WO2023165298A1

WO2023165298A1 - Method and device for determining dirt level of cleaning device, and storage medium

Info

Publication number: WO2023165298A1
Application number: PCT/CN2023/074515
Authority: WO
Inventors: 王文光; 郁顺昌; 杨盛
Original assignee: 追觅创新科技(苏州)有限公司
Priority date: 2022-03-01
Filing date: 2023-02-06
Publication date: 2023-09-07
Also published as: CN116739961A

Abstract

The present application relates to the technical field of computers, and disclosed thereby are a method and device for determining the dirt level of a cleaning device, and a storage medium. The method comprises: acquiring a target image of a cleaning member on a cleaning device; determining a cleaning member region in the target image; performing region division on the cleaning member region, and obtaining at least two sub-regions; and on the basis of the pixel value of each sub-region, determining the dirt level of the cleaning device. The problems of a dirt measuring result obtained by a conventional dirt detection means not being able to directly reflect the dirt level of a cleaning device and the reliability of the obtained dirt measuring result being low can be solved. Since the target image of the cleaning member can be acquired, direct measuring of the dirt level of the cleaning member can be achieved, and the reliability of the dirt level measuring result is increased.

Description

Method, equipment and storage medium for determining the degree of dirtiness of cleaning equipment

This application claims the priority of the following patent application: a Chinese patent application submitted to the China Patent Office on March 1, 2022, with the application number 202210196525.1, and the title of the invention is "method, equipment and storage medium for determining the degree of dirtiness of cleaning equipment", The entire contents of the aforementioned patent applications are incorporated by reference in this application.

technical field

The present application belongs to the field of computer technology, and in particular relates to a method, device and storage medium for determining the degree of dirtiness of cleaning equipment.

Background technique

As the working hours of the cleaning equipment increase, the degree of dirtiness of the cleaning parts on the cleaning equipment gradually increases. In order to prevent the cleaning parts from secondary pollution on the surface to be cleaned, it is usually necessary to detect the degree of dirt of the cleaning equipment, so as to clean the cleaning parts in time when the degree of dirt is high.

The method for determining the degree of dirtiness of traditional cleaning equipment includes: comparing the ground environmental parameters of the ground before cleaning with the ground environmental parameters of the ground after cleaning to obtain the absolute value of the difference of the ground environmental parameters; comparing the absolute value with the reference value Compare them to get the detection result of the degree of dirt.

However, the difference value of the ground environment parameters can only indirectly reflect the degree of dirtiness of the cleaning equipment, but cannot directly detect the degree of dirtiness of the cleaning equipment.

Contents of the invention

The technical problems to be solved in this application include the problem that the dirt detection results obtained by traditional dirt detection methods cannot directly reflect the degree of dirt of the cleaning equipment, and the reliability of the obtained dirt detection results is not high.

In order to solve the above technical problems, the present application provides a method for determining the degree of dirtiness of cleaning equipment, including:

Acquiring a target image of a cleaning piece on the cleaning device;

determining the area of the cleaning element in the target image;

Divide the area of the cleaning element to obtain at least two sub-areas;

The degree of soiling of the cleaning device is determined based on the pixel values of each sub-area.

Optionally, during the working process, the cleaning member rotates around a central axis perpendicular to the surface to be cleaned rotate;

The region of the cleaning element is divided to obtain at least two sub-regions, including:

Taking the central axis of the cleaning element in the area of the cleaning element as the center of each sub-area, the area of the cleaning element is divided to obtain the at least two sub-areas.

Optionally, the cleaning element has a circular shape as a whole, and correspondingly, the area of the cleaning element has a circular shape as a whole; the central axis passes through the center of the circle;

Taking the central axis of the cleaning element in the cleaning element area as the center of each sub-area, the area of the cleaning element is divided to obtain the at least two sub-areas, including:

Taking the center of the circle as the center of the sub-area, dividing the cleaning element area into n sub-areas according to preset n division coefficients;

Among them, the first sub-area is a circle whose radius is the product of the first division coefficient and R, and the i-th sub-area is the outer circle whose radius is the product of the i-th division coefficient and R minus the radius of the i-1th division The ring obtained by the inner circle of the product of the coefficient and R; the R is the radius of the cleaning part area; the i takes integers from 2 to n in turn, and the n is an integer greater than 1, and the nth division The coefficient is 1.

Optionally, after determining the degree of dirtiness of the cleaning device based on the pixel value of each sub-region, the method further includes:

generating a data description value of the degree of dirtiness; wherein, the data description value includes a high-order bit and a low-order bit, and both the high-order bit and the low-order bit are positively correlated with the degree of dirtiness, so The high-order bits are used to describe the number of integer bits of the degree of dirtiness, and the low-order bits are the first m digits of the integer bits, the low-order bits In the case where the integer is zero, it is the fractional part of the degree of contamination; the m is a positive integer;

Using the data description value of the degree of dirt to compare different degrees of dirt to determine the cleaning effect of the cleaning device.

Optionally, the use of the data description value to compare different degrees of dirt includes:

Compare the high-order bits corresponding to different degrees of dirtiness;

In the case that the high-order bits corresponding to different dirty degrees are the same, compare the low-order bits corresponding to different dirty degrees;

In the case of different high-order bits corresponding to different soiling degrees, it is determined that the soiling degree with a larger high-order bit is larger.

Optionally, the degree of dirtiness includes the degree of local dirtiness of different sub-regions; the use of the data description value to compare different degrees of dirtiness includes:

Using the data description value to compare the local dirtiness of different sub-regions;

Wherein, different subareas include the same subarea corresponding to different cleaning pieces on the cleaning device; and/or, different subareas corresponding to the same cleaning piece on the cleaning equipment.

Optionally, the determining the degree of dirtiness of the cleaning device based on the pixel value of each sub-region includes:

determining the cumulative sum of pixel values of target pixels in the sub-area, where the target pixel is a pixel in the sub-area that satisfies a preset dirty condition;

The local dirty degree of each sub-region is determined based on the cumulative sum of pixel values to obtain the dirty degree of the cleaning device; the cumulative sum of pixel values is negatively correlated with the local dirty degree.

Optionally, the method also includes:

Based on the pixel value of the cleaning element area, determine the global dirt level of the cleaning element area, the dirt level of the cleaning device includes the global dirt level and the local dirt level of each sub-area;

Based on the local soiling degree and the global soiling degree, the cleaning effect of the cleaning device is determined.

Optionally, the determining the cleaning piece area in the target image includes:

Foreground extraction is performed on the target image to obtain the area of the cleaning element.

On the other hand, the present application also provides a cleaning device, which includes: a processor and a memory; a program is stored in the memory, and the program is loaded and executed by the processor to realize the cleaning provided by the above aspect Method for determining the degree of soiling of equipment.

In another aspect, the present application also provides a computer-readable storage medium, which is characterized in that a program is stored in the storage medium, and when the program is executed by a processor, the method for determining the degree of dirtiness of the cleaning equipment provided in the above aspect is implemented .

The technical solution provided by the present application has at least the following advantages: by acquiring the target image of the cleaning piece on the cleaning device; determining the area of the cleaning piece in the target image; dividing the area of the cleaning piece into at least two sub-areas; based on each sub-area The pixel value of the cleaning equipment determines the degree of dirtiness of the cleaning equipment; it can solve the dirt detection results obtained by the traditional dirt detection method, which cannot be directly reflected Reflecting the degree of dirt of the cleaning equipment, the reliability of the obtained dirt detection results is not high; since the target image of the cleaning parts can be collected, it is possible to directly detect the degree of dirt of the cleaning parts and improve the detection of the degree of dirt reliability of the results.

In addition, for the cleaning piece that rotates around the central axis perpendicular to the surface to be cleaned during the working process, since the distribution of the degree of dirt in the same concentric circle area is consistent, the central axis of the cleaning piece in the cleaning piece area is used as the In the center of the area, the division of the cleaning area can make the distribution of dirt in each sub-area basically consistent; it can avoid that when the distribution of dirt in the same sub-area is inconsistent, the degree of local dirt cannot accurately reflect the The problem of the degree of dirt at each position in the sub-region; the accuracy of the determined local degree of dirt can be improved.

In addition, based on the cumulative sum of the pixel values of the target pixels in each sub-region, the local dirty degree of the sub-region is calculated, since the target pixel is a pixel that meets the preset dirty conditions in the sub-region; therefore, it is possible to avoid The influence of pixels other than the target pixel on the degree of local dirt further improves the accuracy of determining the degree of local dirt.

In addition, since the target image may include other interference areas in addition to the cleaning area, in this embodiment, by determining the cleaning area in the target image, other interference areas can be eliminated. On the one hand, it can save the analysis of other interference areas. On the other hand, it can also avoid the problem that other interference areas affect the detection result of the degree of dirt of the cleaning parts, thereby improving the reliability of the detection of the degree of dirt.

In addition, by converting different degrees of dirt into data description values for comparison, it may not be necessary to compare all values of the degree of dirt, which can improve the comparison efficiency of the degree of dirt.

In addition, the cleaning efficiency of the cleaning equipment is determined by combining the local and global dirt levels, so that electronic equipment can be analyzed from both local and global perspectives when judging the cleaning effect of the cleaning equipment, thereby improving the reliability of judging the cleaning effect sex.

Description of drawings

In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the specific embodiments or prior art. Obviously, the accompanying drawings in the following description These are some implementations of the present application. For those skilled in the art, other drawings can also be obtained according to these drawings without creative work.

Fig. 1 is a schematic structural diagram of a cleaning device provided by an embodiment of the present application;

Fig. 2 is a schematic structural diagram of a system for determining the degree of dirtiness of cleaning equipment provided by an embodiment of the present application;

Fig. 3 is a flowchart of a method for determining the degree of dirtiness of cleaning equipment provided by an embodiment of the present application;

Fig. 4 is a schematic diagram of the cleaning part area obtained by using the foreground extraction algorithm provided by an embodiment of the present application;

Fig. 5 is a schematic diagram of the area of the cleaning piece obtained through the segmentation operation provided by an embodiment of the present application;

Fig. 6 is a schematic diagram of a sub-region provided by an embodiment of the present application;

Fig. 7 is a schematic diagram of the degree of dirt of each cleaning piece provided by an embodiment of the present application;

Fig. 8 is a schematic diagram of the degree of dirt and the corresponding data description value provided by an embodiment of the present application;

Fig. 9 is a block diagram of a device for determining the degree of dirtiness of cleaning equipment provided by an embodiment of the present application;

Fig. 10 is a block diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

The technical solutions of the present application will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are some of the embodiments of the present application, not all of them. Hereinafter, the present application will be described in detail with reference to the drawings and embodiments. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

It should be noted that the terms "first" and "second" in the description and claims of the present application and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence.

In this application, unless stated to the contrary, the used orientation words such as "upper, lower, top, bottom" are generally used for the directions shown in the drawings, or for the parts themselves in the vertical, In terms of vertical or gravitational direction; similarly, for the convenience of understanding and description, "inside and outside" refer to inside and outside relative to the outline of each component itself, but the above orientation words are not used to limit the present application.

Fig. 1 is a schematic structural diagram of a cleaning device provided by an embodiment of the present application. The cleaning device may be an electronic device with a cleaning function such as a sweeper, a vacuum cleaner, and a mopping machine. This embodiment does not limit the implementation of the cleaning device. As shown in Figure 1, cleaning equipment includes at least: cleaning Component 110 and a controller (not shown in the figure).

The cleaning part 110 refers to a part that is in contact with the surface to be cleaned to clean the surface to be cleaned during the cleaning process of the cleaning device. Wherein, the surface to be cleaned may be a floor, a desktop, a wall, a surface of a solar cell, etc., and the type of the surface to be cleaned is not limited in this embodiment.

Optionally, the cleaning member 110 may be a rag, a brush, and/or a rolling brush, etc., and this embodiment does not limit the implementation of the cleaning member 110 . In addition, the number of cleaning parts 110 can be one or at least two. When there are at least two cleaning parts, the types of different cleaning parts are the same or different. This embodiment does not limit the number of cleaning parts 110 .

Without loss of generality, the cleaning element 110 is connected to the cleaning device through a driving element, and the driving element is connected to a controller to drive the cleaning element 110 to move under the control of the controller.

In one example, the cleaning element 110 rotates around a central axis perpendicular to the surface to be cleaned during operation. For example: referring to the cleaning equipment shown in FIG. 1 , at this time, the cleaning member 110 is located at the bottom of the cleaning equipment, and takes the central axis perpendicular to the surface to be cleaned as the rotation axis, and rotates around the rotation axis.

When the cleaning member 110 rotates around the central axis perpendicular to the surface to be cleaned, the degree of dirt on the edges of the concentric circles of the same concentric circle is usually the same.

In Figure 1, the center of the cleaning part passes the central axis (that is, the center coincides with the central axis) as an example. In actual implementation, one end of the cleaning part can also pass the central axis, such as the rotation mode of the brush on the sweeper. The embodiment does not limit the rotation mode of the cleaning element.

In addition, in FIG. 1 , the cleaning piece 110 is circular as an example for illustration. In actual implementation, the cleaning piece 110 may also be rectangular or irregular in shape. This embodiment does not limit the shape of the cleaning piece 110 .

Wherein, "the overall shape is circular" means that when the cleaning device remains stationary, the cleaning range formed by the cleaning element 110 is circular. Based on this, there may be uneven burrs on the edge of the cleaning element 110 , but this does not affect the result that the cleaning range is circular.

In other examples, the cleaning element 110 may also rotate around a central axis parallel to the surface to be cleaned during operation. Such as the rotation mode of the roller brush on the washing machine. Similarly, when the cleaning member 110 rotates around the central axis parallel to the surface to be cleaned, the degree of dirt at the edges of the concentric circles of the same concentric circle is usually the same.

The structure of the above-mentioned cleaning equipment is only schematic. In actual implementation, the cleaning equipment may also include other components required to perform cleaning work, such as: power supply components, communication components, etc., this Embodiments are not listed one by one here.

Optionally, based on the above embodiments, it can be known that the distribution of the dirt of the cleaning element is regular due to the working process of the cleaning element. Based on this, the present embodiment provides a system for determining the degree of dirt, which can collect a target image of a cleaning piece on a cleaning device and analyze the target image, so as to detect the degree of dirt of the cleaning device.

Referring to the system for determining the degree of contamination shown in FIG. 2 , the system at least includes a placement frame 210 , an image acquisition component 220 located on the placement frame 210 , and an electronic device 230 connected to the image acquisition component 220 .

The placing frame 210 is used for placing one or at least two cleaning devices, so that the cleaning parts on the cleaning devices are located within the collection range of the image collection component 220 .

The image acquisition component 220 may be an electronic device with an image acquisition function such as a camera, a camera, and a mobile phone. This embodiment does not limit the implementation of the image acquisition component 220 .

In this embodiment, the image acquisition component 220 is configured to acquire an image of a target including cleaning parts.

The electronic device 230 may be a desktop computer, a tablet computer, a notebook computer, a mobile phone, etc., and the implementation manner of the electronic device 230 is not limited in this embodiment.

In this embodiment, the electronic device 230 is used to acquire the target image of the cleaning piece on the cleaning device; determine the area of the cleaning piece in the target image; divide the area of the cleaning piece into at least two sub-areas; based on the pixel value of each sub-area Determine how dirty the cleaning equipment is.

At least two subregions are divided based on the distribution of dirt on the cleaning element.

In this embodiment, the degree of dirtiness of the cleaning equipment is determined based on the pixel value of each sub-region by dividing the area of the cleaning piece; the degree of dirtiness of the cleaning piece can be detected directly, and the reliability of the detection result of the degree of dirtiness can be improved. sex.

The method for determining the degree of dirtiness of the cleaning equipment will be introduced below. The following embodiments are described by taking the electronic device 230 in the system for determining the degree of contamination shown in FIG. 2 as an example for execution of the method.

It should be added that, in actual implementation, the method for determining the degree of contamination is not limited to the application in the system for determining the degree of contamination shown in FIG. The collection component 220 and the electronic device 230 are implemented in the same device system, and this embodiment does not limit the application scenarios of the method for determining the degree of contamination.

Fig. 3 is a flowchart of a method for determining the degree of dirtiness of cleaning equipment provided by an embodiment of the present application , the method includes at least the following steps:

Step 301, acquiring a target image of a cleaning piece on a cleaning device.

Specifically, the target image is obtained by collecting images of the surface of the cleaning piece that is in contact with the surface to be cleaned. In this way, the degree of dirtiness of the cleaning piece can be directly obtained by analyzing the target image.

Step 302, determine the area of the cleaning piece in the target image.

Since the target image may include other interference areas in addition to the cleaning area, based on this, in this step, by determining the cleaning area in the target image, other interference areas can be eliminated. On the one hand, it can save analysis of other interference areas On the other hand, it can also avoid the problem that other interference areas affect the detection result of the degree of dirt of the cleaning parts, thereby improving the reliability of the detection of the degree of dirt.

In an example, determining the area of the cleaning piece in the target image includes: performing foreground extraction on the target image to obtain the area of the cleaning piece.

The electronic device uses a foreground extraction algorithm to perform foreground extraction on the target image. Among them, the foreground extraction algorithm includes but is not limited to: algorithms based on image segmentation, that is, pixels are divided into background or foreground based on discontinuity and correlation of pixels, such as: edge detection algorithm, or clustering algorithm, etc.; or, based on Compared with algorithms based on image segmentation, the image matting algorithm emphasizes details more, such as: Knockout matting algorithm, or image matting algorithm based on probability statistics, etc. This embodiment does not limit the implementation of the foreground extraction algorithm.

For example: the area of the clean part obtained by using the foreground extraction algorithm is shown in FIG. 4 .

In another example, determining the area of the cleaning element in the target image includes: receiving a segmentation operation on the area of the cleaning element in the target image to obtain the area of the cleaning element. The segmentation operation may be an operation of outlining the edge of the cleaning piece in the target image, or an operation of clicking the edge position of the cleaning piece. This embodiment does not limit the implementation of the segmentation operation.

For example, the area of the cleaning piece obtained through the segmentation operation is shown in FIG. 5 .

Step 303, divide the area of the cleaning element to obtain at least two sub-areas.

In this embodiment, the area of the cleaning element is divided based on the distribution law of the degree of dirt during the working process of the cleaning element.

For example: the cleaning member shown in Figure 1 rotates around a central axis perpendicular to the surface to be cleaned during the working process. At this time, the distribution of the degree of dirt in the same concentric circle area is consistent. Based on this, yes The area of the cleaning parts is divided to obtain at least two sub-areas, including: taking the central axis of the cleaning parts in the area of the cleaning parts as the center of each sub-area, and dividing the area of the cleaning parts to obtain at least two sub-areas.

Assuming that the cleaning piece is circular as a whole, correspondingly, the area of the cleaning piece is circular as a whole; the central axis passes through the center of the circle. Taking the central axis of the cleaning piece in the cleaning piece area as the center of each sub-area, divide the cleaning piece area into at least two sub-areas, including: take the center of the circle as the center of the sub-area, and divide according to the preset n The coefficient divides the cleaning piece area into n sub-areas.

Among them, the first sub-area is a circle whose radius is the product of the first division coefficient and R, and the i-th sub-area is the outer circle whose radius is the product of the i-th division coefficient and R minus the radius of the i-1th division The ring obtained by the inner circle of the product of the coefficient and R; R is the radius of the cleaning piece area; i takes integers from 2 to n in turn, n is an integer greater than 1, and the nth division coefficient is 1. The division coefficient is a value greater than 0 and less than or equal to 1, and the ith division coefficient is positively correlated with the value of i.

Taking n as 3, the first division coefficient as 0.3, and the second division coefficient as 0.7 as an example for illustration, refer to FIG. 6 for the obtained at least two sub-regions. According to Fig. 6, it can be seen that the first sub-region 61 is a circle centered on the central axis of the cleaning element and a radius of 0.3R; the second sub-region 62 is a circle centered on the central axis of the cleaning element and a radius of 0.7R The ring obtained by subtracting the first sub-region 61; the third sub-region 63 is the ring obtained by subtracting a circle with a radius of 0.7R from a circle with a radius R taking the central axis of the cleaning element as the center.

In Figure 6, n is 3, the first division coefficient is 0.3, and the second division coefficient is 0.7 as an example. In actual implementation, the value of n and the value of the i-th division coefficient are all acceptable. Adjusted based on detection requirements, this embodiment does not limit the values of n and the division coefficient.

In the case that the cleaning piece is not circular, it can also be divided based on the above-mentioned area division principle, the difference is that R is the minimum distance between the central axis of the cleaning piece and the edge of the cleaning piece; the nth sub-area is no longer a ring , but the area obtained by subtracting the inner circle whose radius is the product of the n-1 division coefficient and R from the figure formed by the edges of the cleaning piece. This embodiment does not limit the shape of the cleaning piece.

Similarly, when the cleaning element rotates around the central axis parallel to the surface to be cleaned, the distribution of the degree of dirt in the same concentric circle area is consistent. Based on this, the area of the cleaning element is divided to obtain at least two sub-areas, including: sequentially dividing the area of the cleaning element into at least two sub-areas in the extension direction of the central axis of the cleaning element in the area of the cleaning element. The at least two sub-regions are divided according to a preset division coefficient, and this embodiment does not limit the value of the division coefficient.

Step 304, determining the degree of dirtiness of the cleaning device based on the pixel value of each sub-region.

In one example, the degree of soiling of the cleaning device includes the degree of local soiling of each sub-area. At this time, the degree of dirtiness of the cleaning equipment is determined based on the pixel values of each sub-region, including: determining the cumulative sum of the pixel values of the target pixels in the sub-region; determining the local dirtiness of each sub-region based on the cumulative sum of pixel values, and obtaining the cleaning equipment degree of contamination. Among them, the cumulative sum of pixel values is negatively correlated with the degree of local dirtiness.

The target pixels are the pixels in the sub-region that meet the preset dirty conditions. For a certain pixel position, the pixel value of the pixel position is negatively correlated with the degree of dirt, that is, the smaller the pixel value, the higher the degree of dirt, for example: the value of a black pixel is 0, at this time, the dirt of the corresponding pixel The degree of pollution is high. Wherein, the pixel value may be a pixel value of a grayscale image, or may be a pixel value of a color image, and this embodiment does not limit the value type of the pixel value. Based on this, the pixels satisfying the preset dirty condition refer to the pixels whose pixel value is smaller than the pixel threshold. The pixel threshold is determined based on the detection requirements of the degree of dirt. For example, the pixel threshold can be 255, that is, the pixels that are not white are all pixels that meet the preset dirty conditions. Of course, the value of the pixel threshold can also be other values , this embodiment does not limit the value of the pixel threshold.

Schematically, the local dirty degree of each sub-region is determined based on the cumulative sum of pixel values to obtain the dirty degree of the cleaning device, which includes: after the cumulative sum of the pixel values is reciprocated, normalization processing is performed to obtain the dirty degree. Specifically, the above process can be expressed by the following formula:
Dv＝Norm(Sum(255/sum(r+g+b))/Area)

Among them, r refers to the R pixel value in the color image pixel, g refers to the G pixel value in the color image pixel, b refers to the G pixel value in the color image pixel; sum represents the summation function; Area is the total number of pixels in the sub-region; Norm Represents the normalization function.

In actual implementation, the manner of accumulating and determining the degree of local dirt based on the accumulation and determination of pixel values may also be the accumulation and reciprocal of the accumulation and sum of pixel values. This embodiment does not limit the calculation method of the degree of local dirt.

In another example, the degree of soiling of the cleaning device also includes a global degree of soiling of the area of the cleaning element. At this time, determining the degree of dirtiness of the cleaning device based on the pixel values of each sub-area includes: determining the global degree of dirtiness of the area of the cleaning element based on the pixel values of the area of the cleaning element.

Wherein, based on the pixel value of the cleaning piece area, determining the global dirty degree of the cleaning piece area includes: determining the cumulative sum of the pixel values of the target pixels in each sub-area, and determining the summation based on the cumulative sum of the pixel values Determine the overall degree of dirtiness and obtain the degree of dirtiness of the cleaning equipment. At this time, the calculation principle of the global dirty degree is the same as the calculation principle of the local dirty degree, which will not be repeated in this embodiment.

For example, the cleaning device includes 4 cleaning parts. After calculating the degree of dirt for each sub-region on each cleaning part, refer to FIG. 7 for the obtained degree of dirt of the cleaning device. According to Figure 7, it can be seen that the degree of dirt includes the local degree of dirt in each sub-area on each cleaning piece. For details, refer to the OutsideScore of the sub-area Outside, the MiddleScore of the sub-area Middle, and the CoreScore of the sub-area Core in Figure 7, and the overall cleaning piece The global dirty degree of , see GlobalScore in Figure 7 for details.

To sum up, the method for determining the degree of dirtiness of the cleaning equipment provided in this embodiment obtains the target image of the cleaning piece on the cleaning equipment; determines the area of the cleaning piece in the target image; divides the area of the cleaning piece, and obtains at least two based on the pixel value of each sub-area to determine the degree of dirt of the cleaning equipment; it can solve the problem of the dirt detection results obtained by the traditional dirt detection method, which cannot directly reflect the dirt degree of the cleaning equipment. The problem of low reliability; since the target image of the cleaning part can be collected, the degree of dirtiness of the cleaning part can be directly detected, and the reliability of the detection result of the degree of dirtiness can be improved.

In addition, since the target image may include other interference areas in addition to the cleaning area, in this embodiment, by determining the cleaning area in the target image, other interference areas can be eliminated. On the one hand, it can save the analysis of other interference areas. On the other hand, it can also avoid the influence of other interference areas on the detection results of the degree of dirtiness of the cleaning parts. problems, thereby improving the reliability of dirt level detection.

Optionally, based on the above embodiment, after the degree of dirt is determined, that is, after step 304, the electronic device may also compare different degrees of dirt to determine the cleaning effect of the cleaning device.

Since the higher the degree of dirt, it means that the cleaning piece absorbs most of the dust on the surface to be cleaned, and the cleaning effect of the cleaning piece is better. Based on this, there is a positive correlation between the degree of soiling and the cleaning effect. That is, the higher the degree of soiling, the better the cleaning effect.

In an example, comparing different dirt levels includes: comparing local dirt levels of different sub-regions.

Optionally, comparing the local contamination levels of different sub-regions includes: for the same sub-region corresponding to different cleaning components on the cleaning device, comparing the local contamination levels of the sub-regions on different cleaning components.

For example: for the 4 cleaning pieces shown in Figure 7, compare the local dirtiness OutsideScore of the same sub-area Outside of the 4 cleaning pieces, and the sorting result obtained after the order of the local dirtiness from large to small is: { (3Outside, 4420.9926), (4Outside, 1582.896), (2Outside, 0.0382), (1Outside, 0.0008)}.

For the comparison of the MiddleScore of the same sub-area Middle of the 4 clean parts, the sorting results obtained according to the order of local dirtiness from large to small are: {(3Middle, 670.7639), (4Middle, 69.1194), (2Middle, 0.0026 ), (1Middle, 0.0006)}.

For the comparison of the CoreScore of the same sub-area of the 4 clean parts, the sorting results obtained according to the order of local dirtiness from large to small are: {(3Core, 0.0935), (4Core, 0.0002), (2Core, 0.0001 ), (1Core, 0.0)}.

And/or, comparing the local dirtiness levels of different sub-areas includes: comparing the local dirtiness levels of different sub-areas for different sub-areas corresponding to the same cleaning piece on the cleaning device.

For example: for the third cleaning piece shown in Figure 7, compare the local dirtiness of the sub-areas Core, Middle, and Outside of the cleaning piece, and sort the results according to the order of local dirtiness from large to small For: {(3Outside, 4420.9926), (3Middle, 670.7639), (3Core, 0.0935)}.

In another example, different levels of soiling are compared, including: comparing different levels of cleanliness The overall degree of soiling of the parts is compared.

For example: for the 4 cleaning pieces shown in Figure 7, compare the GlobalScore of the global dirtiness of the 4 cleaning pieces, and the sorting result obtained after the order of the global dirtiness from large to small is: {(3Global, 2523.0202 ), (4Global, 834.9248), (2Global, 0.0205), (1Global, 0.0006)}.

In the above-mentioned embodiment, when there are many digits of the numerical values of different soiling degrees, the electronic device needs to compare more digits, which will lead to the problem of low comparison efficiency of soiling degrees.

Based on the above technical problems, in this embodiment, after determining the degree of dirt of the cleaning device based on the pixel value of each sub-region, that is, after step 304, it also includes: generating a data description value of the degree of dirt; using the data description of the degree of dirt Values are compared for different degrees of soiling to determine how well a cleaning device cleans.

Among them, the data description value includes high-order bits and low-order bits. Both high-order bits and low-order bits are positively correlated with the degree of dirt. The high-order bits are used to describe the number of integer bits of the degree of dirt. If the bit is not zero, it is the first m digits of the integer, and the low-order bit is the fractional part of the degree of dirtiness when the integer is zero; m is a positive integer. For example, m may be 2, or all integer bits, etc., and the value of m is not limited in this embodiment. In this way, electronic equipment can describe the degree of dirtiness from two dimensions. Specifically, the high-order bit level describes the degree of dirtiness from the dimension of the number of integer bits. The more integer digits, the larger the value. The low-order bit degree describes the degree of dirt from the dimension of the specific value of the fractional part. The larger the decimal part, the larger the value.

For example: After converting the degree of dirtiness into a data description value, refer to Figure 8. According to Figure 8, the local dirtiness degree OutsideScore of the sub-region Outside can be described by the data description values oLevel and oDegree; the local dirtiness of the sub-region Middle The degree MiddleScore can be described by the data description values mLevel and mDegree; the local dirt degree CoreScoree of the sub-region Core can be described by the data description values cLevel and cDegree.

Based on the above principle, when comparing the degree of dirtiness, the higher-order bit level can be compared first, and then the lower-order bit degree can be compared when the higher-order bit levels are the same. Specifically, use the data description value to compare different dirt levels, including: comparing the high-order bits corresponding to different dirt levels; when the high-order bits corresponding to different dirt levels are the same, compare The low-order bits corresponding to the degree of dirtiness are compared; in the case of different high-order bits corresponding to different degrees of dirtiness Next, it is determined that higher order bits are more dirty.

In the case that the low-order bits corresponding to different soiling degrees are the same, the original numerical values of the soiling degrees can be compared.

In this way, for different degrees of dirtiness of integer bits, the sorting result can be obtained by comparing the high-order bits; and for the same degree of dirtiness of the high-order bits, the sorting result can be obtained by comparing the low-order bits, which can improve the degree of dirtiness. degree of comparative efficiency.

In one example, the degree of dirtiness includes the local degree of dirtiness of different sub-regions; correspondingly, using the data description value to compare different degrees of dirtiness includes: using the data description value to compare the local degree of dirtiness of different sub-regions Comparison; wherein, the different subareas include the same subarea corresponding to different cleaning pieces on the cleaning device; and/or, different subareas corresponding to the same cleaning piece on the cleaning equipment.

In another example, the degree of soiling includes the global degree of soiling of different cleaning parts; correspondingly, using the data description value to compare different degrees of soiling includes: using the data description value to compare the global degree of soiling of different cleaning parts Compare.

In this embodiment, by converting different degrees of dirt into data description values for comparison, it may not be necessary to compare all values of the degrees of dirt, which can improve the comparison efficiency of the degrees of dirt.

Optionally, based on the above-mentioned embodiments, in the case that the degree of dirt includes the local degree of dirt of each sub-region and the global degree of dirt of each cleaning piece, the electronic device may also be based on the degree of local dirt and the degree of global dirt , to determine the cleaning effect of the cleaning equipment.

Specifically, when each local degree of dirt is greater than a first threshold and each global degree of dirt is greater than a second threshold, it is determined that the cleaning device has achieved the desired cleaning effect; when at least one degree of local dirt is less than or equal to the first threshold, Or in a case where at least one global degree of dirt is less than or equal to the second threshold, it is determined that the cleaning device does not achieve the desired cleaning effect.

In this embodiment, the cleaning effect is divided into the expected cleaning effect and the expected cleaning effect as an example. In actual implementation, the cleaning effect can also be divided into more levels. The degree of dirt can also adaptively correspond to multiple division thresholds, and this embodiment does not limit the manner of determining the cleaning effect based on the degree of local dirt and the degree of global dirt.

In this embodiment, the cleaning equipment is determined by combining the local dirty degree and the global dirty degree. Cleaning efficiency enables electronic equipment to analyze from local and global perspectives when judging the cleaning effect of cleaning equipment, thereby improving the reliability of judging the cleaning effect.

Fig. 9 is a block diagram of an apparatus for determining a degree of dirtiness of a cleaning device provided by an embodiment of the present application. The device at least includes the following modules: an image acquisition module 910 , an area determination module 920 , an area division module 930 and a dirt determination module 940 .

An image acquisition module 910, configured to acquire a target image of the cleaning piece on the cleaning device;

an area determination module 920, configured to determine the area of the cleaning piece in the target image;

An area division module 930, configured to perform area division on the area of the cleaning element to obtain at least two sub-areas;

A dirt determination module 940, configured to determine the degree of dirt of the cleaning device based on the pixel value of each sub-region.

Relevant details refer to the above-mentioned examples.

It should be noted that when the device for determining the degree of dirtiness of the cleaning equipment provided in the above embodiments determines the degree of dirtiness of the cleaning equipment, it only uses the division of the above-mentioned functional modules for illustration. The above function allocation is completed by different functional modules, that is, the internal structure of the device for determining the degree of dirtiness of the cleaning device is divided into different functional modules to complete all or part of the functions described above. In addition, the device for determining the degree of dirtiness of the cleaning equipment provided by the above embodiments and the embodiment of the method for determining the degree of dirtiness of the cleaning equipment belong to the same concept, and its specific implementation process is detailed in the method embodiment, and will not be repeated here.

Fig. 10 is a block diagram of an electronic device provided by an embodiment of the present application. The device may be the electronic device described in FIG. 1 , and the device includes at least a processor 1001 and a memory 1002 .

The processor 1001 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 1001 can adopt at least one hardware form among DSP (Digital Signal Processing, digital signal processing), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array, programmable logic array) accomplish. The processor 1001 may also include a main processor and a coprocessor, the main processor is a processor for processing data in a wake-up state, and is also called a CPU (Central Processing Unit, central processing unit); the coprocessor is Low-power processor for processing data in standby state. In some embodiments, the processor 1001 may be integrated with a GPU (Graphics Processing Unit, image processor), and the GPU is used to render and draw the content required to be displayed on the display screen. system. In some embodiments, the processor 1001 may further include an AI (Artificial Intelligence, artificial intelligence) processor, where the AI processor is configured to process computing operations related to machine learning.

Memory 1002 may include one or more computer-readable storage media, which may be non-transitory. The memory 1002 may also include high-speed random access memory and non-volatile memory, such as one or more magnetic disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1002 is used to store at least one instruction, and the at least one instruction is used to be executed by the processor 1001 to realize the cleaning device provided by the method embodiment in this application method for determining the degree of contamination.

In some embodiments, the external reference calibration device may optionally further include: a peripheral device interface and at least one peripheral device. The processor 1001, the memory 1002, and the peripheral device interface may be connected through a bus or a signal line. Each peripheral device can be connected with the peripheral device interface through a bus, a signal line or a circuit board. Schematically, peripheral devices include but are not limited to: radio frequency circuits, touch screens, audio circuits, and power supplies.

Of course, the external reference calibration device may also include fewer or more components, which is not limited in this embodiment.

Optionally, the present application also provides a computer-readable storage medium, where a program is stored in the computer-readable storage medium, and the program is loaded and executed by a processor to realize the degree of dirtiness of the cleaning equipment in the above method embodiment. Determine the method.

Optionally, the present application also provides a computer product, the computer product includes a computer-readable storage medium, and a program is stored in the computer-readable storage medium, and the program is loaded and executed by a processor to implement the above method embodiments Method for determining the degree of soiling of cleaning equipment.

The technical features of the above-mentioned embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, should be considered as within the scope of this specification.

The above-mentioned embodiments only represent several implementation modes of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as limiting the scope of the patent for the invention. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the scope of protection of the patent application should be based on the appended claims.

Apparently, the embodiments described above are only part of the embodiments of the present application, rather than all Example of the section. Based on the embodiments in this application, those skilled in the art may make other changes or changes in different forms without creative work, which shall fall within the scope of protection of this application.

Claims

A method for determining the degree of contamination of cleaning equipment, characterized in that the method comprises:

Acquiring a target image of a cleaning piece on the cleaning device;

determining the area of the cleaning element in the target image;

Divide the area of the cleaning element to obtain at least two sub-areas;

The degree of soiling of the cleaning device is determined based on the pixel values of each sub-area.
The method according to claim 1, wherein the cleaning member rotates around a central axis perpendicular to the surface to be cleaned during operation;

The region of the cleaning element is divided to obtain at least two sub-regions, including:

Taking the central axis of the cleaning element in the area of the cleaning element as the center of each sub-area, the area of the cleaning element is divided to obtain the at least two sub-areas.
The method according to claim 2, characterized in that, taking the central axis of the cleaning element in the cleaning element area as the center of each sub-area, the area of the cleaning element is divided into regions to obtain the at least Two sub-areas, including:

In the extension direction of the central axis of the cleaning element in the cleaning element area, the cleaning element area is sequentially divided into at least two sub-areas; wherein the at least two sub-areas are divided according to a preset division factor.
The method according to claim 2 or 3, characterized in that, the overall shape of the cleaning element is circular, and correspondingly, the area of the cleaning element is overall circular; the central axis passes through the center of the circle;

Taking the central axis of the cleaning element in the cleaning element area as the center of each sub-area, the area of the cleaning element is divided to obtain the at least two sub-areas, including:

Taking the center of the circle as the center of the sub-area, dividing the cleaning element area into n sub-areas according to preset n division coefficients;

Among them, the first sub-area is a circle whose radius is the product of the first division coefficient and R, and the i-th sub-area is the outer circle whose radius is the product of the i-th division coefficient and R minus the radius of the i-1th division The ring obtained by the inner circle of the product of the coefficient and R; the R is the radius of the cleaning part area; the i takes integers from 2 to n in turn, and the n is an integer greater than 1, and the nth division The coefficient is 1.
The method according to claim 2 or 3, characterized in that, the overall cleaning piece is not circular;

The central axis of the cleaning piece in the cleaning piece area is the center of each sub-area At the center, the area of the cleaning element is divided into areas to obtain the at least two sub-areas, including:

Taking the central axis of the cleaning piece in the cleaning piece area as the center of each sub-area, divide the cleaning piece area into n sub-areas according to preset n division coefficients;

Among them, the first sub-area is a circle whose radius is the product of the first division coefficient and R; the i-th sub-area is the outer circle whose radius is the product of the i-th division coefficient and R minus the radius of the i-1th division The ring obtained by the inner circle of the product of the coefficient and R; the nth sub-region is the area obtained by subtracting the inner circle of the product of the n-1 division coefficient and R from the figure formed by the edge of the cleaning piece; R is the minimum distance between the central axis of the cleaning piece and the edge of the cleaning piece; the i takes a positive integer from 2 to n-1 in sequence.
The method according to any one of claims 1-5, wherein after determining the degree of dirtiness of the cleaning device based on the pixel value of each sub-area, further comprising:

generating a data description value of the degree of dirtiness; wherein, the data description value includes a high-order bit and a low-order bit, and both the high-order bit and the low-order bit are positively correlated with the degree of dirtiness, so The high-order bits are used to describe the number of integer bits of the degree of dirtiness, and the low-order bits are the first m digits of the integer bits, the low-order bits In the case where the integer is zero, it is the fractional part of the degree of contamination; the m is a positive integer;

Using the data description value of the degree of dirt to compare different degrees of dirt to determine the cleaning effect of the cleaning device.
The method according to claim 6, wherein said comparing different degrees of dirt by using said data description value comprises:

Compare the high-order bits corresponding to different degrees of dirtiness;

In the case that the high-order bits corresponding to different dirty degrees are the same, compare the low-order bits corresponding to different dirty degrees;

In the case of different high-order bits corresponding to different soiling degrees, it is determined that the soiling degree with a larger high-order bit is larger.
The method according to claim 6, wherein the degree of dirtiness includes local dirtiness levels of different sub-regions; and comparing different dirtiness levels using the data description value includes:

Using the data description value to compare the local dirtiness of different sub-regions;

Wherein, different subregions include the same subregion corresponding to different cleaning parts on the cleaning equipment. area; and/or, different sub-areas corresponding to the same cleaning piece on the cleaning device.
The method according to any one of claims 1-8, wherein the determining the degree of dirtiness of the cleaning device based on the pixel value of each sub-area comprises:

determining the cumulative sum of pixel values of target pixels in the sub-area, where the target pixel is a pixel in the sub-area that satisfies a preset dirty condition;

The local dirty degree of each sub-region is determined based on the cumulative sum of pixel values to obtain the dirty degree of the cleaning device; the cumulative sum of pixel values is negatively correlated with the local dirty degree.
The method according to claim 9, wherein said accumulating and determining the local dirtiness of each sub-region based on said pixel value comprises:

The pixel values in the sub-area are accumulated and reciprocated, and normalized, as the local dirtiness of the sub-area.
The method according to any one of claims 1-10, further comprising:

Based on the pixel value of the cleaning element area, determine the global dirt level of the cleaning element area, the dirt level of the cleaning device includes the global dirt level and the local dirt level of each sub-area;

Based on the local soiling degree and the global soiling degree, the cleaning effect of the cleaning device is determined.
The method according to claim 11, wherein the determining the cleaning effect of the cleaning equipment based on the local dirtiness level and the global dirtiness level comprises:

When each local degree of dirt is greater than a first threshold and each global degree of dirt is greater than a second threshold, it is determined that the cleaning device achieves a desired cleaning effect;

When at least one local degree of dirt is less than or equal to the first threshold, or at least one global degree of dirt is less than or equal to the second threshold, it is determined that the cleaning device does not achieve the desired cleaning effect.
The method according to claim 1, wherein said determining the area of the cleaning element in the target image comprises:

Foreground extraction is performed on the target image to obtain the area of the cleaning element.
An electronic device, characterized in that the electronic device includes a processor and the A memory is connected to the processing, and a program is stored in the memory, and when the processor executes the program, it is used to realize the method for determining the degree of dirtiness of the cleaning equipment according to any one of claims 1 to 13.
A computer-readable storage medium, characterized in that a program is stored in the storage medium, and when the program is executed by a processor, it is used to determine the degree of dirtiness of the cleaning device according to any one of claims 1 to 13 method.