage positions and types, then detection results are visualized through an OpenCV interface, detected videos are stored, and a user can rapidly know whether damage exists or not and whether damage types and damage specific positions only by watching calibrated videos. The invention builds the pipeline damage detection model aiming at the specific task of pipeline damage detection, and the model has better applicability to the pipeline damage detection task and can greatly improve the efficiency of pipeline damage detection.
The pipe damage detection device in the embodiment of the present invention is described in detail from the point of view of the modularized functional entity in fig. 5, and the pipe damage detection apparatus in the embodiment of the present invention is described in detail from the point of view of hardware processing.
Fig. 6 is a schematic structural diagram of a pipe damage detection device according to an embodiment of the present invention, where the pipe damage detection device 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, one or more storage mediums 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the pipe damage detection apparatus 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the pipe damage detection device 600.
The pipe damage detection device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the pipe damage detection apparatus structure shown in fig. 6 is not limiting of the pipe damage detection apparatus and may include more or fewer components than shown, or certain components may be combined, or a different arrangement of components. The invention also provides a pipeline damage detection device, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the pipeline damage detection method in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, in which instructions are stored which, when executed on a computer, cause the computer to perform the steps of the pipe damage detection method.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of detecting damage to a pipe, the method comprising:
Obtaining a plurality of pipeline inspection video samples, and marking damage information of the pipeline inspection video samples frame by frame to obtain damaged positive sample images and damaged negative sample images;
inputting the positive sample image and the negative sample image into a preset target detection network for feature extraction to obtain a sample feature map;
according to the sample feature map, invoking a preset AutoFusion algorithm to search an evaluation index of a feature extraction layer connection part of the target detection network, and taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network;
Calling a preset Stacking integration algorithm to integrate the optimal target detection network to obtain a pipeline damage detection model;
acquiring a pipeline inspection video to be detected;
Inputting the pipeline inspection video into a preset pipeline damage detection model to detect frame by frame, and outputting a detection result;
If the detection result is that the pipeline damage exists in the current video frame, a preset OpenCV interface is called, and the five-dimensional vector in the detection result is visualized as a detection frame;
combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain a pipeline inspection annotation video marked with the damage position and the damage type of the pipeline;
and according to the sample feature map, invoking a preset AutoFusion algorithm to search an evaluation index of a feature extraction layer connection part of the target detection network, and taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network comprises the following steps:
Invoking a preset AutoFusion algorithm, and performing unitary operation and maintenance operation on the connection part of the feature extraction layer of the target detection network to obtain a unitary operation value;
Inputting the unary operation value into a preset operation layer to perform amplitude function operation to obtain an operand;
combining the unary operation value and the operand to obtain a combination of evaluation indexes;
Taking a target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network;
The step of calling a preset Stacking integration algorithm to integrate the optimal target detection network, and the step of obtaining a pipeline damage detection model comprises the following steps:
calling a preset Stacking integration algorithm, and inputting the sample feature map into the optimal target detection network to perform integration operation to obtain a first layer element feature;
Averaging the first layer element characteristics and inputting the average value into the optimal target detection network to perform integrated operation to obtain second layer element characteristics;
And according to the second layer element characteristics, carrying out parameter adjustment on the optimal target detection network until the optimal target detection network converges, and obtaining a pipeline damage detection model.
2. The method for detecting pipeline damage according to claim 1, wherein inputting the positive sample image and the negative sample image into a preset target detection network for feature extraction, and obtaining a sample feature map comprises:
Inputting the positive sample image and the negative sample image into a preset input layer for data enhancement to obtain an enhanced sample picture;
performing size scaling and cutting on the enhanced sample picture to obtain a standard sample picture;
inputting the standard sample picture into a preset CSP network for feature extraction to obtain sample feature information;
And inputting the sample characteristic information into a preset Neck network to perform characteristic fusion, so as to obtain a sample characteristic diagram.
3. The method for detecting pipeline damage according to claim 1, wherein inputting the pipeline inspection video into a preset pipeline damage detection model for frame-by-frame detection, and outputting the detection result comprises:
inputting the pipeline inspection video into a CSP network in a preset pipeline damage detection model to perform feature extraction frame by frame to obtain feature information;
Inputting the characteristic information into Neck networks in a preset pipeline damage detection model to perform characteristic fusion, so as to obtain a characteristic diagram;
and analyzing the category information and the position information of the feature map, and outputting a detection result.
4. The method for detecting a damage to a pipeline according to any one of claims 1 to 3, further comprising, after the combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain a pipeline inspection annotation video marked with a damage location and a damage type, the steps of:
Playing the pipeline inspection annotation video, and judging whether the pipeline damage exists in the current video frame;
if yes, screenshot is carried out on the current video frame, a pipeline damage picture is obtained, and pipeline damage information in the pipeline damage picture is extracted;
And storing the pipeline damage picture, the pipeline damage information and the current video playing time point in an associated mode, and outputting a CSV format file containing the pipeline damage information.
5. A pipe damage detection device, characterized in that the pipe damage detection device comprises:
The marking unit is used for acquiring a plurality of pipeline inspection video samples, and marking damage information on the pipeline inspection video samples frame by frame to obtain damaged positive sample images and damaged negative sample images;
the feature extraction unit is used for inputting the positive sample image and the negative sample image into a preset target detection network to perform feature extraction so as to obtain a sample feature map;
The network optimization unit is used for calling a preset AutoFusion algorithm to search an evaluation index of a feature extraction layer connection part of the target detection network according to the sample feature map, and taking the target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network;
The model integration unit is used for calling a preset Stacking integration algorithm to integrate the optimal target detection network to obtain a pipeline damage detection model;
The acquisition module is used for acquiring a pipeline inspection video to be detected;
The detection module is used for inputting the pipeline inspection video into a preset pipeline damage detection model to carry out frame-by-frame detection and outputting a detection result;
the visualization module is used for calling a preset OpenCV interface if the detection result is that the pipeline damage exists in the current video frame, and visualizing the five-dimensional vector in the detection result into a detection frame;
The output module is used for combining the detection frame with a corresponding video frame in the pipeline inspection video to obtain a pipeline inspection annotation video marked with the damage position and the damage type of the pipeline;
the network optimization unit is specifically configured to:
Invoking a preset AutoFusion algorithm, and performing unitary operation and maintenance operation on the connection part of the feature extraction layer of the target detection network to obtain a unitary operation value;
Inputting the unary operation value into a preset operation layer to perform amplitude function operation to obtain an operand;
combining the unary operation value and the operand to obtain a combination of evaluation indexes;
Taking a target detection network corresponding to the combination with the highest evaluation index as an optimal target detection network;
The model integration unit is specifically used for:
calling a preset Stacking integration algorithm, and inputting the sample feature map into the optimal target detection network to perform integration operation to obtain a first layer element feature;
Averaging the first layer element characteristics and inputting the average value into the optimal target detection network to perform integrated operation to obtain second layer element characteristics;
And according to the second layer element characteristics, carrying out parameter adjustment on the optimal target detection network until the optimal target detection network converges, and obtaining a pipeline damage detection model.
6. The pipe damage detection device of claim 5, wherein the feature extraction unit is specifically configured to:
Inputting the positive sample image and the negative sample image into a preset input layer for data enhancement to obtain an enhanced sample picture;
performing size scaling and cutting on the enhanced sample picture to obtain a standard sample picture;
inputting the standard sample picture into a preset CSP network for feature extraction to obtain sample feature information;
And inputting the sample characteristic information into a preset Neck network to perform characteristic fusion, so as to obtain a sample characteristic diagram.
7. The pipe damage detection device of claim 5, wherein the detection module is specifically configured to:
inputting the pipeline inspection video into a CSP network in a preset pipeline damage detection model to perform feature extraction frame by frame to obtain feature information;
Inputting the characteristic information into Neck networks in a preset pipeline damage detection model to perform characteristic fusion, so as to obtain a characteristic diagram;
and analyzing the category information and the position information of the feature map, and outputting a detection result.
8. The pipe damage detection device of any one of claims 5-7, further comprising:
The storage module is used for playing the pipeline inspection annotation video and judging whether the current video frame has pipeline damage or not;
if yes, screenshot is carried out on the current video frame, a pipeline damage picture is obtained, and pipeline damage information in the pipeline damage picture is extracted;
And storing the pipeline damage picture, the pipeline damage information and the current video playing time point in an associated mode, and outputting a CSV format file containing the pipeline damage information.
9. A pipe damage detection apparatus, the pipe damage detection apparatus comprising: a memory and at least one processor, the memory having instructions stored therein;
The at least one processor invokes the instructions in the memory to cause the pipe damage detection device to perform the pipe damage detection method of any one of claims 1-4.
10. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the pipe damage detection method of any one of claims 1-4.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011385962.5A CN112446870B (en) | 2020-12-02 | 2020-12-02 | Pipeline damage detection method, device, equipment and storage medium |
PCT/CN2021/083573 WO2022116433A1 (en) | 2020-12-02 | 2021-03-29 | Pipeline damage detection method and apparatus, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011385962.5A CN112446870B (en) | 2020-12-02 | 2020-12-02 | Pipeline damage detection method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112446870A CN112446870A (en) | 2021-03-05 |
CN112446870B true CN112446870B (en) | 2024-07-09 |
Family
ID=74740456
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011385962.5A Active CN112446870B (en) | 2020-12-02 | 2020-12-02 | Pipeline damage detection method, device, equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112446870B (en) |
WO (1) | WO2022116433A1 (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112446870B (en) * | 2020-12-02 | 2024-07-09 | 平安科技(深圳)有限公司 | Pipeline damage detection method, device, equipment and storage medium |
CN112966678B (en) * | 2021-03-11 | 2023-01-24 | 南昌航空大学 | Text detection method and system |
CN113362285B (en) * | 2021-05-21 | 2023-02-07 | 同济大学 | Steel rail surface damage fine-grained image classification and detection method |
CN114429639B (en) * | 2022-01-27 | 2024-05-03 | 广联达科技股份有限公司 | Pipeline annotation recognition method and device |
CN116123988B (en) * | 2023-04-14 | 2023-07-11 | 国家石油天然气管网集团有限公司 | Pipeline geometric deformation detection method and system based on data processing |
CN116382224B (en) * | 2023-06-05 | 2023-08-04 | 云印技术(深圳)有限公司 | Packaging equipment monitoring method and system based on data analysis |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110287798A (en) * | 2019-05-27 | 2019-09-27 | 魏运 | Vector network pedestrian detection method based on characteristic module and context fusion |
CN111667011A (en) * | 2020-06-08 | 2020-09-15 | 平安科技(深圳)有限公司 | Damage detection model training method, damage detection model training device, damage detection method, damage detection device, damage detection equipment and damage detection medium |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109815997B (en) * | 2019-01-04 | 2024-07-19 | 平安科技(深圳)有限公司 | Method and related device for identifying vehicle damage based on deep learning |
CN110264444B (en) * | 2019-05-27 | 2020-07-17 | 阿里巴巴集团控股有限公司 | Damage detection method and device based on weak segmentation |
CN110390666B (en) * | 2019-06-14 | 2023-06-27 | 平安科技(深圳)有限公司 | Road damage detection method, device, computer equipment and storage medium |
CN110490079B (en) * | 2019-07-19 | 2022-06-03 | 万翼科技有限公司 | Patrol data processing method and device, computer equipment and storage medium |
CN112446870B (en) * | 2020-12-02 | 2024-07-09 | 平安科技(深圳)有限公司 | Pipeline damage detection method, device, equipment and storage medium |
-
2020
- 2020-12-02 CN CN202011385962.5A patent/CN112446870B/en active Active
-
2021
- 2021-03-29 WO PCT/CN2021/083573 patent/WO2022116433A1/en active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110287798A (en) * | 2019-05-27 | 2019-09-27 | 魏运 | Vector network pedestrian detection method based on characteristic module and context fusion |
CN111667011A (en) * | 2020-06-08 | 2020-09-15 | 平安科技(深圳)有限公司 | Damage detection model training method, damage detection model training device, damage detection method, damage detection device, damage detection equipment and damage detection medium |
Also Published As
Publication number | Publication date |
---|---|
CN112446870A (en) | 2021-03-05 |
WO2022116433A1 (en) | 2022-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112446870B (en) | Pipeline damage detection method, device, equipment and storage medium | |
CN110378222B (en) | Method and device for detecting vibration damper target and identifying defect of power transmission line | |
CN110569837B (en) | Method and device for optimizing damage detection result | |
CN110264444B (en) | Damage detection method and device based on weak segmentation | |
CN110969166A (en) | Small target identification method and system in inspection scene | |
CN110633738B (en) | Rapid classification method for industrial part images | |
CN117593304B (en) | Semi-supervised industrial product surface defect detection method based on cross local global features | |
Farag | A lightweight vehicle detection and tracking technique for advanced driving assistance systems | |
CN112989947A (en) | Method and device for estimating three-dimensional coordinates of human body key points | |
CN114419029A (en) | Training method of surface defect detection model, surface defect detection method and device | |
CN114049356A (en) | Method, device and system for detecting structure apparent crack | |
CN111179270A (en) | Image co-segmentation method and device based on attention mechanism | |
CN115830407A (en) | Cable pipeline fault discrimination algorithm based on YOLOV4 target detection model | |
CN116206334A (en) | Wild animal identification method and device | |
Nassar et al. | Assessing data quality of annotations with Krippendorff alpha for applications in computer vision | |
CN114662605A (en) | Flame detection method based on improved YOLOv5 model | |
CN118037692A (en) | Steel surface defect detection method and system based on computer vision | |
CN116805387B (en) | Model training method, quality inspection method and related equipment based on knowledge distillation | |
TW201601119A (en) | Method for recognizing and locating object | |
Yin et al. | Road Damage Detection and Classification based on Multi-level Feature Pyramids. | |
CN117829243A (en) | Model training method, target detection device, electronic equipment and medium | |
CN112733864A (en) | Model training method, target detection method, device, equipment and storage medium | |
CN114549548A (en) | Glass image segmentation method based on polarization clue | |
CN112818965B (en) | Multi-scale image target detection method and system, electronic equipment and storage medium | |
CN114782877A (en) | Valve fault detection method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |