CN110836705A - Liquid level video analysis method and device - Google Patents
Liquid level video analysis method and device Download PDFInfo
- Publication number
- CN110836705A CN110836705A CN201810929030.9A CN201810929030A CN110836705A CN 110836705 A CN110836705 A CN 110836705A CN 201810929030 A CN201810929030 A CN 201810929030A CN 110836705 A CN110836705 A CN 110836705A
- Authority
- CN
- China
- Prior art keywords
- liquid level
- analyzed
- image
- equipment
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
Abstract
The embodiment of the invention provides a liquid level video analysis method and a liquid level video analysis device, which relate to the technical field of image processing, and the method comprises the following steps: the liquid level monitoring method includes the steps of obtaining multiple frames of images to be analyzed and liquid level monitoring moments corresponding to the multiple frames of images to be analyzed from a liquid level video, then carrying out edge detection on the images to be analyzed to determine the liquid level of equipment to be detected in the images to be analyzed, then determining the liquid level height of the equipment to be detected at the liquid level monitoring moments corresponding to the images to be analyzed according to the liquid level of the equipment to be detected in the images to be analyzed, finally determining the rule of the liquid level height of the equipment to be detected along with time change according to the liquid level monitoring moments corresponding to the multiple frames of images to be analyzed and the liquid level height of the equipment to be detected at the liquid level monitoring moments corresponding to the multiple frames of images to be analyzed, and therefore automatic measurement of the liquid level height of the equipment to be detected is achieved.
Description
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to a liquid level video analysis method and device.
Background
Due to factors such as environmental limitation, safety consideration or experiment period, many devices do not have the condition that the liquid level changes are monitored on site by experimenters in real time when oil experiments are carried out. However, for the performance test of the equipment, the change rule of the liquid level is an important working condition parameter. In order to solve the problems, at present, during an experiment, a liquid level change video of the experiment process is recorded, and then the liquid level change process in the video is analyzed to determine the change rule of the liquid level. However, when the liquid level change process is analyzed, a video needs to be played back, and then scale data of the liquid level needs to be manually recorded, so that the method is time-consuming and labor-consuming, and data information is inevitably lost due to human fatigue and other factors.
Disclosure of Invention
The embodiment of the invention provides a liquid level video analysis method and device, and solves the problem that in the prior art, liquid level change needs to be analyzed by manually marking liquid level scales in a liquid level video, so that the analysis efficiency and the analysis precision are low.
In a first aspect, an embodiment of the present invention provides a method for analyzing a liquid level video, where the method includes:
acquiring a plurality of frames of images to be analyzed and liquid level monitoring moments corresponding to the plurality of frames of images to be analyzed from a liquid level video, wherein the liquid level video is a liquid level change process video of equipment to be detected which is monitored in advance;
performing edge detection on the image to be analyzed to determine the liquid level of the equipment to be analyzed in the image to be analyzed aiming at any one image to be analyzed in the plurality of frames of images to be analyzed;
determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level of the equipment to be detected in the image to be analyzed;
and determining the rule of the liquid level height of the equipment to be tested along with the change of time according to the liquid level monitoring time corresponding to the multiple frames of images to be analyzed and the liquid level height of the equipment to be tested at the liquid level monitoring time corresponding to the multiple frames of images to be analyzed.
Because a plurality of frames of images to be analyzed are selected from the liquid level video, the images to be analyzed are subjected to edge detection to determine the liquid level of the equipment to be tested in the images to be analyzed, and then the liquid level height of the equipment to be tested in the real world is further determined, the automatic measurement of the liquid level height of the equipment to be tested is realized, the liquid level scale does not need to be manually read to determine the liquid level height, the labor cost is saved, and the precision and the efficiency are improved. Secondly, each frame of image to be analyzed corresponds to a liquid level monitoring moment, after edge detection is carried out on each frame of image to be analyzed to determine the liquid level height of the equipment to be tested, the rule of the liquid level height of the equipment to be tested changing along with time can be determined by combining the monitoring moment corresponding to the image to be analyzed and the liquid level height of the equipment to be tested, and automatic analysis of the liquid level change is achieved.
Optionally, the determining the liquid level of the device to be detected in the image to be analyzed by performing edge detection on the image to be analyzed includes:
marking a liquid level window area of the equipment to be tested from the image to be analyzed;
carrying out edge detection on the liquid level window area to determine the liquid level in the liquid level window area;
and determining the liquid level in the liquid level window area as the liquid level of the equipment to be tested in the image to be analyzed.
Because the liquid level window area is further determined from the image to be analyzed, then the edge detection is carried out on the liquid level window area, the edge detection range is reduced, the liquid level detection of the equipment to be detected is prevented from being influenced by objects in the area except the liquid level window area in the image to be analyzed, and the liquid level detection precision of the equipment to be detected is improved.
Optionally, before the edge detection is performed on the liquid level window region to determine the liquid level in the liquid level window region, the method further includes:
acquiring a reference image from the liquid level video, wherein the liquid level of a liquid level window area in the reference image is zero;
and carrying out difference map processing on the liquid level window area in the image to be analyzed and the liquid level window area in the reference image.
Because before carrying out edge detection to the liquid level window region, adopt the liquid level window region of reference image to treat the liquid level window region of analysis image and carry out the difference picture processing, and the difference between the liquid level window region in the reference image and the liquid level window region of the image of treating analysis is only the liquid level difference, so carry out the difference picture and handle the back, can filter the liquid level detection of influence object except the liquid level in the liquid level window region of the image of treating analysis image to improve the precision of liquid level detection.
Optionally, the edge detection on the liquid level window region to determine the liquid level in the liquid level window region includes:
carrying out horizontal edge detection on the liquid level window area to determine a horizontal edge line in the liquid level window area;
and when the length of the horizontal edge line is determined to be larger than a preset threshold value, determining the horizontal edge line as the liquid level in the liquid level window area.
Optionally, the determining, according to the liquid level of the device to be tested in the image to be analyzed, the liquid level height of the device to be tested at the liquid level monitoring time corresponding to the image to be analyzed includes:
determining the difference value between the liquid level of the equipment to be detected in the image to be analyzed and the reference liquid level of the equipment to be detected in the image to be analyzed as the liquid level height of the equipment to be detected in the image to be analyzed;
and determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level height of the equipment to be detected in the image to be analyzed and the proportional relation between the liquid level window area in the image to be analyzed and the liquid level window of the equipment to be detected.
In a second aspect, an embodiment of the present invention provides a liquid level video analysis apparatus, including:
the acquisition module is used for acquiring a plurality of frames of images to be analyzed and liquid level monitoring moments corresponding to the plurality of frames of images to be analyzed from a liquid level video, wherein the liquid level video is a liquid level change process video of equipment to be monitored in advance;
the detection module is used for carrying out edge detection on the image to be analyzed aiming at any one image to be analyzed in the plurality of frames of images to be analyzed so as to determine the liquid level of the equipment to be detected in the image to be analyzed;
the processing module is used for determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level of the equipment to be detected in the image to be analyzed;
and the analysis module is used for determining the rule of the liquid level height of the equipment to be tested changing along with time according to the liquid level monitoring time corresponding to the multi-frame images to be analyzed and the liquid level height of the equipment to be tested at the liquid level monitoring time corresponding to the multi-frame images to be analyzed.
Optionally, the detection module is specifically configured to:
marking a liquid level window area of the equipment to be tested from the image to be analyzed;
carrying out edge detection on the liquid level window area to determine the liquid level in the liquid level window area;
and determining the liquid level in the liquid level window area as the liquid level of the equipment to be tested in the image to be analyzed.
Optionally, the detection module is further configured to:
before edge detection is carried out on the liquid level window area to determine the liquid level in the liquid level window area, a reference image is obtained from the liquid level video, and the liquid level in the liquid level window area in the reference image is zero;
and carrying out difference map processing on the liquid level window area in the image to be analyzed and the liquid level window area in the reference image.
Optionally, the detection module is specifically configured to:
carrying out horizontal edge detection on the liquid level window area to determine a horizontal edge line in the liquid level window area;
and when the length of the horizontal edge line is determined to be larger than a preset threshold value, determining the horizontal edge line as the liquid level in the liquid level window area.
Optionally, the processing module is specifically configured to:
determining the difference value between the liquid level of the equipment to be detected in the image to be analyzed and the reference liquid level of the equipment to be detected in the image to be analyzed as the liquid level height of the equipment to be detected in the image to be analyzed;
and determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level height of the equipment to be detected in the image to be analyzed and the proportional relation between the liquid level window area in the image to be analyzed and the liquid level window of the equipment to be detected.
In a third aspect, an embodiment of the present invention provides a liquid level video analysis apparatus, including at least one processing unit and at least one storage unit, where the storage unit stores a computer program, and when the program is executed by the processing unit, the processing unit is caused to execute any of the steps of the method described above.
In a fourth aspect, embodiments of the present invention provide a computer-readable medium storing a computer program executable by a terminal device, when the program is run on a liquid level video analysis device, causing the liquid level video analysis device to perform any of the steps of the method described above.
In the embodiment of the invention, as a plurality of frames of images to be analyzed are selected from the liquid level video, the edge detection is carried out on the images to be analyzed to determine the liquid level of the equipment to be tested in the images to be analyzed, and then the liquid level height of the equipment to be tested in the real world is further determined, the automatic measurement of the liquid level height of the equipment to be tested is realized, the liquid level scale does not need to be manually read to determine the liquid level height, the labor cost is saved, and the precision and the efficiency are improved. Secondly, each frame of image to be analyzed corresponds to one liquid level monitoring moment, after edge detection is carried out on each frame of image to be analyzed to determine the liquid level height of the equipment to be tested, the rule of the liquid level height of the equipment to be tested changing along with time can be determined by combining the monitoring moment corresponding to the image to be analyzed and the liquid level height of the equipment to be tested, and automatic analysis of the liquid level change is achieved.
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 diagram of an application scenario in which the present invention is applied;
FIG. 2 is a schematic structural diagram of a liquid level video analyzer according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating a method for analyzing a liquid level video according to an embodiment of the present invention;
FIG. 4 is a flow chart illustrating a method for analyzing a liquid level video according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a device under test applicable to the embodiment of the present invention;
FIG. 6a is a schematic view of a liquid level window area according to an embodiment of the present invention;
FIG. 6b is a schematic view of a liquid level window area according to an embodiment of the present invention;
FIG. 6c is a schematic view of a liquid level window area according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a process for detecting a liquid level height of a device under test according to an embodiment of the present invention;
FIG. 8 is a flow chart illustrating a method for analyzing a liquid level video according to an embodiment of the present invention;
FIG. 9 is a schematic structural diagram of a liquid level video analyzer according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of a liquid level video analysis apparatus to which the embodiment of the invention is applied.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The liquid level video analysis method in the embodiment of the present invention may be applied to an application scenario as shown in fig. 1, where the application scenario includes a device to be tested 101, an image capturing device 102, and a liquid level video analysis apparatus 103. The device under test 101 may be a device requiring detection of a change in liquid level, and the performance of the device under test is analyzed by detecting the change in liquid level. For example, the performance of the air conditioner is detected by detecting the liquid level change of an instrument for loading a refrigerant in the air conditioner. Image capture device 102 is used to record video of the liquid level variation process of the device under test, and image capture device 102 may be a video recorder, a video camera, or the like. In order to ensure the accuracy of detecting the liquid level of the device under test, the relative position between the device under test 101 and the image capturing device 102 is not changed, and meanwhile, in the recording process, the environments of the device under test 101 and the image capturing device 102 are also not changed, for example, the ambient light is kept stable and consistent. After the image acquisition equipment 102 acquires the video of the liquid level change process of the equipment to be tested, the liquid level video is sent to the liquid level video analysis device 103, and then the liquid level video analysis device 103 analyzes the liquid level video to determine the rule that the liquid level height of the equipment to be tested changes along with time.
Further, in the application scenario diagram shown in fig. 1, a schematic structural diagram of the liquid level video analysis apparatus 103 is shown in fig. 2, and the liquid level video analysis apparatus 103 includes: a liquid level video analysis module 1031, a liquid level identification and detection module 1032, a liquid level data recording module 1033, and a result output module 1034. Specifically, the liquid level video analysis module 1031 acquires multiple frames of images to be analyzed from the liquid level video, and determines the liquid level monitoring time of the acquired multiple frames of images to be analyzed according to the recording time of each frame of image pair in the liquid level video. The liquid level video analysis module 1031 sends the multiple frames of images to be analyzed and the liquid level monitoring moments corresponding to the multiple frames of images to be analyzed to the liquid level identification and detection module 1032. The liquid level recognition and detection module 1032 performs horizontal edge detection on the liquid level window region in multiple frames of images to be analyzed, determines the liquid level of the device to be tested in the multiple frames of images to be analyzed, and then determines the liquid level height of the device to be tested in the real world according to the proportional relationship between the liquid level window region in the images to be analyzed and the liquid level window of the device to be tested. Then, the liquid level identification and detection module 1032 sends the liquid level monitoring time corresponding to the multiple frames of images to be analyzed and the liquid level height of the device under test at the liquid level monitoring time corresponding to the multiple frames of images to be analyzed to the liquid level data recording module 1033. The liquid level data recording module 1033 correspondingly stores the liquid level height and the liquid level monitoring time of the equipment to be tested, and a curve of the liquid level height of the equipment to be tested changing with time can be drawn according to the liquid level height and the liquid level monitoring time of the equipment to be tested. The liquid level data recording module 1033 outputs the liquid level height variation curve and the liquid level data through the result output module 1034, so that the tester can further analyze the performance of the device under test through the liquid level height variation curve and the liquid level data.
Based on the application scenario diagram shown in fig. 1 and the schematic structural diagram of the liquid level video analysis apparatus shown in fig. 2, an embodiment of the present invention provides a flow of a liquid level video analysis method, where the flow of the method may be executed by the liquid level video analysis apparatus, as shown in fig. 3, and the method includes the following steps:
step S301, obtaining multiple frames of images to be analyzed and liquid level monitoring moments corresponding to the multiple frames of images to be analyzed from the liquid level video.
Specifically, the liquid level video is a video of a liquid level change process of a device to be detected which is monitored in advance, wherein the device to be detected can be any device which needs to monitor liquid level change, and each frame image in the liquid level video corresponds to one liquid level monitoring moment. For example, the air conditioner generates a refrigeration effect by transferring heat through a refrigerant, and the refrigerant is easy to absorb heat to become gas and easy to release heat to become liquid. When a refrigerating unit in the air conditioner operates, refrigerant in the evaporator evaporates to absorb heat, and the liquid level in the evaporator changes. The refrigerating effect of the air conditioner can be obtained by analyzing the liquid level change in the evaporator. Air conditioners are required to test the performance of air conditioners, particularly the refrigeration function, just before they are put on the market. When the refrigeration effect of the air conditioner is tested through monitoring the liquid level change of the evaporator, because the monitoring time is long, a tester cannot be in on-site real-time monitoring all the time, so that the liquid level change process of the evaporator is recorded in real time through the video equipment, and then the recorded liquid level video is analyzed to determine the rule that the liquid level of the evaporator changes along with the time, so that the refrigeration effect of the air conditioner is tested.
Optionally, in step S301, the plurality of images to be analyzed may be each frame of image in the liquid level video, or may be partial images selected from the liquid level video according to a certain rule.
For example, if the liquid level of the device under test changes obviously with time, in order to improve the accuracy of liquid level detection of the device under test, each frame of image in the liquid level video may be taken as an image to be analyzed.
For example, if the liquid level of the device under test does not change significantly with time, for example, the liquid level of the device under test does not change substantially within 10 seconds, one frame of image can be selected from the liquid level video as the image to be analyzed every 10 seconds, thereby improving the efficiency of the liquid level video analysis.
Step S302, aiming at any one frame of image to be analyzed in the plurality of frames of images to be analyzed, carrying out edge detection on the image to be analyzed to determine the liquid level of the equipment to be detected in the image to be analyzed.
In a possible implementation manner, the edge detection is directly performed on the image to be analyzed, and the detected horizontal edge line is used as the liquid level of the equipment to be detected in the image to be analyzed.
In another possible implementation, the edge detection is performed on the liquid level window area in the image to be analyzed, and the detected horizontal edge line is used as the liquid level of the device to be detected in the image to be analyzed, which specifically includes the following steps, as shown in fig. 4:
step S401, a liquid level window area of the equipment to be analyzed is marked from the image to be analyzed.
The liquid level window is a component of the liquid level meter for indicating and observing the liquid level in the container, the liquid level meter is installed on the equipment to be tested, and then the liquid level in the equipment to be tested is observed through the liquid level window, and exemplarily, the position relation among the liquid level meter, the liquid level window and the equipment to be tested is shown in fig. 5.
When recording the liquid level video of the equipment to be tested, the video equipment records to whole equipment, and when confirming the liquid level of the equipment to be tested, mainly through observing the liquid level window, in order to improve the liquid level detection precision, can follow the liquid level window region that marks the equipment to be tested in waiting to analyze the image earlier, regard the liquid level window region as the analysis object. Alternatively, the liquid level window region can be marked manually from the image to be analyzed, and can also be marked from the image to be analyzed by an image recognition method.
And S402, carrying out edge detection on the liquid level window area to determine the liquid level in the liquid level window area.
In one possible embodiment, the horizontal edge detection is performed on the liquid level window region to determine a horizontal edge line in the liquid level window region, and when it is determined that a horizontal edge line is detected from the liquid level window region, it is determined whether the length of the horizontal edge line is greater than a preset threshold (e.g., 2/3 of the width of the liquid level window region), and if so, the horizontal edge line is determined as the liquid level in the liquid level window region. After the horizontal edge line is detected, whether the horizontal edge line is the liquid level is further judged according to the length of the horizontal edge line, and therefore liquid level detection precision is improved.
In a possible implementation manner, horizontal edge detection is performed on the liquid level window region to determine a horizontal edge line in the liquid level window region, and when a plurality of horizontal edge lines are determined to be detected from the liquid level window region, the liquid level in the liquid level window region is determined from the plurality of horizontal edge lines according to the liquid level of the device to be tested in the previous frame of image to be analyzed and the liquid level of the device to be tested in the next frame of image to be analyzed. Illustratively, when the liquid level window area is subjected to horizontal edge detection due to bubbles appearing on the liquid level surface of the device to be detected, three horizontal edge lines are determined, namely a horizontal edge line a, a horizontal edge line B and a horizontal edge line C. The liquid level of the former frame of image to be analyzed is the liquid level M, and the liquid level of the latter frame of image to be analyzed is the liquid level N. If the horizontal edge line a is located between the liquid level M and the liquid level N, and neither the horizontal edge line B nor the horizontal edge line C is located between the liquid level M and the liquid level N, the horizontal edge line a is determined as the liquid level in the liquid level window area. If the horizontal edge line a and the horizontal edge line B are located between the liquid level M and the liquid level N, and the horizontal edge line C is not located between the liquid level M and the liquid level N, the horizontal edge line a or the horizontal edge line B is determined as the liquid level in the liquid level window area, or a position in the middle of the horizontal edge line a or the horizontal edge line B is determined as the liquid level in the liquid level window area.
In one possible embodiment, the liquid level window area is subjected to horizontal edge detection to determine a horizontal edge line in the liquid level window area, and when a plurality of horizontal edge lines are determined to be detected from the liquid level window area, the longest horizontal edge line in the plurality of horizontal edge lines is determined as the liquid level in the liquid level window area. Illustratively, the horizontal edge detection of the liquid level window area is set to determine three horizontal edge lines, namely a horizontal edge line a, a horizontal edge line B and a horizontal edge line C, wherein the horizontal edge line a is the longest of the three horizontal edge lines, and the horizontal edge line a is determined as the liquid level in the liquid level window area.
When the edge of the liquid level window area of the image to be analyzed is detected, a plurality of horizontal lines can be detected due to the influence of other objects except the liquid level in the image, and when the plurality of horizontal lines appear, the liquid level can be determined from the plurality of horizontal lines according to the liquid level in the image to be analyzed in the front frame and the rear frame or the length of the horizontal line, so that the liquid level detection precision can be effectively improved.
And S403, determining the liquid level in the liquid level window area as the liquid level of the equipment to be tested in the image to be analyzed.
Because the liquid level window area is further determined from the image to be analyzed, then the edge detection is carried out on the liquid level window area, the edge detection range is reduced, the liquid level detection of the equipment to be detected is prevented from being influenced by objects in the area except the liquid level window area in the image to be analyzed, and the liquid level detection precision of the equipment to be detected is improved.
Optionally, before the edge detection is performed on the liquid level window region to determine the liquid level in the liquid level window region, a reference image may be obtained from the liquid level video, where the liquid level in the liquid level window region in the reference image is zero, and then the difference map processing is performed on the liquid level window region in the image to be analyzed and the liquid level window region in the reference image.
Specifically, the difference map processing removes an object included in the image to be analyzed in common with the reference image. For example, setting the liquid level window area in the reference image as shown in fig. 6a, the liquid level window area shown in fig. 6a has no liquid level because the liquid level of the device under test in the reference image is zero. The setting of the liquid level window area in the image to be analyzed is shown in fig. 6b, where the liquid level is present in fig. 6 b. FIG. 6c shows the difference between FIG. 6a and FIG. 6 b. As shown in fig. 6c, since both fig. 6a and fig. 6b include the border of the liquid level window, after the difference map processing is performed, the border portion of the liquid level window in the image to be analyzed can be removed, and the liquid level in the image to be analyzed is left. Further, edge detection is performed on the image shown in FIG. 6c, the liquid level in the image shown in FIG. 6c can be determined, and the influence of factors such as the frame of a liquid level window in the image to be analyzed on liquid level detection is avoided.
Because before carrying out edge detection to the liquid level window region, adopt the liquid level window region of reference image to treat the liquid level window region of analysis image and carry out the difference picture processing, and the difference between the liquid level window region in the reference image and the liquid level window region of the image of treating analysis is only the liquid level difference, so carry out the difference picture and handle the back, can filter the liquid level detection of influence object except the liquid level in the liquid level window region of the image of treating analysis image to improve the precision of liquid level detection.
Step S303, determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level of the equipment to be detected in the image to be analyzed.
Optionally, the liquid level obtained by edge detection is the liquid level of the device to be detected in the image to be analyzed, and the actual liquid level height of the device to be detected in the real world needs to be further determined according to the liquid level in the image to be analyzed, which specifically includes the following steps, as shown in fig. 7:
step S701, determining a difference value between the liquid level of the equipment to be detected in the image to be analyzed and the reference liquid level of the equipment to be detected in the image to be analyzed as the liquid level height of the equipment to be detected in the image to be analyzed.
Specifically, the bottom of a liquid level window area of the device to be tested in the image to be analyzed is used as a reference liquid level of the device to be tested, and the liquid level height of the device to be tested in the image to be analyzed is determined by measuring the distance between the liquid level in the image to be analyzed and the bottom of the liquid level area in the image to be analyzed.
Step S702, determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level height of the equipment to be detected in the image to be analyzed and the proportional relation between the liquid level window area in the image to be analyzed and the liquid level window of the equipment to be detected.
Since the liquid level height of the device to be tested in the image to be analyzed is not the actual liquid level height of the device to be tested, but is the liquid level height after scaling, the liquid level height of the device to be tested in the image to be analyzed needs to be further converted into the actual liquid level height of the device to be tested. In the embodiment of the invention, the scale reference standard component is arranged on the equipment to be tested, and the height of the standard component is known. And then measuring the height of the standard part in the image to be analyzed, taking the proportional relation between the height of the standard part in the image to be analyzed and the actual height of the standard part as the proportional relation between the liquid level window area in the image to be analyzed and the liquid level window of the equipment to be tested, and further determining the actual liquid level height of the equipment to be tested according to the proportional relation and the liquid level height of the equipment to be tested in the image to be analyzed. The proportional relation between the object in the image to be analyzed and the actual object is determined by setting the standard component, so that after the image to be analyzed is detected to determine the liquid level height of the equipment to be tested in the image to be analyzed, the liquid level height of the equipment to be tested in the image can be directly converted into the actual liquid level height of the equipment to be tested according to the proportional relation, the automatic detection of the liquid level height of the equipment to be tested is realized, and the efficiency and the precision of liquid level detection are improved.
Step S304, determining the rule of the liquid level height of the equipment to be tested along with the change of time according to the liquid level monitoring time corresponding to the multiple frames of images to be analyzed and the liquid level height of the equipment to be tested at the liquid level monitoring time corresponding to the multiple frames of images to be analyzed.
In specific implementation, the liquid level monitoring time and the liquid level height of the equipment to be tested are correspondingly stored, and then a liquid level change curve between the monitoring time and the liquid level height of the equipment to be tested is drawn. After the liquid level is detected in the image to be analyzed, the actual liquid level height of the equipment to be analyzed can be marked in the image to be analyzed, and then a plurality of frames of images to be analyzed with the marked liquid level form an analysis video in sequence. And finally, outputting the liquid level height data, the liquid level change curve and the analysis video to a tester so that the tester can analyze the performance of the equipment to be tested according to the data.
For better explaining the embodiment of the present invention, a method for analyzing a liquid level video according to the embodiment of the present invention is described below with reference to a specific implementation scenario, as shown in fig. 8, the method includes the following steps:
step S801, an image to be analyzed is acquired.
Step S802, marking the liquid level window area manually.
Step S803, a reference image is obtained, and the liquid level in the liquid level window region in the reference image is zero.
Step S804, a difference map processing is performed on the liquid level window region in the image to be analyzed and the liquid level window region in the reference image.
Step S805, carrying out horizontal edge detection on the liquid level window area in the image to be analyzed to determine the liquid level.
Step S805, determining the liquid level height of the equipment to be tested in the image to be analyzed according to the liquid level of the liquid level window area in the image to be analyzed.
In step S807, the height of the standard in the image to be analyzed is detected.
Step S808, determining the proportional relation between the height of the standard component in the image to be analyzed and the actual height of the standard component.
And step S809, determining the actual height of the equipment to be tested according to the proportional relation and the liquid level height of the equipment to be tested in the image to be analyzed.
Step S810, marking the actual liquid level height of the equipment to be tested in the image to be analyzed.
In step S811, whether the current image to be analyzed is the last frame of image to be analyzed is determined, if yes, step S812 is executed, otherwise, step S801 is executed.
And step S812, outputting the liquid level change curve and an analysis video consisting of a plurality of frames of images to be analyzed.
In the embodiment of the invention, as a plurality of frames of images to be analyzed are selected from the liquid level video, the edge detection is carried out on the images to be analyzed to determine the liquid level of the equipment to be tested in the images to be analyzed, and then the liquid level height of the equipment to be tested in the real world is further determined, the automatic measurement of the liquid level height of the equipment to be tested is realized, the liquid level scale does not need to be manually read to determine the liquid level height, the labor cost is saved, and the precision and the efficiency are improved. Secondly, each frame of image to be analyzed corresponds to one liquid level monitoring moment, after edge detection is carried out on each frame of image to be analyzed to determine the liquid level height of the equipment to be tested, the rule of the liquid level height of the equipment to be tested changing along with time can be determined by combining the monitoring moment corresponding to the image to be analyzed and the liquid level height of the equipment to be tested, and automatic analysis of the liquid level change is achieved.
Based on the same technical concept, an embodiment of the present invention provides a liquid level video analysis apparatus, as shown in fig. 9, the apparatus 900 includes: an acquisition module 901, a detection module 902, a processing module 903, and an analysis module 904.
An obtaining module 901, configured to obtain multiple frames of images to be analyzed and liquid level monitoring moments corresponding to the multiple frames of images to be analyzed from a liquid level video, where the liquid level video is a liquid level change process video of a device to be monitored in advance;
a detection module 902, configured to perform edge detection on the image to be analyzed to determine a liquid level of the device to be analyzed in the image to be analyzed, for any one image to be analyzed in the multiple frames of images to be analyzed;
the processing module 903 is configured to determine, according to the liquid level of the device to be detected in the image to be analyzed, a liquid level height of the device to be detected at a liquid level monitoring time corresponding to the image to be analyzed;
and the analysis module 904 is configured to determine a rule that the liquid level height of the device to be tested changes with time according to the liquid level monitoring time corresponding to the multiple frames of images to be analyzed and the liquid level height of the device to be tested at the liquid level monitoring time corresponding to the multiple frames of images to be analyzed.
Optionally, the detecting module 902 is specifically configured to:
marking a liquid level window area of the equipment to be tested from the image to be analyzed;
carrying out edge detection on the liquid level window area to determine the liquid level in the liquid level window area;
and determining the liquid level in the liquid level window area as the liquid level of the equipment to be tested in the image to be analyzed.
Optionally, the detecting module 902 is further configured to:
before edge detection is carried out on the liquid level window area to determine the liquid level in the liquid level window area, a reference image is obtained from the liquid level video, and the liquid level in the liquid level window area in the reference image is zero;
and carrying out difference map processing on the liquid level window area in the image to be analyzed and the liquid level window area in the reference image.
Optionally, the detecting module 902 is specifically configured to:
carrying out horizontal edge detection on the liquid level window area to determine a horizontal edge line in the liquid level window area;
and when the length of the horizontal edge line is determined to be larger than a preset threshold value, determining the horizontal edge line as the liquid level in the liquid level window area.
Optionally, the processing module 903 is specifically configured to:
determining the difference value between the liquid level of the equipment to be detected in the image to be analyzed and the reference liquid level of the equipment to be detected in the image to be analyzed as the liquid level height of the equipment to be detected in the image to be analyzed;
and determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level height of the equipment to be detected in the image to be analyzed and the proportional relation between the liquid level window area in the image to be analyzed and the liquid level window of the equipment to be detected.
An embodiment of the present invention provides a liquid level video analysis apparatus, including at least one processing unit, a display unit and at least one storage unit, wherein the storage unit stores a computer program, and when the program is executed by the processing unit, the processing unit executes the steps of the liquid level video analysis method. As shown in fig. 10, the schematic diagram of the hardware structure of the terminal device in the embodiment of the present invention is shown, where the terminal device may specifically be a desktop computer, a portable computer, a smart phone, a tablet computer, and the like. Specifically, the liquid level video analysis apparatus may comprise a memory 1001, a processor 1002 and a computer program stored on the memory, wherein the processor 1002 implements the steps of any of the liquid level video analysis methods in the above embodiments when executing the program. Memory 1001 may include, among other things, Read Only Memory (ROM) and Random Access Memory (RAM), and provides program instructions and data stored in memory 1001 to processor 1002.
Further, the liquid level video analysis apparatus described in the embodiment of the present application may further include an input device 1003, an output device 1004, and the like. The input device 1003 may include a keyboard, mouse, touch screen, etc.; the output device 1004 may include a Display device such as a Liquid Crystal Display (LCD), a Cathode Ray Tube (CRT), a touch screen, or the like. The memory 1001, the processor 1002, the input device 1003, and the output device 1004 may be connected by a bus or other means, and fig. 10 illustrates an example of connection by a bus. The processor 1002 calls the program instructions stored in the memory 1001 and executes the liquid level video analysis method provided by the above-mentioned embodiment according to the obtained program instructions.
Embodiments of the present invention further provide a computer-readable storage medium storing a computer program executable by a liquid level video analysis apparatus, which when the program is run on the liquid level video analysis apparatus, causes the liquid level video analysis apparatus to perform the steps of the liquid level video analysis method.
It should be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, 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 flow or flows 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 flow or flows and/or block diagram 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 preferred 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. Therefore, it is intended that the appended claims be interpreted as including preferred 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.
Claims (12)
1. A liquid level video analysis method is characterized by comprising the following steps:
acquiring a plurality of frames of images to be analyzed and liquid level monitoring moments corresponding to the plurality of frames of images to be analyzed from a liquid level video, wherein the liquid level video is a liquid level change process video of equipment to be detected which is monitored in advance;
performing edge detection on the image to be analyzed to determine the liquid level of the equipment to be analyzed in the image to be analyzed aiming at any one image to be analyzed in the plurality of frames of images to be analyzed;
determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level of the equipment to be detected in the image to be analyzed;
and determining the rule of the liquid level height of the equipment to be tested along with the change of time according to the liquid level monitoring time corresponding to the multiple frames of images to be analyzed and the liquid level height of the equipment to be tested at the liquid level monitoring time corresponding to the multiple frames of images to be analyzed.
2. The method of claim 1, wherein the edge detection of the image to be analyzed to determine a level of a device under test in the image to be analyzed comprises:
marking a liquid level window area of the equipment to be tested from the image to be analyzed;
carrying out edge detection on the liquid level window area to determine the liquid level in the liquid level window area;
and determining the liquid level in the liquid level window area as the liquid level of the equipment to be tested in the image to be analyzed.
3. The method of claim 2, wherein prior to determining the liquid level in the liquid level window region by performing edge detection on the liquid level window region, further comprising:
acquiring a reference image from the liquid level video, wherein the liquid level of a liquid level window area in the reference image is zero;
and carrying out difference map processing on the liquid level window area in the image to be analyzed and the liquid level window area in the reference image.
4. The method of claim 2, wherein said edge detecting the liquid level window region to determine the liquid level in the liquid level window region comprises:
carrying out horizontal edge detection on the liquid level window area to determine a horizontal edge line in the liquid level window area;
and when the length of the horizontal edge line is determined to be larger than a preset threshold value, determining the horizontal edge line as the liquid level in the liquid level window area.
5. The method as claimed in any one of claims 2 to 4, wherein the determining the liquid level height of the device under test at the liquid level monitoring time corresponding to the image to be analyzed according to the liquid level of the device under test in the image to be analyzed comprises:
determining the difference value between the liquid level of the equipment to be detected in the image to be analyzed and the reference liquid level of the equipment to be detected in the image to be analyzed as the liquid level height of the equipment to be detected in the image to be analyzed;
and determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level height of the equipment to be detected in the image to be analyzed and the proportional relation between the liquid level window area in the image to be analyzed and the liquid level window of the equipment to be detected.
6. A liquid level video analyzing apparatus, comprising:
the acquisition module is used for acquiring a plurality of frames of images to be analyzed and liquid level monitoring moments corresponding to the plurality of frames of images to be analyzed from a liquid level video, wherein the liquid level video is a liquid level change process video of equipment to be monitored in advance;
the detection module is used for carrying out edge detection on the image to be analyzed aiming at any one image to be analyzed in the plurality of frames of images to be analyzed so as to determine the liquid level of the equipment to be detected in the image to be analyzed;
the processing module is used for determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level of the equipment to be detected in the image to be analyzed;
and the analysis module is used for determining the rule of the liquid level height of the equipment to be tested changing along with time according to the liquid level monitoring time corresponding to the multi-frame images to be analyzed and the liquid level height of the equipment to be tested at the liquid level monitoring time corresponding to the multi-frame images to be analyzed.
7. The apparatus of claim 6, wherein the detection module is specifically configured to:
marking a liquid level window area of the equipment to be tested from the image to be analyzed;
carrying out edge detection on the liquid level window area to determine the liquid level in the liquid level window area;
and determining the liquid level in the liquid level window area as the liquid level of the equipment to be tested in the image to be analyzed.
8. The apparatus of claim 7, wherein the detection module is further to:
before edge detection is carried out on the liquid level window area to determine the liquid level in the liquid level window area, a reference image is obtained from the liquid level video, and the liquid level in the liquid level window area in the reference image is zero;
and carrying out difference map processing on the liquid level window area in the image to be analyzed and the liquid level window area in the reference image.
9. The apparatus of claim 7, wherein the detection module is specifically configured to:
carrying out horizontal edge detection on the liquid level window area to determine a horizontal edge line in the liquid level window area;
and when the length of the horizontal edge line is determined to be larger than a preset threshold value, determining the horizontal edge line as the liquid level in the liquid level window area.
10. The apparatus according to any one of claims 7 to 9, wherein the processing module is specifically configured to:
determining the difference value between the liquid level of the equipment to be detected in the image to be analyzed and the reference liquid level of the equipment to be detected in the image to be analyzed as the liquid level height of the equipment to be detected in the image to be analyzed;
and determining the liquid level height of the equipment to be detected at the liquid level monitoring moment corresponding to the image to be analyzed according to the liquid level height of the equipment to be detected in the image to be analyzed and the proportional relation between the liquid level window area in the image to be analyzed and the liquid level window of the equipment to be detected.
11. A liquid level video analyzing apparatus, comprising at least one processing unit and at least one memory unit, wherein the memory unit stores a computer program which, when executed by the processing unit, causes the processing unit to carry out the steps of the method according to any one of claims 1 to 5.
12. A computer-readable medium, characterized in that it stores a computer program executable by a terminal device, which program, when run on a level video analysis device, causes the level video analysis device to perform the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810929030.9A CN110836705A (en) | 2018-08-15 | 2018-08-15 | Liquid level video analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810929030.9A CN110836705A (en) | 2018-08-15 | 2018-08-15 | Liquid level video analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110836705A true CN110836705A (en) | 2020-02-25 |
Family
ID=69572992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810929030.9A Pending CN110836705A (en) | 2018-08-15 | 2018-08-15 | Liquid level video analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110836705A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112642022A (en) * | 2020-12-31 | 2021-04-13 | 遵义师范学院 | Infusion monitoring system and monitoring method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002031562A (en) * | 2000-07-14 | 2002-01-31 | Toshiba Corp | Water level measuring device, and water level measuring method |
| JP3583659B2 (en) * | 1999-08-04 | 2004-11-04 | 富士通株式会社 | Liquid level detection method |
| CN101246028A (en) * | 2008-03-28 | 2008-08-20 | 周振峰 | Fuel tank oil material anti-theft monitoring system |
| CN102165288A (en) * | 2009-11-19 | 2011-08-24 | 韩国建设技术研究院 | Method for recognizing a liquid level using temporal variation in the distribution of the pixel concentration in images, and apparatus for recognizing a liquid level using same |
| CN104819754A (en) * | 2015-05-13 | 2015-08-05 | 山东大学 | Medicine bottle liquid level detection method based on image processing |
| CN106643965A (en) * | 2016-12-23 | 2017-05-10 | 贵州电网有限责任公司电力科学研究院 | Method for accurately recognizing liquid level by template matching |
| CN108318101A (en) * | 2017-12-26 | 2018-07-24 | 北京市水利自动化研究所 | Water gauge water level video intelligent monitoring method based on deep learning algorithm and system |
-
2018
- 2018-08-15 CN CN201810929030.9A patent/CN110836705A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3583659B2 (en) * | 1999-08-04 | 2004-11-04 | 富士通株式会社 | Liquid level detection method |
| JP2002031562A (en) * | 2000-07-14 | 2002-01-31 | Toshiba Corp | Water level measuring device, and water level measuring method |
| CN101246028A (en) * | 2008-03-28 | 2008-08-20 | 周振峰 | Fuel tank oil material anti-theft monitoring system |
| CN102165288A (en) * | 2009-11-19 | 2011-08-24 | 韩国建设技术研究院 | Method for recognizing a liquid level using temporal variation in the distribution of the pixel concentration in images, and apparatus for recognizing a liquid level using same |
| CN104819754A (en) * | 2015-05-13 | 2015-08-05 | 山东大学 | Medicine bottle liquid level detection method based on image processing |
| CN106643965A (en) * | 2016-12-23 | 2017-05-10 | 贵州电网有限责任公司电力科学研究院 | Method for accurately recognizing liquid level by template matching |
| CN108318101A (en) * | 2017-12-26 | 2018-07-24 | 北京市水利自动化研究所 | Water gauge water level video intelligent monitoring method based on deep learning algorithm and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112642022A (en) * | 2020-12-31 | 2021-04-13 | 遵义师范学院 | Infusion monitoring system and monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110349145B (en) | Defect detection method, defect detection device, electronic equipment and storage medium | |
| CN102362291B (en) | Face feature point detection device and method | |
| EP2975602B1 (en) | Method and device for determining the level of residual image of display | |
| CN107515825B (en) | Fluency testing method and device, storage medium and terminal | |
| CN111753635B (en) | Intelligent scoring method and device for chemical experiment operation and storage medium | |
| JP2020186957A (en) | Vibration analysis system, vibration analysis method, and program | |
| CN110108554A (en) | Test result evaluation method and Material Testing Machine | |
| CN110836705A (en) | Liquid level video analysis method and device | |
| CN112687211B (en) | Method and device for measuring smear of display panel and storage medium | |
| CN114283124A (en) | Smudginess detection method, device, equipment and storage medium | |
| KR20230042706A (en) | Neural network analysis of LFA test strips | |
| TW201404878A (en) | Device for automatically rapidly analyzing biological cells and related method thereof | |
| CN110836706B (en) | Liquid level detection method and device | |
| CN113362270A (en) | Method and device for monitoring abnormal display of display screen picture | |
| CN105427315B (en) | Digital instrument image position testing method and device | |
| CN107566826A (en) | The method of testing and device of grating image processor | |
| CN108781280B (en) | Test method, test device and terminal | |
| US20220114819A1 (en) | Cell tracking method, image processing device, and program | |
| CN106686371A (en) | Frame rate testing method, device, equipment and system | |
| CN112073713B (en) | Video leakage test method, device, equipment and storage medium | |
| CN114638096A (en) | Method, device and equipment for displaying logic among program variables and storage medium | |
| CN106326097B (en) | Method and device for testing page perception performance | |
| CN114973287A (en) | Information extraction method, system, storage medium and equipment based on construction drawing | |
| CN114202522A (en) | Red blood silk non-contact measuring method, storage medium and processor | |
| US7961931B2 (en) | Positioning measurement apparatus and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200225 |
|
| RJ01 | Rejection of invention patent application after publication |