CN115897130A - Material identification control method for washing equipment - Google Patents
Material identification control method for washing equipment Download PDFInfo
- Publication number
- CN115897130A CN115897130A CN202110949255.2A CN202110949255A CN115897130A CN 115897130 A CN115897130 A CN 115897130A CN 202110949255 A CN202110949255 A CN 202110949255A CN 115897130 A CN115897130 A CN 115897130A
- Authority
- CN
- China
- Prior art keywords
- material type
- clothes
- type
- determined
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B40/00—Technologies aiming at improving the efficiency of home appliances, e.g. induction cooking or efficient technologies for refrigerators, freezers or dish washers
Landscapes
- Control Of Washing Machine And Dryer (AREA)
Abstract
The invention relates to the technical field of intelligent household appliances, and particularly provides a material identification control method for washing equipment, aiming at solving the problem that the material identification of clothes of the existing washing equipment is inaccurate. To this end, the recognition control method of the present invention comprises the steps of: acquiring a static image of the clothes in a static state after the clothes are put into an inner barrel of the washing equipment; determining the material type of the clothes according to the static image; judging whether the material type can be determined according to the static image; controlling the inner barrel to rotate under the condition that the material type cannot be determined according to the static image; in the process of rotating the inner barrel, acquiring a first dynamic video of clothes in a rotating state; the material type is determined according to the first dynamic video, different methods are sequentially adopted for recognizing different types of materials until the material type of the clothes is determined, accuracy and precision of material type recognition are improved, and user experience is improved.
Description
Technical Field
The invention relates to the technical field of intelligent household appliances, and particularly provides a material identification control method for washing equipment.
Background
With the improvement of living standard of people, people have higher and higher requirements on the intellectualization of the washing machine, and for clothes, the most obvious characteristic of the clothes is the material. People expect that the washing machine is more intelligent, can acquire attribute information such as the material of clothing automatically to recommend suitable washing procedure and confirm washing parameter according to the material of clothing etc. not only can be with the clothing sanitization, but also can avoid the clothing to receive the damage, for example real silk class clothing, unsuitable washing often will damage the clothing etc..
In the prior art, most clothes material identification control methods adopt image identification on static images of clothes, so as to determine the material of the clothes. However, in the process of shooting an image, pixels of the camera, the external illumination intensity and the like have great influence on the image quality, and clothes made of any material are identified by the same method, but appearances of some materials are very similar, so that the accuracy of identifying the material of the clothes through a static image is low, the material of the clothes cannot be accurately identified, and further, a recommended washing program is not suitable, and the user experience is not facilitated.
Therefore, there is a need in the art for a new material identification control method for a washing machine to solve the above problems.
Disclosure of Invention
The invention aims to solve the technical problem, namely, the problem of inaccurate clothes material identification of the existing washing equipment.
The invention provides a material identification control method for washing equipment, which comprises the following steps: acquiring a static image of the laundry in a static state after the laundry is put into an inner tub of the washing apparatus; determining the material type of the clothes according to the static image; judging whether the material type can be determined according to the static image; controlling the inner barrel to rotate under the condition that the material type cannot be determined according to the static image; in the process of rotating the inner barrel, acquiring a first dynamic video of clothes in a rotating state; determining the material type from the first dynamic video.
In a preferred embodiment of the above recognition control method, the step of "determining the material type of the clothing based on the static image" includes: calling a classification model to identify the static image; the step of "judging whether the material type can be determined from the still image" specifically includes: judging whether the material type belongs to a first type or not according to the identification result; determining that the material type can be determined if the material type belongs to the first type; and/or if the material type does not belong to the first type, determining that the material type cannot be determined; the classification model is the first type according to the material type which can be determined by the static image, and the first type comprises woolen, wool, cashmere and down.
In a preferred embodiment of the above recognition control method, the step of "determining the material type according to the first dynamic video" specifically includes: calling a preset model to analyze the first dynamic video; judging whether the material type can be determined or not according to the analysis result; controlling the washing equipment to execute water injection operation under the condition that the material type cannot be determined; controlling the inner tub to rotate after the washing apparatus performs a water filling operation; acquiring a second dynamic video of clothes in a rotating state in the process of rotating the inner barrel; determining the material type from the second dynamic video.
In the above preferred technical solution of the recognition control method, the step of "calling a preset model to analyze the first dynamic video" specifically includes: converting the first dynamic video into a plurality of first images according to a first preset sampling period; respectively preprocessing the plurality of first images to obtain target information of each first image; inputting all the target information into the preset model; the preset model analyzes all the target information; the step of determining whether the material type can be determined according to the analysis result specifically includes: judging whether the material type belongs to a second type; determining that the material type can be determined if the material type is of the second type; and/or if the material type does not belong to the second type, determining that the material type cannot be determined; and the material type which can be determined by the preset model according to the target information is the second type, and the second type comprises silk.
In a preferred embodiment of the above recognition control method, "preprocessing each of the plurality of first images to obtain the target information of each of the first images" specifically includes: identifying the clothing in each first image and the outline of the clothing in the image; determining the target information according to the contour; wherein the target information includes at least one of a contour pixel number curve, an instantaneous change curve, and an average distance of a circle center of the laundry.
In a preferred embodiment of the above recognition control method, the step of "determining the material type according to the second dynamic video" specifically includes: converting the second dynamic video into a plurality of second images according to a second preset sampling period; respectively determining the motion information of the clothes corresponding to each second image according to the plurality of second images; determining the material type according to all the motion information; wherein the motion information comprises a centroid average speed and/or a motion area total area ratio; and the material type which can be determined according to the motion information is a third type, and the third type comprises cotton, terylene and cotton-polyester blended fabric.
In a preferred technical solution of the above identification control method, "converting the second dynamic video into a plurality of second images according to a second preset sampling period" specifically includes: and segmenting the second dynamic video according to the second preset sampling period, so that each obtained second image comprises a complete image of clothes in the second dynamic video.
In a preferred embodiment of the above identification control method, the step of "controlling the washing device to perform a water injection operation" includes: acquiring the volume of the clothes; determining a preset water level according to the volume; and injecting water into the washing equipment to the preset water level.
In a preferred embodiment of the above recognition control method, the recognition control method further includes: judging whether the clothes are suitable for washing according to the material type under the condition that the material type can be determined; and selectively recommending a washing program or sending prompt information according to the material type based on the judgment result.
In a preferred embodiment of the above identification control method, "selectively recommending a washing program or sending a prompt message according to the material type based on the determination result" includes:
if the clothes are suitable for water washing, recommending a washing and protecting program according to the material type; and/or if the laundry is not suitable for washing, sending a prompt message to prompt the user that the laundry is not suitable for washing.
In the preferred technical scheme of the identification control method, after the clothes are put into an inner barrel of the washing machine, a static image of the clothes in a static state is obtained; determining the material type of the clothes according to the static image; judging whether the material type can be determined according to the static image; controlling the inner barrel to rotate under the condition that the material type cannot be determined according to the static image; in the process of rotating the inner barrel, acquiring a first dynamic video of clothes in a rotating state; the material type is determined from the first dynamic video.
Compared with the technical scheme that material identification is only carried out once according to the image of the clothes no matter what type of material the clothes are made of in the prior art, the method determines the material type of the clothes according to the static image of the clothes in a static state, and determines the material type of the clothes for the first time; in the process, different types of materials are sequentially identified by different methods until the material types of the clothes are determined, the different types of materials can be identified in a targeted manner, the material types of the clothes can be accurately identified, the accuracy and precision of material type identification are improved, and further the user experience is improved.
Furthermore, the classification model is called to identify the static image, whether the material type of the clothes is woolen, wool, cashmere or down can be accurately identified according to the identification result, the material of the woolen, wool, cashmere and down can be identified in a targeted manner, and the accuracy and precision of identifying the material of the woolen, wool, cashmere and down are improved.
Furthermore, a preset model is called to analyze the first dynamic video, whether the material type can be determined or not is judged according to the analysis result, whether the material type of the clothes is the material type corresponding to the preset model or not can be accurately identified, and therefore the material type of the identified clothes is accurately determined; under the condition that the material type cannot be determined, the material type of the clothes is determined to be the type which cannot be accurately determined according to the static image and the first dynamic video, at the moment, the washing machine is controlled to execute water injection operation, after the washing machine injects water to a preset water level, the inner barrel is controlled to rotate, the second dynamic video of the clothes in a rotating state is obtained in the rotating process of the inner barrel, the material type is determined according to the second dynamic video, the material type of the clothes is determined for the third time, in the process, different methods are sequentially adopted for identifying specific material types until the material type of the clothes is determined, the material type of the clothes can be accurately identified, the accuracy and precision of material type identification are improved, and further user experience is improved.
Further, converting the first dynamic video into a plurality of first images according to a first preset sampling period; respectively preprocessing the plurality of first images to obtain target information of each first image; inputting all target information into a preset model; the preset model analyzes all target information, and the preset model can accurately identify whether the material type of the clothes is silk or not according to the analysis result because the material type which can be determined according to the target information is silk, so that the clothes material of silk can be identified in a targeted manner, and the accuracy and precision of silk material identification are improved.
Further, converting the second dynamic video into a plurality of second images according to a second preset sampling period; respectively determining the motion information of the clothes corresponding to each second image according to the plurality of second images; the material type is determined according to all the motion information, and the material type which can be determined according to the motion information comprises cotton, polyester and cotton-polyester blended fabric, so that whether the material type of the clothes is cotton, polyester or cotton-polyester blended fabric can be accurately identified according to the motion information, the material of the clothes comprising the cotton, polyester and cotton-polyester blended fabric can be identified in a targeted manner, and the accuracy and precision of identifying the cotton, polyester and cotton-polyester blended fabric are improved.
Furthermore, under the condition that the material type can be determined, the material type of the clothes is accurately identified, at the moment, whether the clothes are suitable for washing can be accurately judged according to the material type, and based on the judgment result, a washing program is selectively recommended or prompt information is sent according to the material type, so that the clothes are prevented from being washed under the condition that the clothes are not suitable for washing, the clothes are prevented from being damaged, and the user experience is further improved.
Drawings
The recognition control method of the present invention will be described with reference to the accompanying drawings in conjunction with a washing machine, in which:
FIG. 1 is a flow chart diagram 1 of an identification control method of the present invention;
FIG. 2 is a flow chart of a method of determining a texture type of a garment from a still image according to the present invention;
FIG. 3 is a first flowchart of a method for determining material type based on a first motion video according to the present invention;
FIG. 4 is a flowchart II of a method of determining material type based on a first motion video in accordance with the present invention;
FIG. 5 is a flowchart of a method of controlling a washing machine to perform a water filling operation according to the present invention;
FIG. 6 is a flow chart of a method of determining material types from a second motion video in accordance with the present invention;
FIG. 7 is a flow chart diagram 2 of the identification control method of the present invention;
FIG. 8 is a flow chart of the present invention for selectively recommending a wash program or sending a reminder;
fig. 9 is a logic diagram of the recognition control method of the present invention.
Detailed Description
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and are not intended to limit the scope of the present invention. For example, although the present application is described in conjunction with a washing machine, the technical solution of the present invention is not limited thereto, and the recognition control method can be obviously applied to other washing apparatuses such as a washing and drying machine, without departing from the principle and scope of the present invention.
It should be noted that the terms "first", "second" and "third" in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified and limited, the term "disposed" is to be understood broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Based on the technical problems proposed in the background art, the invention provides a material identification control method for a washing machine, which aims to determine the material type of clothes according to a static image of the clothes in a static state and determine the material type of the clothes for the first time; in the process, materials of different types are identified sequentially by different methods until the material types of the clothes are determined, the materials of different types can be identified in a targeted manner, the material types of the clothes can be identified accurately, the accuracy and precision of identifying the material types are improved, and further the user experience is improved.
Referring first to fig. 1, a material recognition control method for a washing machine of the present invention will be described. Fig. 1 is a flowchart 1 of an identification control method according to the present invention.
As shown in fig. 1, the material recognition control method for a washing machine of the present invention includes the steps of:
s100, after clothes are put into an inner barrel of a washing machine, obtaining a static image of the clothes in a static state;
s200, determining the material type of the clothes according to the static image;
s300, judging whether the material type can be determined according to the static image;
s400, controlling the inner barrel to rotate under the condition that the material type cannot be determined according to the static image;
s500, acquiring a first dynamic video of clothes in a rotating state in the rotating process of the inner barrel;
and S600, determining the material type according to the first dynamic video.
In step S100, a still image of the laundry in the inner tub is photographed by a photographing device such as a camera or a camera provided in the washing machine. It should be noted that, although the "tub" is used, the washing machine is not limited to the pulsator washing machine, and may be a drum washing machine.
In step S400, in order to further determine the material type of the laundry in the case where it is determined that the material type cannot be determined from the still image, the inner tub is controlled to rotate so that the photographing device photographs the first dynamic video of the laundry in a rotating state, so that the material type of the laundry is determined again from the first dynamic video in a non-water state.
In step S500, a first moving image of the laundry in the inner tub is captured by an imaging device such as a camera. For example, a first moving video of a first preset duration, such as 30s, 45s, or 60s, is captured.
Preferably, the material types of the clothes comprise three types, wherein the first type comprises materials with obvious appearance characteristics, such as woolen cloth, wool, cashmere, down feather and the like; the second type includes the great material of surface smoothness degree such as silk, and the third type includes cotton, dacron and cotton polyester blended spinning etc. and washes the class material, and the material of second type and third type all belongs to the fibre class, and when bucket rotated including this fibre class material, especially in the twinkling of an eye that the direction of rotation changed, because inertial action, the instantaneous motion state of the material of two kinds has obvious difference. Of course, the specific material types included in each type are not limited to the above listed material types, for example, the first type may also include rabbit hair, marten skin, etc., the second type may also include silk, etc., and the third type may also include cotton hemp, polyester fiber, etc., and the specific material types included in each type may be flexibly adjusted and set according to the actual material types and their performances in the field.
Based on the classification result, different methods are sequentially adopted to identify the characteristics of different materials until the material type of the clothes is determined, so that the accuracy and precision of material type identification are ensured.
Referring to fig. 2, a method of determining a material type of laundry according to a still image of the present invention will be described. Fig. 2 is a flowchart of a method for determining a texture type of a garment according to a still image according to the present invention.
As shown in fig. 2, the step of "determining the material type of the clothes according to the still image" in the step S200 specifically includes:
and S211, calling a classification model to identify the static image.
The classification model is a model which is preset on a washing machine and obtained by training according to image samples of clothing materials such as woolen cloth, wool, cashmere, down feather and fibers, and labels such as woolen cloth, wool labels, cashmere labels, down feather labels and fiber labels are marked on the image samples. That is to say, the classification model can identify the clothing materials of the woolen, the wool, the cashmere and the down in a targeted manner according to the first type of materials of the woolen, the wool, the cashmere and the down which can be determined by the static image, so that the accuracy and the precision of identifying the materials of the woolen, the wool, the cashmere and the down are improved; however, if the type of the clothing is silk, cotton, polyester, cotton-polyester blended fiber, the material of the clothing can only be determined to be fiber, but the specific material type cannot be determined. The classification model may be other classification models such as a sentet model, a Keras model, a VGG model, and an AtoC model, and no matter what classification model is adopted, the specific method for identifying the material corresponding to any one model should not limit the present invention.
With reference to fig. 2, in step S300, the step of determining whether the material type can be determined according to the still image includes:
s311, judging whether the material type belongs to a first type or not according to the identification result; if yes, go to step S312; if not, go to step S313;
s312, judging that the material type can be determined;
and S313, judging that the material type cannot be determined.
In step S312, if the material type belongs to the first type, it indicates that the material type of the clothes corresponding to the static image is one of woolen, wool, cashmere, or down, and the classification model can determine the material type of the clothes, that is, the woolen, the wool, the cashmere, or the down, according to the first type of materials of the woolen, the wool, the cashmere, and the down that can be determined by the static image.
In step S313, if the material type does not belong to the first type, it is indicated that the material type of the clothing corresponding to the static image is not woolen, wool, cashmere, or down, and may be other fiber materials such as silk, cotton, polyester, cotton-polyester blend, and the like, and the classification model can only determine that the material of the clothing is fiber, but cannot identify the specific material type of the clothing.
For example, in the above process, the similarity between the static image and the image sample of the material of the first type of clothing, such as woolen cloth, wool, cashmere, and down, may be calculated, and when the similarity is greater than a preset similarity (e.g. 95%), the label (e.g. wool label) corresponding to the image sample is determined as the material type of the clothing; when the similarity is less than or equal to the preset similarity, the label (e.g., woolen label) corresponding to the image sample is not determined as the material type of the clothing. Wherein, the similarity can be represented by Euler distance or cosine distance.
It should be noted that, in the above process, step S312 and step S313 do not have a sequence, are parallel, and are only related to the determination result of whether the material type belongs to the first type, and the corresponding step may be executed according to different determination results.
Referring to fig. 3 to 6, a method of determining a material type according to a first dynamic video and a second dynamic video of the present invention will be described. FIG. 3 is a flowchart 1 of a method for determining material types from a first dynamic video according to the present invention; FIG. 4 is a flow chart of a method of determining material types from a first motion video of the present invention 2; FIG. 5 is a flowchart of a method of controlling a washing machine to perform a water filling operation according to the present invention; FIG. 6 is a flow chart of a method of determining material types from a second motion video in accordance with the present invention.
As shown in fig. 3, in step S600, the step of "determining the material type according to the first dynamic video" specifically includes:
s611, calling a preset model to analyze the first dynamic video;
s612, judging whether the material type can be determined according to the analysis result;
s613, controlling the washing machine to execute water filling operation under the condition that the material type cannot be determined;
s614, controlling the inner barrel to rotate after the washing machine performs water injection operation;
s615, in the rotating process of the inner barrel, a second dynamic video of the clothes in a rotating state is obtained;
and S616, determining the material type according to the second dynamic video.
The preset model is a model which is preset on the washing machine and trained according to dynamic video samples of the second type and the third type of clothes rotating along with the inner barrel in a water-free state and target information samples of the clothes corresponding to the dynamic video samples. In the model training process, taking a pulsator washing machine as an example, dynamic video samples of the second type and the third type of clothes rotating along with an inner drum of the washing machine are shot when no water exists, and the videos are converted into pictures according to a set sampling period, such as 0.03s, 0.05s or 0.08 s. The outline of the clothes is identified by edge detection, the number of pixels in the outline of the clothes is related to the spread area of the clothes in the barrel, and the difference value of the pixels in the outline of two adjacent frames of pictures reflects the instantaneous deformation of the clothes. Because the camera is arranged above the inner barrel of the washing machine and is fixed in position, the circle center of the impeller can be positioned in the picture, some points in the outline of the clothes can be randomly selected, the average distance from each point to the circle center of the impeller can be calculated, and the distance is related to the size, weight and silk-slip degree of the clothes. And recording information such as a contour pixel number curve, an instantaneous change curve, an average distance between the contour pixel number curve and the circle center and the like when the second type and the third type are respectively placed in the washing machine to rotate without water, obtaining a preset model through training of a large amount of sample data, and distinguishing materials of the second type and the third type. And because the second type only comprises silk, the third type comprises cotton, terylene and cotton-polyester blended fabric, and the difference of instantaneous motion states of the cotton, terylene and cotton-polyester blended fabric is very small, whether the material type of the clothes is silk can be accurately determined, but if the material type of the clothes is the third type, only the material of the clothes can be determined to be cotton-polyester (namely the third type), but the specific material type cannot be determined.
That is to say, the preset model can determine the material type according to the first dynamic video of the clothes and the target information of the corresponding clothes and only comprises silk, so that whether the material type of the clothes is silk or not can be accurately identified, the material of the silk clothes can be identified in a targeted manner, and the accuracy and precision of silk material identification are improved.
The preset model may be a CNN model, a ResNet18 model, a ResNet101 model, a deplabv 3+ model, a ResNeXt model, an HRNet model, or other deep learning models or linear regression models, and no matter what model is adopted, the specific method for identifying the material corresponding to any model should not be any limitation to the present invention.
Wherein the target information comprises a contour pixel number curve of the clothes, an instantaneous change curve and an average distance of a circle center. Of course, the target information may also include any one or two of a contour pixel number curve, a temporal variation curve, and an average distance of the center of a circle of the laundry.
As shown in fig. 4, in step S611, the step of "calling the preset model to analyze the first dynamic video" includes:
s621, converting the first dynamic video into a plurality of first images according to a first preset sampling period;
s622, respectively preprocessing the plurality of first images to obtain target information of each first image;
s623, inputting all target information into a preset model;
s624, analyzing all target information by a preset model;
in step S621, the first preset sampling period corresponds to a set sampling period corresponding to the training preset model, for example, images are collected every 0.03S, 0.05S, or 0.08S, and the first dynamic video is converted into a plurality of first images, such as 10, 20, or 30 images. Of course, the first preset sampling period may be different from the corresponding set sampling period when the preset model is trained, and is not listed here.
In step S622, a preset model is used to respectively pre-process the plurality of first images, so as to obtain target information of each first image. The method specifically comprises the following steps: identifying clothes in each first image and the outlines of the clothes in the images, and determining target information according to the outlines, wherein the target information comprises the number curve of pixels of the outlines of the clothes, the instantaneous change curve and the average distance of the circle center. It should be noted that the content specifically included in the target information is consistent with the specific content of the target information when the preset model is trained, and is changed according to the change of the specific content of the target information when the preset model is trained.
Continuing to refer to fig. 4, in step S612, the step of determining whether the material type can be determined according to the analysis result includes:
s631, judging whether the material type belongs to a second type; if yes, go to step S632; if not, go to step S633;
s632, judging that the material type can be determined;
and S633, judging that the material type cannot be determined.
In step S631, comparing the target information such as the contour pixel number curve, the instantaneous change curve, and the average distance between the centers of circles of the clothes with the target information samples stored in the preset model one by one, and determining whether there is a target information sample completely or substantially consistent with the target information in the preset model, if yes, determining the material type corresponding to the target information sample completely or substantially consistent with the target information as the material type of the clothes, for example, the second type; if not, the material type corresponding to the target information sample completely or basically consistent with the target information is not determined as the material type of the clothes. The substantial agreement may be an agreement degree of 90%, 95%, or the like.
In step S632, if the material type belongs to the second type, it indicates that the material type of the clothing corresponding to the first dynamic video is silk, and the preset model can determine the material type of the clothing, that is, silk, because the material type that can be determined according to the first dynamic video of the clothing and the target information of the corresponding clothing only includes silk.
In step S633, if the material type does not belong to the second type, it is indicated that the material type of the clothing corresponding to the first dynamic video is not silk, and may be a third type such as cotton, polyester, and cotton-polyester blend, and the preset model can only determine that the material of the clothing is cotton-polyester (i.e., the third type), but cannot determine the specific material type, and thus cannot identify the specific material type of the clothing.
In the above process, step S632 and step S633 are not in sequence, and are parallel, and only related to the determination result of whether the material type belongs to the second type, and the corresponding step may be executed according to different determination results.
As shown in fig. 5, the step of "controlling the washing machine to perform the water filling operation" in step S613 specifically includes:
s641, obtaining the volume of the clothes;
s642, determining a preset water level according to the volume;
and S643, filling water into the washing machine to a preset water level.
Correspondingly, in step S614, after the washing machine is filled with water to the preset water level, the inner tub is controlled to rotate.
Or, in an alternative embodiment, the weight of the clothes can be obtained, and the preset water level can be determined according to the weight; alternatively, the preset water level may be determined according to a set washing program, and the preset water level may be determined in any manner as long as the preset water level can be determined to fill the washing machine with water up to the preset water level.
In step S613 to step S616, in order to further determine the material type of the laundry in the case where it is determined that the material type cannot be determined, the washing machine is controlled to perform the water filling operation, and the inner tub is controlled to rotate, so that the photographing device photographs the second dynamic video of the laundry in a rotating state, so as to determine the material type again based on the second dynamic video of the water state.
Further, a second dynamic video of the laundry in the inner tub is photographed by a photographing device such as a camera, a camcorder, etc. For example, a second dynamic video of a second preset duration, such as 20s, 40s, or 60s, is captured.
As shown in fig. 6, in step S616, the step of "determining the material type according to the second dynamic video" specifically includes:
s651, converting the second dynamic video into a plurality of second images according to a second preset sampling period;
s652, respectively determining the motion information of the clothes corresponding to each second image according to the plurality of second images;
and S653, determining the material type according to all the motion information.
Wherein the motion information includes a centroid average speed of the laundry and a total area of the motion region. Of course, the motion information may include only the centroid average speed or the total area of the motion region of the laundry.
The material type which can be determined according to the second dynamic video and the motion information comprises cotton, terylene and cotton-polyester blended fabric.
In step S651, the second dynamic video is segmented according to a second preset sampling period, so that each obtained second image includes a complete image of the clothing in the second dynamic video. The second preset sampling period may be to cut the image every 0.02s, 0.04s, or 0.05s, etc., and convert the second dynamic video into a plurality of second images, such as 5, 15, 25, or 35, etc., where each second image includes a complete image of the clothing.
In step S652, the centroid average speed and the total area ratio of the moving region are calculated in the following manner.
The centroid average speed calculation method comprises the following steps: and respectively estimating the position of the mass center of the clothes through the segmented region of the same clothes in each second image, solving the coordinate difference of the corresponding position of the mass center in two adjacent frames of images, further solving the motion distance of the mass center, determining the interval time of the two frames of images according to a second preset sampling period, and solving the average velocity v of the mass center according to the motion distance d of the mass center and the interval time t, namely v = d/t.
The method for calculating the total area ratio of the motion area comprises the following steps: defining a blank image, supposing that the gray value of each pixel point of the blank image is 0, sequentially overlapping the divided second images on the blank image according to the original positions of the divided second images from the first frame second image obtained by sampling, calculating the number of pixels with the gray value not being 0 after the overlapping is finished, and dividing the number of pixels by the total number of pixels to obtain the area ratio of the motion area.
Respectively calculating the average speed of the center of mass of the clothes and the total area ratio of the motion area according to the method, wherein the calculated average speed of the center of mass of the clothes is 0.409m/s, and the total area ratio of the motion area of the clothes is 0.468%; for another example, the calculated average speed of the mass center of the clothes is 0.441m/s, and the total area of the motion area of the clothes is 0.491%; as another example, the calculated average speed of the center of mass of the laundry is 0.408m/s, and the total area occupying ratio of the motion region of the laundry is 0.591%.
In step S653, the material type is determined according to all the motion information, and the determined material type is cotton, polyester, or cotton-polyester blended fabric. For example, if the average speed of the center of mass of the clothes calculated in step S652 is 0.409m/S, the area ratio of the motion area of the cotton is 0.468%, and the calculated average speed of the center of mass of the clothes is respectively matched with the first preset average speed of the center of mass of the cotton, which is 0.41m/S, and the area ratio of the first preset motion area of the cotton, which is 0.47%, the type of the clothes is determined to be cotton; if the average speed of the center of mass of the clothes calculated in step S652 is 0.441m/S, and the total area percentage of the motion area of the clothes is 0.491%, which are respectively matched with the second preset average speed of the center of mass of the terylene 0.44m/S, and the area percentage of the second preset motion area of the terylene 0.49%, it is determined that the material type of the clothes is the terylene; for another example, if the average speed of the center of mass of the clothes calculated in step S652 is 0.411m/S, the total area percentage of the movement area of the clothes is 0.591%, the third preset average speed of the center of mass of the clothes blended with cotton and polyester is 0.41m/S, and the third preset movement area percentage of the cotton and polyester is 0.59%, the material type of the clothes is determined to be cotton and polyester.
Namely, the material type of the clothes is determined by respectively adopting different methods through the static image, the first dynamic video and the second dynamic video in sequence, and the material type of the clothes is finally determined to be cotton, terylene or cotton-polyester blended fabric, so that the accuracy and precision of material type identification are improved, and further the user experience is improved.
Further, if the material type of the laundry belongs to the first type, the material type of the laundry, such as wool, can be determined through the still image of the laundry, and the recognition of the material type of the laundry is performed only once.
If the material type of the clothes belongs to the second type, firstly, the material type of the clothes is determined not to belong to the first type through the static image of the clothes, secondly, the material type of the clothes is determined through the first dynamic video of the clothes in a water-free state, for example, silk, and the material type of the clothes is identified twice.
If the material type of the clothes belongs to the third type, the material type of the clothes is determined not to belong to the first type through a static image of the clothes, the material type of the clothes is determined not to belong to the second type through a first dynamic video of the clothes in a water-free state, and the material type of the clothes is determined through a second dynamic video of the clothes in a water-containing state, for example, cotton, and the material type of the clothes is identified for three times.
The recognition control method of the present invention is further described with reference to fig. 7 and 8. FIG. 7 is a flow chart 2 of the identification control method of the present invention; FIG. 8 is a flow chart of the present invention for selectively recommending a wash program or sending a reminder message.
As shown in fig. 7, in the case where it is determined that the material type can be determined, the recognition control method further includes:
s700, judging whether the clothes are suitable for washing according to the material type;
and S800, selectively recommending a washing and caring program or sending prompt information according to the material type based on the judgment result.
Under the condition that the material type can be determined, the material type of the clothes is accurately identified, at the moment, whether the clothes are suitable for washing or not can be accurately judged according to the material type, and based on the judgment result, the washing and protecting program is selectively recommended or prompt information is sent according to the material type, so that the clothes are prevented from being washed under the condition that the clothes are not suitable for washing, the clothes are prevented from being damaged, and the user experience is further improved.
As shown in fig. 8, in step S800, the step of "selectively recommending a washing program or sending a prompt message according to the material type based on the determination result" specifically includes:
s811, if the clothes are suitable for water washing, recommending a washing and protecting program according to the material type;
and S812, if the clothes are not suitable for washing, sending a prompt message to prompt the user that the clothes are not suitable for washing.
In step S811, if the laundry is suitable for water washing, indicating that the material of the laundry is a material that does not cause damage to the laundry when washed with water, such as cotton, polyester, and a blend of cotton and polyester, a washing and care program is recommended according to the material type.
In step S812, if the clothes are not suitable for washing, it indicates that the material of the clothes is a material that damages the clothes due to washing with water, such as silk, woolen cloth, wool, cashmere, and down, and in order to avoid damaging the clothes, a prompt message is sent to prompt the user that the clothes are not suitable for washing.
Furthermore, prompt information can be sent to intelligent terminals such as mobile phones, tablet computers, intelligent bracelets, intelligent watches and the like in the forms of characters, pictures, animations and the like; or the prompting module can directly send prompting information in the forms of voice, characters, pictures, animation and the like.
