CN110599458A - Underground pipe network detection and evaluation cloud system based on convolutional neural network - Google Patents
Underground pipe network detection and evaluation cloud system based on convolutional neural network Download PDFInfo
- Publication number
- CN110599458A CN110599458A CN201910750559.9A CN201910750559A CN110599458A CN 110599458 A CN110599458 A CN 110599458A CN 201910750559 A CN201910750559 A CN 201910750559A CN 110599458 A CN110599458 A CN 110599458A
- Authority
- CN
- China
- Prior art keywords
- module
- defect
- neural network
- convolutional neural
- pipeline
- 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
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 59
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 238000011156 evaluation Methods 0.000 title claims abstract description 42
- 230000007547 defect Effects 0.000 claims abstract description 102
- 238000012502 risk assessment Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims description 23
- 238000013138 pruning Methods 0.000 claims description 13
- 230000008439 repair process Effects 0.000 claims description 4
- 239000002689 soil Substances 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 9
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 238000011176 pooling Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000002950 deficient Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000007849 functional defect Effects 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 229910000906 Bronze Inorganic materials 0.000 description 1
- 239000010974 bronze Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- KUNSUQLRTQLHQQ-UHFFFAOYSA-N copper tin Chemical compound [Cu].[Sn] KUNSUQLRTQLHQQ-UHFFFAOYSA-N 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010348 incorporation Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008521 reorganization Effects 0.000 description 1
- 239000013585 weight reducing agent Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2136—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on sparsity criteria, e.g. with an overcomplete basis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
- H04N7/185—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source from a mobile camera, e.g. for remote control
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Signal Processing (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
Abstract
The invention discloses a convolution neural network-based underground pipe network detection and evaluation cloud system, which comprises a cloud server module, a defect identification service module and a risk evaluation service module; the defect identification service module is used for detecting and identifying the defect information of the underground pipeline, and the defect identification service module identifies and detects the defect information of the pipeline through a GoogleNe convolutional neural network; the cloud server module transmits the acquired underground pipeline video and image information to the defect identification service module through the underground pipe network risk assessment cloud system to detect and identify the underground pipeline; the defect identification service module transmits the detected and identified information to the risk evaluation service module through the underground pipe network risk evaluation cloud system to carry out risk evaluation on the pipeline information. The invention aims to provide the underground pipe network detection and evaluation cloud system based on the convolutional neural network, which has the advantages of strong intelligent degree and high detection efficiency, greatly improves the detection precision and saves the labor cost.
Description
Technical Field
The invention relates to the technical field of pipeline detection, in particular to a convolution neural network-based underground pipe network detection and evaluation cloud system.
Background
The safe operation of the drainage pipeline is directly related to urban public safety and environmental protection, and the defect detection of the drainage pipeline network is more and more emphasized. The CCTV technology is a widely used drainage pipeline defect detection technology.
There are also a number of experts and scholars who propose to use image processing methods to automatically identify pipe defects in CCTV video, such as Tung-Ching Su et al using morphological methods to detect pipe cracks, and Alaa Hawari et al using Gabor filtering and brightness correction in addition to morphological methods to detect cracks for detecting deposits and dislocations, respectively. However, such conventional image processing methods still cannot meet the automation requirement of pipeline defect detection. On one hand, the pipeline defects are various, and the detection of various defects is difficult to effectively solve by a single algorithm. If a plurality of algorithms are integrated for simultaneous detection, the detection efficiency is inevitably reduced, and the development, operation and maintenance and cost are overhigh. On the other hand, the detection method based on the traditional image processing has limited precision because the pipeline environment is complex.
The Chinese patent application numbers are: 201711221526.2, application date is 11/29/2017, publication date is: year 2018, 04, 06, with patent names: the invention discloses an underground pipeline defect automatic identification method based on deep learning, which comprises the steps of preparing an underground pipeline positive sample set and an underground pipeline negative sample set required by training a convolutional neural network, preprocessing the sample sets, modifying the sample sets into uniform size of 300 x 300 in batches, and then performing data lifting to generate sample data for training; designing a structure of a convolutional neural network, training, and acquiring a weight connection matrix W when the network converges for a later detection process; for video data, firstly eliminating 10 frames before and after a video, roughly selecting a defective target frame, and then sampling key frames of the video every 10 ms; inputting each sampling frame of the video into a convolutional neural network, and judging whether a defect exists or not; and summarizing whether the video contains defects or not according to the result of each frame acquired in the step five. The method improves the utilization rate of data, and automatically learns the characteristics of the image of the defective pipeline through the convolutional network, thereby realizing the automatic identification of the defective pipeline.
The patent literature discloses an automatic underground pipeline defect identification method based on deep learning, but the method has low detection efficiency, high maintenance cost and limited detection precision.
Disclosure of Invention
In view of this, the invention provides a convolution neural network-based underground pipe network detection and evaluation cloud system which has strong intelligent degree and high detection efficiency, greatly improves the detection precision, and saves the labor cost.
In order to realize the purpose of the invention, the following technical scheme can be adopted:
a convolution neural network-based underground pipe network detection and evaluation cloud system comprises a cloud server module, a defect identification service module and a risk evaluation service module; the cloud server module is used for storing underground pipeline videos and image information, the defect identification service module is used for detecting and identifying underground pipeline defect information, and the defect identification service module is used for identifying and detecting the pipeline defect information through a convolutional neural network; the convolutional neural network comprises a GoogLeNet convolutional neural network; the risk assessment module is used for performing risk assessment on the defects of the underground pipeline;
the cloud server module transmits the acquired underground pipeline video and image information to the defect identification service module through the underground pipe network risk assessment cloud system to detect and identify the underground pipeline; the defect identification service module transmits the detected and identified information to the risk evaluation service module through the underground pipe network risk evaluation cloud system to carry out risk evaluation on the pipeline information.
The google lenet convolutional neural network comprises 9 linearly stacked inclusion modules.
The inclusion module of the cloud linear stack includes 3 filters to perform convolution operations on the input signal.
The GoogLeNet convolutional neural network adopts a pruning method to identify and detect the defect information of the pipeline.
The pruning method is to reduce the number of channels of the convolution kernel by minimizing the error between the feature graph after the cropping and the feature graph before the cropping.
The number of channels is given by the formulaAnd obtaining a result. subject to | | | β | | | non-phosphor0≤c'
The cloud server module comprises a video storage module and an image acquisition module; the video storage module is used for storing video information of the underground pipeline; the image acquisition module is used for acquiring image information of the underground pipeline.
The defect identification service module comprises a defect identification module, a defect statistics module and a defect reporting module; the defect identification module is used for detecting and analyzing underground pipeline cracks; the defect counting module is used for recording and storing the defect information of the underground pipeline; and the defect reporting module is used for carrying out communication transmission on the defect information of the underground pipeline.
The risk assessment service module comprises a risk assessment module and an intelligent decision-making module; the risk assessment module is used for performing risk assessment on the defect information of the underground pipeline; and the intelligent decision module is used for making a decision on the evaluation of the defect information of the underground pipeline.
The risk assessment module obtains an assessment result through a formula R which is 0.7 XF +0.1 XK +0.05 XE +0.15 XT;
wherein, R is the pipe section repair index; f-defect parameter; k is a regional importance parameter; e-pipeline importance parameter; t-soil property influence parameter.
The technical scheme provided by the invention has the beneficial effects that 1) the invention detects and analyzes the defects of the underground pipeline by a convolutional neural network, the detection efficiency is high, and the detection precision is greatly improved; 2) the invention has high intelligent degree and low maintenance cost, and greatly saves the labor power of the interior operation; 3) the invention detects the defects of the underground pipeline through the convolutional neural network, greatly improves the technical grade and achieves the purpose of upgrading and updating.
