Eccentricity detection method and device, clothes processing equipment and storage medium

Abstract

The invention relates to an eccentricity detection method and device, clothes processing equipment and a storage medium. The method comprises the steps that when the clothes processing equipment is in the dewatering process, the current image of each target barrel is obtained, and the current image comprises three sets of light-emitting objects of different colors on the outer wall of an outer barrel of the target barrel; and determining the current eccentricity of the target cylinder according to the current image. Therefore, according to the two-dimensional image containing the luminous object on the outer wall of the outer cylinder, the eccentricity of the cylinder body can be detected in real time in the dewatering process of the clothes treatment equipment, the detection precision is improved, the risk that the cylinder body impacts the box body in the high-rotating-speed dewatering stage is reduced, normal use of the clothes treatment equipment is guaranteed, and the clothes treatment equipment is convenient to use. And the service life of the clothes processing equipment is prolonged. Besides, the method is not only suitable for eccentricity detection of single-drum clothes processing equipment, but also suitable for eccentricity detection of multi-drum clothes processing equipment, and eccentricity detection of one or more drums in the multi-drum clothes processing equipment can be achieved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of clothing processing equipment, and in particular to an eccentricity detection method, device, clothing processing equipment and storage medium. Background Art

[0002] In the related art, when washing machines, dryers and other clothing processing equipment are dehydrating, the uneven distribution of clothes can easily cause eccentricity inside the clothing processing equipment, causing the drum of the clothing processing equipment to hit the box body and affect the use and life of the clothing processing equipment. At present, tension sensors, motor magnetic moment sensors, lasers and gravity sensors are usually used to detect the eccentricity of the drum wall of the clothing processing equipment in the dehydration state. The eccentricity cannot be accurately located, and the detection takes a long time. There is a greater risk of dehydration accelerating the drum to hit the box body. Therefore, how to better detect the eccentricity of clothing processing equipment has become an urgent problem to be solved. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides an eccentricity detection method, device, clothing processing equipment and storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, there is provided an eccentricity detection method, which is applied to a clothes processing device, wherein the clothes processing device comprises at least one drum, and three groups of luminous objects of different colors are arranged on the outer wall of the outer drum of each drum;

[0005] The method comprises:

[0006] When the clothes processing device is in the dehydration process, for each target cylinder, a current image of the target cylinder is acquired, wherein the target cylinder is a cylinder whose inner cylinder is in a rotating state, and the current image includes the three groups of luminous objects of different colors on the outer wall of the outer cylinder of the target cylinder;

[0007] According to the current image, the current eccentricity of the target cylinder is determined.

[0008] Optionally, determining the current eccentricity of the target cylinder according to the current image includes:

[0009] Determine the current pixel spacing corresponding to the target barrel according to the current image, wherein the current pixel spacing includes the current longitudinal pixel distance between two groups of reference points and the current pixel offset of the target barrel, and the two groups of reference points are two preset groups of luminous objects among the three groups of luminous objects of different colors on the outer wall of the outer barrel of the target barrel;

[0010] Determine the target distance displacement corresponding to the current pixel spacing according to the pre-constructed target correspondence relationship between the pixel spacing and the distance displacement of the target cylinder, wherein the distance displacement includes: a reference distance between the target cylinder and the image acquisition device on the target axis of the world coordinate system, and a reference offset of the target cylinder on the axis other than the target axis of the world coordinate system, and the image acquisition device is used to acquire the image of the target cylinder in real time during the dehydration process;

[0011] The current eccentricity of the target cylinder is determined according to the target distance displacement.

[0012] Optionally, the target correspondence relationship is constructed in the following manner:

[0013] Determine a reference correspondence between the longitudinal pixel distance between the two groups of reference points and the reference distance according to the triangle similarity principle in the imaging process of the image acquisition device;

[0014] For each of the reference distances in the reference correspondence, determining a first pixel offset caused by different degrees of reference offsets of the target barrel on a second axis when the target barrel has not been offset on the first axis and the distance between the target barrel and the image acquisition device on the target axis is the reference distance, wherein the other axes include the first axis and the second axis; for each of the different degrees of reference offsets on the second axis, determining a second pixel offset caused by different degrees of reference offsets of the target barrel on the first axis when the target barrel has the reference offset on the second axis and the distance between the target barrel and the image acquisition device on the target axis is the reference distance;

[0015] The target corresponding relationship is constructed according to the reference corresponding relationship, each of the first pixel offsets, and each of the second pixel offsets.

[0016] Optionally, determining a current pixel spacing corresponding to the target cylinder according to the current image includes:

[0017] Performing color channel separation on the current image to obtain a first color channel image and a second color channel image, wherein the color of the color channel corresponding to the first color channel image is the color of one set of reference points in the two sets of reference points, and the color of the color channel corresponding to the second color channel image is the color of the other set of reference points in the two sets of reference points;

[0018] Determining a current longitudinal pixel distance between the two groups of reference points according to the first color channel image and the second color channel image;

[0019] The current pixel offset of the target drum is determined according to the pixel offset between the current image and a reference image, wherein the reference image is an image of the target drum captured by the image acquisition device when the laundry processing device is in a non-working state.

[0020] Optionally, determining the current longitudinal pixel distance between the two groups of reference points according to the first color channel image and the second color channel image includes:

[0021] Binarizing the first color channel image to obtain a first binary image, and binarizing the second color channel image to obtain a second binary image;

[0022] A longitudinal pixel distance between a set of reference points in the first binary image and a set of reference points in the second binary image is determined as a current longitudinal pixel distance between the two sets of reference points.

[0023] Optionally, the binarization processing of the first color channel image includes:

[0024] Obtaining a target segmentation threshold of a color channel corresponding to the first color channel image;

[0025] The first color channel image is binarized according to the target segmentation threshold.

[0026] Optionally, the target segmentation threshold is predetermined by:

[0027] Performing color channel separation on the reference image to obtain a third color channel image, wherein the color channel corresponding to the third color channel image is the same as the color channel corresponding to the first color channel image;

[0028] The target segmentation threshold is determined by using a maximum inter-class variance method according to the color intensity of each pixel in the third color channel image.

[0029] Optionally, determining the target segmentation threshold by using a maximum inter-class variance method according to the color intensity of each pixel in the third color channel image includes:

[0030] For each preset segmentation threshold among multiple preset segmentation thresholds, determine the pixel ratio of the first target pixel in the third color channel image, the average color intensity of all the first target pixels, and the average color intensity of all the second target pixels according to the preset segmentation threshold and the color intensity of each pixel in the third color channel image, wherein the color intensity of the first target pixel is greater than the preset segmentation threshold, and the color intensity of the second target pixel is less than or equal to the preset segmentation threshold; determine the variance corresponding to the preset segmentation threshold according to the pixel ratio, the average color intensity of all the first target pixels, the average color intensity of all the second target pixels, and the average color intensity of the third color channel image;

[0031] The preset segmentation threshold corresponding to the maximum value among all the variances is determined as the target segmentation threshold.

[0032] Optionally, before the step of determining the longitudinal pixel distance between a group of reference points in the first binary image and a group of reference points in the second binary image, determining the current longitudinal pixel distance between the two groups of reference points according to the first color channel image and the second color channel image further includes:

[0033] performing compression processing on the first binary image and the second binary image respectively;

[0034] Determining the longitudinal pixel distance between a set of reference points in the first binary image and a set of reference points in the second binary image comprises:

[0035] The longitudinal pixel distance between a group of reference points in the first binary image obtained after the compression process and a group of reference points in the second binary image obtained after the compression process is determined.

[0036] Optionally, the method further comprises:

[0037] determining whether the laundry processing device is eccentric according to the current eccentricity of each target drum;

[0038] If the clothes processing device is eccentric, the clothes processing device is controlled to enter an eccentricity processing process.

[0039] According to a second aspect of an embodiment of the present disclosure, there is provided an eccentricity detection device, which is applied to a clothes processing device, wherein the clothes processing device comprises at least one drum, and three groups of luminous objects of different colors are arranged on the outer wall of the outer drum of each drum;

[0040] The eccentricity detection device comprises:

[0041] an acquisition module, configured to acquire, for each target cylinder, a current image of the target cylinder when the clothes processing device is in a dehydration process, wherein the target cylinder is a cylinder whose inner cylinder is in a rotating state, and the current image includes the three groups of luminous objects of different colors on the outer wall of the outer cylinder of the target cylinder;

[0042] The first determination module is configured to determine the current eccentricity of the target cylinder according to the current image.

[0043] According to a third aspect of an embodiment of the present disclosure, there is provided a clothes processing device, comprising:

[0044] At least one cylinder, each of which has three groups of luminous objects of different colors arranged on its outer wall;

[0045] Processor; and

[0046] a memory for storing processor-executable instructions;

[0047] Wherein, the processor is configured to:

[0048] When the clothes processing device is in the dehydration process, for each target cylinder, a current image of the target cylinder is acquired, wherein the target cylinder is a cylinder whose inner cylinder is in a rotating state, and the current image includes the three groups of luminous objects of different colors on the outer wall of the outer cylinder of the target cylinder;

[0049] According to the current image, the current eccentricity of the target cylinder is determined.

[0050] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored, and when the program instructions are executed by a processor, the steps of the eccentricity detection method provided in the first aspect of the present disclosure are implemented.

[0051] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: during the dehydration process of the clothing processing device, for each cylinder whose inner cylinder is in a rotating state, an image of three groups of luminous objects of different colors arranged on the outer wall of the outer cylinder containing the cylinder can be obtained, and then the eccentricity of the cylinder can be detected based on the image. In this way, based on the two-dimensional image of the luminous object on the outer wall of the outer cylinder containing the cylinder, the eccentricity of the cylinder can be detected in real time during the dehydration process of the clothing processing device. Compared with the one-dimensional linear detection method in the related art, the detection accuracy is improved, thereby reducing the risk of the cylinder hitting the box during the high-speed dehydration stage, ensuring the normal use of the clothing processing device, and extending the service life of the clothing processing device. In addition, the above-mentioned eccentricity detection method is not only applicable to the eccentricity detection of single-drum clothing processing equipment, but also applicable to the eccentricity detection of multi-drum clothing processing equipment, and can realize the eccentricity detection of one or more cylinders in the dehydration state in the multi-drum clothing processing equipment.

[0052] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0054] Figure 1 It is a schematic structural diagram of a clothes processing device according to an exemplary embodiment.

[0055] Figure 2 is a flow chart of an eccentricity detection method according to an exemplary embodiment.

[0056] Figure 3 The diagram is a schematic diagram showing a reference corresponding relationship between a longitudinal pixel distance between two groups of reference points and a reference distance according to an exemplary embodiment.

[0057] Figure 4A is a current image of a target cylinder according to an exemplary embodiment.

[0058] Figure 4B yes Figure 4A The first color channel image corresponding to the current image shown.

[0059] Figure 4C yes Figure 4A The second color channel image corresponding to the current image shown.

[0060] Figure 4D Yes Figure 4CThe first binary image shown is obtained after the first color channel image is binarized.

[0061] Figure 4E Yes Figure 4D The second binary image shown is obtained after the second color channel image is binarized.

[0062] Figure 5 is a schematic diagram showing a longitudinal pixel distance according to an exemplary embodiment.

[0063] Figure 6 is a block diagram of an eccentricity detection device according to an exemplary embodiment.

[0064] Figure 7 is a block diagram of a clothes treating apparatus according to an exemplary embodiment. DETAILED DESCRIPTION

[0065] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0066] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0067] Before introducing the eccentricity detection method of the laundry processing device, the structure of the laundry processing device is first described. Specifically, the laundry processing device may include a housing and at least one drum, and three groups of luminous objects of different colors are arranged on the outer wall of the outer drum of each drum.

[0068] In the present disclosure, the clothing processing equipment may be a washing machine, a clothes dryer, etc., wherein the washing machine may be a pulsator washing machine or a drum washing machine, which is not specifically limited in the present disclosure. The above-mentioned cylinder includes an inner cylinder and an outer cylinder, wherein the outer cylinder is sleeved on the outer circumference of the inner cylinder, and the luminous object may be a fluorescent stone, a fluorescent light source, etc. Three groups of luminous objects of different colors are arranged on the outer wall of the outer cylinder of each cylinder of the clothing processing equipment, wherein the number of luminous objects contained in each group of the three groups of luminous objects is the same, and the number of luminous objects in each group may be one or more. By way of example, the colors of the three groups of luminous objects are red, green and blue, respectively.

[0069] For example, Figure 1As shown, the above-mentioned clothing processing device is a double-drum washing machine, which specifically includes two drums, an upper drum and a lower drum, wherein three groups of fluorescent stones of different colors are arranged on the outer walls of the outer drums of the upper drum and the lower drum, each group contains 3 fluorescent stones, and these three groups of fluorescent stones of different colors constitute a fluorescent stone array.

[0070] Figure 2 FIG. 1 is a flow chart showing a method for detecting eccentricity according to an exemplary embodiment, wherein the method can be applied to a clothes processing device. Figure 2 As shown, the above eccentricity detection method may include the following S201 and S202.

[0071] In S201, when the clothes treating apparatus is in a dehydration process, for each target drum, a current image of the target drum is acquired.

[0072] In the present disclosure, the target drum is a drum whose inner drum is in a rotating state. When the clothing processing device includes one drum, for example, a single-drum washing machine, a single-drum clothes dryer, etc., the inner drum of the one drum rotates during the dehydration process, that is, the one drum is the target drum, and in this case, the target drum is one. When the clothing processing device includes multiple drums, the inner drums of the multiple drums can rotate simultaneously during the dehydration process, or the inner drums of some of the drums can rotate. For example, the clothing processing device is a double-drum washing machine. During the dehydration process, the inner drums of the double drums can rotate simultaneously, or the inner drum of only one drum can rotate. In this case, the target drum is one or more.

[0073] The current image of the target cylinder includes three groups of luminous objects of different colors on the outer wall of the outer cylinder of the target cylinder.

[0074] Since the light inside the cavity of the clothing processing equipment is usually dim, a luminous object that can emit light independently can be set on the outer wall of the outer cylinder of each cylinder, and then the luminous object on the outer wall of the outer cylinder of the cylinder can be photographed to achieve the positioning of the cylinder based on the photographed image containing the luminous object.

[0075] During the dehydration process, the image of the target cylinder can be collected in real time by an optical flow sensor, camera or other image acquisition device arranged on the inner wall of the outer shell of the clothing processing device. When the clothing processing device includes multiple cylinders, each cylinder can be respectively provided with a corresponding image acquisition device for acquiring the image of the corresponding cylinder. At this time, the image of the cylinder includes three groups of luminous objects of different colors on the outer wall of the outer cylinder of the cylinder. Of course, in order to save the equipment cost and processing flow of the clothing processing device, multiple cylinders can share one image acquisition device, that is, the image acquisition device is used to simultaneously acquire images including luminous objects on multiple cylinders. At this time, the acquired image simultaneously includes three groups of luminous objects of different colors on the outer wall of the outer cylinder of each cylinder.

[0076] For example, Figure 1 As shown, the above-mentioned clothing processing device is a double-drum washing machine. A wide-angle camera is arranged on the inner wall of the double-drum washing machine shell. The wide-angle camera is used to simultaneously photograph the upper drum fluorescent stone array and the lower drum fluorescent stone array. The obtained image is as shown in FIG. Figure 4A shown.

[0077] In S202, the current eccentricity of the target cylinder is determined according to the current image.

[0078] In the present disclosure, the current eccentricity of the target drum refers to the offset of the current three-dimensional spatial position of the target drum relative to the three-dimensional spatial position of the target drum when the target drum is in a stationary state (ie, the laundry processing device is in a non-working state).

[0079] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: during the dehydration process of the clothing processing device, for each cylinder whose inner cylinder is in a rotating state, an image of three groups of luminous objects of different colors arranged on the outer wall of the outer cylinder containing the cylinder can be obtained, and then the eccentricity of the cylinder can be detected based on the image. In this way, based on the two-dimensional image of the luminous object on the outer wall of the outer cylinder containing the cylinder, the eccentricity of the cylinder can be detected in real time during the dehydration process of the clothing processing device. Compared with the one-dimensional linear detection method in the related art, the detection accuracy is improved, thereby reducing the risk of the cylinder hitting the box during the high-speed dehydration stage, ensuring the normal use of the clothing processing device, and extending the service life of the clothing processing device. In addition, the above-mentioned eccentricity detection method is not only applicable to the eccentricity detection of single-drum clothing processing equipment, but also applicable to the eccentricity detection of multi-drum clothing processing equipment, and can realize the eccentricity detection of one or more cylinders in the dehydration state in the multi-drum clothing processing equipment.

[0080] The following is a detailed description of the specific implementation method of determining the current eccentricity of the target cylinder according to the current image in the above S102. Specifically, it can be achieved by the following steps (1) to (3):

[0081] Step (1): According to the current image, determine the current pixel spacing corresponding to the target cylinder.

[0082] In the present disclosure, the current pixel spacing includes the current longitudinal pixel distance between two groups of reference points and the current pixel offset of the target cylinder. The two groups of reference points are two preset groups of luminous objects among three groups of luminous objects of different colors on the outer wall of the outer cylinder of the target cylinder, wherein the preset two groups of luminous objects can be any two groups of luminous objects among the three groups of luminous objects of different colors on the outer wall of the outer cylinder of the target cylinder, or can be two groups of luminous objects determined from the three groups of luminous objects according to the colors of the three groups of luminous objects (described in detail below).

[0083] Among them, when the number of each group of luminous objects on the outer wall of the outer tube of the target cylinder is one, three luminous objects of different colors are located on the same circular cross section of the target cylinder (it can also be an elliptical cross section, that is, the target cylinder is a cylindrical cylinder). At this time, each group of reference points includes one luminous object, and the current pixel distance between the two groups of reference points is the longitudinal pixel distance between the two luminous objects in the two groups of reference points in the pixel coordinate system. When the number of each group of luminous objects on the outer wall of the outer tube of the target cylinder is multiple, three groups of luminous objects of different colors form an array. At this time, each luminous object in each group of reference points is located on a straight line, and the straight lines where each group of reference points in the two groups of reference points are located are parallel. The current longitudinal pixel distance between the two groups of reference points is the longitudinal pixel distance between the straight lines where each group of reference points in the two groups of reference points are located in the pixel coordinate system.

[0084] Step (2): Determine the target distance displacement corresponding to the current pixel spacing according to the pre-constructed target correspondence relationship between the pixel spacing and the distance displacement of the target cylinder.

[0085] In the present disclosure, the distance displacement of the target cylinder may include: a reference distance between the target cylinder and the image acquisition device on the target axis of the world coordinate system, and a reference offset of the target cylinder on other axes of the world coordinate system except the target axis. The image acquisition device is used to capture the image of the target cylinder in real time during the dehydration process.

[0086] For example, Figure 1 As shown, the world coordinate system can be as follows: the origin is the optical center of the image acquisition device, the X-axis is the opposite direction of the image acquisition device, the Z-axis is vertically upward, the Y-axis is determined by the right-hand rule, the above-mentioned target axis is the X-axis, and the other axes include the Z-axis and the Y-axis, wherein the Z-axis of the world coordinate system corresponds to the Y-axis of the image coordinate system, and the Y-axis of the world coordinate system corresponds to the x-axis of the image coordinate system.

[0087] Step (3): Determine the current eccentricity of the target cylinder according to the target distance displacement.

[0088] In the present disclosure, the current eccentricity includes the eccentricity component of the target cylinder on the target axis and the eccentricity component of the target cylinder on each other axis. After determining the reference distance between the target cylinder and the image acquisition device on the target axis in the world coordinate system, the eccentricity component of the target cylinder on the target axis can be determined based on the difference between the reference distance and the static distance; at the same time, the reference offset of the target cylinder on the other axes is determined as the current eccentricity component of the target cylinder on the other axes. The static distance is the distance between the target cylinder and the image acquisition device on the target axis when the clothing processing device is in a non-working state (i.e., when the target cylinder is in a static state).

[0089] For example, Figure 1As shown, the current eccentricity includes the eccentricity component of the target barrel on the X axis, the eccentricity component of the target barrel on the Y axis, and the eccentricity component of the target barrel on the Z axis. After determining the reference distance between the target barrel and the image acquisition device on the X axis (i.e., the target axis), the eccentricity component of the target barrel on the X axis can be determined according to the difference between the reference distance and the static distance; at the same time, the reference offset of the target barrel on the Y axis is used as the current eccentricity component of the target barrel on the Y axis, and the reference offset of the target barrel on the Z axis is used as the current eccentricity component of the target barrel on the Z axis.

[0090] Specifically, the target correspondence relationship between the above pixel spacing and the distance displacement of the target cylinder can be achieved by the following steps (a) to (c):

[0091] Step (a): According to the triangle similarity principle in the imaging process of the image acquisition device, a reference correspondence relationship between the longitudinal pixel distance between two groups of reference points and the reference distance is determined.

[0092] For example, the two sets of reference points include Figure 1 The top row of luminous objects on the upper tube shown in FIG. 1 (hereinafter referred to as the first group of reference points) and Figure 1 The middle row of luminous objects on the upper tube shown in FIG. (hereinafter referred to as the second group of reference points). Figure 3 As shown, the vertical distance from the first set of reference points to the second set of reference points is D R-G (fixed value, which can be pre-calibrated), the absolute horizontal distance from the image acquisition device to the edge of the upper tube is Distance, which is the reference distance between the upper tube and the image acquisition device on the target axis (i.e., X axis) of the world coordinate system. On the image projection plane of the image acquisition device, the distance from the imaging point pixel center of the leftmost reference point in the first group of reference points to the imaging point pixel center of the leftmost reference point in the second group of reference points is d r-g , which is the vertical pixel distance between the two sets of reference points. The focal length from the camera lens to the bottom light-sensing chip is f.

[0093] Based on the triangle similarity principle in the imaging process of the image acquisition device, it can be seen that D R-G d r-g , Distance and f satisfy the following relationship:

[0094]

[0095] From this, we can know In this way, each longitudinal pixel distance d can be calculated according to the formula r-gThe corresponding reference distance Distance is a reference correspondence relationship between the longitudinal pixel distance between the two groups of reference points and the reference distance. For example, the reference distance Distance corresponding to 1 pixel, 2 pixels, ..., N pixels can be calculated respectively, where the current image is an image of size N*N.

[0096] As another example, the two sets of reference points include Figure 1 The bottom row of luminous objects on the upper tube shown in FIG. 1 (hereinafter referred to as the first group of reference points) and Figure 1 The middle row of luminous objects on the upper tube shown in FIG. (hereinafter referred to as the second group of reference points). Figure 3 As shown, the vertical distance from the first set of reference points to the second set of reference points is D B-R (fixed value, which may be pre-calibrated); on the image projection plane of the image acquisition device, the distance between the imaging point pixel center of the leftmost reference point in the first set of reference points and the imaging point pixel center of the leftmost reference point in the second set of reference points is d b-r , which is the vertical pixel distance between the two sets of reference points.

[0097] Based on the triangle similarity principle in the imaging process of the image acquisition device, it can be seen that D B-R d b-r , Distance and f satisfy the following relationship:

[0098]

[0099] From this, we can know In this way, each longitudinal pixel distance d can be calculated according to the formula b-r The corresponding reference distance Distance is a reference corresponding relationship between the longitudinal pixel distance between the two groups of reference points and the reference distance. For example, the reference distance Distance corresponding to 1 pixel, 2 pixels, ..., N pixels can be calculated respectively.

[0100] As another example, the two sets of reference points include Figure 1 The bottom row of luminous objects on the upper tube shown in FIG. 1 (hereinafter referred to as the first group of reference points) and Figure 1 The middle row of luminous objects on the upper tube shown in FIG. 1 (hereinafter referred to as the second group of reference points). The vertical distance from the first group of reference points to the second group of reference points is D B-G (fixed value, which can be pre-calibrated) On the image projection plane of the image acquisition device, the distance between the imaging point pixel center of the leftmost reference point in the first group of reference points and the imaging point pixel center of the leftmost reference point in the second group of reference points is d b-g , which is the vertical pixel distance between the two sets of reference points.

[0101] Based on the triangle similarity principle in the imaging process of the image acquisition device, it can be seen that D B-G d b-g , Distance and f satisfy the following relationship:

[0102]

[0103] From this, we can know In this way, each longitudinal pixel distance d can be calculated according to the formula b-g The corresponding reference distance Distance is a reference corresponding relationship between the longitudinal pixel distance between the two groups of reference points and the reference distance. For example, the reference distance Distance corresponding to 1 pixel, 2 pixels, ..., N pixels can be calculated respectively.

[0104] Step (b): for each reference distance in the reference correspondence, determine the first pixel offset generated by the reference offset of the target barrel on the second axis when the target barrel has not been offset on the first axis and the distance between the target barrel and the image acquisition device on the target axis is the reference distance, and the other axes include the first axis and the second axis; for each reference offset of the reference offset of the second axis, determine the second pixel offset generated by the reference offset of the target barrel on the second axis when the target barrel has the reference offset and the distance between the target barrel and the image acquisition device on the target axis is the reference distance. The pixel offset of the target barrel includes the first pixel offset and the second pixel offset.

[0105] For example, the target axis is the X-axis, the first axis is the Y-axis, and the second axis is the Z-axis. For each reference distance in the reference correspondence, it can be determined first that when the target barrel has not been offset on the Y-axis and the distance between the target barrel and the image acquisition device on the X-axis is the reference distance, a first pixel offset caused by different degrees of reference offsets of the target barrel on the Z-axis occurs; and then, for each reference offset of different degrees of reference offsets on the Z-axis, it is determined that when the target barrel has the reference offset on the Z-axis and the distance between the target barrel and the image acquisition device on the X-axis is the reference distance, a second pixel offset caused by different degrees of reference offsets of the target barrel on the Y-axis occurs.

[0106] Step (c): constructing a target corresponding relationship according to the reference corresponding relationship, each first pixel offset and each second pixel offset.

[0107] Specifically, the above target correspondence is Pix 筒 (i,j,k) and World 筒 The correspondence between (x, y, z), where Pix筒 (i,j,j) is the pixel spacing, World 筒 (x, y, z) is the distance displacement, i is the longitudinal pixel distance between the two sets of reference points, j is the second pixel offset, k is the first pixel offset, x is the reference distance between the target cylinder and the image acquisition device on the target axis of the world coordinate system, y is the reference offset of the target cylinder on the first axis, and z is the reference offset of the target cylinder on the second axis. At this time, the following first correspondence can be constructed based on the reference correspondence to construct Pix 筒 (i,0,0) and World 筒 The corresponding relationship between (x,0,0) is as follows:

[0108] Pix 筒 (1 pixel, 0, 0) - World 筒 (△x1,0,0)

[0109] Pix 筒 (2 pixels, 0, 0) - World 筒 (△x2,0,0)

[0110] Pix 筒 (3 pixels, 0, 0) - World 筒 (△x3,0,0)

[0111] …

[0112] Pix 筒 (N pixels, 0, 0) - World 筒 (△xN,0,0)

[0113] Among them, △x1, △x2, ..., △xN are reference distances in the first corresponding relationship.

[0114] Then, according to Pix 筒 (i,0,0) and World 筒 The corresponding relationship between (x, 0, 0) and the offset of each first pixel, construct Pix 筒 (i,0,k) and World 筒 The corresponding relationship between (x, 0, z) is as follows:

[0115] Pix 筒 (1 pixel, 0, Z11 pixel) - World 筒 (△x1,0,△z1)

[0116] Pix 筒 (1 pixel, 0, Z12 pixels) - World 筒 (△x1,0,△z2)

[0117] …

[0118] Pix 筒 (1 pixel, 0, Z1N pixel) - World 筒 (△x1,0,△zN)

[0119] Pix 筒 (2 pixels, 0, Z21 pixels) - World 筒 (△x2,0,△z1)

[0120] Pix 筒 (2 pixels, 0, Z22 pixels) - World 筒 (△x2,0,△z2)

[0121] …

[0122] Pix 筒 (2 pixels, 0, Z2N pixels) - World 筒 (△x2,0,△zN)

[0123] …

[0124] Pix 筒 (N pixels, 0, ZN1 pixels) - World 筒 (△xN,0,△z1)

[0125] Pix 筒 (N pixels, 0, ZN2 pixels) - World 筒 (△xN,0,△z2)

[0126] …

[0127] Pix 筒 (N pixels, 0, ZNN pixels) - World 筒 (△xN,0,△zN)

[0128] Wherein, △z1, △z2, ..., △zN are different degrees of reference offsets of the target cylinder on the second axis; Z11 pixel is the first pixel offset caused by the reference offset of △z1 on the second axis when the target cylinder is not offset on the first axis and the distance between the target cylinder and the image acquisition device on the target axis is △x1; Z12 pixel is the first pixel offset caused by the reference offset of △z2 on the second axis when the target cylinder is not offset on the first axis and the distance between the target cylinder and the image acquisition device on the target axis is △x1. The first pixel offset generated when the target cylinder is not offset on the first axis and the distance between the target cylinder and the image acquisition device on the target axis is △x1, the first pixel offset generated when the target cylinder is offset by a reference offset of △zN on the second axis; the first pixel offset generated when the target cylinder is not offset on the first axis and the distance between the target cylinder and the image acquisition device on the target axis is △x2, the first pixel offset generated when the target cylinder is offset by a reference offset of △z1 on the second axis; the first pixel offset generated when the target cylinder is not offset on the first axis , and the distance between the target barrel and the image acquisition device on the target axis is △x2, the target barrel on the second axis generates a first pixel offset caused by a reference offset of △z2; Z2N pixels are the first pixel offset caused by a reference offset of △zN on the second axis when the target barrel is not offset on the first axis and the distance between the target barrel and the image acquisition device on the target axis is △x2; ZN1 pixels are the first pixel offset caused by a reference offset of △zN on the second axis when the target barrel is not offset on the first axis and the distance between the target barrel and the image acquisition device on the target axis is △xN. The first pixel offset is the reference offset of △z1 on the second axis of the cylinder; ZN2 pixels are the first pixel offset caused by the reference offset of △z2 on the second axis of the target cylinder when the target cylinder has not offset on the first axis and the distance between the target cylinder and the image acquisition device on the target axis is △xN; ZNN pixels are the first pixel offset caused by the reference offset of △zN on the second axis of the target cylinder when the target cylinder has not offset on the first axis and the distance between the target cylinder and the image acquisition device on the target axis is △xN.

[0129] Finally, according to Pix 筒 (i,0,k) and World 筒 The correspondence between (x, 0, z) and the offset of each second pixel, construct Pix 筒 (i,j,k) and World 筒 The correspondence between (x, y, z) (i.e., the target correspondence) is as follows:

[0130] Pix 筒 (1 pixel, Y11 pixel, z11 pixel) - World筒 (△x1,△y1,△z1)

[0131] Pix 筒 (1 pixel, Y12 pixels, Z11 pixels) - World 筒 (△x1,△y2,△z1)

[0132] …

[0133] Pix 筒 (1 pixel, Y1N pixel, Z11 pixel) - World 筒 (△x1,△yN,△z1)

[0134] Pix 筒 (1 pixel, Y21 pixels, Z12 pixels) - World 筒 (△x1,△y1,△z2)

[0135] Pix 筒 (1 pixel, Y22 pixels, Z12 pixels) - World 筒 (△x1,△y2,△z2)

[0136] …

[0137] Pix 筒 (1 pixel, Y2N pixel, Z11 pixel) - World 筒 (△x1,△yN,△z2)

[0138] …

[0139] Among them, △y1, △y2, ..., △yN are reference offsets of different degrees on the first axis of the target cylinder; Y11 pixel is the reference offset of △z1 on the second axis of the target cylinder, and when the distance between the target cylinder and the image acquisition device on the target axis is △x1, the second pixel offset caused by the reference offset of △y1 on the first axis of the target cylinder; Y12 pixel is the reference offset of △z1 on the second axis of the target cylinder, and when the distance between the target cylinder and the image acquisition device on the target axis is △x1, the second pixel offset caused by the reference offset of △y2 on the first axis of the target cylinder; Y1N pixel is the reference offset of △z1 on the second axis of the target cylinder, and when the distance between the target cylinder and the image acquisition device on the target axis is △x1, the second pixel offset caused by the reference offset of △y2 on the first axis of the target cylinder The pixel Y21 is the second pixel offset generated by the reference offset of △z2 occurring on the second axis of the target cylinder, and when the distance between the target cylinder and the image acquisition device on the target axis is △x1, the reference offset of △y1 occurring on the first axis of the target cylinder is the second pixel offset generated; the pixel Y22 is the second pixel offset generated by the reference offset of △z2 occurring on the second axis of the target cylinder, and when the distance between the target cylinder and the image acquisition device on the target axis is △x1, the reference offset of △y2 occurring on the first axis of the target cylinder is the second pixel offset generated; the pixel Y2N is the second pixel offset generated by the reference offset of △z2 occurring on the second axis of the target cylinder, and when the distance between the target cylinder and the image acquisition device on the target axis is △x1, the reference offset of △yN occurring on the first axis of the target cylinder is the second pixel offset.

[0140] In the above embodiment, since the cylinder has an arc, it is necessary to determine the Pix gradient one by one along the target axis. 筒 (i,0,j) and World 筒 The correspondence between (x, 0, z), similarly, it is necessary to determine Pix along the second axis gradient by gradient 筒 (i,j,j) and World 筒 The correspondence between (x, y, z) (i.e., the target correspondence). Therefore, according to the target correspondence between the pixel spacing and the distance displacement of the target cylinder, the distortion effect of the curvature curve of the cylinder surface on the similar proportional relationship of "near big and far small" can be effectively improved, and the convergence of the precision error in this application scenario can be improved to avoid the phenomenon of small "far end" error and large "near end" error, so as to more accurately detect the eccentricity of the cylinder.

[0141] In addition, when the target barrel is not offset on the first axis and the distance between the target barrel and the image acquisition device on the target axis is the reference distance, the first pixel offset generated by the reference offset of different degrees on the second axis of the target barrel can be determined in the following manner:

[0142] For each reference offset of different degrees of reference offset of the target cylinder on the second axis, a calibration image of the target cylinder is obtained when the target cylinder has no offset on the first axis, the distance between the target cylinder and the image acquisition device on the target axis is the reference distance, and the target cylinder has the reference offset on the second axis; then, a first pixel offset corresponding to the reference offset is determined based on the pixel offset between the calibration image and the reference image.

[0143] In addition, a method similar to that for determining the first pixel offset caused by different degrees of reference offset of the target barrel on the second axis can be used to determine the second pixel offset caused by different degrees of reference offset of the target barrel on the first axis when the reference offset occurs on the second axis and the distance between the target barrel and the image acquisition device on the target axis is the reference distance, which will not be repeated in the present disclosure.

[0144] The following is a detailed description of the specific implementation method of determining the current pixel spacing corresponding to the target cylinder according to the current image in step (1) above. Specifically, it can be achieved by the following steps (11) to (13):

[0145] Step (11): Separate the color channels of the current image to obtain a first color channel image and a second color channel image.

[0146] In the present disclosure, the color of the color channel corresponding to the first color channel image is the color of one of the two groups of reference points, and the color of the color channel corresponding to the second color channel image is the color of the other of the two groups of reference points. Figure 4A The current image shown is separated into color channels to obtain Figure 4B The first color channel image and Figure 4C The second color channel image shown in .

[0147] For example, the colors of the three groups of luminous objects are red, green and blue respectively, and the colors of the above two groups of reference points are red and green. The current image can be separated into red channel (i.e., R channel separation) and green channel (i.e., G channel separation) to obtain a red channel separated image and a green channel separated image (i.e., a first color channel image and a second color channel image).

[0148] Step (12): Determine the current longitudinal pixel distance between the two groups of reference points based on the first color channel image and the second color channel image.

[0149] Step (13): Determine the current pixel offset of the target cylinder based on the pixel offset between the current image and the reference image.

[0150] In the present disclosure, the reference image is an image of the target drum captured by the image acquisition device when the clothing processing equipment is in a non-working state, that is, the reference image is an image of the target drum when it is in a stationary state, and the current image is a real-time image of the inner drum of the target drum during rotation. The current pixel offset of the target drum is determined by determining the pixel offset between the real-time image and the reference image.

[0151] Specifically, the pixel offset of the current image relative to the reference image in the pixel coordinate system can be determined as the current pixel offset of the target cylinder.

[0152] The original image (i.e., the current image) captured by the image acquisition device on the inner wall of the outer shell of the clothing processing equipment and the corresponding single color channel image obtained after color channel separation can highlight the characteristics of the luminous object of the corresponding color. In this way, based on the dim light in the cavity of the clothing processing equipment, the characteristics of luminous objects of different colors can be fully utilized to accurately identify the luminous objects of the corresponding colors (i.e., the reference points) from the two single color channel images (i.e., the first color channel image and the second color channel image) obtained after color channel separation, thereby accurately determining the current longitudinal pixel distance between the two groups of reference points and realizing accurate detection of the eccentricity of the target cylinder.

[0153] The following is a detailed description of the specific implementation method of determining the current longitudinal pixel distance between the two groups of reference points according to the first color channel image and the second color channel image in the above step (12). Specifically, it can be achieved by the following steps (121) and (122):

[0154] Step (121): binarizing the first color channel image to obtain a first binary image, and binarizing the second color channel image to obtain a second binary image.

[0155] Specifically, the target segmentation threshold of the color channel corresponding to the first color channel image can be obtained first; then, the first color channel image can be binarized according to the target segmentation threshold. In addition, the second color channel image can be binarized in a similar manner, except that the target segmentation threshold of the color channel corresponding to the second color channel image is different from the target segmentation threshold of the color channel corresponding to the first color channel image, which will not be repeated here. Among them, the target segmentation threshold of the color channel corresponding to the first color channel image and the target segmentation threshold of the color channel corresponding to the second color channel image are both predetermined.

[0156] For example, by Figure 4B The first color channel image shown in the figure is binarized to obtain Figure 4DThe first binary image shown is obtained by Figure 4C The second color channel image shown in is binarized to obtain Figure 4E The second binary image is shown.

[0157] Step (122): Determine the longitudinal pixel distance between a set of reference points in the first binary image and a set of reference points in the second binary image as the current longitudinal pixel distance between the two sets of reference points.

[0158] Specifically, based on morphological principles, a group of reference points can be identified from the first binary image, and at the same time, another group of reference points can be identified from the second binary image. After that, the longitudinal pixel distance between the straight lines where the two groups of standard points are located is determined as the current longitudinal pixel distance between the two groups of reference points of the target cylinder.

[0159] Take the clothes processing equipment as a double drum washing machine and the target drum as the upper drum as an example. Figure 4D A set of reference points are identified in the first binary image shown as Figure 5 As shown in the left figure, from Figure 4E A set of reference points are identified in the second binary image shown as Figure 5 As shown in the figure on the right, the vertical pixel distance between the straight lines where the two sets of standard points are located is d r-g .

[0160] The original image (i.e., the current image) captured by the image acquisition device on the inner wall of the outer shell of the clothing processing device, and the corresponding single color channel image obtained after color channel separation can highlight the characteristics of the luminous object of the corresponding color, but there is still interference from the images of the drum, supporting springs, water pipes, wires, etc. in the clothing processing device. Therefore, it is also necessary to perform binarization processing on the single color channel image to separate the reference point features in each single color channel image from the background, significantly enhance the feature expression of sparse reference points, thereby avoiding the influence of other components in the clothing processing device on the reference points, further improve the accuracy of the current longitudinal pixel distance between the two groups of reference points, and realize the accurate detection of the eccentricity of the target drum.

[0161] In addition, the specific method for determining the target segmentation threshold of the color channel corresponding to the first color channel image is described in detail below. Specifically, it can be achieved by following the steps [1] and [2]:

[0162] Step [1]: Separate the reference image by color channel to obtain a third color channel image, wherein the color channel corresponding to the third color channel image is the same as the color channel corresponding to the first color channel image.

[0163] Step [2]: According to the color intensity of each pixel in the third color channel image, the maximum inter-class variance method is used to determine the target segmentation threshold.

[0164] Specifically, for each preset segmentation threshold among the multiple preset segmentation thresholds, the pixel ratio of the first target pixel points in the third color channel image, the average color intensity of all the first target pixel points, and the average color intensity of all the second target pixel points can be determined according to the preset segmentation threshold and the color intensity of each pixel point in the third color channel image; then, the variance corresponding to the preset segmentation threshold is determined according to the pixel ratio, the average color intensity of all the first target pixel points, the average color intensity of all the second target pixel points, and the average color intensity of the third color channel image;

[0165] Finally, the preset segmentation threshold corresponding to the maximum value among all variances is determined as the target segmentation threshold.

[0166] Among them, the color intensity of the first target pixel is greater than the preset segmentation threshold, the color intensity of the second target pixel is less than or equal to the preset segmentation threshold, and the color intensity average of the third color channel image is the average color intensity of each pixel in the third color channel image.

[0167] For example, the variance corresponding to the preset segmentation threshold may be determined by the following equation according to the pixel ratio, the average color intensity of all first target pixels, the average color intensity of all second target pixels, and the average color intensity of the third color channel image:

[0168]

[0169] Among them, T R is the preset segmentation threshold; The preset segmentation threshold T R The corresponding variance; w R0 is the pixel ratio; C R0 is the average color intensity of all first target pixels; C R is the average color intensity of the third color channel image; C R1 is the average color intensity of all second target pixels.

[0170] In addition, the target segmentation threshold of the color channel corresponding to the second color channel image and the target segmentation threshold of the reference color channel can be determined respectively in a manner similar to that of determining the target segmentation threshold of the color channel corresponding to the first color channel image, which will not be described in detail here. The reference color channel is a color channel of the three colors involved in the three groups of luminous objects of different colors, excluding the color channel corresponding to the first color channel image and the color channel corresponding to the second color channel image.

[0171] Among them, the two color channels with larger target segmentation thresholds corresponding to the color channels of the three colors involved in the three groups of luminous objects of different colors can be used as two target color channels, and the luminous objects of the two colors corresponding to the two target color channels can be used as the preset two groups of luminous objects.

[0172] In addition, before the above step (122), the above step (12) may further include the following step (123):

[0173] Step (123): compress the first binary image and the second binary image respectively.

[0174] At this time, the above step (122) can determine the longitudinal pixel distance between a group of reference points in the first binary image obtained after compression processing and a group of reference points in the second binary image obtained after compression processing. In this way, the data processing amount can be reduced while ensuring the uniqueness of the reference points to be positioned, so that the reference points can be quickly identified, the eccentricity detection efficiency of the clothing processing device can be improved, and it is more suitable for occasions of real-time dehydration and eccentricity detection of clothing processing equipment.

[0175] In addition, the above eccentricity detection method may further include the following steps:

[0176] determining whether the laundry processing device is eccentric according to the current eccentricity of each target drum;

[0177] If the clothes processing device is eccentric, the clothes processing device is controlled to enter an eccentricity processing process.

[0178] In the present disclosure, for the current eccentricity of each target cylinder, if the eccentricity components of the target cylinder on the three axes of the world coordinate system are all less than the safety distance threshold corresponding to the corresponding axis, it is determined that the target cylinder is not eccentric; if there is an eccentricity component of the target cylinder on the three axes of the world coordinate system that is greater than or equal to the safety distance threshold corresponding to the corresponding axis, it is determined that the target cylinder is eccentric. If there is an eccentric target cylinder in the clothing processing device, it is determined that the clothing processing device is eccentric. At this time, the output efficiency of the main control space vector pulse width modulation is reduced, and the motor speed is reduced to ensure the structural safety of the clothing processing device.

[0179] Figure 6 3 is a block diagram of an eccentricity detection device according to an exemplary embodiment, wherein the eccentricity detection device 300 is applied to a clothes processing device, wherein the clothes processing device comprises at least one drum, and the outer wall of the outer drum of each drum is provided with three groups of luminous objects of different colors. Figure 6 , the eccentricity detection device 300 may include:

[0180] The acquisition module 301 is configured to acquire, for each target cylinder, a current image of the target cylinder when the clothes processing device is in a dehydration process, wherein the target cylinder is a cylinder whose inner cylinder is in a rotating state, and the current image includes the three groups of luminous objects of different colors on the outer wall of the outer cylinder of the target cylinder;

[0181] The first determination module 302 is configured to determine the current eccentricity of the target cylinder according to the current image.

[0182] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: during the dehydration process of the clothing processing device, for each cylinder whose inner cylinder is in a rotating state, an image of three groups of luminous objects of different colors arranged on the outer wall of the outer cylinder containing the cylinder can be obtained, and then the eccentricity of the cylinder can be detected based on the image. In this way, based on the two-dimensional image of the luminous object on the outer wall of the outer cylinder containing the cylinder, the eccentricity of the cylinder can be detected in real time during the dehydration process of the clothing processing device. Compared with the one-dimensional linear detection method in the related art, the detection accuracy is improved, thereby reducing the risk of the cylinder hitting the box during the high-speed dehydration stage, ensuring the normal use of the clothing processing device, and extending the service life of the clothing processing device. In addition, the above-mentioned eccentricity detection method is not only applicable to the eccentricity detection of single-drum clothing processing equipment, but also applicable to the eccentricity detection of multi-drum clothing processing equipment, and can realize the eccentricity detection of one or more cylinders in the dehydration state in the multi-drum clothing processing equipment.

[0183] Optionally, the first determining module 302 includes:

[0184] A first determination submodule is configured to determine a current pixel spacing corresponding to the target barrel according to the current image, wherein the current pixel spacing includes a current longitudinal pixel distance between two groups of reference points and a current pixel offset of the target barrel, and the two groups of reference points are two preset groups of luminous objects among the three groups of luminous objects of different colors on the outer wall of the outer barrel of the target barrel;

[0185] A second determination submodule is configured to determine a target distance displacement corresponding to the current pixel spacing according to a pre-constructed target correspondence relationship between the pixel spacing and the distance displacement of the target cylinder, wherein the distance displacement includes: a reference distance between the target cylinder and an image acquisition device on a target axis of a world coordinate system, and a reference offset of the target cylinder on an axis other than the target axis of the world coordinate system, wherein the image acquisition device is used to acquire an image of the target cylinder in real time during the dehydration process;

[0186] The third determination submodule is configured to determine the current eccentricity of the target cylinder according to the target distance displacement.

[0187] Optionally, the target correspondence relationship may be constructed by a relationship construction device, wherein the relationship construction device includes:

[0188] A second determination module is configured to determine a reference correspondence relationship between the longitudinal pixel distance between the two groups of reference points and the reference distance according to a triangle similarity principle in an imaging process of the image acquisition device;

[0189] a third determining module configured to determine, for each reference distance in the reference correspondence, a first pixel offset generated by different degrees of reference offsets of the target barrel on a second axis when the target barrel is not offset on the first axis and the distance between the target barrel and the image acquisition device on the target axis is the reference distance, wherein the other axes include the first axis and the second axis; a fourth determining module configured to determine, for each of the different degrees of reference offsets on the second axis, a second pixel offset generated by different degrees of reference offsets of the target barrel on the first axis when the target barrel is offset on the second axis and the distance between the target barrel and the image acquisition device on the target axis is the reference distance;

[0190] A construction module is configured to construct the target corresponding relationship according to the reference corresponding relationship, each of the first pixel offsets, and each of the second pixel offsets.

[0191] Optionally, the first determining submodule includes:

[0192] a channel separation submodule, configured to perform color channel separation on the current image to obtain a first color channel image and a second color channel image, wherein the color of the color channel corresponding to the first color channel image is the color of one set of reference points in the two sets of reference points, and the color of the color channel corresponding to the second color channel image is the color of the other set of reference points in the two sets of reference points;

[0193] a fourth determination submodule, configured to determine a current longitudinal pixel distance between the two groups of reference points according to the first color channel image and the second color channel image;

[0194] The fifth determination submodule is configured to determine the current pixel offset of the target cylinder based on the pixel offset between the current image and a reference image, wherein the reference image is an image of the target cylinder captured by the image acquisition device when the clothing processing device is in a non-working state.

[0195] Optionally, the fourth determining submodule includes:

[0196] A binarization submodule is configured to perform binarization processing on the first color channel image to obtain a first binary image, and to perform binarization processing on the second color channel image to obtain a second binary image;

[0197] The sixth determination submodule is configured to determine a longitudinal pixel distance between a group of reference points in the first binary image and a group of reference points in the second binary image as a current longitudinal pixel distance between the two groups of reference points.

[0198] Optionally, the binarization submodule includes:

[0199] an acquisition submodule, configured to acquire a target segmentation threshold of a color channel corresponding to the first color channel image;

[0200] The processing submodule is configured to perform binarization processing on the first color channel image according to the target segmentation threshold.

[0201] Optionally, the target segmentation threshold is predetermined by a threshold determination device, wherein the threshold determination device comprises:

[0202] a channel separation module, configured to perform color channel separation on the reference image to obtain a third color channel image, wherein the color channel corresponding to the third color channel image is the same as the color channel corresponding to the first color channel image;

[0203] The fifth determination module is configured to determine the target segmentation threshold by using the maximum inter-class variance method according to the color intensity of each pixel in the third color channel image.

[0204] Optionally, the fifth determining module includes:

[0205] A seventh determination submodule is configured to determine, for each preset segmentation threshold among a plurality of preset segmentation thresholds, a pixel ratio of a first target pixel in the third color channel image, an average color intensity value of all the first target pixels, and an average color intensity value of all the second target pixels according to the preset segmentation threshold and the color intensity of each pixel in the third color channel image, wherein the color intensity of the first target pixel is greater than the preset segmentation threshold, and the color intensity of the second target pixel is less than or equal to the preset segmentation threshold; an eighth determination submodule is configured to determine a variance corresponding to the preset segmentation threshold according to the pixel ratio, the average color intensity value of all the first target pixels, the average color intensity value of all the second target pixels, and the average color intensity value of the third color channel image;

[0206] The ninth determination submodule is configured to determine the preset segmentation threshold corresponding to the maximum value of all the variances as the target segmentation threshold.

[0207] Optionally, the fourth determining submodule further includes:

[0208] a compression processing submodule, configured to perform compression processing on the first binary image and the second binary image respectively before the sixth determination submodule determines the longitudinal pixel distance between a set of reference points in the first binary image and a set of reference points in the second binary image;

[0209] The sixth determination submodule is configured to determine a longitudinal pixel distance between a group of reference points in the first binary image obtained after compression processing and a group of reference points in the second binary image obtained after compression processing.

[0210] Optionally, the eccentricity detection device 300 further includes:

[0211] a sixth determining module, configured to determine whether the laundry processing device is eccentric according to the current eccentricity of each target drum;

[0212] The control module controls the clothes processing device to enter an eccentricity processing process if the clothes processing device is eccentric.

[0213] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0214] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, and when the program instructions are executed by a processor, the steps of the eccentricity detection method provided by the present disclosure are implemented.

[0215] Figure 7 8 is a block diagram of a laundry processing apparatus 800 according to an exemplary embodiment. Figure 7 The laundry processing device 800 may include at least one drum ( Figure 7 ) and one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input / output interface 812, a sensor component 814, and a communication component 816.

[0216] The processing component 802 generally controls the overall operation of the clothing treatment device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned eccentricity detection method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0217] The memory 804 is configured to store various types of data to support the operation of the laundry treatment device 800. Examples of such data include instructions for any application or method operating on the laundry treatment device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0218] The power supply component 806 provides power to the various components of the laundry treating device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the laundry treating device 800.

[0219] The multimedia component 808 includes a screen that provides an output interface between the clothing processing device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the clothing processing device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0220] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the laundry processing device 800 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0221] The input / output interface 812 provides an interface between the processing component 802 and the peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0222] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the clothing processing device 800. For example, the sensor assembly 814 can detect the on / off state of the clothing processing device 800, the relative positioning of the components, such as the display and keypad of the clothing processing device 800, and the sensor assembly 814 can also detect the position change of the clothing processing device 800 or a component of the clothing processing device 800, the presence or absence of contact between the user and the clothing processing device 800, the orientation or acceleration / deceleration of the clothing processing device 800, and the temperature change of the clothing processing device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0223] The communication component 816 is configured to facilitate wired or wireless communication between the clothing processing device 800 and other devices. The clothing processing device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0224] In an exemplary embodiment, the clothing processing device 800 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above-mentioned eccentricity detection method.

[0225] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by the processor 820 of the laundry processing device 800 to complete the above-mentioned eccentricity detection method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0226] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and has a code portion for executing the above-mentioned eccentricity detection method when the computer program is executed by the programmable device.

[0227] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0228] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An eccentricity detection method, applied to a clothing processing device, characterized in that: The laundry processing device comprises at least one drum, and three groups of luminous objects of different colors are arranged on the outer wall of the outer drum of each drum; The method comprises: When the clothes processing device is in the dehydration process, for each target cylinder, a current image of the target cylinder is acquired, wherein the target cylinder is a cylinder whose inner cylinder is in a rotating state, and the current image includes the three groups of luminous objects of different colors on the outer wall of the outer cylinder of the target cylinder; According to the current image, the current eccentricity of the target cylinder is determined.

2. The method according to claim 1, characterized in that Determining the current eccentricity of the target cylinder according to the current image includes: Determine the current pixel spacing corresponding to the target barrel according to the current image, wherein the current pixel spacing includes the current longitudinal pixel distance between two groups of reference points and the current pixel offset of the target barrel, and the two groups of reference points are two preset groups of luminous objects among the three groups of luminous objects of different colors on the outer wall of the outer barrel of the target barrel; Determine the target distance displacement corresponding to the current pixel spacing according to the pre-constructed target correspondence relationship between the pixel spacing and the distance displacement of the target cylinder, wherein the distance displacement includes: a reference distance between the target cylinder and the image acquisition device on the target axis of the world coordinate system, and a reference offset of the target cylinder on the axis other than the target axis of the world coordinate system, and the image acquisition device is used to acquire the image of the target cylinder in real time during the dehydration process; The current eccentricity of the target cylinder is determined according to the target distance displacement.

3. The method according to claim 2, characterized in that The target correspondence relationship is constructed in the following way: Determine a reference correspondence between the longitudinal pixel distance between the two groups of reference points and the reference distance according to the triangle similarity principle in the imaging process of the image acquisition device; For each of the reference distances in the reference correspondence, determining a first pixel offset caused by different degrees of reference offsets of the target barrel on a second axis when the target barrel has not been offset on the first axis and the distance between the target barrel and the image acquisition device on the target axis is the reference distance, wherein the other axes include the first axis and the second axis; for each of the different degrees of reference offsets on the second axis, determining a second pixel offset caused by different degrees of reference offsets of the target barrel on the first axis when the target barrel has the reference offset on the second axis and the distance between the target barrel and the image acquisition device on the target axis is the reference distance; The target corresponding relationship is constructed according to the reference corresponding relationship, each of the first pixel offsets, and each of the second pixel offsets.

4. The method according to claim 2, characterized in that: Determining the current pixel spacing corresponding to the target cylinder according to the current image includes: Performing color channel separation on the current image to obtain a first color channel image and a second color channel image, wherein the color of the color channel corresponding to the first color channel image is the color of one set of reference points in the two sets of reference points, and the color of the color channel corresponding to the second color channel image is the color of the other set of reference points in the two sets of reference points; Determining a current longitudinal pixel distance between the two groups of reference points according to the first color channel image and the second color channel image; The current pixel offset of the target drum is determined according to the pixel offset between the current image and a reference image, wherein the reference image is an image of the target drum captured by the image acquisition device when the laundry processing device is in a non-working state.

5. The method according to claim 4, characterized in that Determining the current longitudinal pixel distance between the two groups of reference points according to the first color channel image and the second color channel image includes: Binarizing the first color channel image to obtain a first binary image, and binarizing the second color channel image to obtain a second binary image; A longitudinal pixel distance between a set of reference points in the first binary image and a set of reference points in the second binary image is determined as a current longitudinal pixel distance between the two sets of reference points.

6. The method according to claim 5, characterized in that The binarization process of the first color channel image comprises: Obtaining a target segmentation threshold of a color channel corresponding to the first color channel image; The first color channel image is binarized according to the target segmentation threshold.

7. The method according to claim 6, characterized in that The target segmentation threshold is predetermined by: Performing color channel separation on the reference image to obtain a third color channel image, wherein the color channel corresponding to the third color channel image is the same as the color channel corresponding to the first color channel image; The target segmentation threshold is determined by using a maximum inter-class variance method according to the color intensity of each pixel in the third color channel image.

8. The method according to claim 7, characterized in that Determining the target segmentation threshold by using the maximum inter-class variance method according to the color intensity of each pixel in the third color channel image includes: For each preset segmentation threshold among multiple preset segmentation thresholds, determine the pixel ratio of the first target pixel in the third color channel image, the average color intensity of all the first target pixels, and the average color intensity of all the second target pixels according to the preset segmentation threshold and the color intensity of each pixel in the third color channel image, wherein the color intensity of the first target pixel is greater than the preset segmentation threshold, and the color intensity of the second target pixel is less than or equal to the preset segmentation threshold; determine the variance corresponding to the preset segmentation threshold according to the pixel ratio, the average color intensity of all the first target pixels, the average color intensity of all the second target pixels, and the average color intensity of the third color channel image; The preset segmentation threshold corresponding to the maximum value among all the variances is determined as the target segmentation threshold.

9. The method according to any one of claims 5 to 8, characterized in that: Before the step of determining the longitudinal pixel distance between a group of reference points in the first binary image and a group of reference points in the second binary image, the step of determining the current longitudinal pixel distance between the two groups of reference points based on the first color channel image and the second color channel image further includes: performing compression processing on the first binary image and the second binary image respectively; Determining the longitudinal pixel distance between a set of reference points in the first binary image and a set of reference points in the second binary image comprises: The longitudinal pixel distance between a group of reference points in the first binary image obtained after the compression process and a group of reference points in the second binary image obtained after the compression process is determined.

10. The method according to any one of claims 1 to 8, characterized in that The method further comprises: determining whether the laundry processing device is eccentric according to the current eccentricity of each target drum; If the clothes processing device is eccentric, the clothes processing device is controlled to enter an eccentricity processing process.

11. An eccentricity detection device, applied to a clothes processing device, characterized in that: The laundry processing device comprises at least one drum, and three groups of luminous objects of different colors are arranged on the outer wall of the outer drum of each drum; The eccentricity detection device comprises: an acquisition module, configured to acquire, for each target cylinder, a current image of the target cylinder when the clothes processing device is in a dehydration process, wherein the target cylinder is a cylinder whose inner cylinder is in a rotating state, and the current image includes the three groups of luminous objects of different colors on the outer wall of the outer cylinder of the target cylinder; The first determination module is configured to determine the current eccentricity of the target cylinder according to the current image.

12. A clothes processing device, characterized in that: include: At least one cylinder, each of which has three groups of luminous objects of different colors arranged on its outer wall; processor; as well as a memory for storing processor-executable instructions; Wherein, the processor is configured to: When the clothes processing device is in the dehydration process, for each target cylinder, a current image of the target cylinder is acquired, wherein the target cylinder is a cylinder whose inner cylinder is in a rotating state, and the current image includes the three groups of luminous objects of different colors on the outer wall of the outer cylinder of the target cylinder; According to the current image, the current eccentricity of the target cylinder is determined.

13. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images