In the above process, step S700 is not in sequence with step S400 and step S613 respectively, and is parallel to step S400, and only needs to be related to the determination result of whether the material type of the laundry is determined, and the corresponding step is executed according to different determination results. Step S811 and step S812 have no sequence, are parallel, and are only related to the determination result of whether the laundry is suitable for washing, and corresponding steps are executed according to different determination results.
One possible control flow of the present invention is described below with reference to fig. 9. Fig. 9 is a logic diagram of the recognition control method of the present invention.
As shown in fig. 9, one possible complete flow of the recognition control method of the present invention is:
s901, after clothes are put into an inner barrel of the washing machine, obtaining static images of the clothes in a static state;
s902, calling a classification model to identify the static image;
s903, judging whether the material type belongs to a first type according to the identification result; if not, executing step S904; if yes, go to step S916;
s904, judging that the material type cannot be determined;
step S905 is performed after step S904;
s905, controlling the inner barrel to rotate, and acquiring a first dynamic video of clothes in a rotating state in the rotating process of the inner barrel;
s906, converting the first dynamic video into a plurality of first images according to a first preset sampling period;
s907, respectively preprocessing the plurality of first images to obtain target information of each first image; the target information comprises a contour pixel number curve of the clothes, an instantaneous change curve and an average distance of a circle center;
s908, inputting all target information into a preset model;
s909, analyzing all target information by a preset model;
s910, judging whether the material type belongs to a second type or not according to the analysis result; if not, executing step S911; if yes, go to step S916;
s911, judging that the material type cannot be determined;
step S912 is executed after step S911;
s912, injecting water into the washing machine to a preset water level, controlling the inner barrel to rotate after the washing machine executes water injection operation, and acquiring a second dynamic video of the clothes in a rotating state in the rotating process of the inner barrel;
s913, converting the second dynamic video into a plurality of second images according to a second preset sampling period;
s914, respectively determining the motion information of the clothes corresponding to each second image according to the plurality of second images; wherein the motion information comprises the average speed of the mass center of the clothes and the total area of the motion area;
s915, determining the material type, such as cotton, according to all the motion information;
s916, judging that the material type can be determined; for example, in step S903, it is determined that the material type can be specified, and the specified material type is wool; in step S910, it is determined that the material type can be determined, and the determined material type is silk;
after step S915 or S916, step S917 is performed;
s917, judging whether the clothes are suitable for washing according to material types; if yes, go to step S918; if not, go to step S919;
s918, recommending a washing and caring program according to the material type;
and S919, sending a prompt message to prompt the user that the clothes are not suitable for washing.
It should be noted that the above-mentioned embodiment is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and in practical applications, those skilled in the art may perform the above-mentioned function allocation by different steps, i.e. the steps in the embodiment of the present invention are further divided or combined as needed. For example, the steps of the above embodiments may be combined into one step, or further divided into multiple sub-steps to complete all or part of the functions described above. For the names of the steps involved in the embodiments of the present invention, they are only for distinguishing the respective steps, and are not to be construed as limiting the present invention.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (10)
1. A material identification control method for washing equipment is characterized by comprising the following steps:
acquiring a static image of the laundry in a static state after the laundry is put into an inner tub of the washing apparatus;
determining the material type of the clothes according to the static image;
judging whether the material type can be determined according to the static image;
controlling the inner barrel to rotate under the condition that the material type cannot be determined according to the static image;
acquiring a first dynamic video of clothes in a rotating state in the process of rotating the inner barrel;
determining the material type from the first dynamic video.
2. The identification control method according to claim 1, wherein the step of determining the type of material of the clothing based on the static image specifically comprises:
calling a classification model to identify the static image;
the step of "judging whether the material type can be determined according to the static image" specifically includes:
judging whether the material type belongs to a first type or not according to the identification result;
determining that the material type can be determined if the material type belongs to the first type; and/or
If the material type does not belong to the first type, determining that the material type cannot be determined;
the classification model is the first type according to the material type which can be determined by the static image, and the first type comprises woolen cloth, wool, cashmere and down.
3. The recognition control method according to claim 1, wherein the step of determining the material type according to the first dynamic video specifically comprises:
calling a preset model to analyze the first dynamic video;
judging whether the material type can be determined or not according to the analysis result;
controlling the washing equipment to execute water injection operation under the condition that the material type cannot be determined;
controlling the inner tub to rotate after the washing apparatus performs a water filling operation;
acquiring a second dynamic video of clothes in a rotating state in the process of rotating the inner barrel;
determining the material type from the second dynamic video.
4. The recognition control method according to claim 3, wherein the step of "calling a preset model to analyze the first dynamic video" specifically comprises:
converting the first dynamic video into a plurality of first images according to a first preset sampling period;
respectively preprocessing the plurality of first images to obtain target information of each first image;
inputting all the target information into the preset model;
the preset model analyzes all the target information;
the step of determining whether the material type can be determined according to the analysis result specifically includes:
judging whether the material type belongs to a second type;
determining that the material type can be determined if the material type is of the second type; and/or
If the material type does not belong to the second type, determining that the material type cannot be determined;
and the material type which can be determined by the preset model according to the target information is the second type, and the second type comprises silk.
5. The recognition control method according to claim 4, wherein the step of "respectively preprocessing the plurality of first images to obtain the target information of each of the first images" specifically includes:
identifying the clothes in each first image and the outline of the clothes in the image;
determining the target information according to the contour;
wherein the target information includes at least one of a contour pixel number curve, an instantaneous change curve, and an average distance of a circle center of the laundry.
6. The recognition control method according to claim 3, wherein the step of determining the material type according to the second dynamic video specifically comprises:
converting the second dynamic video into a plurality of second images according to a second preset sampling period;
respectively determining the motion information of the clothes corresponding to each second image according to the plurality of second images;
determining the material type according to all the motion information;
wherein the motion information comprises a centroid average speed and/or a motion area total area ratio;
and the material type which can be determined according to the motion information is a third type, and the third type comprises cotton, terylene and cotton-polyester blended fabric.
7. The recognition control method according to claim 6, wherein the step of converting the second dynamic video into a plurality of second images according to a second preset sampling period specifically comprises:
and segmenting the second dynamic video according to the second preset sampling period, so that each obtained second image comprises a complete image of clothes in the second dynamic video.
8. The identification control method according to claim 3, wherein the step of controlling the washing apparatus to perform the water filling operation specifically comprises:
acquiring the volume of the clothes;
determining a preset water level according to the volume;
and injecting water into the washing equipment to the preset water level.
9. The recognition control method according to any one of claims 1 to 8, characterized by further comprising:
judging whether the clothes are suitable for washing according to the material type under the condition that the material type can be determined;
and selectively recommending a washing program or sending prompt information according to the material type based on the judgment result.
10. The identification control method according to claim 9, wherein the step of selectively recommending a washing program or sending a prompt message according to the material type based on the determination result specifically includes:
if the clothes are suitable for water washing, recommending a washing and protecting program according to the material type; and/or
And if the clothes are not suitable for washing, sending prompt information to prompt the user that the clothes are not suitable for washing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110949255.2A CN115897130A (en) | 2021-08-18 | 2021-08-18 | Material identification control method for washing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110949255.2A CN115897130A (en) | 2021-08-18 | 2021-08-18 | Material identification control method for washing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115897130A true CN115897130A (en) | 2023-04-04 |
Family
ID=86486876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110949255.2A Pending CN115897130A (en) | 2021-08-18 | 2021-08-18 | Material identification control method for washing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115897130A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117273769A (en) * | 2023-08-15 | 2023-12-22 | 青岛美瑞泰洗涤服务科技有限公司 | Clothing data collection and analysis method and system |
| CN117273769B (en) * | 2023-08-15 | 2024-06-07 | 青岛美瑞泰洗涤服务科技有限公司 | Clothing data collection and analysis method and system |
-
2021
- 2021-08-18 CN CN202110949255.2A patent/CN115897130A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117273769A (en) * | 2023-08-15 | 2023-12-22 | 青岛美瑞泰洗涤服务科技有限公司 | Clothing data collection and analysis method and system |
| CN117273769B (en) * | 2023-08-15 | 2024-06-07 | 青岛美瑞泰洗涤服务科技有限公司 | Clothing data collection and analysis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107354662B (en) | Device for clothing processing and its control method, device and computer readable storage medium | |
| CN103820971B (en) | A kind of intelligence of the washing machine based on wireless automatic identification technology washing methods | |
| CN106868792A (en) | The clothes processing method and device of image content-based search engine | |
| CN109137388B (en) | Laundry washing method, apparatus and laundry treating apparatus | |
| CN107904856B (en) | Washing machine starting method and device | |
| KR20170110658A (en) | Determination of the color value of the textile article | |
| CN107904860B (en) | Method and device for treating clothes in washing machine | |
| CN107974799A (en) | A kind of method and washing machine of intelligent recognition washing clothing | |
| CN108876934A (en) | Key point mask method, device and system and storage medium | |
| Kaur et al. | Facial Emotion Recognition | |
| CN109594288A (en) | A kind of laundry process, system and washing machine | |
| CN110069983A (en) | Vivo identification method, device, terminal and readable medium based on display medium | |
| CN109610132A (en) | Laundry process, device and controller | |
| CN113160966A (en) | Tongue picture diagnosis method and tongue picture diagnosis system based on multi-task learning | |
| CN108875709A (en) | One kind flocks together behavioral value method, apparatus, electronic equipment and storage medium | |
| CN115897130A (en) | Material identification control method for washing equipment | |
| CN109086696A (en) | A kind of anomaly detection method, device, electronic equipment and storage medium | |
| CN113159876B (en) | Clothing collocation recommendation device, method and storage medium | |
| KR102208690B1 (en) | Apparatus and method for developing style analysis model based on data augmentation | |
| CN116630500A (en) | Virtual article generation method, virtual clothing generation method and electronic device | |
| CN113463327B (en) | Clothing display method and device, electronic equipment and computer readable storage medium | |
| CN115082669A (en) | Garment fabric recommendation method and device, electronic equipment and storage medium | |
| CN110796645A (en) | Certificate photo quality evaluation method, storage medium and processor | |
| CN110189296B (en) | Method and equipment for marking reflecting state of blood vessel wall of fundus image | |
| CN113201905A (en) | Clothes volume estimation method and control method of clothes treatment equipment and clothes treatment system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |