Method for determining a load movement trajectory in a fabric treatment device and electronic device

Abstract

The embodiment of the application discloses a kind of determination method of load movement trajectory in fabric treatment equipment and electronic equipment, belong to fabric treatment equipment control technical field.Therein, the determination method of load movement trajectory in fabric treatment equipment includes: when fabric treatment equipment reaches the target speed corresponding to current operating mode, continuously obtain the image information of load contained in inner tube of fabric treatment equipment;Image information is input into load contour extraction model, and multiple frame contour images are obtained;The contour image that load rolls in inner tube for one week is determined in multiple frame contour images, and is determined as load contour information;Feature points in load contour information are extracted, and the motion trajectory of load is determined using feature points.The embodiment of the application can obtain image information, to determine whether load exists to stick tube or not to be thrown up, improve the execution efficiency in the fabric treatment equipment of load, improve the use experience of user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fabric treatment equipment control, in particular to a method for determining the motion trajectory of a load in a fabric treatment equipment and an electronic device. BACKGROUND

[0002] With the continuous development of fabric treatment equipment technology, washing effect and clothes protection have become the focus of users. In the washing process of the fabric treatment equipment, the motion trajectory and rotational speed control of the clothes play a key role in the washing effect. However, in actual use, due to the differences in weight, material, volume, etc. of the clothes, the clothes may stick to the cylinder wall due to too high rotational speed, or may not be fully thrown up due to too low rotational speed during the operation of the fabric treatment equipment. These situations may affect the washing effect and have certain impact on the clothes and the fabric treatment equipment itself.

[0003] In order to more accurately obtain the motion trajectory of the load in the drum and realize flexible adjustment of the rotational speed, the present patent proposes an optimized fabric treatment equipment control method, aiming to improve the rotational speed control accuracy in the washing process. SUMMARY

[0004] The embodiments of the present application provide a method for determining the motion trajectory of a load in a fabric treatment equipment and an electronic device, to at least solve the technical problem that the rotational speed adjustment is not flexible due to the inability to accurately obtain the motion trajectory of the load in the related art.

[0005] According to a first aspect of the embodiments of the present application, a method for determining the motion trajectory of a load in a fabric treatment equipment is provided, comprising:

[0006] continuously obtaining image information of the load contained in the inner drum of the fabric treatment equipment when the fabric treatment equipment reaches the target rotational speed corresponding to the current operation mode;

[0007] inputting the image information into a load contour extraction model to obtain a plurality of contour images;

[0008] determining the contour image of the load rolling one round in the inner drum from the plurality of contour images, and determining the contour image as load contour information;

[0009] extracting feature points in the load contour information, and determining the motion trajectory of the load by using the feature points.

[0010] In combination with the first aspect, in an optional implementation manner of the embodiments of the present application, the load contour extraction model is trained by the following manner:

[0011] obtain target image information containing load contour labels;

[0012] The target image information is taken as input, and the target contour image corresponding to the output of the load contour labeling and load contour extraction model is compared;

[0013] The load contour extraction model is trained based on the difference between the target contour image and the load contour labeling.

[0014] In combination with the first aspect, in an optional implementation manner of the embodiments of the present application, the load contour information is determined from the contour images in which the load rolls one round in the inner cylinder, and includes:

[0015] The contour image in which the distance between the load and the preset position is the smallest in the contour images is determined as the first contour image;

[0016] The contour image in which the distance between the load and the preset position is the smallest after the first contour image in the contour images is determined as the last contour image;

[0017] The contour images between the first contour image and the last contour image, and the first contour image and the last contour image are determined as the load contour information.

[0018] In combination with the first aspect, in an optional implementation manner of the embodiments of the present application, when the fabric treatment device is a drum fabric treatment device, the preset position is the bottom of the barrel.

[0019] In combination with the first aspect, in an optional implementation manner of the embodiments of the present application, the load contour information contains the contour images in which the load rolls one round in the inner cylinder, and the feature points in the load contour information are extracted, and the motion trajectory of the load is determined by using the feature points, including:

[0020] The feature points of each contour image in the load contour information are extracted;

[0021] The feature points of each adjacent two contour images are matched;

[0022] The matched feature points of the adjacent two contour images are connected to obtain the motion trajectory.

[0023] In combination with the first aspect, in an optional implementation manner of the embodiments of the present application, the method further includes:

[0024] The target rotating speed is adjusted according to the motion trajectory.

[0025] In combination with the first aspect, in an optional implementation manner of the embodiments of the present application, the target rotating speed is adjusted according to the motion trajectory, including:

[0026] The trajectory state of the load is determined according to the motion trajectory;

[0027] The rotating speed correction value for correcting the target rotating speed is determined according to the trajectory state;

[0028] The target rotating speed is adjusted by using the rotating speed correction value.

[0029] In combination with the first aspect, in an optional implementation of the embodiments of the present application, the trajectory state includes an over trajectory, a good trajectory and an under trajectory, and the determination of the rotating speed correction value for correcting the target rotating speed according to the trajectory state includes:

[0030] When the trajectory state is the over trajectory, the rotating speed correction value is determined as a first correction value;

[0031] When the trajectory state is the good trajectory, the rotating speed correction value is determined as a second correction value;

[0032] When the trajectory state is the under trajectory, the rotating speed correction value is determined as a third correction value, wherein the first correction value is a negative value, the second correction value is zero, and the third correction value is a positive value.

[0033] In the method for determining the movement trajectory of the load in the fabric treatment equipment provided by the embodiments of the present application, first, when the fabric treatment equipment reaches the target rotating speed corresponding to the current operating mode, the image information of the load contained in the inner drum of the fabric treatment equipment is continuously acquired, then based on the image information, the load profile information of the load is obtained, the feature points in the load profile information are extracted, and the movement trajectory of the load is determined by using the feature points, and finally the target rotating speed is adjusted according to the movement trajectory. Through the scheme, the image of the load movement is analyzed, the movement trajectory of the load in the inner drum is determined, the execution efficiency of the load in the fabric treatment equipment is improved, and the use experience of the user is improved.

[0034] According to the second aspect of the embodiments of the present application, a determination device for the movement trajectory of a load in a fabric treatment equipment is provided, which includes:

[0035] An acquisition unit is configured to continuously acquire image information of a load contained in an inner drum of a fabric treatment equipment when the fabric treatment equipment reaches a target rotating speed corresponding to a current operating mode;

[0036] A determination unit is configured to input the image information into a load profile extraction model to obtain a plurality of profile images;

[0037] The determination unit is further configured to determine a profile image in which the load rolls one round in the inner drum from the plurality of profile images, and determine the profile image as load profile information;

[0038] An extraction unit is configured to extract feature points in the load profile information, and determine the movement trajectory of the load by using the feature points.

[0039] According to a third aspect of the embodiments of the present application, the present application provides an electronic device, comprising a memory and a processor, the memory and the processor are connected to each other in communication, the memory stores computer instructions, and the processor executes the computer instructions to perform the method for determining the load movement trajectory in the fabric treatment device according to the first aspect or any one of the corresponding embodiments.

[0040] According to a fourth aspect of the embodiments of the present application, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are executed by a processor to implement the method for determining the load movement trajectory in the fabric treatment device according to any one of the above aspects.

[0041] According to a fifth aspect of the embodiments of the present application, the present application provides a computer program product or a computer program, the computer program product comprises a computer program, and the computer program is stored in a computer readable storage medium; the processor of the computer device reads the computer program from the computer readable storage medium, and the processor executes the computer program to implement the method for determining the load movement trajectory in the fabric treatment device according to any one of the above aspects.

[0042] The technical effects obtained by the above second to fifth aspects are similar to the technical effects obtained by the corresponding technical means in the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 is a flowchart of the method for determining the load movement trajectory in the fabric treatment device provided by the embodiments of the present application;

[0044] Figure 2 is a specific flowchart of the method for determining the load movement trajectory in the fabric treatment device provided by the embodiments of the present application;

[0045] Figure 3 is an execution flowchart of the method for determining the load movement trajectory in the fabric treatment device provided by the embodiments of the present application;

[0046] Figure 4 is a structure diagram of the model network provided by the embodiments of the present application;

[0047] Figure 5 is a schematic diagram of the movement trajectory provided by the embodiments of the present application;

[0048] Figure 6 is a structure diagram of the device for determining the load movement trajectory in the fabric treatment device provided by the embodiments of the present application;

[0049] Figure 7FIG. 1 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0051] It should be understood that "multiple" mentioned herein refers to two or more. In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B; "and / or" herein only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second", etc. are used to distinguish the same items or similar items with basically the same function and role. Those skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. also do not limit the difference.

[0052] In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0053] As in the background art, with the continuous development of fabric treatment equipment technology, washing effect and clothes protection have become the focus of users. In the washing process of the fabric treatment equipment, the motion trajectory and rotation speed control of the clothes play a key role in the washing effect. However, in actual use, due to the differences in weight, material, volume, etc. of the clothes, the clothes may be attached to the cylinder wall due to too high rotation speed, or may not be fully thrown due to too low rotation speed during the operation of the fabric treatment equipment. These situations may affect the washing effect and have a certain impact on the clothes and the fabric treatment equipment itself.

[0054] In order to more accurately obtain the motion trajectory of the load in the drum and realize flexible adjustment of the rotation speed strategy, the present patent proposes an optimized fabric treatment equipment control method, aiming to improve the rotation speed control accuracy in the washing process.

[0055] Based on this, the embodiment of the application provides a method for determining the movement trajectory of a load in a fabric treatment device. Figure 1 Referring to the flowchart of the method for determining the movement trajectory of a load in a fabric treatment device, the method comprises the following processing procedures.

[0056] S101: When the fabric treatment device reaches the target rotating speed corresponding to the current operating mode, continuously acquire image information of the load in the inner drum of the fabric treatment device.

[0057] In specific implementation, when the rotating speed of the fabric treatment device reaches the target rotating speed corresponding to the current operating mode, the image information of the load in the inner drum of the fabric treatment device is continuously acquired. Specifically, the image information can be acquired according to the sensor (such as a camera) arranged in the inner drum of the fabric treatment device. The image information can be directly acquired, or the video information can be acquired first, and then the image information is extracted from the video information.

[0058] S102: Obtain load contour information of the load based on the image information.

[0059] In specific implementation, the position of the load in the image, i.e., the load contour information, is identified according to the image information obtained in step S101, so as to further determine the movement trajectory of the load in the inner drum according to the load contour information. The load contour information can be obtained by using an identification algorithm, or the image information can be analyzed by using a deep neural network to obtain the load contour information.

[0060] S103: Extract feature points in the load contour information, and determine the movement trajectory of the load by using the feature points.

[0061] In specific implementation, the feature points in the load contour information are extracted and connected, so that the more accurate movement trajectory of the load in the inner drum can be obtained according to the feature points.

[0062] In this step, after the movement trajectory is determined, the target rotating speed can also be adjusted according to the movement trajectory. Specifically, whether the load is in the state of sticking to the inner drum or not being thrown up in the inner drum is judged according to the movement trajectory, so as to adjust the target rotating speed, so that the trajectory of the load in the inner drum is more reasonable, and the cleaning or drying efficiency of the load is improved.

[0063] With the embodiment, firstly, image information of the load in the inner drum of the fabric treatment equipment is continuously obtained when the fabric treatment equipment reaches the target rotating speed corresponding to the current operating mode, then based on the image information, load profile information of the load is obtained, feature points in the load profile information are extracted, and the motion trajectory of the load is determined by using the feature points, and finally the target rotating speed is adjusted according to the motion trajectory. Through the scheme, the image of the load motion is analyzed to determine the motion trajectory of the load in the inner drum, and then it is determined whether the load is in the case of sticking to the inner drum or not being thrown up, the execution efficiency of the load in the fabric treatment equipment is improved, and then the use experience of the user is improved.

[0064] In the above embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments. The steps shown in the related flowcharts can be executed in a computer system such as a group of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here. In other words, the order of the steps described in the foregoing embodiments is only an example, and reasonable adjustment of the order of the steps based on the content of the embodiments of the present application is also within the protection scope of the embodiments of the present application.

[0065] As shown in Figure 2 The method for determining the motion trajectory of the load in the fabric treatment equipment specifically includes the following processing processes:

[0066] S201: When the fabric treatment equipment reaches the target rotating speed corresponding to the current operating mode, continuously obtain image information of the load in the inner drum of the fabric treatment equipment.

[0067] In specific implementation, the embodiment can be used in some operating modes of the fabric treatment equipment that require the inner drum to rotate, such as washing mode or drying and spinning mode, when the rotating speed of the fabric treatment equipment reaches the target rotating speed corresponding to the current operating mode, the image information of the load in the inner drum is continuously obtained within a certain time. Specifically, the image information can be obtained according to the sensor such as the camera arranged in the inner part of the fabric treatment equipment, the image information can be directly obtained, or the video information can be obtained first, and then the image information is extracted from the video information, which is not limited in the embodiment of the present disclosure.

[0068] S202: Input the image information into the load profile extraction model to obtain a plurality of profile images.

[0069] In specific implementation, the image information obtained in the above steps is input into a load contour extraction model to extract multiple frame contour images. The load contour extraction model can use a YOLOv5 instance segmentation model, or other lightweight instance segmentation models such as YOLOv8-Seg, YOLO-NAS-Seg, MobileOne-Seg, Mask R-CNN, EfficientViT-Seg, etc., which are not limited in the embodiments of the present disclosure. In this embodiment, YOLOv5 is taken as an example for illustration. For training of the model, the labeled data can be used for training. Specifically, the target image information is taken as input, the target contour image corresponding to the output of the load contour extraction model is compared with the load contour label, and the load contour extraction model is trained based on the difference between the target contour image and the load contour label.

[0070] S203: Determine the contour image in which the load rotates one round in the inner cylinder from the multiple frame contour images, and determine the load contour information.

[0071] In specific implementation, the contour image in which the load rotates one round in the inner cylinder is selected from the multiple frame contour images, so as to better reflect the motion trajectory. Specifically, in selecting the contour image, the contour image in which the distance between the load and the preset position is the smallest after the first frame contour image is determined as the last frame contour image, and the contour images between the first frame contour image and the last frame contour image are combined to obtain the load contour information.

[0072] Specifically, the types of the fabric treatment equipment can be divided into a pulsator fabric treatment equipment, a drum fabric treatment equipment and an inclined drum fabric treatment equipment, and the rotation modes of the inner cylinders of each type are different.

[0073] Taking the drum fabric treatment equipment and the inclined drum fabric treatment equipment as examples, the position of the load changes with the rotation of the drum. The position change rule of the load rotating one round is first rising, then falling, then rising again, and then falling again, and so on. The preset position can be selected as the bottom of the barrel. At this time, the contour image with the lowest height is determined as the first frame contour image. After the first frame contour image is determined, the highest height of the load in the subsequent image frames can be tracked. At this time, the load starts to fall, and the height value changes from high to low. When the load reaches the bottom of the cylinder again, it is the critical point of the rise and fall of the load height. Therefore, the image at this point is determined as the last frame contour image.

[0074] Taking the pulsator fabric treatment equipment as an example, any place on the cylinder wall can be selected as the preset position.

[0075] S204: Extract feature points in the load contour information.

[0076] In specific implementation, feature points of each frame of the contour image in the load contour information are extracted, and the feature points can be a cuff, a pocket corner, a button, a special pattern, etc. of the load.

[0077] S205: determining a motion trajectory of the load by using the feature points.

[0078] In specific implementation, the feature points of each two adjacent contour images are matched, and if the matching is successful, the matched feature points in the two adjacent contour images are connected, and then the motion trajectory is obtained after all the feature points are connected. When the motion trajectory is obtained, since the two adjacent images have respective matching results, the matching results of the first image and the second image and the matching results of the second image and the third image can not be one-to-one corresponding, at this time, only the intersection part of the matching results is retained, and finally a plurality of feature point sets are obtained, and then a feature point set with the highest feature point similarity cumulative value is selected as input data for fitting the load trajectory, and the feature points are fitted into a curve by using polynomial fitting, so as to represent the motion trajectory of the load.

[0079] S206: adjusting the target speed according to the motion trajectory.

[0080] In specific implementation, first, a trajectory state of the load is determined according to the motion trajectory, the trajectory state includes an excessive trajectory, a good trajectory and a low trajectory, then a speed correction value for correcting the target speed is determined according to the trajectory state, and finally the target speed is adjusted by using the speed correction value. Specifically, when the trajectory state is the excessive trajectory, the speed correction value is determined as a first correction value, the first correction value is a negative value, that is, the speed needs to be reduced, when the trajectory state is the good trajectory, the speed correction value is determined as a second correction value, the second correction value is zero, that is, the speed does not need to be adjusted at this time, and when the trajectory state is the low trajectory, the speed correction value is determined as a third correction value, the third correction value is a positive value, that is, the speed needs to be increased. After the target speed is adjusted, the adjusted image information can be further obtained, and then the adjusted target speed is detected and further adjusted.