Drawings
FIG. 1 is a schematic diagram of an underground pipe network detection and evaluation cloud system based on a convolutional neural network according to an embodiment of the present invention;
FIG. 2 is a block diagram of a detection and evaluation cloud system of a underground pipe network based on a convolutional neural network according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a defect identification process of a cloud system for underground pipe network detection and evaluation based on a convolutional neural network according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating convolutional neural network defect identification of a convolutional neural network-based underground pipe network detection and evaluation cloud system according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a google lenet convolutional neural network of a detection and evaluation cloud system of an underground pipe network based on a convolutional neural network according to an embodiment of the present invention;
FIG. 6 is a graph of map importance parameters of an underground pipe network detection and evaluation cloud system based on a convolutional neural network according to an embodiment of the present invention;
FIG. 7 is an underground pipeline importance diagram of an underground pipe network detection and evaluation cloud system based on a convolutional neural network according to an embodiment of the present invention;
fig. 8 is a soil property influence chart of the underground pipe network detection and evaluation cloud system based on the convolutional neural network according to the embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and embodiments thereof.
Example 1
Referring to fig. 1 and 2, an underground pipe network detection and evaluation cloud system 4 based on a convolutional neural network comprises a cloud server module 41, a defect identification service module 42 and a risk evaluation service module 43; the cloud server module 41 is configured to store video and image information of the underground pipeline, the defect identification service module 42 is configured to detect and identify defect information of the underground pipeline, and the defect identification service module 42 identifies and detects the defect information of the pipeline through a convolutional neural network; the convolutional neural network comprises a GoogLeNet convolutional neural network; the risk assessment module 43 is used for performing risk assessment on the defects of the underground pipeline;
the cloud server module 41 transmits the collected underground pipeline video and image information to the defect identification service module 42 through the underground pipe network risk assessment cloud system 4 to detect and identify the underground pipeline; the defect identification service module 42 transmits the detected and identified information to the risk assessment service module 43 through the underground pipe network risk assessment cloud system 4 to perform risk assessment on the pipeline information.
The Convolutional Neural Network (CNN) is a feedforward Neural Network, and functions of local receptive field, convolution, pooling and the like are introduced into the Neural Network. The convolutional neural network is composed of convolutional layers, full-link layers, pooling layers and the like.
The invention adopts a deep convolutional neural network to construct a defect identification model, referring to fig. 4, the deep neural network carries out multilayer representation on a target by constructing a multilayer network so as to represent abstract semantic information of data by multilayer high-level features, and better feature robustness is obtained. The deep neural network is a local receptive field, a weight sharing layer and a posing layer, so that network parameters are simplified, and the network has certain displacement, scale, scaling and nonlinear deformation stability.
Convolutional neural networks have some advantages over conventional techniques: the method has good fault-tolerant capability, parallel processing capability and self-learning capability, can solve the problems of complex environmental information, unclear background knowledge and uncertain inference rule, allows the sample to have larger defect and distortion, and has high operation speed, good self-adaption performance and higher resolution. The method fuses the feature extraction function into a multilayer perceptron through structural reorganization and weight reduction, and omits a complicated image feature extraction process before identification.
First we construct a training set for model training, which contains a large number of pipeline defect images and non-defect images. And adjusting and optimizing the model parameters through a BP (back propagation) algorithm to finally obtain the depth model.
In the identification stage, the read-in video data bronze drum is preprocessed to obtain a preprocessed image, and then the preprocessed image is sent to a convolutional neural network for defect identification.
Example 2
Referring to fig. 2, fig. 3 is different from the above embodiment in that, in the present embodiment, the cloud server module 41 includes a video storage module 411 and an image acquisition module 412; the video storage module 411 is used for storing video information of the underground pipeline; the image acquisition module 412 is used for acquiring image information of the underground pipeline.
