CN108760739B - System and method for detecting rust state of civil air defense door - Google Patents
System and method for detecting rust state of civil air defense door Download PDFInfo
- Publication number
- CN108760739B CN108760739B CN201810541824.8A CN201810541824A CN108760739B CN 108760739 B CN108760739 B CN 108760739B CN 201810541824 A CN201810541824 A CN 201810541824A CN 108760739 B CN108760739 B CN 108760739B
- Authority
- CN
- China
- Prior art keywords
- image
- air defense
- defense door
- rust
- civil air
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
A civil air defense door rust state detection system and method, the system includes the light path layout module used for obtaining the video image of the front and back of the door leaf of the civil air defense door; the data acquisition module is used for receiving the video image acquired by the light path layout module; the intelligent analysis module is used for determining the corrosion state abnormal condition of the civil air defense door; the display terminal is used for displaying the determined corrosion state abnormal condition of the civil air defense door, and the electric main control box is respectively and electrically connected with the light path layout module, the data acquisition module, the image data server, the intelligent analysis module and the display terminal. The automatic rust state monitoring of people's air defense door that has realized shows people's air defense door corrosion state in real time, makes things convenient for fortune dimension personnel to know people's air defense door state in time and maintains it, guarantees the reliability of people's air defense door wartime, has improved work efficiency.
Description
Technical Field
The invention belongs to the technical field of civil air defense doors, and particularly relates to an automatic detection system for a rust state of a civil air defense door.
Background
The civil air defense door is a door at the entrance and exit of the civil protection project, and is used for protecting refuge people in wartime, blocking toxic gas and blasting and killing. The civil air defense door is in a normally open state in peace period, and due to the fact that the civil air defense door is exposed outside all the year round, the phenomenon of corrosion is frequently generated on the surface of the civil air defense door. The accumulated result of the corrosion on the surface of the door which lasts for a long time is to make the protection function of the door be greatly discounted, the war preparedness requirement can not be met, and the barrier and closure function can not be realized in the real war period. Therefore, the door is found in time at the early stage of door corrosion, the civil air defense door is maintained in time, and the door corrosion damage can be avoided.
The rust of the civil air defense door is mainly found by routine inspection of inspectors. For most civil air defense projects, the polling period of a polling person is long, and too many polling points are difficult to meet. The timeliness and comprehensiveness of the problem finding can not meet the requirements.
How to design an automatic detection system for the rust of the civil air defense door becomes a problem which needs to be solved urgently by the technical personnel in the field.
Disclosure of Invention
In view of this, the present invention provides a system for detecting the rust state of a civil air defense door, so as to comprehensively find the rust state of the civil air defense door in real time, maintain the civil air defense door in time, and improve the wartime safety and the maintenance convenience of the civil air defense door.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a civil air defense door corrosion state detection system comprises
The light path layout module comprises two cameras which are respectively arranged on two corresponding sides of the front surface and the back surface of the door leaf of the civil air defense door and used for obtaining video images of the front surface and the back surface of the door leaf of the civil air defense door;
the data acquisition module is used for receiving the video image acquired by the light path layout module;
the image data server is used for storing original and real-time video image information of the civil air defense door leaf;
the intelligent analysis module is used for analyzing and comparing the original and real-time video images of the civil air defense door leaf stored in the image data server: comparing the difference between the original video image and the real-time video image, outputting a difference image, comparing the difference image with a training sample of a training sample library, and determining the corrosion state abnormal condition of the civil air defense door;
the display terminal is used for displaying the determined abnormal situation of the rust state of the civil air defense door;
and the electric main control box is electrically connected with the light path layout module, the data acquisition module, the image data server, the intelligent analysis module and the display terminal respectively.
Also comprises a control host which is electrically connected with the electric main control box,
the control host machine is connected with the main control box through an electric main control box:
turn on/off the optical path layout module, or
Starting the intelligent analysis module to analyze and compare the images, or,
and acquiring video image information of a door leaf of the civil air defense door stored in the image data server, or acquiring the corrosion state abnormal condition of the civil air defense door confirmed by the intelligent analysis module.
