Ground dirt identification method and sweeper

Abstract

The invention provides a ground smudginess identification method and a sweeper, the sweeper comprises a sweeper host and at least one identification system, the at least one identification system is arranged on the sweeper host and electrically connected with the sweeper host, the identification system comprises a light source and at least one ground identification device, and the light source is electrically connected with the at least one ground identification device. Wherein the light source projects light required by detection to the ground, the ground recognition device obtains corresponding spectral data through the received reflected light, compares the obtained spectral data with reference spectral data of a corresponding position in a spectral database, and judges whether stains exist at the position or not according to a comparison result; if the set stain judgment threshold value is not exceeded, judging that the current position has no stain; and if the blot judgment threshold value is exceeded, judging that the blot exists at the current position.

Description

Technical Field

[0001] The present invention relates to the technical field of spectrum recognition, and in particular to a method for identifying dirt on a floor and a sweeping machine. Background Art

[0002] With the development of technology, sweepers are becoming more and more common in every household. Sweepers can not only automatically clean the floor, but also achieve very impressive cleaning results in some cases. However, due to the complex home environment, in order to achieve efficient and high-performance cleaning, it is necessary to identify the floor. It is not only necessary to identify the floor materials such as carpets, floors, tiles, but also to effectively identify whether there are stains, and further distinguish between dry stains, wet stains and oil stains, so as to intelligently select cleaning strategies based on the types, so as to achieve the purpose of intelligence, energy saving and noise reduction.

[0003] Common household stains can be divided into oil stains, water stains and non-water stains. At the molecular level, the difference is the hydrogen-containing groups. For example, oil stains are dominated by CH, while the main component of water stains is water, mainly OH, and non-water stains after air drying may contain CH, OH, NH, etc. Near-infrared spectroscopy (780-2500nm) technology can effectively detect the information of hydrogen-containing groups, and is very friendly to non-contact measurement, making it an ideal stain identification method. However, near-infrared spectroscopy technology has serious spectral band overlap, is affected by stray light and interference from the measured substance, and usually requires the use of chemometrics to establish regression or pattern recognition models for quantitative or qualitative analysis. Usually, a large amount of sample data is required to establish a model, and the extrapolation ability of the established model is poor, that is, the sample needs to be representative enough. Near-infrared spectroscopy has strong penetration, and the collected stain spectral signal is the superposition of stain and ground signals. Affected by the difference in floor materials, the collected stain signals are quite different, and even cover up the differences between oil stains, water stains and non-water stains. Especially for a small amount of dry stains, the floor signal is greater than the stain signal. Therefore, how to accurately extract the stain signal and realize classification is an important issue for using spectral technology in sweeping robots.

[0004] Therefore, how to accurately identify stains has become an urgent problem to be solved. Summary of the invention

[0005] A major advantage of the present invention is that it provides a method for identifying ground dirt and a sweeping machine, wherein the sweeping machine includes a sweeping machine body and an identification system, and the identification system can obtain ground information through spectral data analysis, such as obtaining the ground category, and / or identifying whether there are stains on the ground, and the type of stains, which is conducive to improving the recognition accuracy.

[0006] Another advantage of the present invention is that it provides a ground dirt recognition method and a sweeper, wherein the ground dirt recognition method proposes a strategy for automatically establishing rapid stain recognition and classification based on spectral technology, thereby realizing stain recognition and classification, which is conducive to improving recognition accuracy.

[0007] Another advantage of the present invention is that it provides a floor dirt identification method and a sweeper, wherein the floor dirt identification method updates the spectral database to effectively avoid errors caused by gradual attenuation of the light source or aging of the device.

[0008] Another advantage of the present invention is that it provides a method for identifying ground dirt and a sweeping machine, wherein the sweeping machine subtracts the collected spectral data from the spectral data that is closest in time and does not exceed a first threshold to obtain a difference spectrum, and further determines the type of dirt as dry stains, wet stains or oily stains based on specific absorption peaks of the difference spectrum.

[0009] According to one aspect of the present invention, a method for identifying ground dirt of the present invention can achieve the aforementioned objectives and other objectives and advantages, wherein the method for identifying ground dirt comprises the following steps:

[0010] (a) collecting spectral data of the ground surface during the operation of the sweeper; and

[0011] (b) The spectral data is compared with the reference spectral data of the corresponding position in the spectral database, and whether there is stain at the position is determined based on the comparison result; if it does not exceed the set stain judgment threshold, it is determined that there is no stain at the current position; if it exceeds the stain judgment threshold, it is determined that there is stain at the current position.

[0012] According to one embodiment of the present invention, in the step (a) of the ground dirt identification method, it further comprises:

[0013] (a.1) when the sweeping machine moves to a certain coordinate position, projecting detection light onto the ground; and

[0014] (a.2) Acquire reflected light from the ground, and acquire spectral data corresponding to the current coordinate position based on the reflected light.

[0015] According to one embodiment of the present invention, before the step (a) of the ground dirt identification method, a device initialization step is further included to collect and record the coordinate positions of the entire area and the spectra of the coordinate positions to form a corresponding spectral database.

[0016] According to one embodiment of the present invention, in the step (b) of the floor dirt identification method, when it is determined that there is no stain at the position, the newly collected spectral data directly replaces the reference spectral data in the original spectral database; or if it does not exceed the stain judgment threshold, the average value of the newly collected spectral data and the reference spectral data of the corresponding coordinate position is calculated, and the average value is used to replace the spectral data of the coordinate position in the spectral database.

[0017] According to an embodiment of the present invention, in the step (b) of the floor dirt identification method, the CI of the newly collected spectral data is compared with the previously set CI limit (CI limit), so as to quickly and simply determine whether the newly collected spectral data is consistent with the reference spectral data;

[0018] in,

[0019] Among them, A unknow is the newly collected spectral data, A reference is the spectral data in the spectral database, σ reference is the standard deviation.

[0020] According to one embodiment of the present invention, in the step (b) of the ground dirt identification method, the standard deviation of the spectral data in the spectral database within a radius of 5 to 20 cm near the specific coordinate position is calculated; if the difference between the newly collected spectral data and the spectral data in the spectral database at any wavelength exceeds 3 to 5 times the standard deviation, it is considered that there is stain.

[0021] According to an embodiment of the present invention, in the step (b) of the floor dirt identification method, the location of the stain is determined by the duration that the difference between the acquired spectral data and the reference spectral data exceeds a stain determination threshold.

[0022] According to one embodiment of the present invention, in the step (b) of the floor dirt identification method, if the difference between the acquired spectral data and the reference spectral data exceeds the stain judgment threshold within the time period of the duration threshold T, it can be determined that the identification system used to detect stains has surface dirt; if the duration of the detected stain does not exceed the duration threshold T, it is determined that the floor has stains.

[0023] According to an embodiment of the present invention, the set duration threshold T is greater than or equal to 1 second.

[0024] According to one embodiment of the present invention, in the step (b) of the ground dirt identification method, the location of the stain is judged according to the fluctuation characteristics of the difference between the acquired spectral data and the reference spectral data within the time threshold T. If the difference fluctuates slightly and conforms to a certain trend law, it is determined that the surface of the ground identification device is dirty.

[0025] According to one embodiment of the present invention, in the step (b) of the floor dirt identification method, the collected spectral data is subtracted from the spectral data that is closest in time and does not exceed the first judgment threshold to obtain a difference spectrum value, and it is judged whether the specific absorption peak of the difference spectrum value exceeds the second judgment threshold; if the OH absorption peak of the stain exceeds the second judgment threshold, it is considered to be a wet stain, and when the CH absorption peak exceeds the third threshold, it is judged to be an oil stain. If both absorption peaks exceed the second judgment threshold and the third judgment threshold, it can be judged as an oil stain. If both the CH absorption peak and the OH absorption peak do not exceed the second judgment threshold and the third judgment threshold, it is judged to be a dry stain.

[0026] According to another aspect of the present application, the present application further provides a sweeping machine, comprising:

[0027] Sweeper host; and

[0028] At least one recognition system, wherein the at least one recognition system is arranged on the main body of the sweeping machine and is electrically connected to the main body of the sweeping machine, the recognition system includes a light source and at least one ground recognition device, wherein the light source projects the light required for detection onto the ground, and the ground recognition device obtains the corresponding spectral data through the received reflected light, and compares the obtained spectral data with the reference spectral data of the corresponding position in the spectral database, and judges whether there is stain at the position according to the comparison result; if it does not exceed the set stain judgment threshold, it is judged that there is no stain at the current position; if it exceeds the stain judgment threshold, it is judged that there is stain at the current position.

[0029] According to one embodiment of the present invention, the ground identification device is selected from a spectral device group consisting of a dispersive spectrometer, a Fourier spectrometer, a narrow-band spectrometer and a computational spectrometer.

[0030] Further objects and advantages of the present invention will be fully apparent from an understanding of the following description and the accompanying drawings.

[0031] These and other objects, features and advantages of the present invention will be more fully understood from the following detailed description and accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. In the accompanying drawings, unless otherwise specified, the same reference numerals are used to represent the same components. Among them:

[0033] Figure 1 It is a schematic diagram of the structural framework of a sweeping machine according to a first preferred embodiment of the present invention.

[0034] Figure 2 It is a schematic diagram of the framework of the spectrum chip of the sweeping machine according to the first preferred embodiment of the present invention.

[0035] Figure 3 It is a flowchart of a method for identifying ground dirt according to the first preferred embodiment of the present invention.

[0036] Figure 4 It is a schematic diagram of the method steps of the ground dirt identification method according to the first preferred embodiment of the present invention. DETAILED DESCRIPTION

[0037] It should be pointed out that the embodiments shown in the drawings are only used as examples to specifically and vividly explain and illustrate the concept of the present invention. The size and structure thereof are not necessarily drawn to scale, nor do they constitute a limitation to the concept of the present invention.

[0038] The directional terms such as up, down, left, right, front, back, front, back, top, bottom, etc. mentioned or may be mentioned in this specification are defined relative to the structures shown in the various drawings. They are relative concepts and may change accordingly according to different positions and different usage conditions. Therefore, these or other directional terms should not be interpreted as restrictive terms.

[0039] Referring to the drawings of this application specification Figures 1 to 4 As shown, a method for identifying ground dirt and a sweeping machine according to the first preferred embodiment of the present application are explained in the following description. The sweeping machine includes a sweeping machine host 10 and at least one identification system 20 provided on the sweeping machine host 10, wherein the identification system 20 is used to identify ground information and determine the type of dirt on the ground.

[0040] Specifically, the identification system 20 includes a light source 21 and at least one ground identification device 22, wherein the light source 21 projects the light required for detection toward the ground, and the detection light is received by the ground identification device 22 after being reflected by the ground. The ground identification device 22 obtains the corresponding spectral data through the received reflected light, and can obtain ground information through spectral data analysis, such as obtaining the ground category, and / or identifying whether there are stains on the ground, and the type of stains.

[0041] Preferably, in this preferred embodiment of the present application, the at least one ground recognition device 22 is arranged on the sweeping machine host 10. As an example, in this preferred embodiment of the present application, the at least one ground recognition device 22 is arranged at the lower end of the sweeping machine host 10, which is arranged adjacent to the light source 21.

[0042] The ground identification device 22 is implemented as a spectroscopic device, such as a dispersion spectrometer, a Fourier spectrometer, a narrowband spectrometer (for example, a spectrometer formed by an FP cavity), or a computational spectrometer in the field of computational spectroscopy. In short, in this application, the specific type of the ground identification device 22 is only used as an example, not a limitation.

[0043] As an example, in a specific example of the present application, the ground identification device 22 is implemented as a computational spectrometer, and the computational spectrometer includes a spectral chip, and the spectral chip includes a filter structure and an image sensor, and the filter structure is located on the photosensitive path of the image sensor, and the filter structure is a broadband filter structure in the frequency domain or wavelength domain. The pass spectra of different wavelengths of the filter structures in each place are not exactly the same. The filter structure can be a structure or material with light scattering characteristics such as a super surface, a photonic crystal, a nanocolumn, a multilayer film, a dye, a quantum dot, a MEMS (micro-electromechanical system), an FP etalon (FP standard), a cavity layer (resonant cavity layer), a waveguide layer (waveguide layer), a diffraction element, a grating component, etc. For example, in an embodiment of the present application, the computational spectroscopy technology can be taken as an example, and the filter structure can be the light modulation layer in the Chinese patent CN201921223201.2, and the spectral chip is a computational spectral chip.

[0044] The image sensor may be a CMOS image sensor (CIS), a CCD, an array photodetector, etc. In addition, the spectral device further includes a signal processing unit, which may be a processing unit such as an MCU, a CPU, a GPU, an FPGA, an NPU, an ASIC, etc., which may export the data generated by the image sensor to an external device for processing.

[0045] In some embodiments, the spectral chip is formed by integrating a filter structure and an image sensor. For example, the filter structure is formed during the process of manufacturing the image sensor. In this case, there is no need to obtain the image sensor and then form the filter structure on the basis of the image sensor.

[0046] More specifically, the light modulation layer includes a plurality of structural units arranged in a specific pattern, and the structural units are arranged in a certain period. Further, each structural unit is composed of at least one micro-nano structure, and the micro-nano structure can be implemented as a hole, a column, a line, and the like.

[0047] Furthermore, the working principle of the spectral chip is provided. After the image sensor measures the spectral response, it is transmitted to the signal processing unit for recovery calculation. The specific description of the process is as follows:

[0048] The intensity signal of the incident light at different wavelengths λ is denoted as x(λ), and the transmission spectrum curve of the light modulation layer is denoted as T(λ). There are m structural units on the light modulation layer, and the transmission spectrum of each structural unit is different. Overall, the light modulation layer can be denoted as Ti(λ) (i=1,2,3,…,m). There is a corresponding physical pixel under each structural unit to detect the light intensity bi modulated by the light modulation layer. In a specific embodiment of the present application, one physical pixel, that is, one physical pixel corresponds to one structural unit, but it is not limited to this. In other embodiments, multiple physical pixels may correspond to one structural unit as a group. Therefore, in the computational spectroscopy device according to the embodiment of the present application, at least two structural units constitute a "spectral pixel" (it can be understood that multiple structural units and corresponding image sensors constitute a spectral pixel). It should be noted that the number of effective transmission spectra (the transmission spectrum used for spectral recovery is called effective transmission spectrum) Ti(λ) of the optical modulation layer may not be consistent with the number of structural units. The transmission spectrum of the filter structure is artificially set, tested, or calculated according to certain rules according to the needs of identification or recovery (for example, the transmission spectrum of each structural unit tested above is an effective transmission spectrum). Therefore, the number of effective transmission spectra of the optical modulation layer may be less than the number of structural units, or even more than the number of structural units; in this variant embodiment, a certain transmission spectrum curve is not necessarily determined by a structural unit. Furthermore, the present invention can use at least one spectral pixel to restore the spectrum.

[0049] The relationship between the spectral distribution of the incident light and the measured value of the image sensor can be expressed as follows:

[0050] bi=∫x(λ)*Ti(λ)*R(λ)dλ

[0051] After further discretization, we get

[0052] bi=Σ(x(λ)*Ti(λ)*R(λ))

[0053] Where R(λ) is the response of the image sensor, expressed as:

[0054] Ai(λ)=Ti(λ)*R(λ),

[0055] The above formula can be expanded into matrix form:

[0056]

[0057] Among them, bi (i = 1, 2, 3, ..., m) is the response of the image sensor after the light to be measured passes through the light modulation layer, which corresponds to the light intensity measurement value of the image sensor corresponding to m structural units. When a physical pixel corresponds to a structural unit, it can be understood as the light intensity measurement value corresponding to m "physical pixels", which is a vector of length m. Matrix A (which can be understood as a transmission spectrum curve, also known as a transmission spectrum matrix) is the system's response to light of different wavelengths, which is determined by two factors: the transmittance of the light modulation layer and the quantum efficiency of the image sensor. A is a matrix, and each row vector corresponds to the response of a structural unit to incident light of different wavelengths. Here, the incident light is discretely and uniformly sampled, with a total of n sampling points. The number of columns of A is the same as the number of sampling points of the incident light. Here, x (λ) is the light intensity of the incident light at different wavelengths λ, that is, the incident light spectrum to be measured.

[0058] In the preferred embodiment of the present application, the sweeping machine is based on a strategy of automatically establishing rapid identification and classification of stains, identifying stains and classifying the types of stains. Therefore, specifically, its working method is as follows:

[0059] When the sweeping machine host 10 of the sweeping machine is in working state, when the sweeping machine host 10 runs to a certain coordinate position, the light source 21 of the recognition system 20 projects the detection light to the ground at the coordinate position, and the reflected light of the ground is received by the ground recognition device 22 of the recognition system 20. The recognition system 20 collects spectral data of the corresponding coordinate position during the operation of the sweeping machine host 10.

[0060] Before the sweeper works for the first time, the device needs to be initialized. Specifically, turn on the sweeper, collect and record the coordinate position of the entire area and the spectrum of the coordinate position to form a corresponding spectral database. It should be understood that in the preferred embodiment of the present application, the entire area can be a room or a house, that is, it refers to a certain area that needs to be cleaned. When the sweeper is turned on, the light source 21 and the ground recognition device 22 of the recognition system 20 will enter the working state, wherein the light source 21 emits light to the ground, generates reflection, is received by the ground recognition device 22, and obtains spectral data; as the sweeper moves, the reference spectral data corresponding to each coordinate position can be obtained, thereby forming a spectral database.

[0061] In short, in this preferred embodiment of the present application, during the initialization process, the sweeper scans the entire area to be cleaned, that is, the recognition system 20 scans each coordinate position and obtains the spectral data corresponding to each coordinate position in the entire area as the reference spectral data of the area.

[0062] The sweeper obtains spectral data of a specific coordinate position in a working state and compares it with reference spectral data of the corresponding coordinate position in a spectral database, and determines whether there is a stain at the coordinate position according to the comparison result. Specifically, a stain determination threshold is set, and the obtained spectral data is compared with the reference spectral data of the corresponding coordinate position in the spectral database. If it does not exceed the stain determination threshold, it is determined that there is no stain at the current coordinate position; if it exceeds the stain determination threshold, it is determined that there is a stain at the current coordinate position.

[0063] When it is determined that there is no stain at the coordinate position, the newly collected spectral data directly replaces the reference spectral data in the original spectral database; or if it does not exceed the stain judgment threshold, the average value of the newly collected spectral data and the reference spectral data at the corresponding coordinate position is calculated, and then the average value is used to replace the spectral data at the coordinate position in the spectral database; thereby updating the spectral database and effectively avoiding errors caused by gradual attenuation of the light source or aging of the device.

[0064] As an example, in the preferred embodiment of the present application, the newly collected spectral data and the reference spectral data in the spectral database are compared by using a consistency check method, that is, the CI of the newly collected spectral data is compared with the previously set CI limit (CI limit), so as to quickly and simply determine whether the newly collected spectral data and the reference spectral data are consistent;

[0065] in,

[0066] Among them, A unknow is the newly collected spectral data, A reference is the spectral data in the spectral database, σ reference is the standard deviation.

[0067] Optionally, in another optional embodiment of the present application, by calculating the standard deviation of the spectral data in the spectral database within a radius of 5 to 20 cm near the specific coordinate position; it can be understood as an area within a radius of 5-20 cm with the coordinate position as the center. If the difference between the newly collected spectral data and the spectral data in the spectral database at any wavelength exceeds 3 to 5 times the standard deviation, it is considered that there is stain.

[0068] It should be noted that when the sweeper is in operation, if the recognition system 20 detects no stains at the coordinate position, it means that there are no stains on the ground at the coordinate position. However, if the recognition system 20 determines that there are stains at the coordinate position, the following situations exist: the first is that there are stains on the ground, and the second is that the recognition system 20 is contaminated, that is, there are stains on the recognition system 20 shown.

[0069] Therefore, when the recognition system 20 recognizes or determines that there is a stain at the coordinate position, it is necessary to further determine the duration of the difference between the spectral data obtained by the ground recognition device 22 and the reference spectral data during the operation of the sweeper to determine the specific location of the stain. Determine whether the duration exceeds the duration threshold T. If, within the time period of the duration threshold T, the difference between the spectral data obtained by the ground recognition device 22 of the recognition system 20 and the reference spectral data exceeds the stain judgment threshold, it can be determined that the recognition system 20 has surface dirt, thereby affecting the normal operation of the sweeper, and it is necessary to start the cleaning work of the recognition system 20. In short, the duration of the difference between the spectral data obtained by the ground recognition device 22 and the reference spectral data exceeds the threshold value to determine whether the dirt is on the ground or on the surface of the recognition system. As an example, the duration threshold T is greater than or equal to 1 second. For higher accuracy, the duration threshold T is set to 2 seconds or more. If the recognition system 20 continues to recognize stains for a period of time exceeding the time threshold T, it is possible that there is dirt on the surface of the ground recognition device 22, which affects the recognition, and the surface cleaning of the recognition device is started; it can also remind the user to determine whether there is dirt on the surface of the ground recognition device 22, and clean it if so.

[0070] It should be noted that although there is a large area of ​​dirt on the ground, the spectral data obtained by the identification device in the dirty area is relatively similar, but there will be certain differences in the thickness and uniformity of the dirt, so the spectral data will inevitably have certain fluctuations; however, since there is dust and other dirt on the surface of the identification device, it is relatively fixed, and the comparison between the corresponding acquired spectral data and the reference spectral data shows small fluctuations and certain regularities, such as the amplitude or frequency of the fluctuations does not change much.

[0071] Therefore, in order to more accurately identify whether there is dirt on the ground or there is surface dirt on the ground identification device 22. Optionally, if the duration exceeds the duration threshold T, and the difference between the spectral data and the reference spectral data fluctuates slightly and is relatively stable, that is, within the duration threshold T, the average absolute deviation of the two spectra before and after is less than 0.001, then it is judged that there is surface dirt on the ground identification device 22. For example, there is dust on the surface cover of the protective identification device, or there is dust on the lens surface of the identification device. In other words, in this preferred embodiment of the present application, under the premise of the presence of dirt, the identification system 20 determines whether the stain is ground stain or surface dirt on the ground identification device 22 according to the fluctuation of the difference between the acquired spectral data and the reference spectral data within the duration threshold T.

[0072] If the identification system 20 detects that the duration of the stain does not exceed the time threshold T, it is determined that the floor has stains. Further, the identification system 20 distinguishes the types of stains, dry stains, wet stains and oil stains based on the acquired spectral data. First, the spectral data collected by the ground identification device 22 is subtracted from the spectral data that is closest in time sequence (during the current operation of the sweeper) and does not exceed the first judgment threshold (i.e., the stain judgment threshold) to obtain a difference vector, and it is determined whether the specific absorption peak of the difference vector exceeds the second judgment threshold; if the OH absorption peak of the stain (near 960nm, 1400nm, 1900nm) exceeds the second judgment threshold, it is considered to be a wet stain, when the CH absorption peak (near 900nm, 1200nm, 1700nm, 2300nm) exceeds the third threshold, it is determined to be an oil stain, if both absorption peaks exceed the second judgment threshold and the third judgment threshold, it can be determined to be an oil stain, if the CH absorption peak and the OH absorption peak do not exceed the second judgment threshold and the third judgment threshold, it is determined to be a dry stain.

[0073] It should be noted that the specific absorption peak described in the present application refers to the response value of different types of stains in the corresponding band. When the light source and the ground identification device are different, the working band may be different, but it is only necessary to judge whether it exceeds the threshold within the working band, and the first judgment threshold, the second judgment threshold and the third judgment threshold can be set according to needs and are fixed values.

[0074] Referring to the drawings of this application specification Figure 4 As shown, a method for identifying dirt on the ground in this preferred embodiment of the present application is further described, wherein the method for identifying dirt on the ground includes the following steps:

[0075] (a) collecting spectral data of the ground surface during the operation of the sweeper; and

[0076] (b) The spectral data is compared with the reference spectral data of the corresponding position in the spectral database, and whether there is stain at the position is determined based on the comparison result; if it does not exceed the set stain judgment threshold, it is determined that there is no stain at the current position; if it exceeds the stain judgment threshold, it is determined that there is stain at the current position.

[0077] In the step (a) of the ground dirt identification method, it further includes:

[0078] (a.1) when the sweeping machine moves to a certain coordinate position, projecting detection light onto the ground; and

[0079] (a.2) Acquire reflected light from the ground, and acquire spectral data corresponding to the current coordinate position based on the reflected light.

[0080] Before the step (a) of the ground dirt identification method, the step of initializing the equipment is further included to collect and record the coordinate positions of the entire area and the spectra of the coordinate positions to form a corresponding spectral database.

[0081] In step (b) of the floor dirt identification method, when it is determined that there is no stain at the position, the newly collected spectral data directly replaces the reference spectral data in the original spectral database; or if it does not exceed the stain judgment threshold, the average value of the newly collected spectral data and the reference spectral data at the corresponding coordinate position is calculated, and the average value is used to replace the spectral data at the coordinate position in the spectral database.

[0082] In the step (b) of the floor dirt identification method, the CI of the newly collected spectral data is compared with the previously set CI limit, so as to quickly and simply determine whether the newly collected spectral data is consistent with the reference spectral data;

[0083] in,

[0084] Among them, A unknow is the newly collected spectral data, A reference is the spectral data in the spectral database, σ reference is the standard deviation.

[0085] In step (b) of the method for identifying floor dirt, the standard deviation of the spectral data in the spectral database within a radius of 5 to 20 cm near the specific coordinate position is calculated; if the difference between the newly collected spectral data and the spectral data in the spectral database at any wavelength exceeds 3 to 5 times the standard deviation, it is considered that there is stain.

[0086] In the step (b) of the floor dirt identification method, the location of the stain is determined by the duration that the difference between the acquired spectral data and the reference spectral data exceeds a stain determination threshold.

[0087] In the step (b) of the floor dirt identification method, if the difference between the acquired spectral data and the reference spectral data exceeds the stain judgment threshold within the time period of the duration threshold T, it can be determined that the identification system used to detect stains has surface dirt; if the duration of the detected stain does not exceed the duration threshold T, it is determined that the floor has stains.

[0088] In step (b) of the floor dirt identification method, the set time threshold T is greater than or equal to 1 second.

[0089] In the step (b) of the ground dirt identification method, the location of the stain is judged based on the fluctuation characteristics of the difference between the acquired spectral data and the reference spectral data within the time threshold T. If the difference fluctuates slightly and conforms to a certain trend law, it is determined that the surface of the ground identification device is dirty.

[0090] In the step (b) of the floor dirt identification method, the collected spectral data is subtracted from the spectral data that is closest in time and does not exceed the first judgment threshold to obtain a difference vector, and it is judged whether the specific absorption peak of the difference vector exceeds the second judgment threshold; if the OH absorption peak of the stain exceeds the second judgment threshold, it is considered to be a wet stain, and when the CH absorption peak exceeds the third threshold, it is judged to be an oil stain. If both absorption peaks exceed the second judgment threshold and the third judgment threshold, it can be judged to be an oil stain. If both the CH absorption peak and the OH absorption peak do not exceed the second judgment threshold and the third judgment threshold, it is judged to be a dry stain.

[0091] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.

[0092] The technical scope of the present invention is not limited to the contents in the above description. Those skilled in the art can make various deformations and modifications to the above embodiments without departing from the technical idea of ​​the present invention, and these deformations and modifications all belong to the protection scope of the present invention.

Claims

1. A method for identifying ground dirt, characterized in that: The ground dirt identification method comprises the following steps: (a) collecting spectral data of the ground surface during the operation of the sweeper; and (b) comparing the spectral data with reference spectral data at the corresponding coordinate position in a spectral database, and determining whether there is stain at the coordinate position according to the comparison result; If it does not exceed the set stain judgment threshold, it is determined that there is no stain at the current coordinate position; If it exceeds the stain judgment threshold, it is determined that there is stain at the current coordinate position.

2. The method for identifying ground dirt according to claim 1, wherein in the step (a) of the method for identifying ground dirt, further comprising: (a.1) When the sweeping machine moves to a certain coordinate position, a detection light is projected onto the ground; and (a.2) Acquire reflected light from the ground, and acquire spectral data corresponding to the current coordinate position based on the reflected light.

3. The method for identifying ground dirt according to claim 2, further comprising a step of initializing the device before step (a) of the method for identifying ground dirt, collecting and recording the coordinate positions of the entire area and the spectra of the coordinate positions to form a corresponding spectral database.

4. The method for identifying floor dirt according to claim 3, wherein in the step (b) of the method for identifying floor dirt, when it is determined that there is no stain at the position, the newly collected spectral data directly replaces the reference spectral data in the original spectral database; or if it does not exceed the stain judgment threshold, the average value of the newly collected spectral data and the reference spectral data at the corresponding coordinate position is calculated, and the average value is used to replace the spectral data at the coordinate position in the spectral database.

5. The method for identifying dirt on a floor according to claim 4, wherein in step (b) of the method for identifying dirt on a floor, the CI of the newly collected spectral data is compared with the previously set CI limit, so as to quickly and simply determine whether the newly collected spectral data is consistent with the reference spectral data; in, Among them, A unknow is the newly collected spectral data, A reference is the spectral data in the spectral database, σ reference is the standard deviation.

6. A method for identifying ground dirt according to claim 4, wherein in step (b) of the method for identifying ground dirt, the standard deviation of the spectral data in the spectral database within a radius of 5 to 20 cm near the specific coordinate position is calculated; if the difference between the newly collected spectral data and the spectral data in the spectral database at any wavelength exceeds 3 to 5 times the standard deviation, it is considered that there is stain.

7. A method for identifying ground dirt according to claim 5 or 6, wherein in the step (b) of the method for identifying ground dirt, the location of the stain is determined by the duration that the difference between the acquired spectral data and the reference spectral data exceeds a stain judgment threshold.

8. A method for identifying floor dirt according to claim 7, wherein in step (b) of the method for identifying floor dirt, if within the time period of the duration threshold T, the difference between the acquired spectral data and the reference spectral data exceeds the stain judgment threshold, it can be determined that the identification system used to detect stains has surface dirt; if the duration of the detected stain does not exceed the duration threshold T, it is determined that the floor has stains.

9. The method for identifying ground dirt according to claim 8, wherein the set time threshold T is greater than or equal to 1 second.

10. A method for identifying ground dirt according to claim 8, wherein in the step (b) of the method for identifying ground dirt, the location of the stain is judged based on the fluctuation characteristics of the difference between the acquired spectral data and the reference spectral data within the time threshold T; if the difference fluctuates slightly and conforms to a certain trend law, it is determined that the surface of the ground identification device is dirty.

11. A method for identifying floor dirt according to claim 10, wherein in the step (b) of the method for identifying floor dirt, a difference vector is obtained by subtracting the collected spectral data from the spectral data that is closest in time and does not exceed the first judgment threshold, and it is judged whether the specific absorption peak of the difference vector exceeds the second judgment threshold; if the OH absorption peak of the stain exceeds the second judgment threshold, it is considered to be a wet stain, and when the CH absorption peak exceeds the third threshold, it is judged to be an oil stain. If both absorption peaks exceed the second judgment threshold and the third judgment threshold, it can be judged to be an oil stain. If both the CH absorption peak and the OH absorption peak do not exceed the second judgment threshold and the third judgment threshold, it is judged to be a dry stain.

12. A sweeping machine, characterized in that: include: Sweeping machine host; and At least one recognition system, wherein the at least one recognition system is arranged on the main body of the sweeping machine and is electrically connected to the main body of the sweeping machine, the recognition system comprises a light source and at least one ground recognition device, wherein the light source projects light required for detection onto the ground, the ground recognition device obtains the corresponding spectral data through the received reflected light, and compares the obtained spectral data with the reference spectral data of the corresponding position in the spectral database, and determines whether there is a stain at the position according to the comparison result; If it does not exceed the set stain judgment threshold, it is determined that there is no stain at the current position; If it exceeds the stain judgment threshold, it is determined that there is stain at the current position.

13. The sweeping machine according to claim 12, wherein the ground recognition device is selected from a spectral device group consisting of a dispersive spectrometer, a Fourier spectrometer, a narrow-band spectrometer and a computational spectrometer.

Images