[0081] In one example, the fabric treatment device is taken as a drum fabric treatment device, and the scheme in the embodiment is described in detail, and the execution steps are as shown in Figure 3 When the program starts to execute, the drum starts to rotate at a certain acceleration from a static state, and when the speed reaches the speed R1 corresponding to the current mode, the next step is performed, otherwise it is continuously looped to determine whether the real-time speed reaches R1. After the set speed requirement is met, the image information in the drum is obtained by using the camera, and then the contour information of the load is obtained by using the load contour extraction model, and in this embodiment, the load contour extraction model is taken as YOLOv5 for example, and the overall structure of the model is as shown in Figure 4As shown, the structure is mainly composed of a backbone network, a feature enhancement network, a target detection head and a mask branch. Among them, Conv represents convolution operation, C3 represents convolution modular combination, n represents the number of cycles, k represents the size of convolution kernel, s represents the convolution step, and SPPF is a feature fusion module. Based on the backbone network, the feature map is obtained, and then the feature enhancement network is used to further strengthen the image features. In this embodiment, the shallow feature map has rich spatial position information, and the deep feature map has rich semantic information. Feature enhancement is realized by fusing upper and lower layers and transverse connection for feature fusion. Therefore, three detection heads are set to realize target detection of different load sizes, and the mask parameters based on the target detection results combined with the mask branch can segment the pixel position where the load is located, i.e. the load contour information.

[0082] After that, during the rotation of the drum, it is judged whether the load is located at the bottom of the drum through the load contour information. The judgment method can be to record N frame contour images within one rotation of the load, compare the highest point pixel coordinates of each frame of contour image, take the frame with the minimum height value as the first frame of contour image, and mark it as P start When P start is determined, start recording each frame of contour image P 1,2，…，n and the last frame of contour image P end when the load returns to the bottom of the drum. At this time, the contour image of the load rotating one circle in the drum is obtained, wherein the determination method of P end can use the height change rule of the load rotating one circle in the drum. For example, the position of the load changes with the rotation of the drum, and the position change rule of the load rotating one circle is first rising and then falling, and then rising and falling, and so on. After P start is determined, the highest height of the load in the subsequent image frames can be tracked, at this time the load starts to fall, and the height value changes from high to low, when the load reaches the bottom of the drum again, it is the critical point of the rise and fall of the load height, then the image where the point is located is determined as the image P end .

[0083] After obtaining the images P start to P end , feature point matching is started, specifically, the adjacent two frames are matched, that is, P start and P1 are matched, P1 and P2 are matched, and so on, until P n and P end are matched. Since we have obtained the load contour information of the load, the matching area is only within the contour of the load, and the area outside the contour does not participate in the feature point matching, so as to improve the efficiency of the feature point matching.

[0084] The feature point matching method is realized by using a scale invariant feature transform (SIFT) algorithm. Firstly, a Gaussian pyramid and a difference Gaussian pyramid are constructed, extreme points in the scale space are detected as feature points, the feature points can be a load sleeve, a pocket corner, a button, a special pattern and the like, then the candidate feature points are accurately positioned and unstable edge points are excluded; subsequently, a main direction is assigned to each key point by calculating the gradient direction of the pixels around the key point, so as to realize rotation invariance; then the image region around the key point is divided into a plurality of small blocks, the gradient direction histogram of each small block is counted, and a 128-dimensional SIFT descriptor is generated; finally, the most similar feature point pairs of the descriptors are found between the two images by using a KNN matching algorithm, and the false matching points are removed by using a RANSAC optimization method, so as to realize high-precision feature point matching. Adjacent two images have respective feature point matching results, and the matching results of the first image and the second image and the matching results of the second image and the third image can not be one-to-one corresponding, at this time, only the intersection part in the matching results is reserved. Finally, a plurality of feature point sets are obtained, each set contains n+2 feature point coordinates and matching similarity, a set with the highest feature point similarity cumulative value is selected as input data of the fitted load trajectory, and the feature points are fitted into a curve by using a polynomial fitting, so as to represent the motion trajectory curve of the load. There can be a case that there is no one or more common feature points in all matching pairs, at this time, the matching results are discarded, the target speed is not adjusted, and the next round of feature point matching is entered.

[0085] The speed is adjusted by the fitted trajectory curve, as shown in FIG. 8, when the inner drum rotates counterclockwise, a rectangular coordinate system is established with the lower left corner of the picture as a coordinate circle point, the horizontal direction as the X-axis and the vertical direction as the Y-axis. The outermost circle is the drum contour, from outside to inside, it is an excessive trajectory, a good trajectory and an insufficient trajectory. The excessive trajectory is a trajectory in which the load motion trajectory is too close to the drum wall (X-axis coordinate value is too small), and the clothes will be close to the drum. The insufficient trajectory is a trajectory in which the load is not thrown high enough (Y-axis coordinate value is too small), and the clothes will not be thrown enough. The good trajectory is a trajectory in which the load motion trajectory is in an ideal state, neither close to the drum nor insufficiently thrown. The judgment standard of the insufficient trajectory is that the highest point of the fitted curve is less than a preset value y1, when the highest point of the fitted curve is greater than the preset value y1, the next round of judgment is entered, when the leftmost point of the fitted curve is less than a preset value x1, the curve is judged as an excessive trajectory, otherwise, the curve is considered as a good trajectory. For example, when the trajectory curve is excessive, that is, the load is close to the drum, the speed correction value is d, for example, d is set to -2, that is, the speed is reduced by 2. The speed R2 is obtained by using the speed correction value to adjust the speed, R2 is assigned to R1, the target speed is updated, in another embodiment, if the inner drum rotates clockwise, the preset value x1 needs to be adjusted, the other steps are the same as those in the above embodiment, and details are not described herein again. Figure 5 The speed is adjusted by the fitted trajectory curve, as shown in FIG. 8, when the inner drum rotates counterclockwise, a rectangular coordinate system is established with the lower left corner of the picture as a coordinate circle point, the horizontal direction as the X-axis and the vertical direction as the Y-axis. The outermost circle is the drum contour, from outside to inside, it is an excessive trajectory, a good trajectory and an insufficient trajectory. The excessive trajectory is a trajectory in which the load motion trajectory is too close to the drum wall (X-axis coordinate value is too small), and the clothes will be close to the drum. The insufficient trajectory is a trajectory in which the load is not thrown high enough (Y-axis coordinate value is too small), and the clothes will not be thrown enough. The good trajectory is a trajectory in which the load motion trajectory is in an ideal state, neither close to the drum nor insufficiently thrown. The judgment standard of the insufficient trajectory is that the highest point of the fitted curve is less than a preset value y1, when the highest point of the fitted curve is greater than the preset value y1, the next round of judgment is entered, when the leftmost point of the fitted curve is less than a preset value x1, the curve is judged as an excessive trajectory, otherwise, the curve is considered as a good trajectory. For example, when the trajectory curve is excessive, that is, the load is close to the drum, the speed correction value is d, for example, d is set to -2, that is, the speed is reduced by 2. The speed R2 is obtained by using the speed correction value to adjust the speed, R2 is assigned to R1, the target speed is updated, in another embodiment, if the inner drum rotates clockwise, the preset value x1 needs to be adjusted, the other steps are the same as those in the above embodiment, and details are not described herein again.

[0086] The above illustrates the method embodiments according to the present application, and the present application further provides a method and device for determining a load movement track in a fabric treatment equipment. Figure 6 FIG. 1 is a structural schematic diagram of a method and device for determining a load movement track in a fabric treatment equipment according to an embodiment of the present application. Referring to FIG. 1, Figure 6 The method and device for determining a load movement track in a fabric treatment equipment 700 includes the following modules.

[0087] An acquisition unit 701 is configured to continuously acquire image information of a load in a drum of the fabric treatment equipment when the fabric treatment equipment reaches a target rotating speed corresponding to a current operating mode;

[0088] A determination unit 702 is configured to obtain load profile information of the load based on the image information;

[0089] An extraction unit 703 is configured to extract feature points in the load profile information, and determine a movement track of the load by using the feature points.

[0090] In a possible implementation, the determination unit 702 is specifically configured to:

[0091] input the image information into a load profile extraction model to obtain a plurality of profile images;

[0092] determine a profile image in which the load rolls one round in the drum from the plurality of profile images, and determine the profile image as the load profile information.

[0093] In a possible implementation, the determination unit 702 trains the load profile extraction model in the following manner:

[0094] acquire target image information containing load profile labels;

[0095] take the target image information as input, compare the load profile labels with target profile images output by the load profile extraction model;

[0096] train the load profile extraction model based on differences between the target profile images and the load profile labels.

[0097] In a possible implementation, the determination unit 702 is specifically configured to:

[0098] determine a profile image in which the load is closest to a preset position from the plurality of profile images as a first profile image;

[0099] determine a profile image in which the load is closest to the preset position after the first profile image from the plurality of profile images as a last profile image;

[0100] The contour images between the first frame contour image and the last frame contour image, and the first frame contour image and the last frame contour image are determined as the load contour information.

[0101] In a possible implementation, the load contour information includes a plurality of frame contour images of the load rolling one round in the inner cylinder, and the extraction unit 703 is specifically configured to:

[0102] extract feature points of each frame contour image in the load contour information;

[0103] perform feature point matching on the feature points of each pair of adjacent frame contour images;

[0104] connect the matched feature points in the adjacent frame contour images to obtain a motion trajectory.

[0105] In a possible implementation, the device further includes:

[0106] The processing unit 704 is configured to adjust the target rotating speed according to the motion trajectory.

[0107] In a possible implementation, the processing unit 704 is specifically configured to:

[0108] determine a trajectory state of the load according to the motion trajectory;

[0109] determine a rotating speed correction value for correcting the target rotating speed according to the trajectory state;

[0110] adjust the target rotating speed by using the rotating speed correction value.

[0111] In a possible implementation, the trajectory state includes an over trajectory, a good trajectory and an under trajectory, and the processing unit 704 is specifically configured to:

[0112] when the trajectory state is the over trajectory, determine that the rotating speed correction value is a first correction value;

[0113] when the trajectory state is the good trajectory, determine that the rotating speed correction value is a second correction value;

[0114] when the trajectory state is the under trajectory, determine that the rotating speed correction value is a third correction value, wherein the first correction value is a negative value, the second correction value is zero, and the third correction value is a positive value.

[0115] The above describes the device embodiments of the present application. For the specific execution process, technical problems and effects, alternative manners and combination manners of data, terms, names, steps, please refer to the description in the method embodiments, which will not be repeated here.

[0116] The embodiment of the present application further provides a computer program product comprising computer program instructions, which, when executed by a processor, cause the processor to perform the steps of the method for determining a load movement trajectory in a fabric treatment device according to various embodiments of the present application described in the above "Exemplary Method" section of the present specification.

[0117] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, etc., and conventional procedural programming languages, such as the "C" programming language or similar programming languages.

[0118] The embodiment of the present application further provides a computer readable storage medium having stored thereon a computer program, which, when executed by a processor, causes the processor to perform the steps of the method for determining a load movement trajectory in a fabric treatment device according to various embodiments of the present application described in the above "Exemplary Method" section of the present specification.

[0119] The embodiment of the present application further provides an electronic device comprising a memory and a processor, wherein the memory has stored therein a method for determining a load movement trajectory in a fabric treatment device, and the processor is configured to execute the method for determining a load movement trajectory in a fabric treatment device by using the method for determining a load movement trajectory in a fabric treatment device described above.

[0120] Specifically, as shown in the Figure 7 The electronic device comprises a processor 100, at least one communication bus 200, a user interface 300, at least one external communication interface 400, and a memory 500. The communication bus 200 is configured to realize the connection and communication between the components. The user interface 300 can include a display screen, and the external communication interface 400 can include a standard wired interface and a wireless interface. The memory 500 has stored therein a method for determining a load movement trajectory in a fabric treatment device. The processor 100 is configured to execute the method for determining a load movement trajectory in a fabric treatment device stored in the memory 500 by using the method described above.

[0121] The descriptions of the above computer program product, computer readable storage medium, and electronic device are similar to those of the above method embodiments, and have similar beneficial effects. For technical details of the computer program product, computer readable storage medium, and electronic device of the present application that are not disclosed, please refer to the descriptions of the method embodiments of the present application.

[0122] The order of the embodiments of the present application or the introduction sequence only serves for description, and does not represent the advantages or disadvantages of the embodiments.

[0123] In several embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other manners. Of course, the described unit embodiments are merely illustrative. For example, the division of the units can be different; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be implemented by using some interfaces, and the indirect couplings or communication connections can be implemented in electronic, mechanical, or other forms.

[0124] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, can be located in one place, or can be distributed on multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0125] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0126] In the above embodiments, all or part can be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website site, computer, server or data center to another website site, computer, server or data center through wired (for example: coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example: infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server, data center, etc. that includes one or more available media sets. The available media can be magnetic media (for example: floppy disk, hard disk, magnetic tape), optical media (for example: digital versatile disc (DVD)) or semiconductor media (for example: solid state disk (SSD)) and the like. It should be noted that the computer-readable storage medium mentioned in the embodiments of the present application can be a non-volatile storage medium, in other words, it can be a non-transitory storage medium.

[0127] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.) and signals involved in the embodiments of the present application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions. For example, the scene data of the current frame in the three-dimensional virtual scene, the device information of the client, and the scene interaction information involved in the embodiments of the present application are all obtained under sufficient authorization.

[0128] The above only describes the preferred embodiments of the present application. It should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should also be considered within the scope of protection of the present application.

Claims

1. A method of determining a load movement trajectory within a fabric treatment apparatus, characterized by, The method comprises: continuously acquiring image information of a load in an inner drum of a fabric treatment device when the fabric treatment device reaches a target rotating speed corresponding to a current operating mode; inputting the image information into a load contour extraction model to obtain a plurality of contour images; determining a contour image in which the load rolls one round in the inner drum from the plurality of contour images, and determining the contour image as load contour information; extracting feature points in the load contour information, and determining a motion trajectory of the load by using the feature points; wherein the load contour extraction model is trained in the following manner: acquiring target image information containing load contour labels; comparing the load contour labels and target contour images output by the load contour extraction model with the target image information as input; training the load contour extraction model based on differences between the target contour images and the load contour labels; the method further comprises: adjusting the target rotating speed according to the motion trajectory; the adjusting the target rotating speed according to the motion trajectory comprises: determining a trajectory state of the load according to the motion trajectory; determining a rotating speed correction value for correcting the target rotating speed according to the trajectory state; adjusting the target rotating speed by using the rotating speed correction value.

2. The method of claim 1, wherein, the determining a contour image in which the load rolls one round in the inner drum from the plurality of contour images, and determining the contour image as load contour information comprises: determining a first contour image in which the load is closest to a preset position from the plurality of contour images; determining a last contour image in which the load is closest to the preset position after the first contour image from the plurality of contour images; determining contour images between the first contour image and the last contour image, and the first contour image and the last contour image as the load contour information.

3. The method of claim 2, wherein, when the fabric treatment device is a drum fabric treatment device, the preset position is a barrel bottom.

4. The method of claim 1, wherein, the load contour information contains a plurality of contour images in which the load rolls one round in the inner drum, and the extracting feature points in the load contour information, and determining a motion trajectory of the load by using the feature points comprises: extracting feature points of each contour image in the load contour information; performing feature point matching on feature points of each adjacent two contour images; connecting matched feature points of adjacent two contour images to obtain the motion trajectory.

5. The method of claim 1, wherein, when the trajectory state comprises an excessive trajectory, a good trajectory, and an excessively low trajectory, the determining a rotating speed correction value for correcting the target rotating speed according to the trajectory state comprises: when the trajectory state is the excessive trajectory, determining the rotating speed correction value as a first correction value; when the trajectory state is the good trajectory, determining the rotating speed correction value as a second correction value; when the trajectory state is the excessively low trajectory, determining the rotating speed correction value as a third correction value, wherein the first correction value is a negative value, the second correction value is zero, and the third correction value is a positive value.

6. An electronic device, comprising: ​ A memory and a processor, which are in communication connection with each other, the memory has computer instructions stored therein, and the processor executes the computer instructions to perform the method for determining the load movement trajectory in the fabric treatment device according to any one of claims 1 to 5.

7. A fabric treatment apparatus characterised in that, It has the electronic device of claim 6.

Images