In the invention, through a video collector 4111, a mobile robot, preferably CCTV, in this embodiment performs video collection on video information of an underground network management, and then sends the video information to a video processing module 4112 to perform video information processing such as cutting, compression, enhancement and the like on the video information, and transmits the video information to a video storage module 411 to store the video information; then, the processed information is transmitted to a video frame extracting module 4113 for performing video frame extraction processing on the video according to the frame rate of 40 fps; after the frame extraction processing, the information is transmitted to a frame processing module 4114 to record the frame information, that is, the frame processing is performed; after the frame processing, the video information is transmitted to a defect identification module 421 for defect identification processing, and after the defect identification module 421 processes the defect information, the video information is transmitted to a defect statistics module 422 for statistics of the defect information; then, the defect information is transmitted to a risk assessment module 431 for risk assessment of the underground pipeline information; the assessed risk information may be transmitted to the risk assessment service module 43; the defect information processed by the defect identification module 421 may also be transmitted to the defect identification service module 42.
Example 3
Referring to fig. 2, the difference from the above embodiment is that in this embodiment, the defect identification service module 42 includes a defect identification module 421, a defect statistics module 422, and a defect reporting module 423; the defect identification module 421 detects and analyzes the cracks of the underground pipeline; the defect counting module 422 is used for recording and storing the defect information of the underground pipeline; the defect reporting module 423 is configured to perform communication transmission on the underground pipeline defect information.
The defect identification service module 42 identifies and detects the pipeline defect information through a convolutional neural network; the convolutional neural network comprises a GoogLeNet convolutional neural network;
referring to fig. 5, the method adopts a google lenet convolutional neural network to identify and detect the pipeline defect information; the google lenet convolutional neural network has 9 linearly stacked inclusion modules.
The inclusion module has 22 layers (27 layers including the pooling layer). Fig. 5 is a raw inclusion module. The inclusion module performs convolution operations on the input signal using 3 filters (1x1,3x3,5x5) of different sizes; in addition, the inclusion module also performs max pooling. The inputs of all sub-layers are finally cascaded and passed to the next incorporation module.
Example 4
In this embodiment, the google lenet convolutional neural network identifies and detects the pipeline defect information by using a pruning method.
The pruning method is to reduce the number of channels of the convolution kernel by minimizing the error between the feature graph after the cropping and the feature graph before the cropping.
The number of channels is given by the formulaAnd obtaining a result. subject to | | | β | | | non-phosphor0≤c'
The GoogleNet convolutional neural network has more convolutional and pooling layers than the VGGNet convolutional neural network, and therefore has better feature discrimination capability. However, due to the fact that the training samples are insufficient, overfitting is easily caused, the GoogleNet convolutional neural network is optimized through a pruning method, network connection can be thinned through network pruning, and the possibility of expanding the network scale is provided. Specifically, when a large neural network is trained, one part is not needed. The method is beneficial to reducing the complexity of the network and improving the generalization capability. The pruning method of the invention reduces the number of channels of the convolution kernel as much as possible by minimizing the error between the feature graph after the cropping and the feature graph before the cropping.
Let CinW and CoutRespectively an input feature map, a convolution kernel and an output feature map. c and n are the number of channels of the input feature map and the number of channels of the output feature map. In the convolution calculation, im2col is used to represent the input feature map, the convolution kernel, and the output feature map, which are: (H W) Cin*kh*kw) (ii) an input feature map of (C)in*kh*kw)*(Cout) (H x W) of (C)out) The output characteristic map of (1). Where H and W are the height and width of the output signature, respectively.
Let CinW and CoutRespectively an input feature map, a convolution kernel and an output feature map. c and n are the number of channels of the input feature map and the number of channels of the output feature map. In the convolution calculation, im2col is used to represent the input feature map, the convolution kernel, and the output feature map, which are: (H W) Cin*kh*kw) (ii) an input feature map of (C)in*kh*kw)*(Cout) (H x W) of (C)out) The output characteristic map of (1). Where H and W are the height and width of the output signature, respectively.
It can be known from the matrix multiplication that the corresponding rows in the convolution kernel are only multiplied by the specific columns in the input feature map matrix, and when we cut the number of channels in the convolution kernel, the number of channels in the corresponding input feature map can be cut, and the convolution kernel of the corresponding upper layer outputting the current input feature map can be cut.
How to select the clipping channel is the key point considered by the invention.