Still include remote control center, remote control center sets up automatic fortune dimension module, control host and remote control center are connected, remote control center acquires, saves people's air defense door corrosion state abnormal conditions through control host to send the fortune dimension scheme in the automatic fortune dimension module for control host.
A detection method for the rust state of a civil air defense door comprises the following steps:
s1: a camera of the light path layout module acquires an image of a door leaf of the civil air defense door;
s2: the data acquisition module receives the video image acquired by the light path layout module and transmits the video image to the intelligent analysis module;
s3: the intelligent analysis module calls original and real-time video images of the civil air defense door leaf stored by the image data server;
s4: the intelligent analysis module carries out image analysis and comparison on the original and real-time video images of the civil air defense door leaf: comparing the difference between the original video image and the real-time video image, outputting a difference image, comparing the difference image with a training sample of a training sample library, and determining the corrosion state abnormal condition of the civil air defense door;
s5: the electric main control box displays the corrosion state abnormal state of the civil air defense door on the display terminal;
the analysis and comparison of the original and real-time video images in step S4 are obtained by the following steps:
s41: establishing a rust image sample library: collecting corrosion image blocks of the metal gate to make a counter sample library, and collecting non-corrosion image blocks of the metal gate to make a positive sample library;
s42, establishing a sample label: setting the label of the sample image in the counter sample library as 1, and setting the label of the sample image in the positive sample library as 0;
s43: the rust image sample library established in the S41 corresponds to the sample label established in the S42 to form a sample label set;
s44: extracting sample image features: converting the image from an rgb space to a Lab image space by utilizing an OpenCV function cvtColor band parameter CV _ BGR2Lab, and calculating a histogram of a three-channel image by utilizing an OpenCV function calcHist to serve as an image feature of a sample;
s45: and (3) classification training: training the sample image characteristics obtained in the S44 by adopting an SVM algorithm in a machine learning module in OpenCV, obtaining a training file after the training is finished, and storing the file in an xml file format;
s46: inputting a real-time image and an original image of the civil air defense door;
s47: image registration: registering the real-time image to the original image;
s48: image comparison and difference output: comparing the structural similarity of the current image and the original image by adopting an SSIM algorithm, and outputting an image block with a large difference degree with the original image in the real-time image as a suspected rust image block;
and S49, corrosion state identification output: extracting the image characteristics of the suspected rust image block by adopting the method of the step S44, and identifying whether the suspected rust image block is a rust image by utilizing the training file formed in the step S45 and a KNN algorithm; in the identification process, more than 20 nearest sample images are searched by using a findBearest function in OpenCV for comparison, and when more than 10 images belong to the rust image, the image block can be considered as the rust image.
The image registration in step S47 is as follows:
s471: solving surf feature description points of the input real-time image and the original image by adopting a surf algorithm;
s472: solving matching points for the feature description points by using a feature matching point algorithm FlanBasedMatcher in opencv;
s473: statistically calculating a matching minimum distance min _ dis from the matching points, and screening the matching points with the matching distance less than 5 times min _ dis as an optimal matching point set by taking min _ dis as a reference;
s474: and (3) solving an affine transformation matrix H between the current real-time image and the original image by using an opencv function findHomography for the optimal matching point set between the real-time image and the original image, and calculating the affine transformation matrix H by using an opencv function warp Peractive to register the current image to the original image.
S491: counting the early warning values in the 20 nearest neighbor sample images found by using findNoresest in the KNN algorithm, counting the number of samples for warning at each level, and taking the maximum number of samples as the early warning level of the rust state; and when the number of samples of the plurality of alarm levels is the same, adopting the highest early warning level to carry out early warning.
Further comprises a rust state alarming step:
s492: assuming that the pixel area of the ith rust image block identified by the rust state is Si, the early warning coefficient is Xi, i is 1,2, … n, n is the number of detected rust, the door leaf pixel area is S, and Sb is the rectangular frame surrounding box pixel area of the detected rust image block; the rust alarm is generated under the following conditions:
(1)、(S1*X1+S2*X2+…….+Sn*Xn)÷10÷S≥0.1；
(2)、Sb÷S≥0.5。
the method also comprises the following intelligent operation and maintenance steps:
s6: inputting an operation and maintenance scheme summarized based on the knowledge and experience of the operation and maintenance expert into a database of a remote data center;
s7: based on the result of the detection of the abnormal state of the rusty state of the civil air defense door at step S5, the corresponding operation and maintenance scheme stored at S6 is invoked.
The operation and maintenance scheme comprises the following steps: the system comprises information of the civil air defense door in an abnormal state, query of standby products, notification of maintenance teams, and optimal routes and maintenance measures for going to abnormal places.
Compared with the prior art, the civil air defense door corrosion state detection system has the following advantages:
due to the adoption of the technical scheme:
(1) the system integrates and collects the electric main control box, the light path layout module, the data acquisition module, the image data server, the intelligent analysis module, the display terminal and the like, controls the camera, the image acquisition analysis module, the intelligent analysis module and the like through the electric main control box, monitors, acquires, analyzes and processes the corrosion state of the civil air defense door in real time, displays the corrosion state of the civil air defense door, facilitates the operation and maintenance personnel to know the state of the civil air defense door and maintain the state of the civil air defense door in time, ensures the reliability of the civil air defense door in wartime, and improves the working efficiency.
(2) Meanwhile, a remote data center is arranged, massive door leaf picture information is stored in real time, a data backup effect is achieved, and the people's air defense door corrosion condition can be obtained in real time through an electronic monitoring and big data analysis mode.
(3) The image data server has the function of storing multiple video images, provides support for multiple times of calling of the intelligent analysis module, provides original images for the door rust prevention state of people and provides service for later-stage fault analysis.
(4) The intelligent analysis module has a self-processing function, and firstly, the door leaf video image acquired by the data acquisition module is compared with the original video image; the rust condition is determined, and the automatic analysis function can realize the alarm function of the grading state of the rust condition of the door leaf of the civil air defense door; the mass data are transmitted in real time in the process, and the processing process is fast and efficient.
(5) The rust state grading early warning is also arranged, so that the grading solution of the corresponding problem is facilitated, and the adaptability is improved; meanwhile, a rust state alarm is preset, so that major safety accidents are avoided.
(6) The operation and maintenance system based on the expert knowledge and experience of the operation and maintenance of the civil air defense door is arranged in the remote control center, so that the function of automatically providing the operation and maintenance scheme of the civil air defense door is realized, a certain automatic maintenance function is realized, and the efficiency is improved; meanwhile, the remote data center has the functions of remotely controlling and issuing the instructions and one-to-many integrated processing, so that the monitoring efficiency and the remote instruction capability are improved, and the problems can be systematically found and the related safety problems can be solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic view of the imaging optical path of the civil air defense door of the invention.
FIG. 2 is a schematic diagram of the detection system of the present invention.
FIG. 3 is a flow chart of civil air defense door rust detection.
Fig. 4 is a flow chart of the analysis and alignment of raw and real-time video images.
Fig. 5 is a flow chart of image registration.
Description of reference numerals:
1: first camera, 2: first light filling lamp, 3: civil air defense door leaf, 4: second camera, 5: and a second fill-in lamp.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
The corrosion of the door leaf of the civil air defense door is a slow process, if the problem can be found in the initial stage of deformation, maintenance measures can be taken in time, and destructive influence can not be caused on the function of the civil air defense door. According to the invention, the camera is used for monitoring the civil air defense door, and the surface data of the civil air defense door is acquired in real time. Based on machine vision measurement technology, this kind of non-contact measurement mode realizes people's air defense door leaf corrosion and detects. By adopting the method, the deformation state of the civil air defense door can be known in real time in peace period, and maintenance units can maintain the civil air defense door in time according to the deformation condition, so that the civil air defense door plays a real role in wartime.
1 System composition, see FIG. 2
The system comprises
The light path layout module comprises two cameras which are respectively arranged on two corresponding sides of the front surface and the back surface of the door leaf of the civil air defense door and used for obtaining video images of the front surface and the back surface of the door leaf of the civil air defense door; in the light path layout, two large surfaces (front and back) of the door need to be monitored, two imaging units are adopted for monitoring, each imaging unit comprises a camera and a light supplementing unit, and lenses of the cameras are matched according to actual installation positions. The relevant components are identified in fig. 1.
