Imaging abnormality diagnosis method and apparatus for laundry treating apparatus, and laundry treating apparatus

Abstract

The present application is actually related to the technical field of smart home, and particularly relates to an imaging abnormality diagnosis method and device of a clothes processing equipment and the clothes processing equipment. The method collects multiple inner drum images of the clothes processing equipment through an image collection device, and judges whether the multiple inner drum images satisfy a preset condition. The preset condition includes that at least one inner drum image includes a lifting rib feature and / or a clothes feature. Then, when the multiple inner drum images do not satisfy the above-mentioned preset condition, it is determined that the clothes processing equipment is in a first imaging abnormality state. The method accurately determines the imaging abnormality state of the clothes processing equipment, which helps to avoid using the inner drum image collected in the imaging abnormality state for clothes recognition, thereby reducing the problem of reducing the clothes recognition accuracy.

Description

Technical Field

[0001] This application belongs to the field of smart home technology, and specifically relates to an imaging anomaly diagnosis method, device and clothing processing equipment for clothing processing. Background Technology

[0002] With the development of smart home technology, clothing processing equipment such as washing machines is becoming increasingly intelligent. For example, through clothing recognition technology, the equipment can identify the material of the clothes inside the drum and accurately recommend processing programs to users.

[0003] Existing garment processing equipment uses data acquisition devices such as optical and infrared sensors to acquire images of the garments inside the drum, identifies the garment material, and then recommends appropriate garment processing programs to the user based on the material. However, when the camera's field of view is obstructed by foreign objects such as stains, fog, or water droplets, resulting in a lack of effective imaging information, or when the lens is damaged or the imaging module malfunctions, existing technology cannot identify the corresponding abnormalities. This can lead to misjudgments of garment information or difficulty in distinguishing between an empty drum and an abnormal imaging state.

[0004] Therefore, how to identify abnormal imaging conditions in clothing processing equipment has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, and garment processing equipment for diagnosing imaging anomalies in garment processing equipment, in order to solve the defects of the prior art that cannot identify the imaging anomalies of garment processing equipment.

[0006] In a first aspect, this application provides an imaging anomaly diagnosis method for a garment processing device, applied to a garment processing device equipped with an image acquisition device for acquiring images of the inner drum of the garment processing device, the method comprising:

[0007] Multiple images of the inner drum of the garment processing equipment are captured using an image acquisition device;

[0008] Determine whether multiple inner cylinder images meet preset conditions, which include: at least one inner cylinder image contains lifting rib features and / or clothing features;

[0009] If multiple images of the inner cylinder do not meet the preset conditions, the clothing processing equipment is determined to be in the first imaging abnormal state.

[0010] In one possible implementation, the method further includes:

[0011] If no clothing features are found in multiple inner drum images, and at least one inner drum image includes lifting rib features, determine whether the weight of the inner drum of the clothing processing equipment is greater than the initial weight of the inner drum.

[0012] If the weight of the inner drum is greater than the initial weight of the inner drum, the garment processing device is determined to be in a second imaging abnormal state, which is used to indicate that garment recognition has failed.

[0013] If the weight of the inner drum is not greater than the initial weight of the inner drum, the garment processing equipment is determined to be in an empty drum state.

[0014] In one possible implementation, after determining that the clothing handling device is in a first imaging abnormality state, the method further includes:

[0015] Multiple inner cylinder images are input into an anomaly classification model, and feature analysis is performed on the multiple inner cylinder images to obtain at least one anomaly feature. The anomaly classification model is trained based on historical anomaly image data, which includes historical anomaly images and corresponding anomaly feature labels.

[0016] Based on at least one abnormal feature, determine at least one imaging abnormality type of the clothing processing device, and generate an abnormal message based on at least one imaging abnormality type;

[0017] Send the above-mentioned abnormal message to the user terminal and / or display the above-mentioned abnormal message on the display interface.

[0018] In one possible implementation, determining at least one imaging anomaly type of the garment processing device based on at least one anomaly feature includes:

[0019] When the abnormal features include the first abnormal feature, the corresponding imaging abnormality type is determined to be the imaging lens that needs cleaning. The first abnormal feature is used to indicate image blur features, image brightness abnormal features, and stain occlusion features.

[0020] If the abnormal features include the second abnormal feature, the corresponding imaging abnormality type is determined to be an image acquisition device malfunction. The second abnormal feature is used to indicate image color cast features, image distortion features, and noise features.

[0021] When the anomalous features include a third anomalous feature, the corresponding imaging anomalous type is determined to be a data transmission anomalous feature, which is used to indicate segmentation line features, image missing features, and low-resolution features.

[0022] In one possible implementation, generating an anomalous message based on at least one imaging anomaly type includes:

[0023] Determine the target operation guide corresponding to each imaging anomaly type, and generate the anomaly message based on the imaging anomaly state, at least one imaging anomaly type, and at least one corresponding target operation guide.

[0024] In one possible implementation, the at least one imaging anomaly type includes: the imaging lens needs cleaning; after determining the target operation guideline corresponding to each imaging anomaly type, the method further includes:

[0025] According to the above target operation guidelines, perform self-cleaning treatment on the imaging lens of the image acquisition device;

[0026] After the self-cleaning process is completed, multiple images of the inner drum of the garment processing equipment are acquired, and it is determined whether the multiple images of the inner drum meet the above-mentioned preset conditions.