In this embodiment, Y in the formula 1 is an original output characteristic diagram, and the second half is a clipped output characteristic diagram. The distance between the two is taken as an error, and the purpose is to keep the difference between the pruned feature map and the original feature map to be minimum under the condition of pruning as much as possible. When beta is 0, the corresponding input layer is invalid, and the pruning effect is achieved. The constraint term in the formula is 0 norm of beta, and c' is a hyperparameter, which represents the minimum number of pruning we want to prune. Because optimizing a loss function with a 0 norm is an NP difficult problem, the invention introduces lasso to replace the original loss function, and sparsizes beta vectors as much as possible. As shown in equation 2
subject to||β||0≤c'
In this embodiment, the GoogleNet convolutional neural network optimization process may be divided into two steps:
a. and fixing the W parameter, and adopting an iterative method to make the beta vector as sparse as possible to reach the preset pruning number.
b. And fixing the iterated beta, changing the input X into X ', wherein X' is the product of the iterated beta and the original input X. The classification module passes through a formula
Example 4
Referring to fig. 6, 7, and 8, the difference between the above embodiments is that, in the present embodiment, the risk assessment service module 43 includes a risk assessment module 431 and an intelligent decision module 432; the risk assessment module 431 is used for performing risk assessment on the defect information of the underground pipeline; the intelligent decision module 432 is used for making decisions on the evaluation of the defect information of the underground pipeline.
The risk assessment module 43 of the present invention uses a formula
R＝0.7×F+0.1×K+0.05×E+0.15×T
Obtaining an evaluation result;
wherein, R is the pipe section repair index; f-defect parameter; k is a regional importance parameter; e-pipeline importance parameter; t-soil property influence parameter.
The risk assessment module 43 may also determine its repair index, which is specified by the following formula:
M＝0.8×G+0.15×K+0.05×E
wherein, M is a pipe section maintenance index; k is a regional importance parameter; e-pipeline importance parameter; g-functional defect parameter of pipe section
The specific calculation is as follows:
when Y ismaxWhen Y is not less than Y, G ═ Ymax(10)
When Y ismaxWhen < Y, G ═ Y (11)
Ymax-pipe segment operating condition parameters, score of the most severe of the functional defects;
y is the pipe section running condition parameter, and the functional defect average score is calculated according to the defect points.
Wherein Y and YmaxThe value depends on the recognition result of the defect recognition model.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (10)
1. A underground pipe network detection and evaluation cloud system based on a convolutional neural network is characterized in that: the system comprises a cloud server module, a defect identification service module and a risk assessment service module; the cloud server module is used for storing underground pipeline videos and image information, the defect identification service module is used for detecting and identifying underground pipeline defect information, and the defect identification service module is used for identifying and detecting the pipeline defect information through a convolutional neural network; the convolutional neural network comprises a GoogLeNet convolutional neural network; the risk assessment module is used for performing risk assessment on the defects of the underground pipeline;
the cloud server module transmits the acquired underground pipeline video and image information to the defect identification service module through the underground pipe network risk assessment cloud system to detect and identify the underground pipeline; the defect identification service module transmits the detected and identified information to the risk evaluation service module through the underground pipe network risk evaluation cloud system to carry out risk evaluation on the pipeline information.
2. The convolutional neural network-based underground pipe network detection and evaluation cloud system of claim 1, wherein: the google lenet convolutional neural network includes 9 linearly stacked inclusion modules.
3. The convolutional neural network-based underground pipe network detection and evaluation cloud system of claim 2, wherein: the inclusion module of the cloud linear stack includes 3 filters to perform convolution operations on the input signal.
4. The convolutional neural network-based underground pipe network detection and evaluation cloud system of claim 1, wherein: the GoogLeNet convolutional neural network adopts a pruning method to identify and detect the defect information of the pipeline.
5. The convolutional neural network-based underground pipe network detection and evaluation cloud system of claim 4, wherein: the pruning method is to reduce the number of channels of the convolution kernel by minimizing the error between the feature graph after the cropping and the feature graph before the cropping.
6. The convolutional neural network-based underground pipe network detection and evaluation cloud system of claim 5, wherein: the number of channels is given by the formulaAnd obtaining a result.
7. The convolutional neural network-based underground pipe network detection and evaluation cloud system of claim 1, wherein: the cloud server module comprises a video storage module and an image acquisition module; the video storage module is used for storing video information of the underground pipeline; the image acquisition module is used for acquiring image information of the underground pipeline.
8. The convolutional neural network-based underground pipe network detection and evaluation cloud system of claim 1, wherein: the defect identification service module comprises a defect identification module, a defect statistics module and a defect reporting module; the defect identification module is used for detecting and analyzing underground pipeline cracks; the defect counting module is used for recording and storing the defect information of the underground pipeline; and the defect reporting module is used for carrying out communication transmission on the defect information of the underground pipeline.
9. The convolutional neural network-based underground pipe network detection and evaluation cloud system of claim 1, wherein: the risk assessment service module comprises a risk assessment module and an intelligent decision-making module; the risk assessment module is used for performing risk assessment on the defect information of the underground pipeline; and the intelligent decision module is used for making a decision on the evaluation of the defect information of the underground pipeline.
10. The convolutional neural network-based underground pipe network detection and evaluation cloud system of claim 9, wherein: the risk assessment module obtains an assessment result through a formula R which is 0.7 XF +0.1 XK +0.05 XE +0.15 XT;
wherein, R is the pipe section repair index; f-defect parameter; k is a regional importance parameter; e-pipeline importance parameter; t-soil property influence parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910750559.9A CN110599458A (en) | 2019-08-14 | 2019-08-14 | Underground pipe network detection and evaluation cloud system based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910750559.9A CN110599458A (en) | 2019-08-14 | 2019-08-14 | Underground pipe network detection and evaluation cloud system based on convolutional neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110599458A true CN110599458A (en) | 2019-12-20 |
Family
ID=68854329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910750559.9A Pending CN110599458A (en) | 2019-08-14 | 2019-08-14 | Underground pipe network detection and evaluation cloud system based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110599458A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563455A (en) * | 2020-05-08 | 2020-08-21 | 南昌工程学院 | Damage identification method based on time series signal and compressed convolution neural network |
| CN114511557A (en) * | 2022-04-02 | 2022-05-17 | 深圳市君合环保水务科技有限公司 | Image processing-based underdrain structure defect detection method |
| CN115086010A (en) * | 2022-06-13 | 2022-09-20 | 北京融讯智晖技术有限公司 | Network risk assessment system based on video cloud command system |
| CN116304677A (en) * | 2023-01-30 | 2023-06-23 | 格兰菲智能科技有限公司 | Channel pruning method and device for model, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563495A (en) * | 2017-08-04 | 2018-01-09 | 深圳互连科技有限公司 | Embedded low-power consumption convolutional neural networks method |
| US20180232640A1 (en) * | 2017-02-10 | 2018-08-16 | Samsung Electronics Co., Ltd. | Automatic thresholds for neural network pruning and retraining |
| CN108982522A (en) * | 2018-08-09 | 2018-12-11 | 北京百度网讯科技有限公司 | Method and apparatus for detecting defect of pipeline |
| CN110119686A (en) * | 2019-04-17 | 2019-08-13 | 电子科技大学 | A kind of safety cap real-time detection method based on convolutional neural networks |
-
2019
- 2019-08-14 CN CN201910750559.9A patent/CN110599458A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180232640A1 (en) * | 2017-02-10 | 2018-08-16 | Samsung Electronics Co., Ltd. | Automatic thresholds for neural network pruning and retraining |
| CN107563495A (en) * | 2017-08-04 | 2018-01-09 | 深圳互连科技有限公司 | Embedded low-power consumption convolutional neural networks method |
| CN108982522A (en) * | 2018-08-09 | 2018-12-11 | 北京百度网讯科技有限公司 | Method and apparatus for detecting defect of pipeline |
| CN110119686A (en) * | 2019-04-17 | 2019-08-13 | 电子科技大学 | A kind of safety cap real-time detection method based on convolutional neural networks |
Non-Patent Citations (4)
| Title |
|---|
| JHONY-HERIBERTO GIRALDO-ZULUAGA 等，: "Automatic Recognition of Mammal Genera on Camera-Trap Images using Multi-Layer Robust Principal Component Analysis and Mixture Neural Networks", 《ARXIV》 * |
| 吴进 等，: "一种基于Lasso回归与SVD融合的深度学习模型压缩方法", 《电讯技术》 * |
| 纪荣嵘 等，: "深度神经网络压缩与加速综述", 《计算机研究与发展》 * |
| 许州等，: "CCTV用于成都市锦兴路排水管道检测与评估", 《中国给水排水》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563455A (en) * | 2020-05-08 | 2020-08-21 | 南昌工程学院 | Damage identification method based on time series signal and compressed convolution neural network |
| CN111563455B (en) * | 2020-05-08 | 2023-07-11 | 南昌工程学院 | Injury identification method based on time sequence signals and compressed convolutional neural network |
| CN114511557A (en) * | 2022-04-02 | 2022-05-17 | 深圳市君合环保水务科技有限公司 | Image processing-based underdrain structure defect detection method |
| CN115086010A (en) * | 2022-06-13 | 2022-09-20 | 北京融讯智晖技术有限公司 | Network risk assessment system based on video cloud command system |
| CN115086010B (en) * | 2022-06-13 | 2023-10-24 | 北京融讯智晖技术有限公司 | Network risk assessment system based on video cloud command system |
| CN116304677A (en) * | 2023-01-30 | 2023-06-23 | 格兰菲智能科技有限公司 | Channel pruning method and device for model, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111353413B (en) | Low-missing-report-rate defect identification method for power transmission equipment | |
| CN110599458A (en) | Underground pipe network detection and evaluation cloud system based on convolutional neural network | |
| CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
| CN110232380A (en) | Fire night scenes restored method based on Mask R-CNN neural network | |
| CN110599459A (en) | Underground pipe network risk assessment cloud system based on deep learning | |
| CN110222592B (en) | Construction method of time sequence behavior detection network model based on complementary time sequence behavior proposal generation | |
| CN113436184B (en) | Power equipment image defect discriminating method and system based on improved twin network | |
| CN116485709A (en) | Bridge concrete crack detection method based on YOLOv5 improved algorithm | |
| CN116030396B (en) | Accurate segmentation method for video structured extraction | |
| CN114155474A (en) | Damage identification technology based on video semantic segmentation algorithm | |
| CN112487938A (en) | Method for realizing garbage classification by utilizing deep learning algorithm | |
| CN110599460A (en) | Underground pipe network detection and evaluation cloud system based on hybrid convolutional neural network | |
| CN111242028A (en) | Remote sensing image ground object segmentation method based on U-Net | |
| CN114898359A (en) | Litchi pest and disease detection method based on improved EfficientDet | |
| CN113888505A (en) | Natural scene text detection method based on semantic segmentation | |
| CN116363536B (en) | Unmanned aerial vehicle inspection data-based power grid infrastructure equipment defect archiving method | |
| CN112418229A (en) | Unmanned ship marine scene image real-time segmentation method based on deep learning | |
| CN117218545A (en) | LBP feature and improved Yolov 5-based radar image detection method | |
| CN116229315A (en) | Time sequence action detection method and device based on coarse-to-fine granularity information capture | |
| CN115439690A (en) | Flue-cured tobacco leaf image grading method combining CNN and Transformer | |
| CN114723953A (en) | Deep neural network for image source detection | |
| CN115100546A (en) | Mobile-based small target defect identification method and system for power equipment | |
| CN114821174A (en) | Power transmission line aerial image data cleaning method based on content perception | |
| CN112016403A (en) | Video abnormal event detection method | |
| CN116109607B (en) | Power transmission line engineering defect detection method based on image segmentation |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191220 |