CN118096634A - Gas leakage detection method and device, electronic equipment and storage medium - Google Patents
Gas leakage detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN118096634A CN118096634A CN202211502396.0A CN202211502396A CN118096634A CN 118096634 A CN118096634 A CN 118096634A CN 202211502396 A CN202211502396 A CN 202211502396A CN 118096634 A CN118096634 A CN 118096634A
- Authority
- CN
- China
- Prior art keywords
- image
- detection
- gas
- infrared image
- leakage
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 252
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000012549 training Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000013135 deep learning Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 9
- 238000003384 imaging method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000003993 interaction Effects 0.000 description 5
- 238000001931 thermography Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 238000009792 diffusion process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 229910018503 SF6 Inorganic materials 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- SFZCNBIFKDRMGX-UHFFFAOYSA-N sulfur hexafluoride Chemical compound FS(F)(F)(F)(F)F SFZCNBIFKDRMGX-UHFFFAOYSA-N 0.000 description 1
- 229960000909 sulfur hexafluoride Drugs 0.000 description 1
- TXEYQDLBPFQVAA-UHFFFAOYSA-N tetrafluoromethane Chemical compound FC(F)(F)F TXEYQDLBPFQVAA-UHFFFAOYSA-N 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The embodiment of the application provides a gas leakage detection method, a device, electronic equipment and a storage medium, and relates to the field of gas leakage detection. Wherein the method comprises the following steps: continuously acquiring an infrared image; performing preliminary detection on a leakage gas target in the infrared image to obtain a detection result; the detection result comprises whether a leaked gas target exists in the infrared image or not and an image area of the leaked gas target in the infrared image; if the detection result indicates that a leaked gas target exists in the infrared image, carrying out fine detection and identification on an image area of the leaked gas target in the infrared image according to a background difference algorithm; and if the identification result indicates that the leaked gas target exists in the image area, obtaining a gas leakage detection result. The embodiment of the application solves the problems that the gas leakage detection is seriously interfered by the environment and the detection accuracy is not high in the related technology, can automatically select and update the background image in the background differential algorithm, and better realizes the automation of the gas leakage detection.
Description
Technical Field
The present application relates to the field of gas leakage detection, and in particular, to a gas leakage detection method, a device, an electronic apparatus, and a storage medium.
Background
With the vigorous development of the chemical industry, the method is particularly important for detecting the leakage of dangerous gas in the production process, and once the leakage of dangerous gas is not detected in time, the method can cause serious harm to the life safety and the environment of staff.
However, in the existing gas leakage detection method, a background is manually extracted from a video by adopting a background extraction algorithm, and the background is differentiated from each video image in the video, so that a gas leakage area is reserved, and gas leakage detection is realized.
From the above, the problem of how to improve the accuracy of gas leakage detection remains to be solved.
Disclosure of Invention
The embodiments of the application provide a gas leakage detection method, a device and an electronic equipment machine storage medium, which can solve the problems that the gas leakage detection in the related technology is seriously interfered by the environment, the detection accuracy is not high, and the background cannot be automatically selected and updated. The technical scheme is as follows:
According to one aspect of an embodiment of the present application, a gas leakage detection method includes: continuously acquiring an infrared image, wherein the infrared image is obtained by shooting an environment in which gas leakage possibly occurs; performing preliminary detection on a leakage gas target in the infrared image to obtain a detection result; the detection result comprises whether a leakage gas target exists in the infrared image or not and an image area of the leakage gas target in the infrared image; if the detection result indicates that the leaked gas target exists in the infrared image, performing fine detection and identification on an image area of the leaked gas target in the infrared image according to a background difference algorithm; and if the identification result indicates that the leaked gas target exists in the image area, obtaining a gas leakage detection result.
According to an aspect of an embodiment of the present application, a gas leakage detection device includes: the image acquisition module is used for continuously acquiring infrared images, and the infrared images are obtained by shooting an environment in which gas leakage possibly occurs; the preliminary detection module is used for carrying out preliminary detection on the leaked gas target in the infrared image to obtain a detection result; the detection result comprises whether a leakage gas target exists in the infrared image or not and an image area of the leakage gas target in the infrared image; the fine detection module is used for carrying out fine detection and identification on an image area of the leaked gas target in the infrared image according to a background difference algorithm if the detection result indicates that the leaked gas target exists in the infrared image; and the result acquisition module is used for acquiring a gas leakage detection result if the identification result indicates that the leaked gas target exists in the image area.
According to one aspect of an embodiment of the present application, an electronic device includes: at least one processor, at least one memory, and at least one communication bus, wherein the memory stores computer programs, and the processor reads the computer programs in the memory through the communication bus; the computer program, when executed by a processor, implements the gas leakage detection method as described above.
According to an aspect of an embodiment of the present application, a storage medium has stored thereon a computer program which, when executed by a processor, implements the gas leakage detection method as described above.
According to an aspect of an embodiment of the present application, a computer product includes a computer program stored in a storage medium, and a processor of the computer product reads the computer program from the storage medium and executes the computer program, so that the computer product implements the gas leakage detection method as described above.
The technical scheme provided by the application has the beneficial effects that:
In the above technical solution, by continuously acquiring an infrared image, the infrared image is obtained by photographing an environment in which gas leakage may occur; preliminary detection is carried out on a leakage gas target in the infrared image to obtain a detection result, wherein the detection result comprises whether the leakage gas target exists in the infrared image or not and an image area of the leakage gas target in the infrared image; if the detection result indicates that a leaked gas target exists in the infrared image, carrying out fine detection and identification on an image area of the leaked gas target in the infrared image according to a background difference algorithm; and if the identification result indicates that the leaked gas target exists in the image area, obtaining a gas leakage detection result. After the leaked gas target is detected in the infrared image preliminarily, the image area of the leaked gas target in the infrared image is further subjected to fine detection and identification processing through a background differential algorithm, so that whether the leaked gas target exists or not is determined more accurately, the problems that the gas leakage detection in the related technology is seriously interfered by the environment and the detection accuracy is low can be effectively solved, the background image is automatically selected and updated in the background differential algorithm, the automation of the gas leakage detection is better realized, and the problem that the background cannot be automatically selected and updated in the related technology is avoided.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that are required to be used in the description of the embodiments of the present application will be briefly described below.
FIG. 1 is a schematic diagram of an implementation environment shown in accordance with an exemplary embodiment;
FIG. 2 is a flow chart illustrating a method of gas leak detection according to an exemplary embodiment;
FIG. 3 is a flowchart of an image processing process, according to an exemplary embodiment;
FIG. 4 is a flowchart illustrating step 350, according to an exemplary embodiment;
FIG. 5 is a flowchart illustrating obtaining a differential image according to an exemplary embodiment;
FIG. 6 is a flow chart illustrating another gas leak detection method according to an exemplary embodiment;
FIG. 7 is a background differential processing flow diagram that is shown in accordance with an exemplary embodiment;
FIG. 8 is a flowchart illustrating acquiring an infrared image dataset, according to an example embodiment;
FIG. 9 is a flowchart illustrating a training gas leak detection model according to an exemplary embodiment;
Fig. 10 is an application scenario of a gas leakage detection method according to an exemplary embodiment;
FIG. 11 is a schematic diagram of a background selection and differencing process flow involved in the application scenario of FIG. 10;
FIG. 12 is a gas leak detection apparatus according to an exemplary embodiment;
FIG. 13 is a hardware configuration diagram of an electronic device shown according to an exemplary embodiment;
fig. 14 is a block diagram illustrating a configuration of an electronic device according to an exemplary embodiment.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
The infrared focal plane detector is a thermal imager device, and mainly converts the intensity of infrared radiation in a target scene into a thermal imaging image, and because gas molecules can absorb infrared radiation in a specific wave band, a region with gas leakage exists in the scene, part of background infrared radiation is absorbed by the gas, the gray value of pixels in the corresponding region is reduced in response to the thermal imaging, the reduction degree is related to the concentration and the absorption degree of the gas, and thus the imaging of the leaked gas is realized.
The infrared imaging technology for gas leakage uses an infrared focal plane detector to image an infrared band, and judges the gas leakage point and the gas diffusion area according to the characteristic of dynamic diffusion during gas leakage and the absorbability of gas molecules in the infrared band. However, in the prior art, the resolution of the infrared image is low, typically 640×480, and the imaging is sensitive to temperature, the contrast of the image is low, the image has non-uniformity and poor quality, and when an object with a lower temperature exists in the field of view, the contrast of the whole image becomes low, so that the application of the imaging to the detection of gas leakage is limited.
As described above, once the dangerous gas leakage occurs without being detected in time, it may cause serious harm to the life safety of the worker and the environment.
In order to avoid dangerous gas leakage which is not detected in time, the method proposed by the prior art comprises the steps of manually extracting a background from a video by adopting a background extraction algorithm, wherein the method is seriously interfered by the environment, a moving object cannot exist in a scene, the background is difficult to update, and the detection accuracy is not high; or detecting the gas by adopting a processing method of deep learning target detection, regarding the leaked gas as target detection, finding a leaked gas target in the infrared image, determining a specific position and dividing. For example, comparing representative R-CNN algorithms, the detection steps include: and extracting the characteristics of the input image to obtain a candidate region possibly containing a leakage gas target, and performing classification regression and segmentation on the candidate region. However, in the method, the time consumption for detecting the leaked gas target by the model is long, so that the real-time performance of gas leakage detection cannot be ensured, and meanwhile, false detection is easy to occur.
It can be seen that the related art still has a defect of low accuracy of gas leakage detection.
Therefore, the gas leakage detection method provided by the application can effectively improve the real-time performance of gas leakage detection, reduce the influence of environment, improve the detection accuracy and realize the automatic selection and updating of the background. Accordingly, the gas leak detection method is applicable to gas leak detection apparatus that may be deployed in an electronic device, e.g., a computer device deployed in von neumann architecture, including, but not limited to, a desktop computer, a notebook computer, a server, and the like.
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.
FIG. 1 is a schematic diagram of an implementation environment for a gas leak detection method. It should be noted that this implementation environment is only one example adapted to the present invention and should not be considered as providing any limitation to the scope of use of the present invention.
The implementation environment includes a user terminal 110, an image capture device 130, a gateway 150, a server side 170, and a router 190.
Specifically, the user terminal 110 may be considered as a user terminal or a terminal, and may be configured (or understood as installed) with a client associated with the smart device 130 to perform gas leakage detection on the infrared image captured by the image capturing device 130, where the user terminal 110 may be an electronic device such as a smart phone, a tablet computer, a notebook computer, a desktop computer, or other devices with display functions, which is not limited herein.
The image acquisition device 130 is disposed in the gateway 150, and communicates with the gateway 150 through its own configured communication module, and is further controlled by the gateway 150. It should be understood that image capture device 130 is generally referred to as one of a plurality of image capture devices 130, and embodiments of the present application are merely illustrated with image capture device 130, i.e., embodiments of the present application are not limited in the number and type of intelligent devices deployed in gateway 150. In one application scenario, image capture device 130 is deployed in gateway 150 by accessing gateway 150 over a local area network. The process of the image acquisition device 130 accessing the gateway 150 through the local area network includes: a local area network is first established by gateway 150, and image capture device 130 joins the local area network established by gateway 150 by connecting to gateway 150. Such local area networks include, but are not limited to: ZIGBEE or bluetooth. The image capturing device 130 may be other electronic devices with thermal imaging functions, such as an infrared focal plane detector.
The interaction between the user terminal 110 and the image capturing device 130 may be implemented through a local area network, or may be implemented through a wide area network. In an application scenario, the ue 110 establishes a communication connection between the router 190 and the gateway 150 in a wired or wireless manner, for example, including but not limited to WIFI, so that the ue 110 and the gateway 150 are disposed in the same local area network, and further the ue 110 may implement interaction with the image capturing device 130 through a local area network path. In another application scenario, the ue 110 establishes a wired or wireless communication connection between the server 170 and the gateway 150, for example, but not limited to, 2G, 3G, 4G, 5G, WIFI, etc., so that the ue 110 and the gateway 150 are deployed in the same wide area network, and further the ue 110 may implement interaction with the smart device 130 through a wide area network path.
The server 170 may be considered as a cloud, a cloud platform, a server, etc., where the server 170 may be a server, a server cluster formed by a plurality of servers, or a cloud computing center formed by a plurality of servers, so as to better provide background services to a large number of user terminals 110. For example, the background service includes a gas leak detection service.
For the image capturing device 130, after capturing the infrared image, the infrared image may be sent to the server 170 through the gateway 150; or the infrared image is transmitted to the user terminal 110 through the gateway 150 and the router 190, so that the gas leakage detection is performed on the infrared image using the server side 170 and the user terminal 110.
The main task of gas leakage detection is to judge whether an input infrared image contains a leakage gas target or not and accurately find out an image area of the leakage gas target in the infrared image. However, the existing gas leakage detection technology has the problems of poor detection instantaneity, incapability of automatically selecting and updating the background, serious environmental interference and the like in the application process, so that false detection is easy to occur when dangerous gas leakage detection is carried out, and serious harm is caused to the life safety of staff and the environment.
In order to overcome the above-mentioned drawbacks, referring to fig. 2, an embodiment of the present application provides a gas leakage detection method, which is suitable for an electronic device, for example, the electronic device may be the server 170 or the user terminal 110 in the implementation environment shown in fig. 1.
The main body of execution of each step of the method is described as an electronic device, but this configuration is not particularly limited.
As shown in fig. 2, the method may include the steps of:
In step 310, the infrared image is continuously acquired.
Wherein, the infrared image is obtained by shooting the environment in which gas leakage may occur.
The embodiment of the application can be applied to electronic equipment, and the electronic equipment can be other image acquisition equipment with a thermal imaging function, such as an infrared focal plane detector.
In some embodiments, the infrared image may be an image acquired by the image acquisition device by capturing an environment where a gas leakage target may occur in real time, or may be a video image frame in a video to be detected acquired by the image acquisition device, where the video to be detected reflects a situation of the environment where the gas leakage may occur. That is, when the embodiment of the application collects the infrared image, the environment in which the gas leakage area may occur can be directly collected, and a certain video image frame in the video frames to be detected can be indirectly collected as the infrared image.
In other words, in the process of capturing an environment in which gas leakage may occur, the continuously acquired infrared image may be a plurality of pictures from independent capturing, or may be a video from continuous capturing, which is not limited herein.
And 330, performing preliminary detection on the leaked gas target in the infrared image to obtain a detection result.
The detection result comprises whether a leaked gas target exists in the infrared image or not and an image area of the leaked gas target in the infrared image. It should be noted that the image area may be marked in the infrared image by a regression frame of a non-limited shape, such as a rectangle, a polygon, a circle, etc., so that the position of the image area is uniquely represented by the coordinates of the regression frame in the infrared image.
In one possible implementation, the preliminary detection of the leaked gas target in the infrared image is implemented by calling a gas leakage detection model; the gas leakage detection model is obtained based on training of an infrared image data set; the infrared image dataset includes a plurality of training images that have been marked for the presence of a leaking gas target.
Specifically, as shown in fig. 3, the size of the infrared image is first adjusted, the infrared image is adjusted to 640 x 640, and then every other pixel of the infrared image is taken as a value, so that the compression of the width and height of the infrared image is realized, and the operation amount in the detection process is reduced. And then, carrying out channel adjustment and feature extraction on the infrared image by using a gas leakage detection model, inputting a feature layer into a feature pyramid to fuse features, and enhancing feature extraction. And predicting whether a leakage gas target exists in the infrared image according to the extracted characteristics to obtain a detection result. The detection result is not only used for indicating whether a leaked gas target exists in the infrared image, but also used for indicating an image area of the leaked gas target in the infrared image. In one possible implementation, the detection results include a classification of whether the leaked gas target is present in the infrared image, and a location of the leaked gas target in an image region in the infrared image.
It should be noted that the position of the image area of the leaking gas target in the infrared image is obtained by marking using a regression frame, and the position of the image area of the leaking gas target in the infrared image is substantially represented by the position of the center point coordinates of the regression frame, which is not particularly limited herein.
In one possible implementation, the gas leak detection model is a deep learning network that is trained and has the ability to detect the presence of a leaking gas target in an infrared image. For example, the deep learning network may be a YoloX deep learning network, which YoloX deep learning network has higher timeliness than a RCNN network, and the operation speed can be improved by 3-5 times in the same hardware environment.
And 350, if the detection result indicates that the leaked gas target exists in the infrared image, performing fine detection and identification on the image area of the leaked gas target in the infrared image according to a background difference algorithm.
Specifically, if the detection result indicates that a leaked gas target exists in the infrared image, extracting coordinates of a center point of a regression frame containing the leaked gas target from the infrared image, so as to obtain a position of the regression frame containing the leaked gas target, namely determining an image area of the leaked gas target in the infrared image, further performing background difference correlation processing on the image area in the regression frame by using a background difference algorithm, and performing further accurate detection and identification on whether the leaked gas target exists in the image area, thereby avoiding false detection of a gas leakage detection model. The background difference algorithm is implemented based on the difference processing of the image area in the infrared image and the background area in the background image, wherein the background image and the infrared image come from the same video, the background image refers to the infrared image in which the leakage gas target is not detected in the video, and it can be understood that the background area in the background image corresponds to the image area in the infrared image, that is, the position of the image area in the infrared image is consistent with the position of the background area in the background image, so that the background image can be automatically selected and updated in the background difference algorithm, and further, the automation of gas leakage detection can be better realized.
After the deep learning network detects that the leaked gas target exists in the infrared image, the background difference algorithm is used for carrying out fine detection and identification processing on the image area of the leaked gas target in the infrared image, so that whether the leaked gas target exists in the image area is further determined, false detection is avoided, the detection accuracy is improved, meanwhile, through the mutual combination of preliminary detection and fine detection, all tasks are prevented from being completed by the deep learning network, and the running time of a model can be saved.
Further, on the one hand, if the detection result indicates that the leaked gas target does not exist in the infrared image, the detection threshold is allowed to be reduced in the process of performing preliminary detection on the leaked gas target in the infrared image, and preliminary detection is repeatedly performed on the leaked gas target in the other continuously acquired infrared images based on the detection prediction after the reduction until the minimum value of the detection threshold is reached or the leaked gas target exists in the infrared image is detected.
The initial range of the detection threshold is set flexibly according to practical situations, and is not specifically limited herein. Of course, in other embodiments, the detection threshold may also be considered as a confidence that the infrared image is detected as having a leaking gas target, and is not specifically limited herein.
Specifically, when the infrared image input to the gas leakage detection model may not detect the existence of the leaked gas target in the infrared image due to low gas leakage concentration or low image resolution, a detection threshold value for determining whether the leaked gas target of the infrared image exists in the gas leakage detection model is reduced, and other continuously acquired infrared images are input to the gas leakage detection model after the detection threshold value is reduced for preliminary detection until the detection threshold value for detecting the existence of the leaked gas target in the infrared image or the gas leakage detection model reaches a minimum value.
In the process, the detection threshold value is adjusted in a self-adaptive mode, the change of the detection environment is better adapted, environmental interference is avoided, and further improvement of the detection accuracy is facilitated.
In step 370, if the identification result indicates that there is a leaking gas target in the image area, a gas leak detection result is obtained.
Wherein the recognition result is used to indicate whether a leakage gas target exists in the image area.
Specifically, if the identification result indicates that no leaked gas target exists in the image area, the method indicates that whether the leaked gas target exists in the infrared image or not is detected by the gas leakage detection model in a false mode, the infrared image is discarded, and the initial range of the detection threshold of the gas leakage detection model is restored, so that preliminary detection is conducted on whether the leaked gas target exists in other continuously acquired infrared images or not.
Conversely, if the identification result indicates that a leaking gas target exists in the image area, a gas leak detection result is obtained, where the gas leak detection result is used to indicate that a leaking gas target exists in the infrared image, and may also be considered as, in one possible implementation, whether the gas leak detection result includes a classification of whether a leaking gas target exists in the infrared image.
In one possible implementation, the gas leak detection results further include an image area of the leaking gas target in the infrared image.
Further, in one possible implementation manner, according to the obtained gas leakage detection result, gray gradient enhancement display is performed on an image area of the leaked gas target in the infrared image, and the enhanced infrared image is output.
Specifically, the gas leakage detection model detection and background difference recognition are performed to obtain a leakage gas target, and the absolute value of the difference value is taken to indicate the change rate of the gray value of the adjacent pixel point according to the difference value between the gray values of the adjacent pixel points in the infrared image, namely the gradient. When the gray value of the adjacent pixel point is not changed, namely the gradient is 0, the gray value cannot be changed even if the gradient is added with the gray value of the corresponding pixel point, and therefore the gray value of the pixel point in the original infrared image can be amplified by taking the absolute value of the difference value of the gray value of the adjacent pixel point for a plurality of times and adding the absolute value of the difference value with the corresponding pixel. In this way, not only the edge of the image area containing the leaked gas target in the infrared image is enhanced, but also the difference between the edge of the image area and the periphery of the image area containing the leaked gas target is enlarged, the enhanced display of the image area containing the leaked gas target is realized, and the enhanced infrared image is output, so that the risk of gas leakage of workers can be more timely and effectively reminded.
According to the gas leakage detection method provided by the application, the target detection in the deep learning is combined with the background difference, the deep learning neural network is used for carrying out preliminary detection on the leaked gas target in the infrared image, the image area where gas leakage is likely to exist in the infrared image is determined, further fine detection and identification are carried out according to the suspected leaked gas target in the background difference degree image area, the interference caused by the detection environment is reduced, and the problems that the real-time performance of gas leakage detection is poor, the background cannot be automatically selected and updated, and the accuracy is low due to serious environmental influence in the prior art are solved.
In addition, the image area with gas leakage is subjected to enhanced display processing and output, so that workers can be timely and effectively reminded of the risk of gas leakage.
Referring to fig. 4, in an exemplary embodiment, step 350 may include the steps of:
step 3510, continuously acquiring a video corresponding to the infrared image of the detected leakage gas target, and extracting a background image from the video; and determining a background area corresponding to the image area in the background image based on the image area of the leaked gas target in the infrared image.
The background image refers to an infrared image in which no leakage gas target is detected in the video. Specifically, for example, in a video of 10 minutes, if gas leakage occurs at 9 minutes, although any one frame of infrared image before 9 minutes can be used as a background image, one frame of infrared image before the infrared image in which the leakage gas target exists is extracted. The selection of the background image is updated in real time in the process of acquiring the background image, so that false recognition detection caused by scene change is reduced.
That is, the infrared image and the background image come from the same video acquired by the image acquisition device. For example, the video is captured for the same environment where gas leakage may occur.
Here, the image region in the infrared image corresponds to the background region in the background image, and means that the position of the image region in the infrared image coincides with the position of the background region in the background image.
In step 3530, the image area in the infrared image and the background area in the background image are subjected to differential processing, so as to obtain a differential image.
Specifically, an infrared image in which a leakage gas target is not detected is extracted from a video acquired by an image acquisition device to serve as a background image, gray values of corresponding pixel points in an image area of the leakage gas target in the infrared image and a corresponding background area in the background image are subtracted, and absolute values are taken, so that a differential image is obtained.
In step 3550, a recognition result is obtained according to whether the differential image contains a leakage gas target.
As shown in fig. 5, the differential image includes a white area and a black area, that is, only the image area (i.e., white area) in which the presence of the leaked gas target is detected in the gas leakage detection model is included in the differential image, and the remaining portion (i.e., black area) is erased, whereby the recognition result can be obtained according to whether the leaked gas target is present in the differential image.
Further, as shown in fig. 6, in one possible implementation, step 3550 may include the steps of:
In step 3551, filtering is performed on the differential image to obtain a differential filtered image.
Step 3553, superposing the differential filtering image with the infrared image of the target detected to have the leaked gas, to obtain a superposed image.
In step 3555, if the superimposed image includes a leakage gas target, the identification result indicates that the differential image includes a leakage gas target.
Specifically, for a video segment, the infrared images in the video segment are subjected to target detection on the leaked gas target through the gas leakage detection model, so that the infrared images with the leaked gas target and the background images without the leaked gas target in the video segment can be determined. As shown in fig. 7, when the gas leakage detection model indicates that a leakage gas target exists in the infrared image (the gas leakage image in fig. 7), the background image in fig. 7 does not have the leakage gas target, and the display of the leakage gas target in the infrared image subjected to background difference processing is not obvious, filtering processing is performed on the obtained difference image, namely, the gray scale contrast of the edge of the image area where the leakage gas target exists in the difference image is enhanced, and a difference filtering image is obtained, so that the enhanced display of the image area where the leakage gas target exists is realized. And superposing the differential filtering image and the infrared image with the original leaked gas target, namely replacing the gray value of the image area where the leaked gas target is located in the original infrared image with the image area which is enhanced in the differential filtering image, thereby obtaining a new superposition image with more obvious image area where the leaked gas target is located.
Based on the cooperation of the embodiments, the image area with the leaked gas target is conveniently and more obviously displayed from the infrared image, so that the staff can better recognize whether the gas leakage exists.
Referring to FIG. 8, in an exemplary embodiment, preliminary detection of a leaked gas target in an infrared image is accomplished by invoking a gas leakage detection model; the gas leakage detection model is obtained based on training of an infrared image data set; the infrared image dataset includes a plurality of training images that have been marked for the presence of a leaking gas target.
The process of marking the training image may include the following steps:
Step 510, simulating gas leakage by using safe gas in an environment where gas leakage possibly occurs, and shooting the environment simulating gas leakage under a plurality of groups of shooting conditions by using an image acquisition device to obtain a plurality of infrared images to be marked containing a leaked gas target;
The shooting conditions refer to different shooting preconditions set for obtaining a plurality of infrared images, and the shooting conditions can be flexibly adjusted according to actual needs of application scenes, for example, the shooting conditions can be any one or a combination of a plurality of different distances, different infrared lenses, different imaging backgrounds and different imaging acquisition positions.
Specifically, the gas leakage is simulated by using a safety gas in an environment where the gas leakage may occur, the safety gas may be sulfur hexafluoride, carbon tetrafluoride, or the like, and the gas leakage scene is photographed by an image acquisition device having an infrared thermal imaging function, such as an infrared focal plane detector, or the like. And according to different infrared lenses, acquiring a plurality of groups of infrared images of gas leakage at different distances, different imaging acquisition positions and different imaging backgrounds.
And 530, marking the leaked gas target in each infrared image to be marked to obtain each training image.
Specifically, the method includes marking the leaked gas target in each infrared image to be marked, specifically, selecting an image area of the leaked gas target in the infrared image by moving a rectangular frame for a mouse, wherein the rectangular frame is as close as possible to the edge of the image area of the leaked gas target in the infrared image, so that each training image is obtained, and training of the gas leakage detection model is facilitated according to each obtained training image. The marking may be implemented using various standard software, such as Labelimg software, which is not limited herein.
As shown in fig. 9, in one possible implementation manner, the training process for the gas leakage detection model may include the following steps:
step 610, inputting the training image in the infrared image dataset into the base model for target detection.
Step 630, determining a loss value according to the detected difference between the leaked gas target in the training image and the leaked gas target marked in the training image.
And 650, if the loss value meets the set convergence condition, training is completed, and the gas leakage detection model is obtained by converging the basic model, otherwise, updating the parameters of the basic model until the loss value meets the set convergence condition.
The basic model may be a YOLO model, a YOLO-based modified deep learning network model, a gas target detection algorithm, or the like, and is not particularly limited herein. It should be noted that, the setting of the convergence condition may be flexibly set according to the actual situation, for example, the convergence condition refers to that the number of iterations reaches a threshold value, or the convergence condition refers to that the loss value reaches a minimum, which is not limited herein.
Through the training process, a gas leakage detection model with the capability of detecting whether a leakage gas target exists in the infrared image is obtained, and then the leakage gas target in the infrared image can be detected.
The basic model has good detection precision and detection speed, the model code is easy to generate, and the target detection network model for gas leakage detection can be obtained after the infrared image dataset provided by the application is trained.
Fig. 10 to 11 are application scenarios of a gas leakage detection method provided by the present application. FIG. 10 is a schematic diagram showing a flow of a gas leakage detection method in an application scenario; fig. 11 shows a schematic diagram of a background selection and difference processing flow in an application scenario.
As shown in fig. 10, first, a detection threshold (confidence) of a gas leak detection model is initialized, and an infrared image acquired by an image acquisition device is input into the gas leak detection model to perform gas leak detection. The infrared image collected by the image collecting device is from an infrared video sequence, and the infrared video sequence is essentially a video stream, namely, an environment where gas leakage may occur is continuously photographed, so that the continuously obtained infrared image is input into a gas leakage detection model, as shown in fig. 11.
For the gas leakage detection model, carrying out preliminary detection on a leakage gas target aiming at each infrared image in the infrared video sequence, if the leakage gas target is not detected, reducing the detection threshold of the gas leakage model, and carrying out preliminary detection on other continuously acquired infrared images until the minimum value of the detection threshold is reached or the leakage gas target of the infrared image is detected; if the leaked gas target is detected, an image area where the leaked gas target is located in the infrared image is obtained and is represented by the position of the regression frame, so that the detection result of each infrared image is obtained. Based on the detection results of the infrared images, the infrared image with the leaked gas target is regarded as a gas leakage image, and the infrared image without the leaked gas leakage target is regarded as a background image, as shown in fig. 11, automatic selection and updating of the background are realized, so that the subsequent regional background difference is performed based on the gas leakage image and the background image.
And carrying out difference on an image area where a leaked gas target in the gas leakage image is located and a corresponding background area in the background image by using a background difference algorithm to realize further accurate detection and identification of the leaked gas target in the image area, thereby completing screening of the leaked gas target in the regression frame and eliminating the possibility of false detection.
Specifically, if no leaked gas target exists in the screened infrared image, which indicates that there is false detection, the initial threshold of the gas leakage detection model is restored, and the target detection flow is returned. Otherwise, if the screened infrared image has a leakage gas target, which indicates that no false detection exists, the image area where the leakage gas target in the infrared image is positioned is subjected to gray gradient enhancement display and then output. For example, a gray gradient enhanced display may refer to a color gradient enhanced display, and is not particularly limited herein.
In the application scene, the continuous detection of the leaked gas target is realized aiming at the infrared video sequence, and the real-time performance is higher. In addition, through preliminary detection and precise detection identification, false detection is not easy to occur on the premise of guaranteeing timeliness, and through self-adaptive adjustment of a detection threshold value, dependence on the background can be effectively reduced, and finally the accuracy of gas leakage detection is fully ensured.
The following are examples of the apparatus of the present application that may be used to perform the gas leak detection method of the present application. For details disclosed in the device embodiments of the present application, please refer to a method embodiment of the gas leakage detection method according to the present application.
Referring to fig. 12, an embodiment of the present application provides a gas leakage detection device 700, including but not limited to: an image acquisition module 710, a preliminary detection module 730, a fine detection module 750, and a result acquisition module 770.
The image acquisition module 710 is configured to continuously acquire an infrared image, where the infrared image is obtained by capturing an environment where gas leakage may occur.
The preliminary detection module 730 is configured to perform preliminary detection on a target of leaked gas in the infrared image, so as to obtain a detection result; the detection result includes whether a leaked gas target exists in the infrared image or not, and an image area of the leaked gas target in the infrared image.
The fine detection module 750 is configured to perform fine detection and identification on an image area of the leaked gas target in the infrared image according to a background difference algorithm if the detection result indicates that the leaked gas target exists in the infrared image.
The result obtaining module 770 is configured to obtain a gas leakage detection result if the identification result indicates that a leakage gas target exists in the image area.
It should be noted that, in the gas leakage detection device provided in the foregoing embodiment, only the division of the above functional modules is used as an example, and in practical application, the above functional distribution may be performed by different functional modules according to needs, that is, the internal structure of the gas leakage detection device may be divided into different functional modules to perform all or part of the functions described above.
In addition, the embodiments of the gas leakage detection apparatus and the embodiments of the gas leakage detection method provided in the foregoing embodiments belong to the same concept, and the specific manner in which each module performs the operation has been described in detail in the method embodiments, which are not described herein again.
Fig. 13 is a schematic diagram showing a structure of an electronic device according to an exemplary embodiment. The electronic device is suitable for use at the server side 170 in the implementation environment shown in fig. 1.
It should be noted that the electronic device is only an example adapted to the present application, and should not be construed as providing any limitation on the scope of use of the present application. Nor should the electronic device be construed as necessarily relying on or necessarily having one or more of the components of the exemplary electronic device 2000 illustrated in fig. 13.
The hardware structure of the electronic device 2000 may vary widely depending on the configuration or performance, as shown in fig. 13, the electronic device 2000 includes: a power supply 210, an interface 230, at least one memory 250, and at least one central processing unit (CPU, central Processing Units) 270.
Specifically, the power supply 210 is configured to provide an operating voltage for each hardware device on the electronic device 2000.
The interface 230 includes at least one wired or wireless network interface 231 for interacting with external devices. For example, the interaction between the user terminal 110 and the image acquisition device 130 in the implementation environment shown in fig. 1 is performed.
Of course, in other examples of the adaptation of the present application, the interface 230 may further include at least one serial-parallel conversion interface 233, at least one input-output interface 235, at least one USB interface 237, and the like, as shown in fig. 13, which is not particularly limited herein.
The memory 250 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, where the resources stored include an operating system 251, application programs 253, and data 255, and the storage mode may be transient storage or permanent storage.
The operating system 251 is used for managing and controlling various hardware devices and applications 253 on the electronic device 2000, so as to implement the operation and processing of the cpu 270 on the mass data 255 in the memory 250, which may be Windows server, mac OS XTM, unixTM, linuxTM, freeBSDTM, etc.
The application 253 is a computer program that performs at least one specific task based on the operating system 251, and may include at least one module (not shown in fig. 13), each of which may respectively include a computer program for the electronic device 2000. For example, the gas leak detection apparatus may be considered as an application 253 deployed on the electronic device 2000.
The central processor 270 may include one or more processors and is configured to communicate with the memory 250 via at least one communication bus to read the computer program stored in the memory 250, thereby implementing the operation and processing of the bulk data 255 in the memory 250. The gas leak detection method is accomplished, for example, by the central processor 270 reading a series of computer programs stored in the memory 250.
Furthermore, the present application can be realized by hardware circuitry or by a combination of hardware circuitry and software, and thus, the implementation of the present application is not limited to any specific hardware circuitry, software, or combination of the two.
Referring to fig. 14, in an embodiment of the present application, an electronic device 4000 is provided, which may specifically include: desktop computers, notebook computers, servers, etc.
In fig. 14, the electronic device 4000 includes at least one processor 4001, at least one communication bus 4002, and at least one memory 4003.
Wherein the processor 4001 is coupled to the memory 4003, such as via a communication bus 4002. Optionally, the electronic device 4000 may further comprise a transceiver 4004, the transceiver 4004 may be used for data interaction between the electronic device and other electronic devices, such as transmission of data and/or reception of data, etc. It should be noted that, in practical applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 is not limited to the embodiment of the present application.
The Processor 4001 may be a CPU (Central Processing Unit ), general purpose Processor, DSP (DIGITAL SIGNAL Processor, data signal Processor), ASIC (Application SPECIFIC INTEGRATED Circuit), FPGA (Field Programmable GATE ARRAY ) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. The processor 4001 may also be a combination that implements computing functionality, e.g., comprising one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
The communication bus 4002 may include a pathway to transfer information between the aforementioned components. The communication bus 4002 may be a PCI (PERIPHERAL COMPONENT INTERCONNECT, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture ) bus or the like. The communication bus 4002 can be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 14, but not only one bus or one type of bus.
Memory 4003 may be, but is not limited to, ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, EEPROM (ELECTRICALLY ERASABLE PROGRAMMABLE READ ONLY MEMORY ), CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 4003 has stored thereon a computer program, and the processor 4001 reads the computer program stored in the memory 4003 through the communication bus 4002.
The computer program when executed by the processor 4001 implements the gas leakage detection method in each of the embodiments described above.
Further, in an embodiment of the present application, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the gas leakage detection method in each of the above embodiments.
In an embodiment of the application, a computer program product is provided, which comprises a computer program stored in a storage medium. The processor of the computer device reads the computer program from the storage medium, and the processor executes the computer program so that the computer device executes the gas leakage detection method in each of the above embodiments.
Compared with the related art, on one hand, through combining preliminary detection of deep learning and fine detection of background difference, specifically, preliminary detection is carried out on a leakage gas target in an infrared image through a deep learning gas leakage detection model, a suspected leakage gas target is determined, then, further fine detection and identification are carried out on an image area of the suspected leakage gas target in the infrared image by adopting a background difference method, when the identification result indicates that the leakage gas target exists in the image area, a gas leakage detection result is obtained, the time required by gas leakage detection is reduced, the instantaneity is improved, the background can be automatically selected and updated from a video, the dependence on the background is reduced, and the accuracy of gas leakage detection is improved; on the other hand, the detection threshold value of the deep learning gas leakage model is adaptively adjusted to adapt to the change of detection environment, so that the real-time performance of gas leakage detection is further effectively improved, and the problems that the real-time performance of gas leakage detection in the related technology is poor, serious environmental interference occurs, the detection accuracy is low, and the background cannot be automatically selected and updated are effectively solved.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The foregoing is only a partial embodiment of the present application, and it should be noted that it will be apparent to those skilled in the art that modifications and adaptations can be made without departing from the principles of the present application, and such modifications and adaptations are intended to be comprehended within the scope of the present application.
Claims (10)
1. A method of detecting gas leakage, the method comprising:
continuously acquiring an infrared image, wherein the infrared image is obtained by shooting an environment in which gas leakage possibly occurs;
performing preliminary detection on a leakage gas target in the infrared image to obtain a detection result; the detection result comprises whether a leakage gas target exists in the infrared image or not and an image area of the leakage gas target in the infrared image;
If the detection result indicates that the leaked gas target exists in the infrared image, performing fine detection and identification on an image area of the leaked gas target in the infrared image according to a background difference algorithm;
And if the identification result indicates that the leaked gas target exists in the image area, obtaining a gas leakage detection result.
2. The method of claim 1, wherein the preliminary detection of the target of the leaked gas in the infrared image, after obtaining the detection result, further comprises:
and if the detection result indicates that the leaked gas target does not exist in the infrared image, allowing a detection threshold to be reduced in the process of carrying out preliminary detection on the leaked gas target in the infrared image, and carrying out preliminary detection on the leaked gas target in other continuously acquired infrared images based on the reduced detection threshold until the minimum value of the detection threshold is reached or the leaked gas target exists in the infrared image.
3. The method of claim 1, wherein said performing fine detection and identification of image areas of said leaked gas target in said infrared image according to a background differential algorithm comprises:
continuously acquiring a video corresponding to the infrared image of the detected leakage gas target, and extracting a background image from the video; the background image refers to an infrared image in the video, wherein the infrared image is not detected to exist the leaked gas target;
determining a background area corresponding to the image area in the background image based on the image area of the leaked gas target in the infrared image;
performing differential processing on an image area in the infrared image and a background area in the background image to obtain a differential image;
and obtaining the identification result according to whether the differential image contains the leaked gas target or not.
4. The method of claim 3, wherein said obtaining said identification result based on whether said differential image contains said leakage gas target comprises:
filtering the differential image to obtain a differential filtering image;
superposing the differential filtering image and the infrared image with the leakage gas target detected to obtain a superposed image;
And if the superimposed image contains the leaked gas target, the identification result indicates that the differential image contains the leaked gas target.
5. The method according to any one of claims 1 to 4, wherein after the gas leak detection result is obtained, the method further comprises:
And according to the obtained gas leakage detection result, carrying out gray gradient enhancement display on the image area of the leaked gas target in the infrared image, and outputting the enhanced infrared image.
6. The method of any one of claims 1 to 4, wherein the preliminary detection of the leaked gas target in the infrared image is accomplished by invoking a gas leak detection model; the gas leakage detection model is obtained based on training of an infrared image data set; the infrared image dataset comprising a plurality of training images marked for the presence of a leakage gas target;
the process for marking the training image comprises the following steps:
Simulating gas leakage by using safe gas in an environment where gas leakage possibly occurs, and shooting the environment in which gas leakage is simulated under a plurality of groups of shooting conditions by using image acquisition equipment to obtain a plurality of infrared images to be marked, wherein the infrared images contain leaked gas targets;
and marking the leaked gas target in each infrared image to be marked to obtain each training image.
7. The method of claim 6, wherein the training process of the gas leak detection model comprises:
Inputting training images in the infrared image data set into a basic model for target detection;
Determining a loss value according to the detected difference between the leakage gas target in the training image and the leakage gas target marked in the training image;
And if the loss value meets the set convergence condition, training is completed, the basic model is converged to obtain the gas leakage detection model, otherwise, the parameters of the basic model are updated until the loss value meets the set convergence condition.
8. A gas leak detection apparatus, the apparatus comprising:
the image acquisition module is used for continuously acquiring infrared images, and the infrared images are obtained by shooting an environment in which gas leakage possibly occurs;
The preliminary detection module is used for carrying out preliminary detection on the leaked gas target in the infrared image to obtain a detection result; the detection result comprises whether a leakage gas target exists in the infrared image or not and an image area of the leakage gas target in the infrared image;
the fine detection module is used for carrying out fine detection and identification on an image area of the leaked gas target in the infrared image according to a background difference algorithm if the detection result indicates that the leaked gas target exists in the infrared image;
and the result acquisition module is used for acquiring a gas leakage detection result if the identification result indicates that the leaked gas target exists in the image area.
9. An electronic device, comprising: at least one processor, at least one memory, and at least one communication bus, wherein,
The memory has stored thereon a computer program, which when executed implements the gas leakage detection method according to any one of claims 1 to 7, and which is read by the processor via the communication bus.
10. A storage medium having stored thereon a computer program, which when executed by a processor implements the gas leakage detection method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211502396.0A CN118096634A (en) | 2022-11-28 | 2022-11-28 | Gas leakage detection method and device, electronic equipment and storage medium |
| PCT/CN2023/133049 WO2024114452A1 (en) | 2022-11-28 | 2023-11-21 | Gas leakage detection method and apparatus, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211502396.0A CN118096634A (en) | 2022-11-28 | 2022-11-28 | Gas leakage detection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118096634A true CN118096634A (en) | 2024-05-28 |
Family
ID=91164476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211502396.0A Pending CN118096634A (en) | 2022-11-28 | 2022-11-28 | Gas leakage detection method and device, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN118096634A (en) |
| WO (1) | WO2024114452A1 (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609907A (en) * | 2012-01-12 | 2012-07-25 | 北京理工大学 | Method for enhancing gas infrared image based on self-adaption time-domain filtering and morphology |
| US9726543B2 (en) * | 2015-02-18 | 2017-08-08 | Providence Photonics, Llc | Apparatus and method for validating leak survey results |
| WO2019213280A1 (en) * | 2018-05-03 | 2019-11-07 | Quantum IR Technologies, LLC | Infrared imaging systems and methods for gas leak detection |
| WO2021246130A1 (en) * | 2020-06-05 | 2021-12-09 | コニカミノルタ株式会社 | Gas leak location identification device, gas leak location identification system, gas leak location identification method, gas leak location estimation model generation device, gas leak location estimation model generation method, and program |
| CN114913211A (en) * | 2021-02-08 | 2022-08-16 | 中国石油化工股份有限公司 | Gas leakage infrared imaging monitoring method and device, electronic equipment and storage medium |
| CN114298989A (en) * | 2021-12-17 | 2022-04-08 | 洛阳热感科技有限公司 | YOLOV 5-based thermal infrared gas leakage detection method, detection device and detection system |
-
2022
- 2022-11-28 CN CN202211502396.0A patent/CN118096634A/en active Pending
-
2023
- 2023-11-21 WO PCT/CN2023/133049 patent/WO2024114452A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024114452A1 (en) | 2024-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110276767B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| US11087447B2 (en) | Systems and methods for quality assurance of image recognition model | |
| CN110473185B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN108764208A (en) | Image processing method and device, storage medium, electronic equipment | |
| WO2021208875A1 (en) | Visual detection method and visual detection apparatus | |
| CN111444744A (en) | Living body detection method, living body detection device, and storage medium | |
| CN106651797B (en) | Method and device for determining effective area of signal lamp | |
| CN109068060B (en) | Image processing method and device, terminal device and computer readable storage medium | |
| CN111046746A (en) | License plate detection method and device | |
| WO2021155153A1 (en) | Computer-based systems configured for reference-free color correction and methods thereof | |
| CN116503414A (en) | Screen defect detection method, device, computer equipment and storage medium | |
| CN113673474B (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN112950564B (en) | Image detection method and device, storage medium and electronic equipment | |
| CN109886864B (en) | Privacy mask processing method and device | |
| CN110688926B (en) | Subject detection method and apparatus, electronic device, and computer-readable storage medium | |
| CN113470065B (en) | Moving object detection and tracking method and apparatus | |
| CN118096634A (en) | Gas leakage detection method and device, electronic equipment and storage medium | |
| CN108737733B (en) | Information prompting method and device, electronic equipment and computer readable storage medium | |
| CN115272682A (en) | Target object detection method, target detection model training method and electronic equipment | |
| CN110765875A (en) | Method, equipment and device for detecting boundary of traffic target | |
| CN112752031B (en) | Image acquisition and detection method and device, electronic equipment and storage medium | |
| CN115829911A (en) | Method, apparatus and computer storage medium for detecting imaging consistency of a system | |
| CN110475044B (en) | Image transmission method and device, electronic equipment and computer readable storage medium | |
| CN110705336B (en) | Image processing method, system, electronic device and readable storage medium | |
| CN114764839A (en) | Dynamic video generation method and device, readable storage medium and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |