CN115423861A

CN115423861A - Gas leakage detection method and device, equipment and storage medium

Info

Publication number: CN115423861A
Application number: CN202210968542.2A
Authority: CN
Inventors: 吴奇文; 蔡敏权; 徐定懿
Original assignee: Guangzhou Keii Electro Optics Technology Co ltd
Current assignee: Guangzhou Keii Electro Optics Technology Co ltd
Priority date: 2022-08-12
Filing date: 2022-08-12
Publication date: 2022-12-02

Abstract

The embodiment of the application discloses a gas leakage detection method, a gas leakage detection device, equipment and a storage medium; the method comprises the following steps: acquiring a plurality of frames of infrared sensing signals in real time; the infrared induction signal is obtained by converting infrared radiation energy of the gas to be detected and the environment obtained by current detection; preprocessing each frame of infrared induction signal to obtain a target signal corresponding to each frame; mapping the target signal to obtain target images corresponding to the frames; and determining the leakage area of the gas to be detected in the target images corresponding to each frame, and determining the leakage state of the gas to be detected based on the leakage areas corresponding to the multi-frame target images connected in time sequence. Therefore, the gas leakage state can be accurately determined, and the detection accuracy is improved.

Description

Gas leakage detection method and device, equipment and storage medium

Technical Field

The embodiment of the application relates to an information processing technology, and relates to but is not limited to a gas leakage detection method, a gas leakage detection device, gas leakage detection equipment and a storage medium.

Background

At present, when a dangerous chemical transport vehicle runs on a road, particularly enters a service station or a toll station, if dangerous gas leakage exists in the vehicle, a great potential safety hazard is caused. For such problems, most of the infrared device technologies are utilized to observe a detection area, and whether the air leaks is judged by observing a shooting result through human eyes, but the above judging mode is easily influenced by factors such as environment, and the human eyes have errors in observation, and are easily influenced by vision, so that the problems of inaccurate judgment or no gas leakage in observation exist. For this reason, the highway operation and maintenance department has no effective solution.

Disclosure of Invention

In view of this, the gas leakage detection method, the gas leakage detection device, the gas leakage detection apparatus, and the gas leakage detection storage medium provided in the embodiments of the present application can determine the gas leakage state more accurately, and improve the detection accuracy. The gas leakage detection method, the gas leakage detection device, the gas leakage detection equipment and the gas leakage detection storage medium are realized in the following way:

the gas leakage detection method provided by the embodiment of the application comprises the following steps: acquiring a plurality of frames of infrared sensing signals in real time; the infrared induction signal is obtained by converting infrared radiation energy of the gas to be detected and the environment obtained by current detection; preprocessing each frame of infrared induction signal to obtain a target signal corresponding to each frame; mapping the target signal to obtain target images corresponding to the frames; and determining the leakage area of the gas to be detected in the target images corresponding to each frame, and determining the leakage state of the gas to be detected based on the leakage areas corresponding to the multi-frame target images connected in time sequence.

In the embodiment of the application, after collecting multiframe infrared induction signals, the infrared induction signals are preprocessed to reduce noise errors and enhance signal characteristics, and the processed signals are mapped into target images, so that the target images are identified and processed to determine the leakage area of the gas to be detected. The detection method is based on signal angle to carry out preprocessing, not directly based on image angle to carry out preprocessing, thereby being capable of accurately determining the leakage state of the gas to be detected and improving the detection accuracy.

In some embodiments, preprocessing the infrared sensing signal to obtain a corresponding target signal includes: respectively carrying out equalization processing on each frame of infrared induction signal to obtain an equalization signal corresponding to each frame; the difference value between all signal values in the equalization signal corresponding to each frame is smaller than a first threshold value; and performing feature enhancement processing on the equalized signals corresponding to the frames to obtain target signals corresponding to the frames respectively.

In some embodiments, equalizing the infrared sensing signals corresponding to each frame to obtain an equalized signal corresponding to each frame includes: filtering each frame of infrared induction signal to obtain a filtering signal corresponding to each frame; respectively counting the occurrence times of various signals with the same value in the filtering signals aiming at each frame to obtain a statistical result corresponding to each frame of filtering signals; and traversing the occurrence times of various signals in the statistical result of each frame, and updating the signals with the occurrence times smaller than a second threshold or larger than a third threshold into the signal values of the adjacent signals so as to obtain balanced signals, wherein the occurrence times of the adjacent signals are larger than the second threshold and smaller than the third threshold.

In some embodiments, performing feature enhancement processing on the equalized signals corresponding to each frame to obtain target signals corresponding to each frame respectively includes: aiming at each frame, performing enhancement processing on the current frame balanced signal to obtain a first enhanced signal; determining a difference value between a current frame balanced signal and an adjacent frame balanced signal to obtain a difference value signal, wherein the difference value signal comprises a gas signal; performing enhancement processing on the difference signal to obtain a second enhanced signal; and performing weighted fusion processing on the second enhanced signal and the first enhanced signal to obtain a target signal corresponding to the current frame.

In some embodiments, determining the leak area of the gas to be detected in the target image comprises: inputting the target image into a pre-trained target recognition model for recognition processing to obtain a gas detection frame of the gas to be detected; and determining the leakage area of the gas to be detected based on the position information of the gas detection frame.

In some embodiments, the method includes the steps of inputting a target image into a pre-trained target recognition model for processing to obtain a gas detection frame of a gas to be detected, where the target image includes a foreground image and a background image, and the foreground image at least includes the gas image to be detected, and the method includes: performing background separation on a target image in a pre-trained target recognition model to obtain a foreground image; and carrying out target detection on the foreground image to obtain a gas detection frame corresponding to the gas to be detected.

In some embodiments, acquiring multiple frames of infrared sensing signals in real time includes: acquiring a plurality of frames of infrared sensing signals in a first time period; segmenting the multi-frame infrared induction signals in the first time period to obtain a plurality of multi-frame infrared induction signals in a second time period, wherein the second time period is a time period obtained after the first time period is segmented; after obtaining the target signal corresponding to each frame of infrared sensing signal, the method further includes: and synthesizing the target signals in the second time periods to obtain a plurality of target signals in the first time period.

The gas leakage detection device that this application embodiment provided includes: the acquisition module is used for acquiring multi-frame infrared sensing signals in real time; the infrared induction signal is obtained by converting infrared radiation energy of the gas to be detected and the environment obtained by current detection; the processing module is used for preprocessing each frame of infrared sensing signal to obtain a target signal corresponding to each frame; the processing module is also used for mapping the target signal to obtain target images corresponding to the frames respectively; the determining module is used for determining the leakage area of the gas to be detected in the target images corresponding to the frames, and determining the leakage state of the gas to be detected based on the leakage areas corresponding to the multi-frame target images connected in time sequence.

The computer device provided by the embodiment of the application comprises a memory and a processor, wherein the memory stores a computer program which can run on the processor, and the processor executes the program to realize the method of the embodiment of the application.

The computer readable storage medium provided by the embodiment of the present application has a computer program stored thereon, and the computer program is used for implementing the method provided by the embodiment of the present application when being executed by a processor.

The gas leakage detection method, the gas leakage detection device, the computer equipment and the computer readable storage medium provided by the embodiment of the application can accurately determine the gas leakage state and improve the detection accuracy, so that the technical problems in the background art are solved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.

Fig. 1 is a schematic flow chart illustrating an implementation of a gas leakage detection method according to an embodiment of the present disclosure;

FIG. 2 is a schematic flow chart illustrating another implementation of a gas leak detection method according to an embodiment of the present disclosure;

FIG. 3 is a schematic flow chart illustrating another implementation of a gas leak detection method according to an embodiment of the present disclosure;

fig. 4 is an effect diagram of a gas leakage detection method according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a gas leakage detecting apparatus according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, specific technical solutions of the present application will be described in further detail below with reference to the accompanying drawings in the embodiments of the present application. The following examples are intended to illustrate the present application but are not intended to limit the scope of the present application.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

It should be noted that the terms "first \ second \ third" are used herein to distinguish similar or different objects and do not denote a particular order or importance to the objects, and it should be understood that "first \ second \ third" may be interchanged with a particular order or sequence where permissible to enable embodiments of the present application described herein to be practiced otherwise than as shown or described herein.

The infrared thermal imaging technology has the obvious advantages of long distance, non-contact, universality, dynamic intuition and the like, and becomes an important research direction in the field of gas detection. Infrared gas imagers have been commonly used for gas detection in a variety of settings due to their ease of use. Particularly, when dangerous chemical transport vehicle is traveling on the highway, especially gets into service station or toll station, if the vehicle has dangerous gaseous leakage, can have serious potential safety hazard, to this type of problem, mostly utilize infrared technique to observe the detection area, judge it and leak gas through people's eye observation shooting result. However, although gas imaging is useful, basic challenges still exist, such as high labor cost for manually operating the gas imager, almost impossible manual operation for a long time, inability of the thermal infrared imager to automatically give real-time feedback of a leakage detection result without judgment of an operator, and the like, and the difficulty in detecting the leaked gas is increased because of low image contrast, no fixed shape, size and irregularity of an image formed after gas infrared imaging. Therefore, the highway operation and maintenance department has no effective detection means, and therefore, how to early warn gas leakage in real time with high accuracy becomes a challenging problem.

In view of this, the embodiments of the present application provide a gas leakage detection method, which is applied to an electronic device, and the electronic device may be various types of devices with information processing capability during implementation. The functions implemented by the method can be implemented by calling program code by a processor in an electronic device, and the program code can be stored in a computer storage medium.

Fig. 1 is a schematic diagram of an implementation process of the gas leakage detection method provided in the embodiment of the present application, which can determine a gas leakage state more accurately and improve detection accuracy. As shown in fig. 1, the method may include the following steps 101 to 104:

101, acquiring a plurality of frames of infrared sensing signals in real time; the infrared induction signal is obtained by converting infrared radiation energy of the gas to be detected and the environment obtained by current detection.

In the embodiment of the present application, a signal acquisition device for acquiring an infrared sensing signal is not limited. Optionally, the signal acquisition device may be various types of thermal infrared imagers, and the thermal infrared imagers are used for acquiring signals of an area environment where gas leakage may exist, so as to obtain a multi-frame infrared sensing signal.

By infrared thermal imager is meant an imaging instrument that uses infrared thermal imaging techniques. The method takes an infrared focal plane device as a core, and converts the difference of infrared radiation energy emitted outwards by a target scenery and the environment where the target scenery is located into a gray image visible to human eyes. Infrared radiation energy in a scene is projected onto an infrared focal plane through an infrared lens, and a detector converts radiation into an electric signal capable of reflecting the intensity of the infrared radiation energy to realize conversion from light to electricity; and then, the electric signal is processed through a circuit system, the processed infrared digital electric signal is converted into a visible light image to be displayed on a display, the conversion from electricity to light is realized, and a macroscopic gray image is obtained.

In the embodiment of the present application, when the infrared sensing signal is acquired, the processing time of the infrared sensing signal is not limited. For example, in some embodiments, the current frame of infrared sensing signals may be processed after a frame of infrared sensing signals is acquired. In other embodiments, centralized processing may also be performed after the multiple frames of infrared sensing signals within the first time period are collected. After obtaining the multiple frames of infrared sensing signals in the first time period, in order to facilitate processing and improve processing efficiency, the multiple frames of infrared sensing signals in the first time period may be divided into multiple time periods, and each frame of infrared sensing signal is respectively subjected to subsequent processing in each second time period.

For this case, step 101 can be specifically realized by executing the following steps 1011 to 1012:

step 1011, acquiring the multi-frame infrared sensing signal in the first time period.

It should be noted that the duration of the first period is not specifically limited, and may be set according to the actual requirement of the user and/or the processing capability of the electronic device. For example, the duration of the first period may be 1S,2S, etc.

Step 1012, performing segmentation processing on the multiple frames of infrared sensing signals in the first time interval to obtain multiple frames of infrared sensing signals in a second time interval, where the second time interval is a time interval obtained after the first time interval is segmented.

After acquiring multiple frames of infrared sensing signals within a longer period of time (first period of time), the first period of time is divided to obtain multiple frames of infrared sensing signals within a short period of time (second period of time), and then the multiple frames of infrared sensing signals within the second period of time are processed respectively.

For example, assuming that the first time period is 10S, 100 frames of infrared sensing signals in 10S are acquired, the 10S is divided into 5 second time periods for processing, that is, each second time period is 2S, and each second time period contains 20 frames of infrared sensing signals.

It should be noted that after the infrared sensing signals of each frame are processed in each second time period and the target signals corresponding to the infrared sensing signals of each frame are obtained, the target signals of each frame in the plurality of second time periods are further synthesized according to the time sequence, so as to obtain the target signals of the plurality of frames in the first time period.

And 102, preprocessing each frame of infrared induction signal to obtain a target signal corresponding to each frame.

In the embodiment of the application, after the gas collection equipment is used for collecting multiple frames of infrared sensing signals, the infrared sensing signals are not directly converted into target images for subsequent processing, but each collected frame of infrared sensing signal is directly preprocessed, so that the noise error in each frame of target signals obtained after processing is small, and the characteristics of the gas signals are strong.

In some embodiments, step 102 may be implemented by performing steps 202 through 203 in the following embodiments.

And 103, mapping the target signal to obtain target images corresponding to the frames respectively.

Here, the mapping process is performed on each frame of target signal to obtain a target image corresponding to each frame of target signal.

In the embodiment of the present application, the format of the target image is not limited, and the target image may be a grayscale image or a color image. For example, a matrix gray scale value can be obtained by converting the target signal into a digital electrical signal, and a gray scale image can be obtained according to the matrix gray scale value.

And 104, determining the leakage area of the gas to be detected in the target image corresponding to each frame, and determining the leakage state of the gas to be detected based on the leakage areas corresponding to the multi-frame target images which are connected in time sequence.

It can be understood that there may be a case where the leakage amount of the gas is small at the time of initial leakage, and if the leakage condition of the gas to be detected is determined by only the leakage area of the gas to be detected in a few frames of target images, there may be a case where the gas leakage state is erroneously determined. Therefore, in the embodiment of the present application, the leakage condition of the gas to be detected is determined not only by the leakage area of the gas to be detected in a few frames of target images, but also by the leakage area of the gas to be detected in consecutive multi-frame target images, so that the state detection result is more accurate.

Optionally, the leakage state of the gas to be detected can be simply divided into a small amount, a medium amount, a large amount and the like, and the leakage state of the gas to be detected in the current time period can be determined by setting different threshold limits and comparing the leakage areas of the gas to be detected in multiple continuous target images.

Specifically, if the leakage area of the gas to be detected in the multiple continuous target images is smaller than a specific numerical value 1, the corresponding leakage state can be determined to be a small amount of leakage; if the leakage area of the gas to be detected in the multiple continuous target images is larger than a specific value 1 and smaller than a specific value 2, determining that the corresponding leakage state is medium leakage; and if the leakage area of the gas to be detected in the multi-frame continuous target images is larger than a specific numerical value 2, determining that the corresponding leakage state is a large amount of leakage.

In some embodiments, step 104 may be implemented by performing steps 205 through 207 in the following embodiments.

In the embodiment of the application, after the multi-frame infrared sensing signals are preprocessed to obtain the corresponding target signals, each frame of target signals is converted into the corresponding target image, so that the target images are subjected to subsequent identification processing, the leakage area of the gas to be detected in the target images is identified, and the leakage state of the gas to be detected is determined according to the leakage area of the gas to be detected in the multi-frame continuous target images. The detection method is based on signal angle to carry out preprocessing, not directly based on image angle to carry out preprocessing, thereby being capable of accurately determining the leakage state of the gas to be detected and improving the detection accuracy.

Fig. 2 is a schematic flow chart illustrating an implementation of the defect detection method according to the embodiment of the present invention, and as shown in fig. 2, the method may include the following steps 201 to 207:

step 201, acquiring a plurality of frames of infrared sensing signals in real time; the infrared sensing signal is obtained by converting infrared radiation energy of the gas to be detected and the environment obtained by current detection.

202, carrying out equalization processing on infrared induction signal distribution corresponding to each frame to obtain an equalization signal corresponding to each frame; the difference value between the signal values in the equalization signal corresponding to each frame is smaller than the first threshold value.

Understandably, due to the process influence of the signal acquisition equipment, the infrared sensing signals acquired by the signal acquisition equipment have the problems of blind spots, dead spots, noise spots and the like, and influence is caused on the upper limit and the lower limit of the single-frame infrared sensing signals. If the infrared sensing signal is not processed, pixel signals in the image are wrong or pixel values are inaccurate when the image is obtained subsequently.

Therefore, the collected infrared sensing signals need to be denoised and rearranged so that the processed infrared sensing signals of each frame do not have noise signals, the difference value between the signal values is smaller than the first threshold value, and the distribution is uniform, so that the contrast of the signals is enhanced, the jitter problem of the signals between frames is reduced, and the definition of the subsequently converted images is higher.

To achieve the above result, in some embodiments, the following steps 2021 to 2023 may be performed:

step 2021, performing filtering processing on each frame of infrared sensing signal to obtain a filtered signal corresponding to each frame.

It can be understood that, because the gas leakage is influenced by factors such as environment, the gas to be detected has the defects of weak characteristics, low contrast, difficulty in observation by human eyes, noise and the like, so after the infrared sensing signal is obtained, the infrared sensing signal needs to be filtered to remove the noise signal in the infrared sensing signal and reduce noise interference.

In the embodiment of the present application, the filtering processing mode is not specifically limited, and a filtering and denoising method may be freely selected for combination processing according to the use environment of the device.

For example, gaussian noise, salt and pepper noise, etc. in the infrared sensing signal can be removed by filtering means such as gaussian filtering, median filtering, and/or wiener filtering.

The gaussian filtering is a weighted average of all signal values, and is obtained by weighted averaging of its own value and other signal values in the neighborhood for each signal value. So-called median filtering, a non-linear digital filter technique often used to remove noise from images or other signals, is designed by examining samples in the input signal and determining whether it represents a signal, using an observation window consisting of an odd number of samples to accomplish this function. The values in the observation window are sorted, and the median value in the middle of the observation window is used as output. The oldest value is then discarded, a new sampled signal value is taken, and the above calculation process is repeated.

Step 2022, counting the occurrence frequency of each type of signal with the same value in the filtered signal for each frame, to obtain a statistical result corresponding to each frame of filtered signal.

It will be appreciated that after the filtered signal is obtained, there will typically be a greater number of signal values in the filtered signal that are the same value. Here, signals having the same value are classified into one type, and the filtered signals are counted for each frame of filtered signals, that is, the number of occurrences of each type of signal having the same value in the filtered signals of the current frame is counted.

Step 2023, in the statistical result of each frame, traversing the occurrence frequency of each type of signal, and updating the signal whose occurrence frequency is smaller than the second threshold or larger than the third threshold to the signal value of the adjacent signal, thereby obtaining the equalized signal.

It can be understood that if the number of times of occurrence of the signals with larger or smaller values is larger, it means that more signals are distributed more intensively, and thus, after the signals are mapped to digital electric signals (i.e. converted into pixel values), the displayed target image will show too bright or too dark. In order to solve the problem, signal values originally distributed and concentrated need to be processed, so that the processed signals are distributed in all ranges of available values in a balanced manner, and thus, a target image obtained by subsequent mapping is bright and dark, so that the contrast and brightness of the target image are improved, and the definition is higher.

In the embodiment of the present application, the adjacent signal is defined as that the number of occurrences of the signal needs to be greater than the second threshold and less than the third threshold, and is adjacent to and closest to the timing sequence of the signal whose number of occurrences is less than the second threshold or greater than the third threshold. That is, even if the timing of a signal whose number of occurrences is less than the second threshold value or greater than the third threshold value is the closest, the number of occurrences is less than the second threshold value or greater than the third threshold value, and it cannot be regarded as an adjacent signal.

In the setting of the threshold interval, the threshold interval may be determined according to the overall signal width of the current filtered signal, that is, the difference between the maximum value and the minimum value of the signal, and different thresholds may be set for filtered signals of different widths.

In some embodiments, after obtaining the equalized signal, the equalized signal may be remapped to map the equalized signal to a suitable range, so as to obtain a mapped signal, so as to reduce the storage space and transmission cost of the signal.

In some embodiments, after the mapping signal is obtained, the mapping signal may be further compressed based on a preset signal compression width to obtain a compressed signal, where a storage space of the compressed signal is smaller than a storage space of the mapping signal. The compressed signal width is not limited here, and may be as wide as 256, 512, 1024, or the like.

Step 203, performing feature enhancement processing on the equalized signals corresponding to each frame to obtain target signals corresponding to each frame.

It can be understood that, in order to enable the subsequent more accurate determination of the leakage condition of the gas to be detected, the contrast, the signal-to-noise ratio, and the like of the gas signal in the whole frame of infrared sensing signal should be improved as much as possible during the previous processing, so as to enhance the characteristics of the gas signal. Thus, the resulting equalized signal may be subjected to a feature enhancement process to enhance the features of the gas signal in the equalized signal.

In some embodiments, step 203 may be implemented by performing steps 2031 to 2034 as follows:

step 2031, for each frame, performing enhancement processing on the current frame equalized signal to obtain a first enhanced signal.

It should be noted that, here, enhancement processing is performed on both the gas signal and the background signal in the equalized signal.

Here, the enhancement processing method used when performing enhancement processing on the equalized signal of the current frame is not limited. For example, in some embodiments, the standard deviation distribution of the equalization signal and the single-point signal between frames may be counted by using a change rule of the equalization signal between frames, and the signals of two adjacent frames are normalized and remapped according to the obtained standard deviation, so as to observe a change trend between frames. Specifically, a mean value, a variance, a standard deviation and/or the like corresponding to each signal value in the current frame equalization signal can be determined based on each signal value in the current frame equalization signal, and then the equalization signal is normalized based on the improved sigmoid function by using the determined values; and performing linear mapping on the normalized result again to obtain a first enhanced signal.

Step 2032, determining the difference between the current frame equalized signal and the adjacent frame equalized signal to obtain a difference signal.

In step 2031, the enhancement processing is performed on the entire equalized signal of the current frame, so that the contrast of the gas signal in the equalized signal is improved, but the contrast of the background signal is also improved. Therefore, after the first enhancement signal is obtained, the gas signal in the first enhancement signal can be further subjected to enhancement processing to obtain a second enhancement signal.

It can be understood that when the signal acquisition device is used for signal acquisition of the area environment where gas leakage may exist, the change rate of the gas signal between different frames is large and the change rate of the background signal is small due to the time-varying characteristic of the gas. Based on this principle, a difference signal between two adjacent frames can be calculated based on the difference between the current frame equalized signal and the adjacent frame equalized signal. Thus, the change rate of the gas signal can be obviously highlighted in the obtained difference signal.

In some embodiments, determining a difference between the current frame equalized signal and the adjacent frame equalized signal to obtain a difference signal may specifically be determining coefficients corresponding to the current frame equalized signal and a subsequent frame, to obtain a difference signal corresponding to the current frame equalized signal. The coefficient can be any value from 0 to 1, and can be set according to actual requirements.

Step 2033, performing enhancement processing on the difference signal to obtain a second enhanced signal.

Here, the enhancement processing method used when performing enhancement processing on the equalized signal of the current frame is not limited. For example, in some embodiments, the enhancement processing may be performed on the difference signal by using a histogram equalization processing method to enhance the contrast and detail information of the difference signal, so as to obtain a second enhanced signal.

Step 2034, performing weighted fusion processing on the second enhanced signal and the first enhanced signal to obtain a target signal corresponding to the current frame.

After a second enhancement signal corresponding to the difference signal (mostly gas signal) is obtained, the second enhancement signal and the first enhancement signal which has completed all signal enhancement are subjected to fusion processing to obtain a target signal corresponding to the current frame. Therefore, the characteristics of the gas signal in the obtained target signal are strong, and the characteristics of the background signal are relatively weak, so that the characteristics of the gas to be detected in the target image obtained by subsequent mapping are obvious, the gas to be detected in the target image can be conveniently detected and identified, and the detection accuracy is improved.

And step 204, mapping the target signal to obtain a corresponding target image.

And step 205, inputting the target image into a pre-trained target recognition model for processing to obtain a gas detection frame of the gas to be detected.

In order to obtain the area of the gas to be detected in the target image, the gas to be detected in the target image can be firstly identified, and the leakage area of the position of the gas to be detected can be represented by the detection frame.

In some embodiments, step 205 may be implemented by performing steps 2051 through 2052 as follows:

step 2051, performing background separation on the target image in a pre-trained target recognition model to obtain a foreground image; the target image comprises a foreground image and a background image, and the foreground image at least comprises a gas image to be detected.

It should be noted that, when the background and foreground separation processing is performed on the target image, the separation criterion is to determine the change rate of the pixel points in the target image, determine that the change is slow as the background image, and determine that the change is fast as the foreground image.

In the embodiment of the present application, the manner of Background separation for the target image is not limited, for example, in some embodiments, the Background separation may be implemented by using a Gaussian Mixture-based Background/generalized Segmentation Algorithm (MOG).

And step 2052, performing target detection on the foreground image to obtain a gas detection frame corresponding to the gas to be detected.

It can be understood that when the gas detection frame corresponding to the gas to be detected in the foreground image is determined, the number of the gas detection frames is generally multiple, a target gas detection frame needs to be determined from multiple candidate gas detection frames, and the leakage area of the gas to be detected is represented according to the area of the target gas detection frame.

Here, the method of specifying the target gas detection frame from among the plurality of candidate gas detection frames is not limited. For example, in some embodiments, the target gas detection box may be determined based on a Non-Maximum Suppression algorithm (NMS) that performs a screening process on a plurality of candidate gas detection boxes, discarding redundant candidate gas detection boxes.

In some embodiments, when the screening processing is performed on a plurality of candidate gas detection frames, detection frames exceeding the boundary of the target image in the candidate gas detection frames may be discarded, so as to prevent resource waste caused by continuing subsequent processing on the candidate gas detection frames exceeding the boundary of the target image.

And step 206, determining the leakage area of the gas to be detected based on the position information of the gas detection frame.

Here, the shape of the gas detection frame is not limited, and the gas detection frame may be a rectangular frame, a circular frame, or the like, or may have another shape or an envelope surrounding the target object, for example.

When the area of the gas detection frame is determined based on the position information of the gas detection, and thus the leakage area of the gas to be detected is determined, the acquisition of the position information may be set according to the shape of the gas detection frame.

For example, in one embodiment, if the gas detection frame is a rectangular frame, such as a rectangular frame or a square frame, the position information of the gas detection frame may include the coordinates of the corner points at the upper left corner and the lower right corner of the gas detection frame. For a gas detection frame, the product of the horizontal coordinate difference value and the vertical coordinate difference value is used as the area of the gas detection frame by determining the horizontal coordinate difference value between the lower right corner point and the upper left corner point of the gas detection frame and the vertical coordinate difference value between the lower right corner point and the upper left corner point, and then the leakage area of the gas to be detected is represented based on the area of the gas detection frame.

In another embodiment, if the gas detection frame is a circular frame, the position information of the gas detection frame may include the circle center coordinates and the radius length of the gas detection frame. For a gas detection frame, the area of the gas detection frame can be determined according to the radius length of the gas detection frame, and then the leakage area of the gas to be detected is represented based on the area of the gas detection frame.

In another embodiment, if the gas detection frame is an envelope surrounding the gas to be detected, the area of the gas detection frame may be determined according to the area of the region actually surrounded by the envelope, and the leakage area of the gas to be detected may be represented based on the area of the gas detection frame.

In some embodiments, the leakage area of the gas to be detected in the target image may also be determined based on the corresponding differential thermodynamic diagram of the target image.

And step 207, determining the leakage state of the gas to be detected based on the leakage areas corresponding to the multi-frame target images connected in time sequence.

In the embodiment of the application, after multiple frames of infrared sensing signals are obtained, the infrared sensing signals are firstly subjected to filtering, equalization, feature enhancement and other processing, then the processed target signals are mapped into the target image, the gas to be detected in the target image is identified, the leakage area of the gas to be detected is determined, and then the leakage state of the gas to be detected is determined according to the leakage area of the gas to be detected in the multiple frames of continuous target images. The detection method is based on signal angle to carry out preprocessing, not directly based on image angle to carry out preprocessing, thereby being capable of accurately determining the leakage state of the gas to be detected and improving the detection accuracy.

An exemplary application of the embodiments of the present application in a practical application scenario will be described below.

Fig. 3 is a general flowchart of a gas leak detection method according to an embodiment of the present application. As shown in fig. 3, the method includes the following steps 301 to 308:

step 301, receiving an input of a sensing signal.

Step 302, processing the input sensing signal by using a denoising algorithm to obtain a denoising signal.

Gaussian noise, salt and pepper noise and the like in the induction signal can be removed by utilizing Gaussian filtering, median filtering, wiener filtering and the like.

And 303, rearranging and reconstructing the denoised signal to obtain a reconstructed signal.

And step 304, performing interframe signal processing on the reconstructed signal to obtain an enhanced signal.

The interframe signal processing mainly comprises high-sensitivity mode processing and interframe signal statistical algorithm processing.

Step 305, mapping the enhanced signal into a target image and outputting and displaying the target image.

And step 306, performing background segmentation on the target image to obtain a foreground area, and performing identification processing on the foreground area by using a depth target detection/segmentation algorithm to obtain a gas area mask or a gas detection frame.

And 307, recording the gas detection frame in the multi-frame image, processing data, and calculating to obtain a leakage state.

And step 308, outputting a gas leakage result.

As shown in fig. 4, an effect diagram of a gas leakage detection method is given, in the diagram 401 is a gas detection frame in a current frame target image, a gas to be detected is in the gas detection frame, and in the diagram 402 is a background area in the current frame target image. Therefore, the gas leakage detection method provided by the embodiment of the application can accurately determine the gas leakage condition.

It should be understood that although the steps in the flowcharts of fig. 1 to 3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

Based on the foregoing embodiments, the present application provides a defect detection apparatus, which includes modules and units included in the modules, and can be implemented by a processor; of course, the implementation can also be realized through a specific logic circuit; in implementation, the processor may be a Central Processing Unit (CPU), a Microprocessor (MPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or the like.

Fig. 5 is a schematic structural diagram of a gas leakage detection apparatus provided in an embodiment of the present application, and as shown in fig. 5, the apparatus 500 includes an obtaining module 501, a processing module 502, and a determining module 503, where: the acquisition module is used for acquiring multi-frame infrared sensing signals in real time; the infrared induction signal is obtained by converting infrared radiation energy of the gas to be detected and the environment obtained by current detection; the processing module is used for preprocessing each frame of infrared sensing signal to obtain a target signal corresponding to each frame; the processing module is also used for mapping the target signal to obtain target images corresponding to the frames respectively; the determining module is used for determining the leakage area of the gas to be detected in the target images corresponding to the frames, and determining the leakage state of the gas to be detected based on the leakage areas corresponding to the multi-frame target images connected in time sequence.

In some embodiments, the processing module is further configured to perform equalization processing on each frame of infrared sensing signal, so as to obtain an equalized signal corresponding to each frame; the difference value between all signal values in the equalization signal corresponding to each frame is smaller than a first threshold value; and performing feature enhancement processing on the equalized signals corresponding to the frames to obtain target signals corresponding to the frames respectively.

In some embodiments, the apparatus further includes an updating module, and the processing module is further configured to perform filtering processing on each frame of infrared sensing signal to obtain a filtered signal corresponding to each frame; for each frame, respectively counting the occurrence times of various signals with the same value in the filtering signals to obtain a statistical result corresponding to each frame of filtering signals; and the updating module is used for traversing the occurrence times of various signals in the statistical result of each frame, and updating the signals with the occurrence times smaller than the second threshold or larger than the third threshold into the signal values of the adjacent signals so as to obtain the balanced signals, wherein the occurrence times of the adjacent signals are larger than the second threshold and smaller than the third threshold.

In some embodiments, the apparatus further includes an enhancement module, a difference processing module, and a weighted fusion module, where the enhancement module is configured to perform enhancement processing on the current frame equalized signal for each frame to obtain a first enhanced signal; the difference processing module is used for determining the difference between the current frame balanced signal and the adjacent frame balanced signal to obtain a difference signal, wherein the difference signal comprises a gas signal; the enhancement module is further used for enhancing the difference signal to obtain a second enhancement signal; and the weighted fusion module is used for carrying out weighted fusion processing on the second enhanced signal and the first enhanced signal to obtain a target signal corresponding to the current frame.

In some embodiments, the processing module is further configured to input the target image into a pre-trained target recognition model for recognition processing, so as to obtain a gas detection frame of the gas to be detected; the determining module is further used for determining the leakage area of the gas to be detected based on the position information of the gas detecting frame.

In some embodiments, the target image includes a foreground image and a background image, the foreground image at least includes a gas image to be detected, the device further includes a separation module and a detection module, the separation module is used for performing background separation on the target image in a pre-trained target recognition model to obtain the foreground image; and the detection module is used for carrying out target detection on the foreground image to obtain a gas detection frame corresponding to the gas to be detected.

In some embodiments, the apparatus further includes a segmentation processing module and a synthesis processing module, and the acquisition module is further configured to acquire multiple frames of infrared sensing signals in a first time period; the division processing module is used for carrying out division processing on the multi-frame infrared induction signals in the first time period to obtain a plurality of multi-frame infrared induction signals in a second time period, wherein the second time period is a time period obtained after the first time period is divided; correspondingly, the synthesis processing module is configured to perform synthesis processing on the target signals in the plurality of second time periods to obtain a plurality of target signals in the first time period.

In this application embodiment, after gathering multiframe infrared induction signal, carry out the preliminary treatment to infrared induction signal earlier to reduce the noise error in the signal, strengthen the signal characteristic, the signal mapping after will handling is the target image again, thereby carries out identification process to the target image, with the area of revealing of confirming to detect gas, and then can comparatively accurately determine the state of revealing of waiting to detect gas, improves detection accuracy.

The above description of the apparatus embodiments, similar to the above description of the method embodiments, has similar beneficial effects as the method embodiments. For technical details not disclosed in the embodiments of the apparatus of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.

It should be noted that the division of the gas leakage detecting apparatus shown in fig. 5 into modules in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation. In addition, functional units in the embodiments of the present application may be integrated into one processing unit, may exist alone physically, or may be integrated into one unit by two or more units. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. Or may be implemented in a combination of software and hardware.

It should be noted that, in the embodiment of the present application, if the method described above is implemented in the form of a software functional module and sold or used as a standalone product, it may also be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a magnetic disk, or an optical disk. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.

An embodiment of the present application provides a computer device, where the computer device may be a server, and an internal structure diagram of the computer device may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The database of the computer device is used for storing data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an interactive mode switching method.

Embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps in the methods provided in the above embodiments.

Embodiments of the present application provide a computer program product containing instructions which, when run on a computer, cause the computer to perform the steps of the method provided by the above-described method embodiments.

Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, the gas leak detection apparatus provided herein may be implemented in the form of a computer program that is executable on a computer device such as that shown in fig. 6. The memory of the computer device may store various program modules that make up the sampling apparatus, such as the acquisition module, the processing module, and the determination module shown in fig. 5. The respective program modules constitute computer programs that cause the processor to execute the steps in the gas leak detection method of the respective embodiments of the present application described in the present specification.

It is to be noted here that: the above description of the storage medium and device embodiments is similar to the description of the method embodiments above, with similar advantageous effects as the method embodiments. For technical details not disclosed in the embodiments of the storage medium, the storage medium and the device of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.

It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" or "some embodiments" means that a particular feature, structure or characteristic described in connection with the embodiments is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" or "in some embodiments" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments. The foregoing description of the various embodiments is intended to highlight various differences between the embodiments, and the same or similar parts may be referred to each other, and for brevity, will not be described again herein.

The term "and/or" herein is merely an association relationship describing an associated object, and means that three relationships may exist, for example, object a and/or object B, may mean: the object A exists alone, the object A and the object B exist simultaneously, and the object B exists alone.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice, such as: multiple modules or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or modules may be electrical, mechanical or other.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules; can be located in one place or distributed on a plurality of network units; some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, all functional modules in the embodiments of the present application may be integrated into one processing unit, or each module may be separately regarded as one unit, or two or more modules may be integrated into one unit; the integrated module can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.

Alternatively, the integrated units described above in the present application may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.

The methods disclosed in the several method embodiments provided in the present application may be combined arbitrarily without conflict to obtain new method embodiments.

Features disclosed in several of the product embodiments provided in the present application may be combined in any combination to yield new product embodiments without conflict.

The features disclosed in the several method or apparatus embodiments provided in the present application may be combined arbitrarily, without conflict, to arrive at new method embodiments or apparatus embodiments.

The above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall cover the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of gas leak detection, the method comprising:

acquiring a plurality of frames of infrared sensing signals in real time; the infrared induction signal is obtained by converting infrared radiation energy of the gas to be detected and the environment obtained by current detection;

preprocessing each frame of the infrared induction signal to obtain a target signal corresponding to each frame;

mapping the target signal to obtain target images corresponding to the frames;

and determining the leakage area of the gas to be detected in the target image corresponding to each frame, and determining the leakage state of the gas to be detected based on the leakage areas corresponding to the target images of the plurality of frames connected in time sequence.

2. The method of claim 1, wherein preprocessing the ir sensing signal to obtain a corresponding target signal comprises:

respectively carrying out equalization processing on the infrared induction signals of each frame to obtain an equalization signal corresponding to each frame; the difference value between the signal values in the equalization signal corresponding to each frame is smaller than a first threshold value;

and performing feature enhancement processing on the equalized signals corresponding to each frame to obtain target signals corresponding to each frame.

3. The method according to claim 2, wherein the equalizing the infrared sensing signals of each frame respectively to obtain an equalized signal corresponding to each frame comprises:

filtering each frame of the infrared induction signals to obtain filtering signals corresponding to each frame;

respectively counting the occurrence times of various signals with the same value in the filtering signals aiming at each frame to obtain a statistical result corresponding to the filtering signals of each frame;

and traversing the occurrence times of the various signals in the statistical result of each frame, and updating the signals with the occurrence times smaller than a second threshold or larger than a third threshold into the signal values of adjacent signals so as to obtain the balanced signals, wherein the occurrence times of the adjacent signals are larger than the second threshold and smaller than the third threshold.

4. The method according to claim 2, wherein the performing the feature enhancement processing on the equalized signals corresponding to each frame to obtain the target signals corresponding to each frame comprises:

aiming at each frame, performing enhancement processing on the current frame balanced signal to obtain a first enhanced signal;

determining a difference value between the current frame balanced signal and the adjacent frame balanced signal to obtain a difference value signal;

enhancing the difference signal to obtain a second enhanced signal;

and performing weighted fusion processing on the second enhanced signal and the first enhanced signal to obtain a target signal corresponding to the current frame.

5. The method of claim 1, wherein determining the leak area of the gas to be detected in the target image comprises:

inputting the target image into a pre-trained target recognition model for recognition processing to obtain a gas detection frame of the gas to be detected;

and determining the leakage area of the gas to be detected based on the position information of the gas detection frame.

6. The method according to claim 5, wherein the target image includes a foreground image and a background image, the foreground image at least includes the gas image to be detected, and the target image is input into a pre-trained target recognition model for processing to obtain a gas detection frame of the gas to be detected, including:

performing background separation on the target image in the pre-trained target recognition model to obtain the foreground image;

and carrying out target detection on the foreground image to obtain a gas detection frame corresponding to the gas to be detected.

7. The method of claim 1, wherein the acquiring a plurality of frames of infrared sensing signals in real time comprises:

acquiring a plurality of frames of infrared sensing signals in a first time period;

dividing the multiple frames of infrared sensing signals in the first time period to obtain multiple frames of infrared sensing signals in a plurality of second time periods, wherein the second time periods are obtained after the first time periods are divided;

after obtaining the target signal corresponding to each frame of infrared sensing signal, the method further includes:

and synthesizing the target signals in the second time periods to obtain a plurality of target signals in the first time period.

8. A gas leak detection apparatus, comprising:

the acquisition module is used for acquiring multi-frame infrared sensing signals in real time; the infrared induction signal is obtained by converting infrared radiation energy of the gas to be detected and the environment obtained by current detection;

the processing module is used for preprocessing the infrared sensing signals of each frame to obtain target signals corresponding to each frame;

the processing module is further configured to perform mapping processing on the target signal to obtain target images corresponding to the frames respectively;

the determining module is used for determining the leakage area of the gas to be detected in the target image corresponding to each frame, and determining the leakage state of the gas to be detected based on the leakage areas corresponding to the target images of the frames connected in time sequence.

9. A computer device comprising a memory and a processor, the memory storing a computer program operable on the processor, wherein the processor when executing the program performs the steps of the method of any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.