The data acquisition module is used for receiving the video image acquired by the light path layout module;
the image data server is used for storing original and real-time video image information of the civil air defense door leaf;
the intelligent analysis module is used for analyzing and comparing the original and real-time video images of the civil air defense door leaf stored in the image data server: comparing the difference between the original video image and the real-time video image, outputting a difference image, comparing the difference image with a training sample of a training sample library, and determining the corrosion state abnormal condition of the civil air defense door;
the display terminal is used for displaying the determined abnormal situation of the rust state of the civil air defense door;
and the electric main control box is electrically connected with the light path layout module, the data acquisition module, the image data server, the intelligent analysis module and the display terminal respectively.
Also comprises a control host which is electrically connected with the electric main control box,
the control host machine is connected with the main control box through an electric main control box:
turn on/off the optical path layout module, or
Starting the intelligent analysis module to analyze and compare the images, or,
and acquiring video image information of a door leaf of the civil air defense door stored in the image data server, or acquiring the corrosion state abnormal condition of the civil air defense door confirmed by the intelligent analysis module.
Still include remote control center, remote control center sets up automatic fortune dimension module, control host and remote control center are connected, remote control center acquires, saves people's air defense door corrosion state abnormal conditions through control host to send the fortune dimension scheme of automatic fortune dimension module for control host.
2 civil air defense door leaf corrosion state detection flow
Fig. 3 is a flow chart of detecting rust state of door leaf of the civil defense door, which is mainly divided into two parts from a large module: a training part and a detection part. The training part is mainly used for training according to the existing metal door rust image sample, and training files generated by training are used for detection. The detection part detects the door leaf corrosion state and positions the door leaf corrosion block; carrying out grading early warning and alarming according to the corrosion condition; and finally, providing an operation and maintenance scheme used by operation and maintenance personnel according to an operation and maintenance plan library established by expert experience.
2.1 training part
The training part is a counter sample library and a positive sample library of the rustless image blocks, which are manufactured based on the metal gate rust image blocks collected by various channels, and a training file is obtained by utilizing a machine learning algorithm to be used by the detection part. The training part only needs to run training software to obtain a training file after collecting samples.
2.1.1 inputting rust image positive and negative samples
The positive sample of the corrosion image is an image block without a corrosion part which is deducted from an image of a civil air defense door or a steel manufacturing door; negative samples are image blocks including rust subtracted from the civil air defense door or steel door image. The resolution size of the image blocks is not less than 20 x 20. In the running process of the system, positive and negative sample images can be continuously collected and retrained to obtain a training file to correct error recognition.
2.1.2 Corrosion identification parameter training
The sample image label indicates whether the sample image belongs to a corrosion image, the corrosion image is 1, the corrosion image is not 0, and in order to realize the corrosion degree alarm in the next step, a 0-10 grade corrosion early warning coefficient is set for the corrosion sample image. All sample images and corresponding labels are formed into a set and provided to the next module for processing.
Extracting sample image features: and converting the image from the rgb space to the Lab image space by utilizing an OpenCV function cvtColor band parameter CV _ BGR2Lab, and calculating a histogram of the three-channel image by utilizing an OpenCV function calcHist as the characteristic of the sample image.
The classification training is carried out by adopting an SVM algorithm in a machine learning module in OpenCV, a training file is obtained after the training is finished, and the file is stored in an xml file format for subsequent detection and identification.
2.2 detection section
2.2.1 image registration
Image registration implementation flow: and solving and inputting surf characteristic description points of the current image and the historical image by adopting a surf algorithm, wherein the historical image is a civil air defense door image acquired when the door is initially installed, and can also be an image without rusting the door after confirmation. And solving the matching points by using a feature matching point algorithm FlannBasedMatcher in opencv, then statistically calculating a minimum matching distance min _ dis in the matching points, and screening the matching points with the matching distance less than 5 times min _ dis as an optimal matching point set by taking the min _ dis as a reference. And (3) solving an affine transformation matrix H between the current image and the historical image by using an opencv function findHomography and finally registering the current image to the historical image by using an opencv function warp Peractive.
2.2.2 image comparison and Difference output
Through the image registration of the previous stage, the current image is registered to the historical image, and the current image and the historical image are compared. For historical images, in software, an interactive mode is adopted to frame out a door leaf area as a follow-up, and only the door leaf area is compared in comparison. The framing out of the sector area in the historical image can be completed only once when the software is deployed and configured. In the comparison, an SSIM algorithm (fully called structural similarity index, namely structural similarity) is adopted, the structural similarity of the two images is compared, and the image blocks with large difference in the current image are output as suspected rust image blocks.
2.2.3 Corrosion status recognition output
And inputting the last suspected rust image block, extracting the image characteristics of the suspected rust image block by adopting a characteristic extraction algorithm with the same rust identification parameter training process, and identifying whether the suspected rust image block is a rust image or not by utilizing a training file and a KNN algorithm. In the identification process, more than 20 nearest sample images are searched by using a findBearest function in OpenCV for comparison, and when more than 10 images belong to the rust image, the image block can be considered as the rust image.
2.2.4 hierarchical early warning of rust states
And counting the early warning values in the 20 nearest neighbor sample images found by using findNoresest in the KNN algorithm, counting the number of samples for warning at each level, and taking the maximum number of samples as the early warning level of the rust state. And when the number of samples of the plurality of alarm levels is the same, adopting the highest early warning level to carry out early warning.
2.2.5 Rust State Warning
The pixel area of the ith rust image block identified by the rust state is assumed to be Si, the early warning coefficient is Xi, i is 1,2, … n, n is the number of detected rust, the door leaf pixel area is S, and Sb is the rectangular box surrounding pixel area of the detected rust image block. The rust alarm is generated under the following conditions:
(1)、(S1*X1+S2*X2+…….+Sn*Xn)÷10÷S≥0.1
(2)、Sb÷S≥0.5
2.2.6 rust corrosion operation and maintenance scheme
The intelligent operation and maintenance is based on the results of intelligent analysis and event analysis, and an operation and maintenance scheme is automatically given by combining the knowledge and experience of operation and maintenance experts of the civil air defense door. Firstly, inputting an operation and maintenance plan library in the system, wherein each stage of early warning comprises an operation and maintenance scheme in the plan library; each alarm contains an operation and maintenance scheme. The operation and maintenance scheme comprises the following steps: the system comprises information of the civil air defense door in an abnormal state, query of standby products, notification of maintenance teams, and optimal routes and maintenance measures for going to abnormal places.
Effects of the invention
(1) Compared with manual regular inspection and observation, the method provided by the patent can realize that the corrosion condition of the civil air defense door can be checked at any time according to the requirement.
(2) This patent utilizes computer vision technique, has realized automatic monitoring people's air defense door corrosion state completely.
(3) The patent provides a hierarchical early warning of people's air defense door corrosion state and warning and automatic generation fortune dimension scheme, provides profitable solution for the corrosion fortune dimension of people's side door.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (6)
1. A detection method for the rust state of a civil air defense door is characterized by comprising the following steps: the method comprises the following steps:
s1: a camera of the light path layout module acquires an image of a door leaf of the civil air defense door;
s2: the data acquisition module receives the video image acquired by the light path layout module and transmits the video image to the intelligent analysis module;
s3: the intelligent analysis module calls original and real-time video images of the civil air defense door leaf stored by the image data server;
s4: the intelligent analysis module carries out image analysis and comparison on the original and real-time video images of the civil air defense door leaf: comparing the difference between the original video image and the real-time video image, outputting a difference image, comparing the difference image with a training sample of a training sample library, and determining the corrosion state abnormal condition of the civil air defense door;
s5: the electric main control box displays the corrosion state abnormal state of the civil air defense door on the display terminal;
wherein, the analysis and comparison of the original and real-time video images in step S4 are obtained by the following steps:
s41: establishing a rust image sample library: collecting corrosion image blocks of the metal gate to make a counter sample library, and collecting non-corrosion image blocks of the metal gate to make a positive sample library;
s42, establishing a sample label: setting the label of the sample image in the counter sample library as 1, and setting the label of the sample image in the positive sample library as 0;
s43: the rust image sample library established in the S41 corresponds to the sample label established in the S42 to form a sample label set;
s44: extracting sample image features: converting the image from an rgb space to a Lab image space by utilizing an OpenCV function cvtColor band parameter CV _ BGR2Lab, and calculating a histogram of a three-channel image by utilizing an OpenCV function calcHist to serve as an image feature of a sample;
s45: and (3) classification training: training the sample image characteristics obtained in the S44 by adopting an SVM algorithm in a machine learning module in OpenCV, obtaining a training file after the training is finished, and storing the file in an xml file format;
s46: inputting a real-time image and an original image of the civil air defense door;
s47: image registration: registering the real-time image to the original image;
s48: image comparison and difference output: adopting an SSIM algorithm to compare the structural similarity of the current real-time image and the original image, and outputting an image block with a large difference degree with the original image in the real-time image as a suspected rust image block;
and S49, corrosion state identification output: extracting the image characteristics of the suspected rust image block by adopting the method of the step S44, and identifying whether the suspected rust image block is a rust image by utilizing the training file formed in the step S45 and a KNN algorithm; in the identification process, more than 20 nearest sample images are searched by using a findBearest function in OpenCV for comparison, and when more than 10 images belong to the rust image, the image block can be considered as the rust image.
2. The method for detecting the rusting state of the civil air defense door according to claim 1, wherein the method comprises the following steps: the image registration in step S47 is as follows:
s471: solving surf feature description points of the input real-time image and the original image by adopting a surf algorithm;
s472: solving matching points for the feature description points by using a feature matching point algorithm FlanBasedMatcher in opencv;
s473: statistically calculating a matching minimum distance min _ dis from the matching points, and screening the matching points with the matching distance less than 5 times min _ dis as an optimal matching point set by taking min _ dis as a reference;
s474: and (3) solving an affine transformation matrix H between the current real-time image and the original image by using an opencv function findHomography for the optimal matching point set between the real-time image and the original image, and calculating the affine transformation matrix H by using an opencv function warp Peractive to register the current image to the original image.
3. The method for detecting the rusting state of the civil air defense door according to claim 2, wherein the method comprises the following steps: the method also comprises the step of rust state grading early warning:
s491: counting the early warning values in the 20 nearest neighbor sample images found by using findNoresest in the KNN algorithm, counting the number of samples for warning at each level, and taking the maximum number of samples as the early warning level of the rust state; and when the number of samples of the plurality of alarm levels is the same, adopting the highest early warning level to carry out early warning.
4. The method for detecting the rusting state of the civil air defense door according to claim 3, wherein the method comprises the following steps: further comprises a rust state alarming step:
s492: assuming that the pixel area of the ith rust image block identified by the rust state is Si, the early warning coefficient is Xi, i is 1,2, … n, n is the number of detected rust, the door leaf pixel area is S, and Sb is the rectangular frame surrounding box pixel area of the detected rust image block; the rust alarm is generated under the following conditions:
(1)、(S1*X1+S2*X2+…….+Sn*Xn)÷10÷S≥0.1；
(2)、Sb÷S≥0.5。
5. the method for detecting the rusting state of the civil air defense door according to the claim 3 or 4, wherein the following steps are carried out: the method also comprises the following intelligent operation and maintenance steps:
s6: inputting an operation and maintenance scheme summarized based on the knowledge and experience of the operation and maintenance expert into a database of a remote data center;
s7: based on the result of the detection of the abnormal state of the rusty state of the civil air defense door at step S5, the corresponding operation and maintenance scheme stored at S6 is invoked.
6. The method for detecting the rusting state of the civil air defense door according to claim 5, wherein the method comprises the following steps: the operation and maintenance scheme comprises the following steps: the system comprises information of the civil air defense door in an abnormal state, query of standby products, notification of maintenance teams, and optimal routes and maintenance measures for going to abnormal places.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810541824.8A CN108760739B (en) | 2018-05-30 | 2018-05-30 | System and method for detecting rust state of civil air defense door |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810541824.8A CN108760739B (en) | 2018-05-30 | 2018-05-30 | System and method for detecting rust state of civil air defense door |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108760739A CN108760739A (en) | 2018-11-06 |
| CN108760739B true CN108760739B (en) | 2020-10-09 |
Family
ID=64004707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810541824.8A Active CN108760739B (en) | 2018-05-30 | 2018-05-30 | System and method for detecting rust state of civil air defense door |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108760739B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114529779B (en) * | 2021-12-31 | 2023-04-07 | 扬州市恒泰人防设备有限公司 | System and method for detecting rust state of civil air defense door |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105157595A (en) * | 2015-09-25 | 2015-12-16 | 浙江中技建设工程检测有限公司 | Method and device for detecting deformation and defects of existing building |
| CN105243672A (en) * | 2015-11-03 | 2016-01-13 | 苏交科集团股份有限公司 | Anticorrosive coating damage distinguishing system and assessment method thereof |
| CN106379784A (en) * | 2016-10-28 | 2017-02-08 | 齐鲁工业大学 | Visual detection method and system for mine reinforcing steel bar inhaul cable |
| CN106875543B (en) * | 2017-01-25 | 2019-06-07 | 杭州视氪科技有限公司 | It is a kind of based on visually impaired people's bill acceptor system of RGB-D camera and recognition methods |
| CN106846608B (en) * | 2017-01-25 | 2019-03-01 | 杭州视氪科技有限公司 | A kind of visually impaired people's paper money recognition glasses based on RGB-D camera |
-
2018
- 2018-05-30 CN CN201810541824.8A patent/CN108760739B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108760739A (en) | 2018-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109001210B (en) | System and method for detecting aging and cracking of sealing rubber strip of civil air defense door | |
| CN111860230B (en) | Automatic detection system and method based on behavior of video monitoring personnel not wearing mask | |
| CN111310947A (en) | Building facility operation and maintenance method, equipment, storage medium and system based on 5G | |
| CN110889339B (en) | Head and shoulder detection-based dangerous area grading early warning method and system | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN209543514U (en) | Monitoring and alarm system based on recognition of face | |
| CN110458794B (en) | Quality detection method and device for accessories of rail train | |
| CN110589647A (en) | Method for real-time fault detection and prediction of elevator door through monitoring | |
| CN117035419B (en) | Intelligent management system and method for enterprise project implementation | |
| CN111783700B (en) | Automatic recognition and early warning method and system for pavement foreign matters | |
| CN110688879A (en) | Storage counting method | |
| CN112132048A (en) | Community patrol analysis method and system based on computer vision | |
| US20230186634A1 (en) | Vision-based monitoring of site safety compliance based on worker re-identification and personal protective equipment classification | |
| CN114662208B (en) | Construction visualization system and method based on Bim technology | |
| CN108760739B (en) | System and method for detecting rust state of civil air defense door | |
| CN117235443A (en) | Electric power operation safety monitoring method and system based on edge AI | |
| KR20210133827A (en) | Apparatus for learning deep learning model and method thereof | |
| CN113052125B (en) | Construction site violation image recognition and alarm method | |
| CN116403162B (en) | Airport scene target behavior recognition method and system and electronic equipment | |
| CN117079203A (en) | Road construction monitoring method, system and storage medium | |
| CN112153341B (en) | Task supervision method, device and system, electronic equipment and storage medium | |
| JPH0460880A (en) | Moving body discrimination and analysis controlling system | |
| KR102435435B1 (en) | System for searching numbers of vehicle and pedestrian based on artificial intelligence | |
| CN113255422A (en) | Process connection target identification management method and system based on deep learning | |
| CN117253176B (en) | Safe production Al intelligent detection method based on video analysis and computer vision |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191121 Address after: No. 1104-12, building 2, No. 118, weijianian 1st Road, Jinniu District, Chengdu City, Sichuan Province Applicant after: Chengdu Tianren Civil Defense Technology Co., Ltd Address before: 100036 room 1328, 13 floor, 5 building, Lianhua court, Haidian District, Beijing. Applicant before: Tian Ren civil defence construction engineering design Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |