CN110836706B - Liquid level detection method and device - Google Patents

The embodiment of the invention discloses a liquid level detection method and a liquid level detection device, which relate to the technical field of image processing, and the method comprises the following steps: the method comprises the steps of obtaining a standard image and an image to be analyzed of the equipment to be analyzed, carrying out difference image processing on the image to be analyzed according to the standard image to obtain a difference image to be analyzed, carrying out horizontal edge detection on the difference image to be analyzed, and determining the liquid level height of the equipment to be analyzed in the image to be analyzed according to one or more horizontal edges of the difference image to be analyzed, wherein the length of the horizontal edges is larger than a first threshold value. Because the longer the horizontal edge is, the more likely the horizontal edge is to be the actual liquid level edge, in the embodiment of the invention, the horizontal edge detection is performed on the image to be analyzed, and the filtering in the horizontal direction is performed on the detected edge, so that the noise edge generated by bubbles in the image to be analyzed can be effectively removed, and the liquid level detection precision is improved.

Liquid level detection method and device

Technical Field

The invention relates to the technical field of image processing, in particular to a liquid level detection method and device.

Background

Oil level height is an important parameter for measuring the performance of equipment such as air conditioners. When an oil experiment of the equipment is carried out, the oil level and the liquid level in the equipment are changed, and the liquid level position needs to be detected relatively accurately in order to determine the oil level and the liquid level change rule of the equipment. In the actual operation of the equipment, the liquid column of the organic liquid is easy to have a gas-liquid mixed state of a lower-section liquid column and an upper-section bubble column. With the conventional edge detection method, due to the existence of the foam liquid, a plurality of false detection edges are inevitably introduced, which is not beneficial to the quantitative analysis of the experiment and also causes the accuracy of the detected liquid level height to be poor. Therefore, there is a need for a liquid level detection method to solve the technical problem of inaccurate liquid level height detection of the prior art.

Disclosure of Invention

The invention provides a liquid level detection method and a liquid level detection device, which are used for solving the technical problem of inaccurate liquid level height detection in the prior art.

The embodiment of the invention provides a liquid level detection method, which comprises the following steps:

acquiring a standard image and an image to be analyzed of equipment to be tested; the image to be analyzed is an image containing liquid level height information of the equipment to be analyzed;

according to the standard image, difference image processing is carried out on the image to be analyzed to obtain a difference image to be analyzed corresponding to the image to be analyzed;

and performing horizontal edge detection on the difference image to be analyzed, and determining the liquid level height of the equipment to be detected in the image to be analyzed according to one or more horizontal edges of which the length is greater than a first set threshold value in the difference image to be analyzed.

Optionally, performing difference map processing on the image to be analyzed according to the standard image to obtain a difference map to be analyzed corresponding to the image to be analyzed, including:

the image to be analyzed and the standard image are subjected to difference to obtain an initial difference image; the gray scale of each pixel in the initial difference image is the difference between the gray scales of the corresponding pixels in the image to be analyzed and the standard image;

and carrying out normalization processing on the gray scale of each pixel in the initial difference image to obtain the difference image to be analyzed.

Optionally, determining the liquid level height of the device to be tested in the image to be analyzed according to one or more horizontal edges of the difference image to be analyzed, where the length of the horizontal edges is greater than a first set threshold, includes:

if it is determined that only one horizontal edge with the length larger than the first set threshold exists in the difference image to be analyzed, taking the horizontal edge as the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position;

and if it is determined that at least two horizontal edges with lengths larger than the first set threshold exist in the difference image to be analyzed, determining the liquid level height according to the horizontal edge with the smallest curvature in the at least two horizontal edges with lengths larger than the first set threshold.

Optionally, determining the liquid level height according to a horizontal edge with a smallest curvature of the at least two horizontal edges with lengths larger than the first set threshold includes:

if the fact that the horizontal edge with the smallest curvature is still multiple in the at least two horizontal edges with the lengths larger than the first set threshold is determined, taking the height average value or the median value of each horizontal edge with the lengths larger than the first set threshold and the smallest curvature as the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position; or,

if the at least two horizontal edges with the lengths larger than the first set threshold value are determined to be multiple horizontal edges with the smallest curvature, performing front-and-back frame correlation analysis according to the two horizontal edges with the smallest centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the smallest curvature, determining the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position.

Optionally, performing correlation analysis on the previous and subsequent frames according to two horizontal edges with the smallest centroid offset degree among the at least two horizontal edges with the smallest curvature and lengths larger than the first set threshold value, and determining the liquid level height, including:

if the fact that the heights of the two horizontal edges with the minimum centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the minimum curvature are higher than the liquid level positions in the image to be analyzed in the previous frame and the image to be analyzed in the next frame in the liquid level change video is determined, the horizontal edge with the lower height in the two horizontal edges is used as the liquid level position in the image to be analyzed, and the liquid level height is calculated according to the liquid level position;

if the two horizontal edges with the minimum centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the minimum curvature are determined to be lower than the liquid level positions in the image to be analyzed in the previous frame and the image to be analyzed in the next frame in the liquid level change video, the horizontal edge with the higher height in the two horizontal edges is used as the liquid level position in the image to be analyzed, and the liquid level height is calculated according to the liquid level position;

if the height of the two horizontal edges with the minimum centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the minimum curvature is determined to be located between the liquid level positions in the previous frame of image to be analyzed and the next frame of image to be analyzed, performing interpolation estimation according to the liquid level positions in the previous frame of image to be analyzed and the next frame of image to be analyzed to obtain the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position.

Based on the same inventive concept, the present invention also provides a liquid level detection apparatus, comprising:

the acquisition module is used for acquiring a standard image and an image to be analyzed of the equipment to be tested; the image to be analyzed is an image containing liquid level height information of the equipment to be analyzed;

the processing module is used for carrying out difference image processing on the image to be analyzed according to the standard image to obtain a difference image to be analyzed corresponding to the image to be analyzed;

and the detection module is used for carrying out horizontal edge detection on the difference image to be analyzed and determining the liquid level height of the equipment to be detected in the image to be analyzed according to one or more horizontal edges with the length larger than a first set threshold value in the difference image to be analyzed.

Optionally, the processing module is specifically configured to:

the image to be analyzed and the standard image are subjected to difference to obtain an initial difference image; the gray scale of each pixel in the initial difference image is the difference between the gray scales of the corresponding pixels in the image to be analyzed and the standard image;

and carrying out normalization processing on the gray scale of each pixel in the initial difference image to obtain the difference image to be analyzed.

Optionally, the detection module is specifically configured to:

if it is determined that only one horizontal edge with the length larger than the first set threshold exists in the difference image to be analyzed, taking the horizontal edge as the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position;

and if it is determined that at least two horizontal edges with lengths larger than the first set threshold exist in the difference image to be analyzed, determining the liquid level height according to the horizontal edge with the smallest curvature in the at least two horizontal edges with lengths larger than the first set threshold.

Optionally, the detection module is further specifically configured to:

if the horizontal edges with the smallest curvature are still multiple horizontal edges in the at least two horizontal edges with the lengths larger than the first set threshold, taking the height average value or the median value of the horizontal edges as the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position; or,

if the at least two horizontal edges with the lengths larger than the first set threshold value are determined, the horizontal edge with the smallest curvature is still multiple, then, according to the two horizontal edges with the smallest centroid deviation degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the smallest curvature, performing front-and-back frame correlation analysis, determining the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position.

Optionally, the detection module is further specifically configured to:

if the fact that the heights of the two horizontal edges with the minimum centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the minimum curvature are higher than the liquid level positions in the image to be analyzed in the previous frame and the image to be analyzed in the next frame in the liquid level change video is determined, the horizontal edge with the lower height in the two horizontal edges is used as the liquid level position in the image to be analyzed, and the liquid level height is calculated according to the liquid level position;

if the two horizontal edges with the minimum centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the minimum curvature are determined to be lower than the liquid level positions in the image to be analyzed in the previous frame and the image to be analyzed in the next frame in the liquid level change video, the horizontal edge with the higher height in the two horizontal edges is used as the liquid level position in the image to be analyzed, and the liquid level height is calculated according to the liquid level position;

if the height of the two horizontal edges with the minimum centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the minimum curvature is determined to be located between the liquid level positions in the previous frame of image to be analyzed and the next frame of image to be analyzed, performing interpolation estimation according to the liquid level positions in the previous frame of image to be analyzed and the next frame of image to be analyzed to obtain the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position.

Another embodiment of the present invention provides a detection apparatus, which includes a memory and a processor, wherein the memory is used for storing program instructions, and the processor is used for calling the program instructions stored in the memory and executing any one of the above methods according to the obtained program.

Another embodiment of the present invention provides a computer storage medium having stored thereon computer-executable instructions for causing a computer to perform any one of the methods described above.

The method and the device for detecting the liquid level of the equipment to be detected can obtain a standard image and an image to be analyzed of the equipment to be detected, carry out difference image processing on the image to be analyzed according to the standard image to obtain a difference image to be analyzed, carry out horizontal edge detection on the difference image to be analyzed, and determine the liquid level height of the equipment to be detected in the image to be analyzed according to one or more horizontal edges of the difference image to be analyzed, wherein the length of the horizontal edges is larger than a first threshold value. Because the longer the horizontal edge is, the more likely the horizontal edge is to be the actual liquid level edge, in the embodiment of the invention, the horizontal edge detection is performed on the image to be analyzed, and the filtering in the horizontal direction is performed on the detected edge, so that the noise edge generated by bubbles in the image to be analyzed can be effectively removed, and the liquid level detection precision is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

FIG. 1 is a schematic diagram of an application scenario in which the embodiment of the present invention is applicable;

FIG. 2 is a schematic flow chart illustrating a liquid level detection method according to an embodiment of the present invention;

fig. 3a and 3b are schematic structural diagrams of a liquid viewing mirror according to an embodiment of the present invention;

FIG. 4 is a schematic flow chart of a method for calculating an actual liquid level height in an image to be analyzed according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a liquid level detecting device according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of a liquid level detection apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The embodiments of the present invention will be described in further detail with reference to the drawings attached hereto.

Fig. 2 exemplarily shows a liquid level detection method provided by an embodiment of the present invention, which can be specifically executed by the liquid level detection apparatus in the above application scenario. As shown in fig. 2, the method comprises the steps of:

step S201: acquiring a standard image and an image to be analyzed of equipment to be tested; the image to be analyzed is an image containing liquid level height information of the equipment to be analyzed;

step S202: according to the standard image, difference image processing is carried out on the image to be analyzed to obtain a difference image to be analyzed corresponding to the image to be analyzed;

step S203: and performing horizontal edge detection on the difference image to be analyzed, and determining the liquid level height of the equipment to be detected in the image to be analyzed according to one or more horizontal edges of which the length is greater than a first set threshold value in the difference image to be analyzed.

The method and the device for detecting the liquid level of the equipment to be detected can obtain a standard image and an image to be analyzed of the equipment to be detected, carry out difference image processing on the image to be analyzed according to the standard image to obtain a difference image to be analyzed, carry out horizontal edge detection on the difference image to be analyzed, and determine the liquid level height of the equipment to be detected in the image to be analyzed according to one or more horizontal edges of the difference image to be analyzed, wherein the length of the horizontal edges is larger than a first threshold value. Because the longer the horizontal edge is, the more likely the horizontal edge is to be the actual liquid level edge, in the embodiment of the invention, the horizontal edge detection is performed on the image to be analyzed, and the filtering in the horizontal direction is performed on the detected edge, so that the noise edge generated by bubbles in the image to be analyzed can be effectively removed, and the liquid level detection precision is improved.

In step S201, both the standard image and the image to be analyzed of the device under test are images including the above-mentioned liquid level viewing lens (especially, the liquid level window area of the liquid level viewing lens). Specifically, the standard image is collected under the condition that no liquid column exists in the liquid scope, and is used as a reference for calculating a difference map between a subsequent image and an image to be analyzed, for example, when the liquid scope equipment is installed but liquid level detection is not performed, the collected image of the liquid scope is used as the standard image, and the standard image does not contain liquid level information of the equipment to be detected; the image to be analyzed can be a frame of image obtained from a liquid level change video of the device to be detected, which is shot in advance, and the image to be analyzed contains liquid level height information of the device to be detected and is an object to be detected and analyzed.

In step S202, difference map processing may be performed on the image to be analyzed according to the standard image, so as to obtain a difference map to be analyzed corresponding to the image to be analyzed. In the embodiment of the present invention, the difference map processing specifically means that an image of the image to be analyzed is subjected to image difference with the standard image, and the gray level of each pixel in the obtained difference map is the difference between the gray levels of the corresponding pixels in the image to be analyzed and the standard image. Compared with the standard image, the image to be analyzed contains basically the same objects but only contains different liquid level height information, so that the environment variables in the image can be effectively removed by performing difference map processing on the image to be analyzed, the difference between the image to be analyzed and the standard image is highlighted, the calculation and analysis of constant edges are effectively reduced in the subsequent detection, and the precision of liquid level detection is improved.

The liquid level height information of the equipment to be tested is embodied in the image to be analyzed, namely the liquid level edge in the image to be analyzed. It will be appreciated that the height of the liquid level edge in the device under test will change over time during operation of the device, while the edge formed by the inherent texture in the field of view will not change over time. For example, the edge formed at the junction of the liquid level window and the metal part of the liquid level viewing mirror is a constant edge which stably exists in the field of view. Therefore, by carrying out difference image processing, the constant variable in the image to be analyzed is removed, the sensitivity to the image change can be enhanced, and the influence of other information irrelevant to the liquid level in the image to be analyzed on the detection of the liquid level height is avoided.

In the embodiment of the present invention, the difference map directly obtained after the difference map processing may be referred to as an initial difference map, and after the initial difference map is obtained, the gray scale of each pixel in the initial difference map may be normalized to obtain the difference map to be analyzed. Specifically, taking any pixel in the initial difference map as an example, after normalization, the gray scale of the pixel satisfies the following relationship:

wherein Gray refers to the Gray level of the pixel in the difference image to be analyzed after normalization, Gray' refers to the Gray level of the pixel in the initial difference image, Gray_maxAnd Gray_minRespectively, the gray level maximum value and the gray level minimum value in all pixels of the initial difference map.

For example, if the minimum value and the maximum value of the gray scale of each pixel in the initial difference map are 0.01 and 0.02, the maximum variation width of the data difference is only 0.01. After normalization, the variation range of the data difference is changed from 0.01 to 1. The first formula is combined to show that the initial difference image is subjected to normalization processing, the variation range of the difference in the difference image can be normalized, small differences are amplified, and the liquid level height information contained in the difference image to be analyzed is more remarkable and convenient to analyze.

In step S203, horizontal edge detection may be performed on the difference map to be analyzed, and the liquid level height of the device to be tested in the image to be analyzed is determined according to the detected one or more horizontal edges.

After the constant edges in the image to be analyzed are removed through difference map processing, the edges reserved in the image to be analyzed are mainly edges formed by bubbles and edges formed by a gas-liquid interface. But typically the bubble forms an edge that is curved (e.g., may be curved or rounded) and results in discrete short edges when horizontal edge detection is performed. Since the inner diameter of the liquid-viewing lens is large enough that the capillary effect is insignificant, the edge formed by the gas-liquid interface is generally a horizontally oriented edge that is much longer than the horizontally oriented edge formed by the gas bubble. Therefore, according to the characteristics that the liquid surface edge can keep a horizontal edge and the bubble edge has a non-horizontal edge, the embodiment of the invention can carry out edge detection in the horizontal direction in the difference image to be analyzed, thereby achieving the effects that the liquid surface edge can be completely reserved and the bubble edge is interrupted in the detection result.

Further, in consideration that a plurality of potential liquid level edges in the horizontal direction may still exist in the detection result, the embodiment of the present invention may perform length filtering in the horizontal direction on each potential liquid level edge, for example, may set a length threshold to filter out pseudo liquid level edge noise generated by bubbles, so as to further improve the liquid level detection accuracy.

Specifically, if only one horizontal edge with the length larger than the first set threshold value exists in the detection result, the horizontal edge can be used as the liquid level position in the image to be analyzed, and the liquid level height is calculated according to the liquid level position; if there are a plurality of horizontal edges with lengths greater than the first set threshold in the detection result, the horizontal edge with the longest length may be directly selected from the plurality of horizontal edges with lengths greater than the first set threshold as the liquid level position in the image to be analyzed, or filtering may be performed again according to the curvature of each horizontal edge, if there is only one horizontal edge with the smallest curvature in the plurality of horizontal edges with lengths greater than the first set threshold, the horizontal edge may be used as the liquid level position in the image to be analyzed, and the liquid level height is calculated; if there are more horizontal edges with the smallest curvature among the horizontal edges with the lengths larger than the first set threshold, a possible implementation manner is to take the average or median of the heights of the horizontal edges with the lengths larger than the first set threshold and the curvatures smaller than the second set threshold as the liquid level position in the image to be analyzed, and calculate the liquid level height; another possible implementation manner is that according to two horizontal edges with the smallest centroid deviation degree in the horizontal edges with the lengths larger than the first set threshold and the curvatures smaller than the second set threshold, performing front-and-back frame correlation analysis, determining the liquid level position in the image to be analyzed, and calculating the liquid level height; if the lengths of all the horizontal edges in the detection result are not larger than the first set threshold value, the liquid level position in the image to be analyzed can be estimated through interpolation estimation, and the liquid level height can be calculated.

In the embodiment of the invention, the determination of the liquid level position in the image to be analyzed through the correlation analysis of the front frame and the back frame specifically comprises the following steps: if the heights of the two finally screened horizontal edges with the minimum centroid offset degree are higher than the liquid level positions in the image to be analyzed in the previous frame and the image to be analyzed in the next frame in the liquid level change video, the horizontal edge with the lower height in the two horizontal edges can be used as the liquid level position in the image to be analyzed, and the liquid level height is calculated according to the liquid level position; if the heights of the two finally screened horizontal edges are lower than the liquid level positions in the image to be analyzed in the previous frame and the image to be analyzed in the next frame in the liquid level change video, the horizontal edge with the higher height in the two horizontal edges can be used as the liquid level position in the image to be analyzed, and the liquid level height is calculated according to the liquid level position; if the heights of the two finally screened horizontal edges are located between the liquid level positions of the previous frame of image to be analyzed and the next frame of image to be analyzed, interpolation estimation can be carried out according to the liquid level positions in the previous frame of image to be analyzed and the next frame of image to be analyzed, the liquid level position in the image to be analyzed is estimated, and the liquid level height is calculated according to the liquid level position.

In the embodiment of the present invention, the first set threshold may be set by a person skilled in the art according to actual needs, and the embodiment of the present invention is not particularly limited thereto. For example, in a possible implementation manner, in order to obtain a higher liquid level detection accuracy, the first set threshold may be set to 2/3 of the sight glass width, and further, if the horizontal edge with the longest length is selected as the liquid level position from among the horizontal edges with the lengths longer than the first set threshold, the horizontal edge with the length longer than 90% of the sight glass width may be directly processed as the longest horizontal edge from among the horizontal edges with the lengths longer than the first set threshold, or further screening and processing may be performed on the horizontal edges with the length longer than 90% of the sight glass width, such as directly calculating an average value or a median value of the edge heights, so as to obtain the liquid level height.

In a possible implementation manner, the detection result of the liquid level detector in the device to be detected can be combined to perform fusion inference on the liquid level position of the device to be detected. Specifically, if there are multiple horizontal edges whose lengths are greater than the first set threshold in the differential image to be analyzed after the length filtering, in the embodiment of the present invention, the liquid level detection result of the liquid level detector in the device to be detected may also be directly adopted as the liquid level height of the device to be detected, and in the case where there is only one horizontal edge whose length is greater than the first set threshold, the liquid level height obtained by performing image analysis on the image to be analyzed is adopted as the liquid level height of the device to be detected.

Because the height of the liquid level position in the image to be analyzed is not the actual liquid level height of the equipment to be analyzed, but the liquid level height after scaling, the embodiment of the invention can calculate the actual liquid level height according to the height of the liquid level position after the liquid level position is determined in the image to be analyzed. The specific method is as follows,

step S401: before an image to be analyzed is collected by the image collecting equipment, a scale reference standard component is arranged on the equipment to be analyzed, and the actual height of the standard component is known.

Step S402: and measuring the height of the standard component in the image to be analyzed, and determining the proportional relation between the actual height of the standard component and the height of the standard component in the image to be analyzed.

In an embodiment of the present invention, the height of the standard in the image to be analyzed may be the number of pixel rows occupied by the standard in the image to be analyzed. Thus, the determined proportional relation between the actual height of the standard component and the height of the standard component in the image to be analyzed is the actual height represented by each row of pixels in the image to be analyzed.

Step S403: and determining the height of the liquid level in the image to be analyzed according to the height of the liquid level position in the image to be analyzed and the proportional relation between the actual height of the standard component and the height of the standard component in the image to be analyzed.

In the embodiment of the invention, the total line number of the image to be analyzed can be subtracted by the line where the liquid level position is located to obtain the liquid level height in the image to be analyzed, and the liquid level height is multiplied by the height information represented by a line of pixels to obtain the actual liquid level height of the equipment to be tested in the image to be analyzed.

As described above, the image to be analyzed is obtained from the liquid level change video previously captured by the image capturing device, and generally, the image capturing device captures the entire device under test (especially, the liquid level sight glass installed in the device under test) when capturing the liquid level change video. However, when determining the level height of the device under test, it is primarily by observing the liquid level in the liquid level window of the sight glass. Therefore, in order to improve the liquid level detection precision, the embodiment of the invention can also calibrate the liquid level window area in the differential image to be analyzed before horizontal edge detection is carried out, and carry out edge detection only in the liquid level window area so as to reduce the range of edge detection and avoid the influence of the area outside the liquid level window in the image to be analyzed on the accuracy of liquid level detection.

Specifically, the liquid level window region in the image to be analyzed may be calibrated in various possible implementation manners, for example, manual calibration may be performed, or calibration may be performed by using an image recognition method.

It should be noted that, the above steps S201 to S203 are only taken as an example of one frame of image to be analyzed selected from the liquid level change video of the device under test, and the process of detecting the liquid level height is described. The technical personnel in the field can select multiple frames of images from the liquid level change video according to the detection requirement to sequentially perform the processing, determine the liquid level height in each frame of image and further obtain the liquid level height change rule of the equipment to be detected.

If the liquid level height of the equipment to be detected obviously changes along with time, in order to improve the liquid level detection precision of the equipment to be detected, each frame of image in the liquid level change video can be used as an image to be analyzed for the processing; if the liquid level height of the equipment to be tested does not change obviously along with time, one frame of image can be selected from the liquid level change video at regular time intervals or frame intervals to be used as an image to be analyzed for the above processing.

Generally, considering that the oil level and the liquid level of the organic liquid in the device under test are changed slowly, the liquid level height of the device under test does not change suddenly in a short time (e.g. 1 second or 0.5 second), and therefore, in order to improve the efficiency of liquid level detection, a frame skipping analysis scheme may be adopted, and one frame of image is selected from a liquid level change video every 10 frames or 20 frames for liquid level detection analysis. It should be noted that the frame interval used in the frame skipping detection may be set by a person skilled in the art according to actual needs, and includes, but is not limited to, the above-mentioned 10 frames and 20 frames, and may be other frame intervals, which is not specifically limited in this embodiment of the present invention.

Similarly, in order to objectively and accurately reflect the change rule of the liquid level height in the equipment to be measured, the technical personnel in the field can also set the shooting time of the liquid level change video by themselves. Generally, the device under test can be taken to uniformly select a plurality of frames of images from a liquid level change video within 2 to 3 hours for liquid level detection and analysis.

the image to be analyzed and the standard image are subjected to difference to obtain an initial difference image; the gray scale of each pixel in the initial difference image is the difference between the gray scales of the corresponding pixels in the image to be analyzed and the standard image;

and carrying out normalization processing on the gray scale of each pixel in the initial difference image to obtain the difference image to be analyzed.

if it is determined that only one horizontal edge with the length larger than the first set threshold exists in the difference image to be analyzed, taking the horizontal edge as the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position;

and if it is determined that at least two horizontal edges with lengths larger than the first set threshold exist in the difference image to be analyzed, determining the liquid level height according to the horizontal edge with the smallest curvature in the at least two horizontal edges with lengths larger than the first set threshold.

if the horizontal edges with the smallest curvature are still multiple horizontal edges in the at least two horizontal edges with the lengths larger than the first set threshold, taking the height average value or the median value of the horizontal edges as the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position; or,

if the at least two horizontal edges with the lengths larger than the first set threshold value are determined to be multiple horizontal edges with the smallest curvature, performing front-and-back frame correlation analysis according to the two horizontal edges with the smallest centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the smallest curvature, determining the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position.

if the fact that the heights of the two horizontal edges with the minimum centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the minimum curvature are higher than the liquid level positions in the image to be analyzed in the previous frame and the image to be analyzed in the next frame in the liquid level change video is determined, the horizontal edge with the lower height in the two horizontal edges is used as the liquid level position in the image to be analyzed, and the liquid level height is calculated according to the liquid level position;

if the two horizontal edges with the minimum centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the minimum curvature are determined to be lower than the liquid level positions in the image to be analyzed in the previous frame and the image to be analyzed in the next frame in the liquid level change video, the horizontal edge with the higher height in the two horizontal edges is used as the liquid level position in the image to be analyzed, and the liquid level height is calculated according to the liquid level position;

if the height of the two horizontal edges with the minimum centroid offset degree in the at least two horizontal edges with the lengths larger than the first set threshold value and the minimum curvature is determined to be located between the liquid level positions in the previous frame of image to be analyzed and the next frame of image to be analyzed, performing interpolation estimation according to the liquid level positions in the previous frame of image to be analyzed and the next frame of image to be analyzed to obtain the liquid level position in the image to be analyzed, and calculating the liquid level height according to the liquid level position.

Another embodiment of the present invention provides a liquid level detecting apparatus, which includes a memory and a processor, wherein the memory is used for storing program instructions, and the processor is used for calling the program instructions stored in the memory and executing any one of the above methods according to the obtained program.

Another embodiment of the present invention provides a computer storage medium having stored thereon computer-executable instructions for causing a computer to perform any one of the methods described above.

The memory may include Read Only Memory (ROM) and Random Access Memory (RAM), and provides the processor with program instructions and data stored in the memory. In an embodiment of the present invention, the memory may be used to store the program of the above liquid level detection method.

The processor is used for executing the liquid level detection method according to the obtained program instructions by calling the program instructions stored in the memory.

Based on the same inventive concept, embodiments of the present invention provide a computer storage medium for storing computer program instructions for the above detection apparatus, which includes a program for executing the above liquid level detection method.

The computer storage media may be any available media or data storage device that can be accessed by a computer, including, but not limited to, magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), Solid State Disks (SSDs)), etc.

From the above, it can be seen that:

the method and the device for detecting the liquid level of the equipment to be detected can obtain a standard image and an image to be analyzed of the equipment to be detected, carry out difference image processing on the image to be analyzed according to the standard image to obtain a difference image to be analyzed, carry out horizontal edge detection on the difference image to be analyzed, and determine the liquid level height of the equipment to be detected in the image to be analyzed according to one or more horizontal edges of the difference image to be analyzed, wherein the length of the horizontal edges is larger than a first threshold value. Because the longer the horizontal edge is, the more likely the horizontal edge is to be the actual liquid level edge, in the embodiment of the invention, the horizontal edge detection is performed on the image to be analyzed, and the filtering in the horizontal direction is performed on the detected edge, so that the noise edge generated by bubbles in the image to be analyzed can be effectively removed, and the liquid level detection precision is improved.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart block or blocks and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While alternative embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following appended claims be interpreted as including alternative embodiments and all such alterations and modifications as fall within the scope of the invention.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.