[0027] In one possible implementation, acquiring multiple images of the inner drum of the garment processing equipment via an image acquisition device includes:

[0028] During the preset garment processing stage, the image acquisition device is controlled to follow the rotation of the inner drum of the garment processing equipment, and multiple images of the inner drum of the garment processing equipment are acquired by the image acquisition device according to a preset cycle. The garment processing stage includes a start-up stage and a rinsing end stage. The preset cycle is set based on the duration of the garment processing stage.

[0029] Secondly, this application provides an imaging anomaly diagnosis device for a garment processing equipment, comprising:

[0030] The acquisition module is used to acquire multiple images of the inner drum of the garment processing equipment through an image acquisition device;

[0031] The judgment module is used to determine whether multiple images of the inner cylinder meet preset conditions, the preset conditions including: at least one inner cylinder contains lifting rib features and / or clothing features;

[0032] The determination module is used to determine that the clothing processing device is in a first imaging abnormal state when none of the multiple inner cylinder images meet the preset conditions.

[0033] In one possible implementation, the judgment module is further configured to determine whether the weight of the inner drum of the clothing processing device is greater than the initial weight of the inner drum when there are no clothing features in any of the multiple inner drum images and at least one inner drum image includes lifting rib features.

[0034] The determining module is further configured to determine that the clothing processing device is in a second imaging abnormal state when the weight of the inner tube is greater than the initial weight of the inner tube, and the second imaging abnormal state is used to indicate that clothing recognition has failed.

[0035] The determining module is further configured to determine that the clothing processing device is in an empty state when the weight of the inner drum is not greater than the initial weight of the inner drum.

[0036] In one possible implementation, the device further includes: a processing module, a sending module, and a display module;

[0037] The processing module is used to input the multiple inner cylinder images into the anomaly classification model, perform feature analysis on the multiple inner cylinder images, and obtain at least one anomaly feature. The anomaly classification model is trained based on historical anomaly image data, which includes historical anomaly images and corresponding anomaly feature labels.

[0038] The determining module is further configured to determine at least one imaging anomaly type of the clothing processing device based on the at least one anomaly feature, and generate an anomaly message based on at least one of the imaging anomaly types;

[0039] The sending module is used to send the abnormal message to the user terminal;

[0040] The display module is used to display the abnormal message on the display interface.

[0041] In one possible implementation, the determining module is further configured to determine the corresponding imaging anomaly type as an imaging lens that needs cleaning when the anomaly features include a first anomaly feature, wherein the first anomaly feature is used to indicate image blur features, image brightness anomaly features, and stain occlusion features.

[0042] The determining module is further configured to determine, when the abnormal feature includes a second abnormal feature, the corresponding imaging abnormality type as an image acquisition device malfunction, wherein the second abnormal feature is used to indicate image color cast features, image distortion features, and noise features.

[0043] The determining module is further configured to determine the corresponding imaging anomaly type as a data transmission anomaly when the anomaly features include a third anomaly feature, wherein the third anomaly feature is used to indicate segmentation line features, image missing features, and low resolution features.

[0044] In one possible implementation, the apparatus further includes: a generation module;

[0045] The determining module is also used to determine the target operation guide corresponding to each of the imaging anomaly types;

[0046] The generation module is used to generate the abnormal message based on the imaging abnormality state, at least one of the imaging abnormality types, and at least one corresponding target operation guide.

[0047] In one possible implementation, the processing module is further configured to perform a self-cleaning process on the imaging lens of the image acquisition device according to the target operation instructions;

[0048] The acquisition module is also used to acquire multiple images of the inner drum of the garment processing device after the self-cleaning process is completed.

[0049] The judgment module is also used to determine whether multiple images of the inner cylinder meet the preset conditions.

[0050] In one possible implementation, the acquisition module is specifically used to control the image acquisition device to follow the rotation of the inner drum of the garment processing equipment during a preset garment processing stage, and to acquire multiple images of the inner drum of the garment processing equipment according to a preset cycle. The garment processing stage includes a start-up stage and a rinsing end stage, and the preset cycle is set based on the duration of the garment processing stage.

[0051] Thirdly, this application provides a garment processing device, comprising:

[0052] Memory;

[0053] processor;

[0054] The memory stores computer-executed instructions;

[0055] The processor executes computer execution instructions stored in the memory to implement the imaging anomaly diagnosis method for the garment processing device as described in the first aspect and various possible implementations thereof.

[0056] Fourthly, this application provides a computer storage medium storing computer execution instructions thereon, which are executed by a processor to implement the imaging anomaly diagnosis method for a garment processing device as described in the first aspect and various possible implementations thereof.

[0057] The imaging anomaly diagnosis method for clothing processing equipment provided in this application acquires multiple images of the inner drum of the clothing processing equipment using an image acquisition device, and determines whether these multiple inner drum images meet preset conditions. These preset conditions include the presence of at least one inner drum image containing lifting rib features and / or clothing features. If none of the multiple inner drum images meet the aforementioned preset conditions, the clothing processing equipment is determined to be in a first imaging anomaly state. This method accurately determines the imaging anomaly state of the clothing processing equipment based on whether multiple inner drum images contain lifting rib features and / or clothing features, helping to avoid using inner drum images acquired under imaging anomaly states for clothing recognition, which would reduce the accuracy of clothing recognition. Attached Figure Description

[0058] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0059] Figure 1 This is the flowchart of the imaging anomaly diagnosis method for the clothing processing equipment provided in the embodiment. Figure 1 ;

[0060] Figure 2 This is the flowchart of the imaging anomaly diagnosis method for the clothing processing equipment provided in the embodiments of this application. Figure 2 ;

[0061] Figure 3 This is a schematic diagram of the imaging anomaly diagnosis device for the clothing processing equipment provided in this application;

[0062] Figure 4 This is a structural schematic diagram of the garment processing equipment provided in this application.

[0063] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0065] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein.

[0066] In this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0067] With the development of smart home technology, washing machines, dryers, and other clothing processing devices typically have multiple clothing processing programs, each corresponding to different materials and colors of clothing. To accurately recommend the appropriate processing program to users, existing clothing processing devices use data acquisition devices such as optical and infrared sensors to acquire images of the clothing inside the drum. These images are then used to identify the corresponding clothing material and color, and finally, the appropriate processing program is recommended to the user based on that material and color.

[0068] For example, when a user washes jeans in a smart washing machine, the machine uses a camera to capture images of the jeans inside the drum, analyzes and identifies the images to determine the corresponding washing program, and then recommends that program to the user.

[0069] However, when the camera's field of view is obstructed by foreign objects such as stains, fog, or water droplets, resulting in a lack of effective imaging information, or when the lens is damaged or the imaging module malfunctions, existing technologies cannot identify the corresponding abnormal imaging state. Consequently, clothing identification is performed based on clothing images collected under abnormal imaging states, leading to misjudgments of clothing material, color, and other information. Furthermore, it may cause difficulties in distinguishing between empty tube states and abnormal imaging states.

[0070] Therefore, how to identify abnormal imaging conditions in clothing processing equipment has become an urgent problem to be solved.

[0071] To address the aforementioned issues, this application provides a method for diagnosing imaging anomalies in a garment processing device. By determining whether multiple images of the inner drum of the garment processing device meet preset conditions, the method identifies whether the device is in an imaging anomaly state. These preset conditions include: at least one inner drum image contains lifting rib features and / or garment features. When none of the aforementioned inner drum images meet the preset conditions, this method determines that the garment processing device is in a first imaging anomaly state. This helps avoid using inner drum images acquired under imaging anomaly conditions for garment recognition, which would reduce garment recognition accuracy.

[0072] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0073] Figure 1 The flowchart of the imaging anomaly diagnosis method for the garment processing equipment provided in the embodiments of this application Figure 1 .like Figure 1As shown, this embodiment provides an imaging anomaly diagnosis method for a garment processing device, applied to a garment processing device equipped with an image acquisition device for acquiring images of the inner drum of the garment processing device, including:

[0074] S101: Acquire multiple images of the inner drum of the garment processing equipment using an image acquisition device.

[0075] The image acquisition device can be, for example, a camera and an image sensor, and the installation location of the image acquisition device includes, but is not limited to, the inner wall of the garment processing equipment or the inside of the cover.

[0076] Specifically, during a preset clothing processing time period, the aforementioned image acquisition device captures multiple images of the inner drum of the clothing processing equipment. These multiple inner drum images are used for clothing recognition, to recommend corresponding clothing processing procedures to the user based on the recognized clothing information, or to adjust the current clothing processing parameters. Furthermore, these multiple inner drum images are also used to monitor the equipment status or clothing status of the clothing processing equipment.

[0077] Optionally, image analysis processing is performed on the aforementioned multiple images of the inner drum to obtain the inner drum status, which includes, but is not limited to, cleanliness level, operating status, and fault status. Cleanliness level can be, for example, the degree of dirt accumulation and foreign matter residue in the inner drum, while fault status can be, for example, the degree of wear. This method determines the inner drum status using multiple images, providing an accurate basis for the cleaning and maintenance of the inner drum of the garment processing equipment. This helps improve the management efficiency of the garment processing equipment and ensures its normal operation and hygiene safety.

[0078] S102: Determine whether multiple inner cylinder images meet preset conditions.

[0079] The preset conditions include: at least one inner cylinder image contains lifting rib features and / or clothing features.

[0080] Specifically, multiple inner tube images are input into a target detection model, which detects each inner tube image to obtain image features, including lifting rib features and / or clothing features. Based on the aforementioned preset conditions, the image features of each inner tube image are analyzed and judged to further determine the imaging state of the clothing processing equipment. The target detection model is trained on a training dataset, which includes multiple inner tube images carrying lifting rib features and / or clothing features. The lifting rib features include the geometric features of the lifting ribs, and the clothing features include, but are not limited to, features related to the style, color, and accessories of the clothing.

[0081] Optionally, if the image features of multiple inner tube images do not meet the preset conditions, as shown in step S103 below, the clothing processing device is determined to be in a first imaging abnormal state; if the image features of multiple inner tube images do not include the lifting rib feature, and at least one inner tube image includes the clothing feature, or if at least one inner tube image includes both the lifting rib feature and the clothing feature, then step S104 below is executed; if the image features of multiple inner tube images do not include the lifting rib feature or the clothing feature, and at least one inner tube image includes the lifting rib feature, then step S105 below is executed.

[0082] It should be noted that steps S104 and S105 below do not have a sequential execution order; they are simply operation steps corresponding to different judgment results of step S102.

[0083] Understandably, preprocessing the multiple inner cylinder images before inputting them into the target detection model improves the accuracy of feature detection. This preprocessing includes, but is not limited to, denoising and contrast enhancement.

[0084] S103: When multiple inner cylinder images do not meet the preset conditions, the clothing processing equipment is determined to be in the first imaging abnormal state.

[0085] If none of the multiple inner drum images meet the preset conditions in step S102, i.e., none of the multiple inner drum images include lifting rib features and / or clothing features, the clothing processing equipment is determined to be in a first imaging abnormal state. This first imaging abnormal state is used to indicate that the image acquisition device of the clothing processing equipment is in an abnormal state. For example, when the washing machine is in the start-up state and the washing machine drum door is detected to be closed, multiple inner drum images are captured by the image acquisition device. If none of the image features in the multiple inner drum images include lifting rib features and / or clothing features, the image acquisition device is determined to be in an abnormal state.

[0086] This method ensures that multiple inner drum images used for garment recognition are acquired when the garment processing equipment is in a normal imaging state. This avoids the situation where garment recognition accuracy is reduced by using inner drum images acquired in an abnormal imaging state. This helps to provide users with more accurate and efficient garment processing services and ensures the normal operation of the garment processing equipment and the washing effect.

[0087] S104: If multiple inner cylinder images do not include the lifting rib feature, and at least one inner cylinder image includes the clothing feature, or if at least one inner cylinder image includes both the lifting rib feature and the clothing feature, then the clothing processing equipment is determined to be in normal imaging condition.

[0088] Specifically, in step S102, if the image features of multiple inner drum images do not include the lifting rib feature, and at least one inner drum image includes the clothing feature, or if at least one inner drum image includes both the lifting rib feature and the clothing feature, then the clothing recognition is successful. This indicates the clothing processing device is in a normal imaging state, allowing for analysis and processing of the clothing features to obtain information such as the clothing material and color. Based on this information, the corresponding clothing processing program is determined, achieving the technical effect of accurately recommending the appropriate clothing processing program to the user. Furthermore, the clothing features can be analyzed to obtain the clothing processing effect. For example, at the end of the washing program, multiple inner drum images are acquired. If no lifting rib feature is detected in any of the inner drum images, and only at least one inner drum image detects the clothing feature, then the clothing processing device is in a normal imaging state. The clothing features are then analyzed to obtain the degree of wrinkles in the inner drum clothing.

[0089] S105: If multiple inner cylinder images do not include the lifting rib feature or clothing feature, and at least one inner cylinder image includes the lifting rib feature, then obtain the load data of the inner cylinder of the clothing processing equipment, and determine whether the clothing processing equipment is in an empty cylinder state or a second imaging abnormal state based on the load data.

[0090] Specifically, in the case where multiple inner cylinder images do not include the lifting rib feature clothing feature, and at least one inner cylinder image includes the lifting rib feature, the load data of the inner cylinder of the clothing processing equipment is obtained. When the load data is greater than zero, the clothing processing equipment is determined to be in a second imaging abnormal state. When the load data is not greater than zero, the clothing processing equipment is determined to be in an empty cylinder state.

[0091] The imaging anomaly diagnosis method for clothing processing equipment provided in this embodiment acquires multiple images of the inner drum of the clothing processing equipment using an image acquisition device, and determines whether these multiple inner drum images meet preset conditions. These preset conditions include the presence of at least one inner drum image containing lifting rib features and / or clothing features. If none of the multiple inner drum images meet the above preset conditions, the clothing processing equipment is determined to be in a first imaging anomaly state. This helps avoid using inner drum images acquired under imaging anomaly conditions for clothing recognition, which would reduce the accuracy of clothing recognition. Furthermore, this method improves the intelligence level of the clothing processing equipment and facilitates providing users with more accurate and efficient clothing processing services, ensuring the normal operation of the clothing processing equipment and the washing effect.

[0092] Figure 2 The flowchart of the imaging anomaly diagnosis method for the garment processing equipment provided in the embodiments of this application Figure 2 .like Figure 2As shown, in this embodiment... Figure 1 Based on the embodiments, a possible imaging anomaly diagnosis method for clothing processing equipment is described in detail. The imaging anomaly diagnosis method for clothing processing equipment shown in this embodiment includes:

[0093] S201: In the preset clothing processing stage, the image acquisition device is controlled to follow the rotation of the inner drum of the clothing processing equipment, and multiple images of the inner drum of the clothing processing equipment are acquired by the image acquisition device according to the preset cycle.

[0094] The garment processing equipment includes, but is not limited to, stages such as start-up, washing completion, rinsing completion, spin-drying completion, and drying completion. These stages can be set according to the equipment's functions or preset according to user needs. Furthermore, the image acquisition device can be, for example, a waterproof camera or a depth camera; this application does not limit its use in this regard.

[0095] Specifically, to acquire multi-angle images of the inner drum of the garment processing equipment and thus improve the accuracy of garment recognition, during a preset garment processing stage, the image acquisition device rotates along with the inner drum of the garment processing equipment and acquires multiple images of the inner drum according to a preset cycle. For example, if the garment processing equipment is a smart washing machine and the image acquisition device is a waterproof camera, and the smart washing machine pauses for 3 seconds every 5 seconds during the washing cycle's end stage, then the preset cycle is set to 5 seconds. When the smart washing machine is in the washing cycle's end stage, an image is acquired every 5 seconds, with a frequency of twice per second, meaning 6 new images of the inner drum are added each preset cycle.

[0096] Understandably, the garment processing equipment is in the startup phase, and when the door is detected to be closed, the inner drum of the garment processing equipment has not yet started to rotate. Therefore, it is sufficient to collect multiple images of the inner drum according to a preset cycle.

[0097] S202: Determine whether multiple inner cylinder images meet preset conditions.

[0098] After obtaining multiple images of the inner cylinder, feature extraction and processing are performed on the multiple inner cylinder images to determine whether each inner cylinder image includes lifting rib features and / or clothing features, thereby determining whether the clothing processing equipment is in an abnormal imaging state.

[0099] Optionally, if no clothing features are found in any of the multiple inner tube images, and at least one inner tube image includes lifting rib features, then step S203 is executed; if none of the multiple inner tube images meet the preset conditions, then step S206 is executed.

[0100] S203: If there are no clothing features in multiple inner drum images, and at least one inner drum image includes lifting rib features, determine whether the weight of the inner drum of the clothing processing equipment is greater than the initial weight of the inner drum.

[0101] The judgment result in step S202 indicates that: none of the multiple inner drum images contain clothing features, and at least one inner drum image includes lifting rib features, indicating that the clothing processing equipment is in an empty drum state or an imaging abnormality state. Therefore, it is necessary to determine whether the weight of the inner drum of the clothing processing equipment is greater than the initial weight of the inner drum to determine whether the clothing processing equipment is in an empty drum state. The initial weight of the inner drum is the weight of the inner drum when it is unloaded. Specifically, the weight of the inner drum is collected by a weight sensor, and it is determined whether this weight is greater than the initial weight of the inner drum.

[0102] This method, even when only the lifting rib features are identified, can further determine whether the garment processing equipment is empty or has an imaging abnormality based on the weight of the inner drum. It accurately distinguishes between empty drum and imaging abnormality, which is beneficial for providing users with precise garment processing services.

[0103] S204: If the weight of the inner drum is greater than the initial weight of the inner drum, the garment processing equipment is determined to be in a second imaging abnormal state.

[0104] If the weight of the inner drum is greater than the initial weight of the inner drum, it indicates that there is clothing inside the clothing processing device, but the clothing features are not recognized. Therefore, the clothing processing device is determined to be in a second imaging abnormal state, which is used to indicate that clothing recognition has failed.

[0105] Optionally, if it is determined that the clothing processing device is in a second imaging abnormality state, the clothing processing program is paused and a warning message is sent to the user.

[0106] Optionally, after determining that the garment processing device is in a second imaging abnormality state, the following steps S207 to S209 are performed: extracting multiple inner tube image features to obtain at least one abnormal feature, determining the imaging abnormality type corresponding to the at least one abnormal feature, and then sending the imaging abnormality type to the user terminal or displaying it on the display interface of the garment processing device. The abnormal features include, but are not limited to, image blurring features and image distortion features. For example, the imaging abnormality type corresponding to image blurring features and image distortion features could be low imaging device resolution.

[0107] S205: If the weight of the inner drum is not greater than the initial weight of the inner drum, determine that the garment processing equipment is in an empty drum state.

[0108] If the weight of the inner drum is not greater than the initial weight of the inner drum, meaning there are no clothes in the inner drum of the clothing processing device, then the clothing processing device is determined to be in an empty drum state. At this time, an alarm message is generated based on this empty drum state. The clothing processing device prompts the user by flashing lights or issuing a voice prompt based on this alarm message, or sends the alarm message to the user terminal to prompt the user to put clothes into the inner drum of the clothing processing device, thereby improving the intelligence level of the clothing processing device.

[0109] S206: When multiple inner cylinder images do not meet the preset conditions, the clothing processing equipment is determined to be in the first imaging abnormal state.

[0110] If the judgment result in step S202 indicates that no lifting rib features and / or clothing features are found in multiple inner drum images, it means that neither clothing features nor lifting rib features were identified from the multiple inner drum images. Therefore, the clothing processing equipment is determined to be in a first imaging abnormality state. This first imaging abnormality state avoids the problem of low recognition accuracy caused by using inner drum images acquired under imaging abnormality states for clothing recognition, and can also prompt the user to quickly locate the abnormal parts of the clothing processing equipment, avoiding poor washing effect or equipment damage due to component malfunction.

[0111] S207: Input multiple inner cylinder images into the anomaly classification model, perform feature analysis on the multiple inner cylinder images, and obtain at least one anomaly feature.

[0112] The anomaly classification model is trained based on historical anomaly image data, which includes historical anomaly images and corresponding anomaly feature labels. For example, a historical anomaly image might only include an inner tube image with lifting rib features; its corresponding anomaly feature label would be: includes lifting rib features, but excludes clothing features.

[0113] Specifically, based on the timestamps of multiple inner cylinder images, an image sequence of multiple inner cylinder images is determined. These images are then input into an anomaly classification model. The model analyzes and processes each inner cylinder image according to the image sequence to obtain at least one anomaly feature. This anomaly feature can be, for example, image color cast, segmentation line features, or stain occlusion features.

[0114] For example, after the anomaly classification model analyzes and processes the images of each inner cylinder, the resulting anomaly feature is the image brightness anomaly feature, which is caused by insufficient light inside the cylinder when the inner cylinder image is acquired.

[0115] S208: Based on at least one abnormal feature, determine at least one imaging abnormality type of the clothing processing device, and generate an abnormal message based on at least one imaging abnormality type.

[0116] After obtaining at least one anomalous feature, the anomaly classification model determines at least one corresponding imaging anomaly type based on that feature. The anomalous features include: image color cast, clothing entanglement, or abnormal image brightness, etc. The corresponding imaging anomaly types include, for example, lens obstruction by a foreign object or image acquisition module malfunction. Furthermore, after obtaining the imaging anomaly type, an anomaly message is generated based on that type. This message includes an imaging anomaly type identifier and the aforementioned imaging anomaly type. The imaging anomaly type identifier is used to indicate that the anomaly indicator light on the clothing handling device is flashing.

[0117] This method efficiently and accurately locates imaging anomaly types based on abnormal features, saving the time and effort of manually diagnosing imaging anomalies. This avoids potential misjudgments or omissions when diagnosing imaging anomalies, providing a basis for users or relevant staff to maintain clothing processing equipment.

[0118] Optionally, to more accurately determine the imaging anomaly type corresponding to each abnormal feature, a method for determining the imaging anomaly type of a garment processing device based on abnormal features is provided. This method includes: when the abnormal features include a first abnormal feature, determining the corresponding imaging anomaly type as an imaging lens requiring cleaning, where the first abnormal feature indicates image blurring, image brightness anomaly, and stain occlusion; when the abnormal features include a second abnormal feature, determining the corresponding imaging anomaly type as an image acquisition device malfunction, where the second abnormal feature indicates image color cast, image distortion, and noise; and when the abnormal features include a third abnormal feature, determining the corresponding imaging anomaly type as a data transmission anomaly, where the third abnormal feature indicates segmentation line features, image missing features, and low-resolution features. The segmentation line feature indicates that the inner tube image is segmented into multiple discontinuous parts. Furthermore, the aforementioned second abnormal feature also indicates image blackout features and colored stripe features.

[0119] S209: Send the exception message to the user terminal and / or display the exception message on the display interface.

[0120] The abnormal message is generated based on the imaging abnormality type, including but not limited to the imaging abnormality type and its identifier. Specifically, after generating the abnormal message, it is sent to the user terminal and / or displayed on the screen so that the user can promptly understand the imaging abnormality status of the garment processing device. Optionally, upon receiving a garment processing instruction from the user based on the imaging abnormality status, the current garment processing program can be stopped based on the instruction, or the current garment processing program can be continued.

[0121] Optionally, the aforementioned abnormal messages may be voice messages and / or text messages, and this application does not impose any restrictions on this.

[0122] The imaging anomaly diagnosis method for the clothing processing equipment provided in this embodiment, in a preset clothing processing stage, controls the image acquisition device to follow the rotation of the inner drum of the clothing processing equipment, and acquires multiple inner drum images of the clothing processing equipment according to a preset cycle through the image acquisition device, and then determines whether the multiple inner drum images meet preset conditions, that is, whether at least one inner drum image includes lifting rib features and / or clothing features. If not, the clothing processing equipment is determined to be in a first imaging anomaly state. If no clothing features are found in the multiple inner drum images, and at least one inner drum image includes lifting rib features, it is determined whether the weight of the inner drum of the clothing processing equipment is greater than the initial weight of the inner drum. If the weight of the inner drum of the clothing processing equipment is greater than the initial weight of the inner drum, the clothing processing equipment is determined to be in a second imaging anomaly state. If the weight of the inner drum of the clothing processing equipment is not greater than the initial weight of the inner drum, the clothing processing equipment is determined to be in an empty drum state. This method analyzes and processes the lifting rib features and clothing features in multiple inner tube images to determine the first imaging anomaly state of the clothing processing equipment. It also distinguishes between the second imaging anomaly state and the empty tube state, enabling the clothing processing equipment to identify clothing even under normal imaging conditions, thus improving the accuracy of clothing recognition. Furthermore, after determining the imaging anomaly state, the method uses an anomaly classification model to analyze the features of multiple inner tube images, obtaining at least one anomaly feature. Based on this at least one anomaly feature, it determines at least one imaging anomaly type of the clothing processing equipment. Then, based on the at least one imaging anomaly type, it generates an anomaly message, sends this message to the user terminal, and / or displays the anomaly message on the display interface, promptly alerting the user to the imaging anomaly type so that the user can take appropriate measures to address the anomaly and ensure the safe operation of the clothing processing equipment. In addition, this method not only distinguishes between the first imaging anomaly state, the second imaging anomaly state, and the empty tube state, but also determines the imaging anomaly type corresponding to each imaging anomaly state, improving the intelligence level of the clothing processing equipment and enhancing the user experience.

[0123] To prevent users from taking incorrect actions after receiving abnormal messages, which could cause secondary damage to the image acquisition device or clothing processing equipment, this embodiment... Figure 2 Based on the embodiments, a method for generating anomaly messages based on at least one of the aforementioned imaging anomaly types is described in detail to provide users with standard response measures after determining the imaging anomaly type. The imaging anomaly diagnosis method for a garment processing device shown in this embodiment includes:

[0124] Determine the target operation guideline corresponding to each imaging anomaly type, and generate an anomaly message based on the imaging anomaly status, at least one imaging anomaly type, and at least one corresponding target operation guideline.

[0125] Specifically, the storage module of the garment processing equipment stores multiple imaging anomaly types and corresponding operation instructions for each imaging anomaly type. Each imaging anomaly type is associated with a different imaging anomaly type identifier. After determining the imaging anomaly type, the operation instruction corresponding to the imaging anomaly type identifier is retrieved from the storage module based on the imaging anomaly type identifier, and this operation instruction is identified as the target operation instruction. Then, an anomaly message is generated based on the corresponding imaging anomaly state, at least one imaging anomaly type, and at least one corresponding target operation instruction.

[0126] This method provides users with accurate target operation guidance, enabling them to correctly handle imaging anomalies according to the guidance, reducing user confusion caused by imaging anomalies, and thus improving the user experience of the garment processing equipment.

[0127] Optionally, the garment processing device can process imaging anomaly types according to target operation guidelines. For example, at least one imaging anomaly type includes: the imaging lens needs cleaning. After determining the target operation guideline corresponding to each imaging anomaly type, the method further includes: performing self-cleaning processing on the imaging lens of the image acquisition device according to the target operation guideline; after completing the self-cleaning processing, acquiring multiple images of the inner tub of the garment processing device, and determining whether the multiple inner tub images meet the aforementioned preset conditions. That is, when the imaging anomaly type is "the imaging lens needs cleaning," the corresponding target operation guideline is to start the imaging lens self-cleaning process. Then, according to the target operation guideline, the imaging lens self-cleaning program is started to perform self-cleaning processing on the imaging lens of the image acquisition device. After the imaging lens self-cleaning program ends, multiple images of the inner tub of the garment processing device are reacquired, and the imaging state of the garment processing device is determined based on the preset conditions in step S202.

[0128] In this method, the clothing processing device processes the corresponding imaging anomaly type based on the target operation guide, eliminating the need for users to manually clean the imaging lens. This provides users with a convenient clothing processing service and improves the automation and intelligence level of the clothing processing device.

[0129] The imaging anomaly diagnosis method for clothing processing equipment provided in this embodiment determines the target operation guide corresponding to each imaging anomaly type and generates an anomaly message based on the imaging anomaly state, at least one imaging anomaly type, and at least one corresponding target operation guide. This anomaly message enables users to promptly grasp the imaging anomaly type of the clothing processing equipment and provides users with accurate target operation guides. This not only avoids the problem of low clothing recognition accuracy caused by using inner tube images collected under imaging anomaly states, but also reduces the time and effort users spend troubleshooting imaging anomaly types and seeking solutions, thereby improving the user experience.

[0130] Figure 3 This is a schematic diagram of the imaging anomaly diagnosis device for the garment processing equipment provided in this application. Figure 3 As shown, this application provides an imaging anomaly diagnosis device for a garment processing equipment. The imaging anomaly diagnosis device 300 for the garment processing equipment includes:

[0131] The acquisition module 301 is used to acquire multiple images of the inner drum of the garment processing equipment through an image acquisition device;

[0132] The judgment module 302 is used to determine whether multiple inner cylinder images meet preset conditions, the preset conditions including: at least one inner cylinder image includes lifting rib features and / or clothing features;

[0133] The determination module 303 is used to determine that the clothing processing device is in a first imaging abnormal state when none of the multiple inner cylinder images meet the preset conditions.

[0134] In one possible implementation, the judgment module 302 is further configured to determine whether the weight of the inner drum of the clothing processing device is greater than the initial weight of the inner drum when there are no clothing features in any of the multiple inner drum images and at least one inner drum image includes lifting rib features.

[0135] The determining module 303 is further configured to determine that the clothing processing device is in a second imaging abnormal state when the weight of the inner tube is greater than the initial weight of the inner tube, and the second imaging abnormal state is used to indicate that clothing recognition has failed.

[0136] The determining module 303 is further configured to determine that the clothing processing device is in an empty state when the weight of the inner drum is not greater than the initial weight of the inner drum.

[0137] In one possible implementation, the device further includes: a processing module 304, a sending module 305, and a display module 306;

[0138] The processing module 304 is used to input the multiple inner cylinder images into the anomaly classification model, perform feature analysis on the multiple inner cylinder images, and obtain at least one abnormal feature. The anomaly classification model is trained based on historical abnormal image data, which includes historical abnormal images and corresponding abnormal feature labels.

[0139] The determining module 303 is further configured to determine at least one imaging anomaly type of the clothing processing device based on the at least one anomaly feature, and generate an anomaly message based on at least one of the imaging anomaly types;

[0140] The sending module 305 is used to send the abnormal message to the user terminal;

[0141] The display module 306 is used to display the abnormal message on the display interface.

[0142] In one possible implementation, the determining module 303 is further configured to determine the corresponding imaging anomaly type as an imaging lens that needs cleaning when the anomaly features include a first anomaly feature, wherein the first anomaly feature is used to indicate image blur features, image brightness anomaly features, and stain occlusion features.

[0143] The determining module 303 is further configured to determine the corresponding imaging anomaly type as an image acquisition device malfunction when the abnormal feature includes a second abnormal feature, wherein the second abnormal feature is used to indicate image color cast features, image distortion features, and noise features.

[0144] The determining module 303 is further configured to determine the corresponding imaging anomaly type as a data transmission anomaly when the anomaly features include a third anomaly feature, wherein the third anomaly feature is used to indicate segmentation line features, image missing features, and low resolution features.

[0145] In one possible implementation, the apparatus further includes: a generation module 306;

[0146] The determining module 303 is also used to determine the target operation guide corresponding to each of the imaging anomaly types;

[0147] The generation module 306 is used to generate the abnormal message based on the imaging abnormality state, at least one of the imaging abnormality types, and at least one corresponding target operation guide.

[0148] In one possible implementation, the processing module 304 is further configured to perform a self-cleaning process on the imaging lens of the image acquisition device according to the target operation instructions;

[0149] The acquisition module 301 is also used to acquire multiple images of the inner drum of the garment processing device after the self-cleaning process is completed.

[0150] The judgment module 302 is also used to determine whether the multiple inner cylinder images meet the preset conditions.

[0151] In one possible implementation, the acquisition module 301 is specifically used to control the image acquisition device to follow the rotation of the inner drum of the garment processing equipment during a preset garment processing stage, and to acquire multiple images of the inner drum of the garment processing equipment according to a preset cycle. The garment processing stage includes a start-up stage and a rinsing end stage, and the preset cycle is set based on the duration of the garment processing stage.

[0152] The imaging anomaly diagnosis device for the clothing processing equipment provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0153] Figure 4 A schematic diagram of the garment processing equipment provided in this application. Figure 4 As shown, this application provides a garment processing device 400, which includes a receiver 401, a transmitter 402, a processor 403, and a memory 404.

[0154] Receiver 401 is used to receive instructions and data;

[0155] Transmitter 402 is used to send commands and data;

[0156] Memory 404 is used to store instructions executed by the computer;

[0157] The processor 403 is used to execute computer execution instructions stored in the memory 404 to implement the various steps of the imaging anomaly diagnosis method for the clothing processing device in the above embodiments. For details, please refer to the relevant descriptions in the foregoing embodiments of the imaging anomaly diagnosis method for the clothing processing device.

[0158] Alternatively, the memory 404 can be either standalone or integrated with the processor 403.

[0159] When the memory 404 is set up independently, the electronic device also includes a bus for connecting the memory 404 and the processor 403.

[0160] This application also provides a computer storage medium storing computer execution instructions, which, when executed by a processor, implement the imaging anomaly diagnosis method of the clothing processing device as described above.

[0161] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0162] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for diagnosing imaging anomalies in a garment processing device, characterized in that, A method applicable to garment processing equipment, wherein the garment processing equipment is equipped with an image acquisition device for acquiring images of the inner drum of the garment processing equipment, the method comprising: The image acquisition device acquires multiple images of the inner drum of the garment processing equipment. Determine whether multiple inner cylinder images meet preset conditions, the preset conditions including: at least one inner cylinder image includes lifting rib features and / or clothing features; When none of the multiple inner cylinder images meet the preset conditions, the clothing processing device is determined to be in a first imaging abnormality state.

2. The method according to claim 1, characterized in that, The method further includes: If no clothing features are found in any of the multiple inner drum images, and at least one inner drum image includes lifting rib features, determine whether the weight of the inner drum of the clothing processing device is greater than the initial weight of the inner drum. If the weight of the inner tube is greater than the initial weight of the inner tube, the garment processing device is determined to be in a second imaging abnormality state, which is used to indicate that garment recognition has failed. If the weight of the inner drum is not greater than the initial weight of the inner drum, the garment processing device is determined to be in an empty drum state.

3. The method according to any one of claims 1-2, characterized in that, After determining that the garment processing device is in a first imaging abnormality state, the method further includes: The multiple inner cylinder images are input into the anomaly classification model, and feature analysis is performed on the multiple inner cylinder images to obtain at least one anomaly feature. The anomaly classification model is trained based on historical anomaly image data, which includes historical anomaly images and corresponding anomaly feature labels. Based on the at least one abnormal feature, at least one imaging abnormality type of the clothing processing device is determined, and an abnormal message is generated based on at least one of the imaging abnormality types; The abnormal message is sent to the user terminal, and / or the abnormal message is displayed on the display interface.

4. The method according to claim 3, characterized in that, Determining at least one imaging anomaly type of the clothing processing device based on the at least one anomaly feature includes: When the abnormal features include the first abnormal feature, the corresponding imaging abnormality type is determined to be that the imaging lens needs to be cleaned. The first abnormal feature is used to indicate image blur features, image brightness abnormal features, and stain occlusion features. When the abnormal features include the second abnormal feature, the corresponding imaging abnormality type is determined to be an image acquisition device malfunction. The second abnormal feature is used to indicate image color cast features, image distortion features, and noise features. If the abnormal features include a third abnormal feature, the corresponding imaging abnormality type is determined to be a data transmission abnormality. The third abnormal feature is used to indicate segmentation line features, image missing features, and low-resolution features.

5. The method according to claim 4, characterized in that, The generation of anomaly messages based on at least one of the imaging anomaly types includes: Determine the target operation guide corresponding to each of the imaging anomaly types, and generate the anomaly message based on the imaging anomaly state, at least one of the imaging anomaly types, and at least one of the corresponding target operation guides.

6. The method according to claim 5, characterized in that, The at least one imaging anomaly type includes: the imaging lens needs cleaning. After determining the target operation guide corresponding to each imaging anomaly type, the method further includes: According to the target operation instructions, the imaging lens of the image acquisition device is self-cleaned. After completing the self-cleaning process, multiple images of the inner drum of the garment processing device are acquired, and it is determined whether the multiple images of the inner drum meet the preset conditions.

7. The method according to claim 1, characterized in that, The acquisition of multiple images of the inner drum of the garment processing equipment via the image acquisition device includes: During the preset garment processing stage, the image acquisition device is controlled to follow the rotation of the inner drum of the garment processing equipment, and multiple images of the inner drum of the garment processing equipment are acquired by the image acquisition device according to a preset cycle. The garment processing stage includes a start-up stage and a rinsing end stage, and the preset cycle is set based on the duration of the garment processing stage.

8. An imaging anomaly diagnosis device for a garment processing equipment, characterized in that, include: The acquisition module is used to acquire multiple images of the inner drum of the garment processing equipment through an image acquisition device; The judgment module is used to determine whether multiple images of the inner cylinder meet preset conditions, the preset conditions including: at least one inner cylinder contains lifting rib features and / or clothing features; The determination module is used to determine that the clothing processing device is in a first imaging abnormal state when none of the multiple inner cylinder images meet the preset conditions.

9. A garment processing device, characterized in that, include: Memory; processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the imaging anomaly diagnosis method for the clothing processing device as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer execution instructions, which, when executed by a processor, are used to implement the imaging anomaly diagnosis method for the clothing processing device as described in any one of claims 1-7.

Images