Intelligent cleaning robot for train cargo compartment and control method

Abstract

The invention discloses a train cargo compartment intelligent cleaning robot and a control method, and the method comprises the steps: obtaining and processing a visual image in a train cargo compartment to obtain a first gray image, carrying out the image analysis of the first gray image, and determining a pollution region in the train cargo compartment and pollution characteristic parameters of the pollution region; evaluating the pollution degree of the polluted area based on the pollution characteristic parameters to obtain a pollution degree evaluation value, and setting cleaning working conditions according to the pollution degree evaluation value; carrying out first cleaning according to a set cleaning working condition, and obtaining a second grayscale image after the first cleaning; comparing and analyzing the first grayscale image and the second grayscale image, determining the cleaning efficiency of the first cleaning, and determining a correction coefficient according to the cleaning efficiency; and according to the correction coefficient, the set sweeping working condition is corrected, and according to the corrected sweeping working condition, the train cargo compartment is swept again. According to the invention, the efficiency and quality of cleaning work can be improved, the labor cost is reduced, and the automation and intelligence of cleaning are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of train cargo compartment cleaning, and in particular to an intelligent train cargo compartment cleaning robot and a control method thereof. Background Art

[0002] In recent years, with the rapid development of industrial automation and intelligent technology, intelligent cleaning robots have been widely used in various fields. Among them, train cargo compartments, as a special cleaning environment, have put forward higher requirements for cleaning equipment.

[0003] However, traditional train cargo compartment cleaning often relies on manual operation, and there are problems such as low cleaning efficiency and difficulty in ensuring cleaning quality. Therefore, it is of great practical significance to develop an intelligent cleaning robot that can autonomously clean in train cargo compartments. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a train cargo compartment intelligent cleaning robot and a control method, comprising:

[0005] Acquire a visual image in a train cargo compartment, and process the visual image to obtain a first grayscale image;

[0006] Performing image analysis on the first grayscale image to determine the contaminated area in the train cargo compartment and contamination characteristic parameters of the contaminated area;

[0007] Evaluate the pollution degree of the polluted area based on the pollution characteristic parameters, obtain the pollution degree evaluation value of the polluted area, and set the cleaning working conditions according to the pollution degree evaluation value;

[0008] Performing a first cleaning according to the set cleaning working conditions, and acquiring a second grayscale image after the first cleaning;

[0009] Comparing and analyzing the first grayscale image and the second grayscale image, determining a cleaning efficiency of the first cleaning, and determining a correction coefficient according to the cleaning efficiency;

[0010] The set cleaning working conditions are corrected according to the correction coefficient, and the train cargo compartment is cleaned again according to the corrected cleaning working conditions.

[0011] Furthermore, the performing of image analysis on the first grayscale image to determine the contaminated area in the train cargo compartment and the contamination characteristic parameters of the contaminated area includes:

[0012] Obtaining grayscale values ​​of all pixels of the first grayscale image, and segmenting the first grayscale image into a plurality of regions according to a threshold segmentation method;

[0013] Calculate the average grayscale value of all pixels in each area, and determine the area with an average grayscale value greater than a preset average value as a contaminated area in the train cargo compartment;

[0014] The area and the average gray value of each polluted region are calculated, and the average gray value of each polluted region is determined as the pollution characteristic parameter of the polluted region.

[0015] Furthermore, the step of evaluating the pollution degree of the polluted area based on the pollution characteristic parameters to obtain the pollution degree evaluation value of the polluted area includes:

[0016] Obtain the area and grayscale value average of each polluted area, and evaluate the grayscale value average to obtain the pollution evaluation value of each polluted area;

[0017] Obtaining the area of ​​each contaminated region, and calculating the ratio of the area of ​​each contaminated region to the area of ​​the first grayscale image, and using the ratio as the weight of each contaminated region;

[0018] The pollution assessment value of each polluted area is weightedly added to the corresponding weight to obtain the pollution degree assessment value of each polluted area.

[0019] Furthermore, the cleaning working conditions are set according to the pollution degree assessment value, including:

[0020] Obtain a pollution degree assessment value △S of the polluted area, pre-set a standard pollution degree assessment value S0, and set a first preset flow difference S1, a second preset flow difference S2, a third preset flow difference S3, and a fourth preset flow difference S4, and S1<S2<S3<S4, and pre-set a first preset working condition matrix A1 (a1, b1), a second preset working condition matrix A2 (a2, b2), a third preset working condition matrix A3 (a3, b3), and a fourth preset working condition matrix A4 (a4, b4), wherein a1-a4 are the first to fourth pre-cleaning intensities, and a1<a2<a3<a4, b1-b4 are the first to fourth cleaning durations, and b1<b2<b3<b4;

[0021] According to the difference between the pollution degree assessment value △S and the standard pollution degree assessment value S0, the preset working condition matrix Ai is set as the cleaning working condition;

[0022] When △S-S0≤S1, the first preset working condition matrix A1 is set as the cleaning working condition;

[0023] When S1<△S-S0≤S2, the second preset working condition matrix A2 is set as the cleaning working condition;

[0024] When S2<△S-S0≤S3, the third preset working condition matrix A3 is set as the cleaning working condition;

[0025] When S3<ΔS-S0≤S4, the fourth preset working condition matrix A4 is set as the cleaning working condition.

[0026] Furthermore, comparing and analyzing the first grayscale image with the second grayscale image to determine the cleaning efficiency of the first cleaning includes:

[0027] Acquire a first grayscale image and a second grayscale image, and overlap the first grayscale image and the second grayscale image;

[0028] Determine a polluted area in the first grayscale image, and determine an area in the second grayscale image that overlaps with the polluted area in the first grayscale image;

[0029] Taking the overlapping area as the polluted overlapping area, and determining the polluted area of ​​the second grayscale image in the polluted overlapping area;

[0030] The polluted area is used as the corresponding polluted area of ​​the second grayscale image, and the area and grayscale value average of the corresponding polluted area are calculated;

[0031] Obtaining the area and grayscale value average of the polluted area in the first grayscale image, and calculating the difference between the area of ​​the polluted area in the first grayscale image and the area of ​​the corresponding polluted area in the second grayscale image to obtain an area change value, and calculating the difference between the grayscale value average of the polluted area in the first grayscale image and the grayscale value average of the corresponding polluted area in the second grayscale image to obtain a grayscale change value;

[0032] The number of contaminated overlapping areas is obtained, and the cleaning efficiency of the first cleaning is determined based on the number of contaminated overlapping areas and the area change value and grayscale change value in each contaminated overlapping area.

[0033] Furthermore, the calculation formula for the cleaning efficiency of the first cleaning is:

[0034]

[0035] Among them, T is the cleaning efficiency of the first cleaning, n is the number of contaminated areas, Xi is the area change value in the i-th contaminated overlapping area, α is the preset coefficient of the area change value, Yi is the grayscale change value in the i-th contaminated overlapping area, and β is the preset coefficient of the grayscale change value.

[0036] Furthermore, determining the correction coefficient according to the cleaning efficiency includes:

[0037] A correction coefficient-cleaning efficiency interval correspondence relationship is preset, and the correction coefficient-cleaning efficiency interval correspondence relationship is associated with a corresponding correction coefficient for each cleaning efficiency interval;

[0038] The current cleaning efficiency is obtained, and based on the mapping relationship between the cleaning efficiency interval to which the cleaning efficiency belongs and the correction coefficient-cleaning efficiency interval correspondence relationship, a correction coefficient corresponding to the cleaning efficiency interval is selected.

[0039] The present invention also provides a train cargo compartment intelligent cleaning robot, comprising:

[0040] A processing module, used for acquiring a visual image in a train cargo compartment and processing the visual image to obtain a first grayscale image;

[0041] A determination module, used for performing image analysis on the first grayscale image to determine the contaminated area in the train cargo compartment and the contamination characteristic parameters of the contaminated area;

[0042] An evaluation module is used to evaluate the pollution degree of the polluted area based on the pollution characteristic parameters, obtain the pollution degree evaluation value of the polluted area, and set the cleaning working conditions according to the pollution degree evaluation value;

[0043] An acquisition module, used for performing a first cleaning according to set cleaning working conditions, and acquiring a second grayscale image after the first cleaning;

[0044] A comparison module, used for comparing and analyzing the first grayscale image with the second grayscale image, determining a cleaning efficiency of the first cleaning, and determining a correction coefficient according to the cleaning efficiency;

[0045] The correction module is used to correct the set cleaning working conditions according to the correction coefficient, and clean the train cargo compartment again according to the corrected cleaning working conditions.

[0046] Compared with the prior art, the intelligent cleaning robot and control method for a train cargo compartment according to the embodiment of the present invention have the following beneficial effects:

[0047] The present invention can realize automatic monitoring and adjustment of the cleaning process of train cargo compartments through image processing and analysis, reducing the need for manual intervention and improving the automation of the cleaning process;

[0048] The present invention can accurately identify the contaminated area in the train cargo compartment through image analysis and feature extraction, which helps to carry out targeted cleaning work and improves cleaning efficiency;

[0049] The present invention can scientifically evaluate the cleanliness of the polluted area in the train cargo compartment by extracting pollution characteristic parameters and evaluating the pollution degree, thus providing an objective basis for the cleaning work.

[0050] The present invention can adjust the cleaning working conditions in real time through comparative analysis and calculation of correction coefficients, making the cleaning strategy more intelligent and flexible, and improving the cleaning effect and efficiency;

[0051] The present invention can provide data support for cleaning decisions by analyzing and processing image data, making cleaning work more fact-based and scientific. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 1 is a schematic diagram of the flow structure of a control method of an intelligent cleaning robot for a train cargo compartment according to an embodiment of the present invention;

[0053] Figure 2 Schematic diagram of the composition of the intelligent cleaning robot for train cargo compartments in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0055] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0056] The terms "second" and "second" are used for descriptive purposes only and should not be understood as indicating or implying a relative degree of importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined with "second" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "multiple" means two or more.

[0057] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technical personnel in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0058] like Figure 1As shown, in an embodiment of the present application, a control method for an intelligent cleaning robot for a train cargo compartment is provided, including: S100: acquiring a visual image in the train cargo compartment, and processing the visual image to obtain a first grayscale image; S500: performing image analysis on the first grayscale image to determine the polluted area in the train cargo compartment and the pollution characteristic parameters of the polluted area; S300: evaluating the degree of pollution in the polluted area based on the pollution characteristic parameters, obtaining a pollution degree evaluation value of the polluted area, and setting cleaning working conditions according to the pollution degree evaluation value; S400: performing a first cleaning according to the set cleaning working conditions, and acquiring a second grayscale image after the first cleaning; S500: comparing and analyzing the first grayscale image with the second grayscale image, determining the cleaning efficiency of the first cleaning, and determining a correction coefficient according to the cleaning efficiency; S600: correcting the set cleaning working conditions according to the correction coefficient, and cleaning the train cargo compartment again according to the corrected cleaning working conditions.

[0059] Furthermore, the present invention can realize automatic monitoring and adjustment of the cleaning process of train cargo compartments through image processing and analysis, thereby reducing the need for manual intervention and improving the automation level of the cleaning process; the present invention can accurately identify contaminated areas in train cargo compartments through image analysis and feature extraction, thereby facilitating targeted cleaning work and improving cleaning efficiency; the present invention can scientifically evaluate the cleanliness level of contaminated areas in train cargo compartments through the extraction of pollution characteristic parameters and the evaluation of the degree of pollution, thereby providing an objective basis for cleaning work; the present invention can adjust the cleaning working conditions in real time through comparative analysis and calculation of correction coefficients, thereby making the cleaning strategy more intelligent and flexible and improving the cleaning effect and efficiency; the present invention can provide data support for cleaning decisions through the analysis and processing of image data, thereby making the cleaning work more fact-based and scientific.

[0060] In an embodiment of the present application, a control method for an intelligent cleaning robot for a train cargo compartment is provided, wherein image analysis is performed on a first grayscale image to determine a contaminated area in the train cargo compartment and contamination characteristic parameters of the contaminated area, including: obtaining grayscale values ​​of all pixels of the first grayscale image, and dividing the first grayscale image into a plurality of areas according to a threshold segmentation method; calculating the average grayscale value of all pixels in each area, and determining an area whose average grayscale value is greater than a preset average as a contaminated area in the train cargo compartment; calculating the area and average grayscale value of each contaminated area, and determining the area and average grayscale value of each contaminated area as the contamination characteristic parameters of the contaminated area.

[0061] Specifically, all pixels of the first grayscale image are traversed to obtain their grayscale values; the image is segmented into several regions according to the grayscale values ​​of the pixels using the threshold segmentation method, and an adaptive threshold segmentation method can be used; for each segmented region, the average grayscale value of all pixels therein is calculated, and the region with an average grayscale value greater than the preset average is determined as a contaminated region in the train cargo compartment; for each region determined as a contaminated region, its area and average grayscale value are calculated, and these values ​​are determined as contamination characteristic parameters of the contaminated region. This step can help determine the contaminated region in the train cargo compartment, and extract the area and average grayscale value of each contaminated region as contamination characteristic parameters for subsequent contamination level assessment and cleaning strategy formulation.

[0062] In an embodiment of the present application, a control method for an intelligent cleaning robot for a train cargo compartment is provided, wherein the pollution degree of a polluted area is evaluated based on pollution characteristic parameters to obtain a pollution degree evaluation value of the polluted area, including: obtaining the area and the average grayscale value of each polluted area, and evaluating the average grayscale value to obtain a pollution evaluation value of each polluted area; obtaining the area of ​​each polluted area, and calculating the ratio of the area of ​​each polluted area to the area of ​​a first grayscale image, and using the ratio as the weight of each polluted area; and performing weighted addition calculation on the pollution evaluation value of each polluted area and the corresponding weight to obtain a pollution degree evaluation value of each polluted area.

[0063] Specifically, for each area determined as a polluted area, obtain its area and grayscale value average, evaluate and determine the grayscale value average of each polluted area, and design an evaluation standard based on the specific situation to map the grayscale value average to a range of pollution evaluation values; obtain the area of ​​each polluted area, and calculate the ratio of the area of ​​each polluted area to the area of ​​the first grayscale image, and use the ratio as the weight of each polluted area; perform weighted addition calculation on the pollution evaluation value of each polluted area and the corresponding weight to obtain the pollution degree evaluation value of each polluted area. This step can obtain the pollution degree evaluation value of each polluted area, which comprehensively considers the pollution degree and area weight of the area, and can help further understand and quantify the pollution degree of each polluted area. These evaluation values ​​can be used to formulate cleaning strategies, optimize cleaning paths, and track the cleaning effects of polluted areas.

[0064] In an embodiment of the present application, a control method for an intelligent cleaning robot for a train cargo compartment is provided, wherein the cleaning working conditions are set according to a pollution degree assessment value, including: obtaining a pollution degree assessment value △S of a polluted area, presetting a standard pollution degree assessment value S0, and setting a first preset flow rate difference S1, a second preset flow rate difference S2, a third preset flow rate difference S3, and a fourth preset flow rate difference S4, and S1<S2<S3<S4, and presetting a first preset working condition matrix A1(a1, b1), a second preset working condition matrix A2(a2, b2), a third preset working condition matrix A3(a3, b3), and a fourth preset working condition matrix A4(a4, b4), wherein a1-a4 are sequentially are the first to fourth pre-cleaning intensities, and a1<a2<a3<a4, b1-b4 are the first to fourth cleaning durations respectively, and b1<b2<b3<b4; according to the difference between the pollution degree assessment value △S and the standard pollution degree assessment value S0, the preset working condition matrix Ai is set as the cleaning working condition; when △S-S0≤S1, the first preset working condition matrix A1 is set as the cleaning working condition; when S1<△S-S0≤S2, the second preset working condition matrix A2 is set as the cleaning working condition; when S2<△S-S0≤S3, the third preset working condition matrix A3 is set as the cleaning working condition; when S3<△S-S0≤S4, the fourth preset working condition matrix A4 is set as the cleaning working condition.

[0065] Specifically, four sets of preset working condition matrices A1 (a1, b1), A2 (a2, b2), A3 (a3, b3) and A4 (a4, b4) are pre-set, which respectively represent different combinations of cleaning intensity and cleaning time. These combinations can correspond to different cleaning working conditions according to the different cleaning intensity and cleaning time. According to the difference between the pollution degree assessment value △S and the standard pollution degree assessment value S0, the preset working condition matrix Ai is set as the cleaning working condition; when △S-S0≤S1, the first preset working condition matrix A1 is set as the cleaning working condition; when S1<△S-S0≤S2, the second preset working condition matrix A2 is set as the cleaning working condition; when S2<△S-S0≤S3, the third preset working condition matrix A3 is set as the cleaning working condition; when S3<△S-S0≤S4, the fourth preset working condition matrix A4 is set as the cleaning working condition. This step allows the dynamic selection of appropriate cleaning working conditions to cope with different degrees of pollution based on different pollution level assessment values. This intelligent adjustment method can help improve cleaning efficiency and ensure that appropriate cleaning strategies are adopted for areas with different degrees of pollution.

[0066] In an embodiment of the present application, a control method for an intelligent cleaning robot for a train cargo compartment is provided, wherein a first grayscale image is compared and analyzed with a second grayscale image to determine the cleaning efficiency of the first cleaning, and the method includes: obtaining the first grayscale image and the second grayscale image, and overlapping the first grayscale image with the second grayscale image; determining a contaminated area in the first grayscale image, and determining an area in the second grayscale image that overlaps with the contaminated area in the first grayscale image; using the overlapping area as a contaminated overlapping area, and determining a contaminated area of ​​the second grayscale image in the contaminated overlapping area; using the contaminated area as a corresponding area of ​​the second grayscale image; The cleaning efficiency of the first cleaning is determined based on the number of overlapping pollution areas and the area change value and grayscale change value in each overlapping pollution area.

[0067] Specifically, the first grayscale image and the second grayscale image of the train cargo compartment are obtained; the first grayscale image is overlapped with the second grayscale image for subsequent area matching and analysis; according to the previous description, the contaminated area in the first grayscale image is determined; in the overlapping images, the area in the second grayscale image that overlaps with the contaminated area in the first grayscale image is determined; the overlapping area is used as the contaminated overlapping area, and the contaminated area of ​​the second grayscale image is determined; for the contaminated area in the first grayscale image and the corresponding contaminated area in the second grayscale image, their area and grayscale value average are calculated respectively; the difference between the area of ​​the contaminated area in the first grayscale image and the area of ​​the corresponding contaminated area in the second grayscale image is calculated to obtain the area change value, and the difference between the grayscale value average of the contaminated area in the first grayscale image and the grayscale value average of the corresponding contaminated area in the second grayscale image is calculated to obtain the grayscale change value; based on the number of contaminated overlapping areas and the area change value and grayscale change value in each contaminated overlapping area, the cleaning efficiency of the first cleaning is determined. This step can help determine the effect of the first cleaning and provide important data for subsequent cleaning strategies and cleaning effect evaluation.

[0068] In an embodiment of the present application, a control method for a train cargo compartment intelligent cleaning robot is provided, and the calculation formula for the cleaning efficiency of the first cleaning is:

[0069]

[0070] Among them, T is the cleaning efficiency of the first cleaning, n is the number of contaminated areas, Xi is the area change value in the i-th contaminated overlapping area, α is the preset coefficient of the area change value, Yi is the grayscale change value in the i-th contaminated overlapping area, and β is the preset coefficient of the grayscale change value.

[0071] In an embodiment of the present application, a control method for an intelligent cleaning robot for a train cargo compartment is provided, wherein the correction coefficient is determined according to the cleaning efficiency, comprising: presetting a correction coefficient-cleaning efficiency interval correspondence relationship, wherein each cleaning efficiency interval is associated with a corresponding correction coefficient in the correction coefficient-cleaning efficiency interval correspondence relationship; obtaining the current cleaning efficiency, and selecting the correction coefficient corresponding to the cleaning efficiency interval based on a mapping relationship between the cleaning efficiency interval to which the cleaning efficiency belongs within the correction coefficient-cleaning efficiency interval correspondence relationship.

[0072] Specifically, define different cleaning efficiency intervals, and for each cleaning efficiency interval, you can pre-set the corresponding correction coefficient. These correction coefficients can represent performance adjustments or correction values ​​at different cleaning efficiencies; obtain the current cleaning efficiency and determine the cleaning efficiency interval to which it belongs; based on the mapping relationship between the cleaning efficiency intervals, select the correction coefficient corresponding to the cleaning efficiency interval in the correction coefficient-cleaning efficiency interval correspondence relationship. This step can dynamically select the corresponding correction coefficient based on the current cleaning efficiency for performance adjustment or correction. Such a mapping relationship can flexibly adjust the system parameters and performance according to the actual cleaning effect and performance requirements.

[0073] like Figure 2 As shown, in an embodiment of the present application, an intelligent cleaning robot for a train cargo compartment is provided, comprising: a processing module for acquiring a visual image in the train cargo compartment, and processing the visual image to obtain a first grayscale image; a determination module for performing image analysis on the first grayscale image to determine the contaminated area in the train cargo compartment and the pollution characteristic parameters of the contaminated area; an evaluation module for evaluating the degree of pollution of the contaminated area based on the pollution characteristic parameters, obtaining an evaluation value of the degree of pollution of the contaminated area, and setting cleaning working conditions according to the evaluation value of the degree of pollution; an acquisition module for performing a first cleaning according to the set cleaning working conditions, and acquiring a second grayscale image after the first cleaning; a comparison module for comparing and analyzing the first grayscale image with the second grayscale image, determining the cleaning efficiency of the first cleaning, and determining a correction coefficient according to the cleaning efficiency; a correction module for correcting the set cleaning working conditions according to the correction coefficient, and cleaning the train cargo compartment again according to the corrected cleaning working conditions.

[0074] In summary, the embodiment of the present invention provides an intelligent cleaning robot and control method for a train cargo compartment, which includes: obtaining and processing a visual image in a train cargo compartment to obtain a first grayscale image, performing image analysis on the image, and determining the polluted area in the train cargo compartment and the pollution characteristic parameters of the polluted area; evaluating the pollution degree of the polluted area based on the pollution characteristic parameters to obtain a pollution degree evaluation value, and setting the cleaning working conditions according to the pollution degree evaluation value; performing a first cleaning according to the set cleaning working conditions, and obtaining a second grayscale image after the first cleaning; comparing and analyzing the first grayscale image with the second grayscale image, determining the cleaning efficiency of the first cleaning, and determining a correction coefficient according to the first grayscale image; correcting the set cleaning working conditions according to the correction coefficient, and cleaning the train cargo compartment again according to the corrected cleaning working conditions. The present invention can improve the efficiency and quality of cleaning work, reduce labor costs, and realize automation and intelligence of cleaning.

[0075] Finally, it should be noted that: Obviously, a person skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technology, the present invention is also intended to include these modifications and variations.

[0076] The above is only an example of implementation of the present invention, but it cannot be used to limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be regarded as falling within the scope of protection of the present invention and being restricted. Technical personnel in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0077] The term "comprises" or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that includes a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, platform, article, or apparatus / platform.

[0078] So far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings. However, it is easy for a person skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, a person skilled in the art can make equivalent changes or substitutions to closely related technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0079] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A control method for an intelligent cleaning robot for a train cargo compartment, characterized in that: include: Acquire a visual image in a train cargo compartment, and process the visual image to obtain a first grayscale image; Performing image analysis on the first grayscale image to determine the contaminated area in the train cargo compartment and contamination characteristic parameters of the contaminated area; Evaluate the pollution degree of the polluted area based on the pollution characteristic parameters, obtain the pollution degree evaluation value of the polluted area, and set the cleaning working conditions according to the pollution degree evaluation value; Performing a first cleaning according to the set cleaning working conditions, and acquiring a second grayscale image after the first cleaning; Comparing and analyzing the first grayscale image and the second grayscale image, determining a cleaning efficiency of the first cleaning, and determining a correction coefficient according to the cleaning efficiency; The set cleaning working conditions are corrected according to the correction coefficient, and the train cargo compartment is cleaned again according to the corrected cleaning working conditions.

2. A train cargo compartment intelligent cleaning robot control method according to claim 1, characterized in that: The performing image analysis on the first grayscale image to determine the contaminated area in the train cargo compartment and the contamination characteristic parameters of the contaminated area includes: Obtaining grayscale values ​​of all pixels of the first grayscale image, and segmenting the first grayscale image into a plurality of regions according to a threshold segmentation method; Calculate the average grayscale value of all pixels in each area, and determine the area with an average grayscale value greater than a preset average value as a contaminated area in the train cargo compartment; The area and the average gray value of each polluted region are calculated, and the average gray value of each polluted region is determined as the pollution characteristic parameter of the polluted region.

3. A train cargo compartment intelligent cleaning robot control method according to claim 2, characterized in that: The step of evaluating the pollution degree of the polluted area based on the pollution characteristic parameters to obtain the pollution degree evaluation value of the polluted area includes: Obtain the area and grayscale value average of each polluted area, and evaluate the grayscale value average to obtain the pollution evaluation value of each polluted area; Obtaining the area of ​​each contaminated region, and calculating the ratio of the area of ​​each contaminated region to the area of ​​the first grayscale image, and using the ratio as the weight of each contaminated region; The pollution assessment value of each polluted area is weightedly added to the corresponding weight to obtain the pollution degree assessment value of each polluted area.

4. A train cargo compartment intelligent cleaning robot control method according to claim 3, characterized in that: The cleaning working conditions are set according to the pollution degree assessment value, including: Obtain a pollution degree assessment value △S of the polluted area, pre-set a standard pollution degree assessment value S0, and set a first preset flow difference S1, a second preset flow difference S2, a third preset flow difference S3, and a fourth preset flow difference S4, and S1<S2<S3<S4, and pre-set a first preset working condition matrix A1 (a1, b1), a second preset working condition matrix A2 (a2, b2), a third preset working condition matrix A3 (a3, b3), and a fourth preset working condition matrix A4 (a4, b4), wherein a1-a4 are the first to fourth pre-cleaning intensities, and a1<a2<a3<a4, b1-b4 are the first to fourth cleaning durations, and b1<b2<b3<b4; According to the difference between the pollution degree assessment value △S and the standard pollution degree assessment value S0, the preset working condition matrix Ai is set as the cleaning working condition; When △S-S0≤S1, the first preset working condition matrix A1 is set as the cleaning working condition; When S1<△S-S0≤S2, the second preset working condition matrix A2 is set as the cleaning working condition; When S2<△S-S0≤S3, the third preset working condition matrix A3 is set as the cleaning working condition; When S3<ΔS-S0≤S4, the fourth preset working condition matrix A4 is set as the cleaning working condition.

5. A control method for a train cargo compartment intelligent cleaning robot according to claim 4, characterized in that: The comparing and analyzing the first grayscale image with the second grayscale image to determine the cleaning efficiency of the first cleaning includes: Acquire a first grayscale image and a second grayscale image, and overlap the first grayscale image and the second grayscale image; Determine a polluted area in the first grayscale image, and determine an area in the second grayscale image that overlaps with the polluted area in the first grayscale image; Taking the overlapping area as the polluted overlapping area, and determining the polluted area of ​​the second grayscale image in the polluted overlapping area; The polluted area is used as the corresponding polluted area of ​​the second grayscale image, and the area and grayscale value average of the corresponding polluted area are calculated; Obtaining the area and grayscale value average of the polluted area in the first grayscale image, and calculating the difference between the area of ​​the polluted area in the first grayscale image and the area of ​​the corresponding polluted area in the second grayscale image to obtain an area change value, and calculating the difference between the grayscale value average of the polluted area in the first grayscale image and the grayscale value average of the corresponding polluted area in the second grayscale image to obtain a grayscale change value; The number of contaminated overlapping areas is obtained, and the cleaning efficiency of the first cleaning is determined based on the number of contaminated overlapping areas and the area change value and grayscale change value in each contaminated overlapping area.

6. A train cargo compartment intelligent cleaning robot control method according to claim 5, characterized in that: The calculation formula of the cleaning efficiency of the first cleaning is: Among them, T is the cleaning efficiency of the first cleaning, n is the number of contaminated areas, Xi is the area change value in the i-th contaminated overlapping area, α is the preset coefficient of the area change value, Yi is the grayscale change value in the i-th contaminated overlapping area, and β is the preset coefficient of the grayscale change value.

7. A train cargo compartment intelligent cleaning robot control method according to claim 5, characterized in that: Determining the correction coefficient according to the cleaning efficiency includes: A correction coefficient-cleaning efficiency interval correspondence relationship is preset, and the correction coefficient-cleaning efficiency interval correspondence relationship is associated with a corresponding correction coefficient for each cleaning efficiency interval; The current cleaning efficiency is obtained, and based on the mapping relationship between the cleaning efficiency interval to which the cleaning efficiency belongs and the correction coefficient-cleaning efficiency interval correspondence relationship, a correction coefficient corresponding to the cleaning efficiency interval is selected.

8. An intelligent cleaning robot for a train cargo compartment, characterized in that: include: A processing module, used for acquiring a visual image in a train cargo compartment and processing the visual image to obtain a first grayscale image; A determination module, used for performing image analysis on the first grayscale image to determine the contaminated area in the train cargo compartment and the contamination characteristic parameters of the contaminated area; An evaluation module is used to evaluate the pollution degree of the polluted area based on the pollution characteristic parameters, obtain the pollution degree evaluation value of the polluted area, and set the cleaning working conditions according to the pollution degree evaluation value; An acquisition module, used for performing a first cleaning according to set cleaning working conditions, and acquiring a second grayscale image after the first cleaning; A comparison module, used for comparing and analyzing the first grayscale image with the second grayscale image, determining a cleaning efficiency of the first cleaning, and determining a correction coefficient according to the cleaning efficiency; The correction module is used to correct the set cleaning working conditions according to the correction coefficient, and clean the train cargo compartment again according to the corrected cleaning working conditions.

Images