Methods, devices, storage media and electronic equipment for identifying foreign objects in washing machines

Abstract

This application provides a method, apparatus, storage medium, and electronic device for identifying foreign objects in a washing machine. The method includes: a positioning step, acquiring first image data of an object in the washing machine and locating a first region on the object using a target detection algorithm; a first acquisition step, acquiring second image data of the first region and determining a first predicted probability of the presence of a foreign object in the first region based on the second image data and a binary classification algorithm; a second acquisition step, acquiring infrared sensing data of the first region and determining a second predicted probability of the presence of a foreign object in the first region based on the infrared sensing data and a deep neural network; and a determination step, determining a final predicted probability of the presence of a foreign object in the first region based on the first and second predicted probabilities. This method detects paper foreign objects both before and during washing, preventing paper foreign objects from being damaged or contaminating clothes and the environment inside the washing tub during washing.

Description

Technical Field

[0001] This application relates to the field of foreign object identification, and more specifically, to a method for identifying foreign objects in a washing machine, a device for identifying foreign objects in a washing machine, a computer-readable storage medium, and an electronic device. Background Technology

[0002] Users inevitably make mistakes when using washing machines, such as putting clothes into the drum without removing foreign objects from pockets. These foreign objects may be important paper items, such as banknotes, invoices, and documents. These paper items are at risk of being damaged during washing, and the resulting paper scraps will stick to the clothes and the inside of the washing machine drum and be difficult to clean, resulting in a poor user experience. Summary of the Invention

[0003] The main objective of this application is to provide a method for identifying foreign objects in a washing machine, a device for identifying foreign objects in a washing machine, a computer-readable storage medium, and an electronic device, so as to at least solve the problem of existing washing machines being unable to identify foreign objects in clothing.

[0004] To achieve the above objectives, according to one aspect of this application, a method for identifying foreign objects in a washing machine is provided, comprising: a positioning step, acquiring first image data of an object in the washing machine, and using a target detection algorithm to locate a first region on the object in the washing machine based on the first image data; a first acquisition step, acquiring second image data of the first region, and determining a first predicted probability of the presence of a foreign object in the first region based on the second image data and a binary classification algorithm; a second acquisition step, acquiring infrared sensing data of the first region, and determining a second predicted probability of the presence of a foreign object in the first region based on the infrared sensing data and a deep neural network; and a determination step, determining a final predicted probability of the presence of a foreign object in the first region based on the first predicted probability and the second predicted probability.

[0005] Optionally, acquiring first image data of an object in the washing machine and using an object detection algorithm to locate a first region on the object in the washing machine based on the first image data includes: controlling the washing machine to enter a waterless rotation mode and acquiring first image data of the object in the washing machine; constructing a YOLO object detection algorithm based on a backbone network, a feature enhancement network, and an object detection head, wherein the YOLO object detection algorithm is trained using multiple sets of training data, each set of training data including: historical image data of historical objects in the washing machine and label data of the historical objects corresponding to the image data of the historical objects acquired within a historical time period; and inputting the first image data into the YOLO object detection algorithm to obtain the localization result of the first region.

[0006] Optionally, acquiring second image data of the first region and determining the probability of the presence of a foreign object in the first region as a first predicted probability based on the second image data and a binary classification algorithm includes: extracting the second image data from the first image data; acquiring a binary classification algorithm, wherein the binary classification algorithm is one of the following: support vector machine, random forest algorithm, decision tree algorithm; and using the binary classification algorithm to determine the first predicted probability based on the second image data.

[0007] Optionally, acquiring infrared sensing data of the first region and determining the probability of the presence of a foreign object in the first region as a second predicted probability based on the infrared sensing data and a deep neural network includes: actively emitting first infrared light towards an object in the washing machine using active infrared technology, and receiving second infrared light reflected by the object through a detector; the active infrared technology being a technology that actively emits infrared light from an infrared light source to detect objects; converting the second infrared light into an electrical signal to obtain the infrared sensing data, and amplifying and filtering the infrared sensing data to obtain a processed digital signal; generating an infrared image of the object using image processing technology based on the processed digital signal; and inputting the infrared image into the deep neural network to obtain the second predicted probability.

[0008] Optionally, determining the final predicted probability of the presence of a foreign object in the first region based on the first predicted probability and the second predicted probability includes: obtaining the weighted average formula A = α SVM ×0.5+α Infrared ×0.5, where A is the final predicted probability, α SVM Let α be the first predicted probability. Infrared The second predicted probability is used; the final predicted probability of the presence of a foreign object in the first region is determined according to the weighted average formula.

[0009] Optionally, after determining the final predicted probability of the presence of a foreign object in the first area based on the first predicted probability and the second predicted probability, the method further includes: stopping the washing program of the washing machine and issuing a warning message when the final predicted probability of the presence of a foreign object in the first area is greater than or equal to a preset probability; and entering the washing program of the washing machine when the final predicted probability of the presence of a foreign object in the first area is less than the preset probability.

[0010] Optionally, if the final predicted probability of a foreign object in the first area is less than the preset probability, after entering the washing program of the washing machine, the method further includes: repeatedly executing the positioning step, the first acquisition step, the second acquisition step, and the determination step until the final predicted probability is greater than or equal to the preset probability or the washing machine finishes washing.

[0011] According to another aspect of this application, a foreign object identification device for a washing machine is provided, comprising: a positioning unit, configured to locate a first region on an object in the washing machine using a target detection algorithm; a first acquisition unit, configured to acquire real-time image data of the first region, and determine a first predicted probability of the presence of a foreign object in the first region based on the real-time image data and a support vector machine model; a second acquisition unit, configured to acquire infrared sensing data of the first region, and determine a second predicted probability of the presence of a foreign object in the first region based on the infrared sensing data and a deep neural network; and a determination unit, configured to determine a final predicted probability of the presence of a foreign object in the first region based on the first predicted probability and the second predicted probability.

[0012] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform any of the aforementioned methods for identifying foreign objects in a washing machine.

[0013] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any of the foreign object identification methods described above in a washing machine.

[0014] Applying the technical solution of this application, the aforementioned method for identifying foreign objects in a washing machine first involves a positioning step, where first image data of an object in the washing machine is acquired, and a target detection algorithm is used to locate a first region on the object in the washing machine based on the first image data. Next, a first acquisition step is taken, acquiring second image data of the first region and determining the probability of a foreign object being present in the first region as a first predicted probability based on the second image data and a binary classification algorithm. Then, a second acquisition step is performed, acquiring infrared sensing data of the first region and determining the probability of a foreign object being present in the first region as a second predicted probability based on the infrared sensing data and a deep neural network. Finally, a determination step is taken, determining the final predicted probability of a foreign object being present in the first region based on the first and second predicted probabilities. This method can detect paper-based foreign objects in real time, stopping the washing program before they spread and become damaged. Furthermore, it analyzes collected false negative and false positive data, optimizes the detection algorithm online, continuously improves detection performance, enhances user experience, and solves the problem of existing washing machines being unable to distinguish foreign objects in clothing. Attached Figure Description

[0015] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for performing a method for identifying foreign objects in a washing machine, according to an embodiment of this application, is shown.

[0017] Figure 2 A flowchart illustrating a method for identifying foreign objects in a washing machine according to an embodiment of this application is shown.

[0018] Figure 3 A schematic diagram of the network structure of a YOLOv5 target detection algorithm according to an embodiment of this application is shown;

[0019] Figure 4 A flowchart illustrating another method for identifying foreign objects in a washing machine according to an embodiment of this application is shown.

[0020] Figure 5 A structural block diagram of a foreign object identification device in a washing machine according to an embodiment of this application is shown.

[0021] The above figures include the following reference numerals:

[0022] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0023] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] As described in the background section, users inevitably make operational errors when using washing machines, such as putting clothes into the washing drum without removing foreign objects from pockets. These foreign objects may be important paper items, such as banknotes, invoices, and documents. These paper items are at risk of being damaged during washing, and the resulting paper scraps will adhere to the clothes and the inner drum of the washing machine, making them difficult to clean and causing a poor user experience. To solve the problem of existing washing machines being unable to identify foreign objects in clothes, embodiments of this application provide a method for identifying foreign objects in a washing machine, a device for identifying foreign objects in a washing machine, a computer-readable storage medium, and an electronic device.

[0027] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0028] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of identifying foreign objects in a washing machine according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0029] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the foreign object identification method in the washing machine in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] This embodiment provides a method for identifying foreign objects in a washing machine that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] Figure 2 This is a flowchart of a method for identifying foreign objects in a washing machine according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0032] Step S201 (Location Step): Obtain first image data of the object in the washing machine, and use a target detection algorithm to locate the first region on the object in the washing machine based on the first image data.

[0033] Specifically, visual sensors are used to monitor the laundry environment, and the YOLO object detection algorithm is used to locate and capture the pocket area of ​​clothing, effectively narrowing the detection area for identifying foreign objects.

[0034] The process of acquiring first image data of an object in the washing machine and locating a first region on the object in the washing machine using a target detection algorithm based on the first image data includes the following steps:

[0035] Step S2011: Control the washing machine to enter the waterless rotation mode and acquire the first image data of the object in the washing machine.

[0036] Step S2012: Construct a YOLO object detection algorithm based on the backbone network, feature enhancement network, and object detection head. The YOLO object detection algorithm is trained using multiple sets of training data. Each set of training data includes image data of historical objects in the washing machine and label data of the historical objects corresponding to the image data of the historical objects, acquired within a historical time period.

[0037] Step S2013: Input the first image data into the YOLO target detection algorithm to obtain the localization result of the first region.

[0038] Specifically, the YOLO algorithm is a fast and efficient real-time object detection algorithm that can automatically and accurately locate target areas, improving the intelligence and automation level of washing machines. Sensors are installed on the washing machine to monitor the washing process and acquire image data of objects. Before washing, the machine is spun without water for a certain period. During this waterless spinning process, the YOLO object detection algorithm, trained on a basic basis, is used to detect pockets in the washing image, thus locating the pocket area.

[0039] In one alternative approach, the YOLO algorithm has multiple versions, generally YOLOv1 to YOLOv7. In this embodiment, the YOLOv5 target detection algorithm is used to locate the pocket region. Figure 3The network structure of the YOLOv5 object detection algorithm is presented, mainly consisting of a backbone network, a feature enhancement network, and object detection heads. Here, Conv represents a convolution operation, C3 represents a modular convolution combination, n represents the number of iterations, k represents the kernel size, s represents the stride, and SPPF is the feature fusion module. Feature maps are obtained based on the backbone network, and the feature enhancement network further strengthens image features. Shallow feature maps contain rich spatial location information, while deep feature maps contain rich semantic information. Feature enhancement is achieved through feature fusion by fusing upper and lower layers and lateral connections. The feature enhancement network outputs three feature maps at different scales, and three detection heads are used to achieve object detection of different pocket sizes. The output of object detection is the location of the bounding rectangle of the pocket region within the monitored image.

[0040] The YOLOv5 object detection algorithm requires image data and label data for training. There is a one-to-one correspondence between the image data and the label data; the information in the label data is the location information of the bounding rectangle of the pocket region in the corresponding image data. A pocket object detection dataset is created for algorithm training to obtain model weights. In the application phase, images are input into the model for inference to obtain pocket object detection results.

[0041] Step S202 (first acquisition step): acquire the second image data of the first region, and determine the probability of the presence of foreign objects in the first region as the first predicted probability based on the second image data and the binary classification algorithm;

[0042] Specifically, the pocket area is classified into two categories based on whether there are paper foreign objects. If paper foreign objects are found, an alarm is triggered and the washing program is stopped to prevent paper scraps from contaminating clothes and causing them to be difficult to clean, thus improving the user experience.

[0043] The process of acquiring second image data of the first region and determining the probability of the presence of a foreign object in the first region as a first predicted probability based on the second image data and a binary classification algorithm includes the following steps:

[0044] Step S2021: Extract the second image data from the first image data;

[0045] Step S2022: Obtain the binary classification algorithm, which is one of the following: Support Vector Machine, Random Forest algorithm, or Decision Tree algorithm;

[0046] Step S2023: The first predicted probability is determined based on the second image data using the aforementioned binary classification algorithm.

[0047] Specifically, after locating the pocket region using the YOLO object detection algorithm, an image of that region is cropped, and the image is further classified into two categories based on whether it contains paper-like foreign objects. Image binary classification can be implemented using specific algorithms such as Support Vector Machines, Random Forest, and Decision Trees.

[0048] In one alternative approach, a Support Vector Machine (SVM) is used for image binary classification. The goal of the SVM is to find an optimal hyperplane that maximizes the margin between the two classes of data points. The hyperplane is mathematically represented as w × x + b = 0, where w is the normal vector, x is the input feature vector, and b is the bias term. The minimum distance from the data points of the two classes to the hyperplane is the margin, and the goal is to find a hyperplane that maximizes this margin. First, feature vectors are extracted from the cropped pocket region image using histogram of orientations (HOC). These feature vectors are then normalized to eliminate dimensional differences between different features. The extracted feature vectors and their corresponding labels are used to train the SVM model. The labels indicate whether the image belongs to the category of "paper foreign object". The support vectors are the data points closest to the hyperplane, determining its position and orientation. During training, only the support vectors affect the hyperplane's position. Finally, feature vectors are extracted from new pocket region images, and the trained SVM model is used to perform binary classification for "paper foreign object," outputting the probability of having a paper foreign object.

[0049] Step S203 (Second Acquisition Step): Acquire the infrared sensing data of the first region, and determine the probability of the presence of foreign objects in the first region as the second predicted probability based on the infrared sensing data and the deep neural network.

[0050] Specifically, an infrared sensing detection branch is introduced to improve the accuracy of judgment, reduce false alarms, reduce losses, and improve the user experience.

[0051] The process of acquiring infrared sensing data of the first region and determining the probability of the presence of a foreign object in the first region as a second predicted probability based on the infrared sensing data and a deep neural network includes the following steps:

[0052] Step S2031: Active infrared technology is used to actively emit first infrared light towards the object in the washing machine, and a detector is used to receive the second infrared light reflected by the object. The active infrared technology is a technology in which an infrared light source actively emits infrared light to detect objects.

[0053] Step S2032: Convert the second infrared light into an electrical signal to obtain the infrared sensing data, and amplify and filter the infrared sensing data to obtain the processed digital signal.

[0054] Step S2033: Generate an infrared image of the object using image processing technology based on the processed digital signal described above;

[0055] Step S2034: Input the infrared image into the deep neural network to obtain the second prediction probability.

[0056] Specifically, considering that the performance of paper foreign object binary classification detection using image methods alone is affected by uncertain factors such as illumination and the size of the paper foreign object, this application also introduces an infrared sensing detection branch. Infrared sensors are mainly divided into two types: active and passive.

[0057] In one alternative approach, a more precise active infrared technology is employed. This involves an infrared light source actively emitting infrared light, which is then received by a detector to detect the reflected infrared signal. Based on pocket localization, the infrared light source emits infrared light into the pocket area at a predetermined frequency and intensity. The emitted infrared light illuminates the pocket area, and the target object reflects a portion of the infrared light. The infrared detector receives the reflected infrared light, converts it into an electrical signal, amplifies and filters it, and then uses image processing techniques to generate an infrared image. The reflectivity of the infrared image is analyzed, utilizing the difference in infrared energy absorption and reflection between paper objects and clothing to detect the presence of paper objects. By collecting a large amount of measured infrared image data as a dataset, a deep neural network is trained using deep learning methods to predict the probability of the presence of paper objects.

[0058] Step S204 (Determination Step): Based on the first prediction probability and the second prediction probability, determine the final prediction probability that there is a foreign object in the first region.

[0059] Specifically, by using a weighted approach combining binary classification and infrared scanning to predict whether a paper foreign object is present in the pocket area, the results are more accurate compared to judging based on only one condition. This reduces false alarms, minimizes losses, and improves the user experience. Furthermore, feedback on false alarm data allows for continuous optimization of paper foreign object recognition performance.

[0060] The determination of the final predicted probability of the presence of a foreign object in the first region, based on the first predicted probability and the second predicted probability, includes the following steps:

[0061] Step S301, obtain the weighted average formula A = α SVM ×0.5+α Infrared ×0.5, where A is the final predicted probability mentioned above, α SVM Let α be the first predicted probability mentioned above. Infrared This refers to the second predicted probability mentioned above;

[0062] Step S302: Determine the final predicted probability of the presence of foreign objects in the first region based on the weighted average formula described above.

[0063] Specifically, for the same pocket area, both the visual image scheme and the infrared image scheme output the probability of the presence of paper foreign objects. The two probabilities are weighted to obtain the final prediction result, improving the accuracy of the prediction. When a paper foreign object is detected, an alarm is immediately issued to remind the user and the washing process is stopped; if no paper foreign object is detected, the washing program begins.

[0064] After determining the final predicted probability of the presence of a foreign object in the first region based on the first and second predicted probabilities, the method further includes the following steps:

[0065] Step S401: If the final predicted probability of the presence of a foreign object in the first area is greater than or equal to the preset probability, stop the washing program of the washing machine and issue a warning message.

[0066] Step S402: If the final predicted probability of the presence of a foreign object in the first area is less than the preset probability, the washing program of the washing machine is entered.

[0067] Specifically, the preset probability in this application is set to 0.6, that is, when A is greater than 0.6, it is considered that there is a paper foreign object.

[0068] Where the final predicted probability of the presence of a foreign object in the first region is less than the preset probability, after entering the washing program of the washing machine, the method further includes: repeatedly executing the positioning step, the first acquisition step, the second acquisition step, and the determination step until the final predicted probability is greater than or equal to the preset probability or the washing machine finishes washing.

[0069] Specifically, once the washing program begins, the washing process is monitored in real time. The process repeatedly performs target detection and pocket location, paper foreign object image classification, infrared sensor paper detection, prediction weighting, and foreign object judgment until a foreign object is detected or the washing program completes. When the user detects a missed or false alarm for a paper foreign object, the washing machine sends the image data and infrared sensor data collected during the washing process to the server for analysis. The server optimizes the detection algorithm and continuously enhances the washing machine's paper foreign object recognition capabilities through online upgrades, thereby improving the user experience.

[0070] The method for identifying foreign objects in a washing machine described in this application first involves a localization step, where first image data of an object in the washing machine is acquired, and a target detection algorithm is used to locate a first region on the object based on the first image data. Next, a first acquisition step acquires second image data of the first region and determines the probability of a foreign object being present in the first region as a first predicted probability based on the second image data and a binary classification algorithm. Then, a second acquisition step acquires infrared sensing data of the first region and determines the probability of a foreign object being present in the first region as a second predicted probability based on the infrared sensing data and a deep neural network. Finally, a determination step determines the final predicted probability of a foreign object being present in the first region based on the first and second predicted probabilities. This method can detect paper-based foreign objects in real time, stopping the washing program before they spread and become damaged. Furthermore, it analyzes collected false negative and false positive data, optimizes the detection algorithm online, continuously improves detection performance, and enhances user experience, solving the problem of existing washing machines being unable to distinguish foreign objects in clothing.

[0071] The complete process of the foreign object identification method in the washing machine described in this application is as follows: Figure 4 As shown, the process includes the following steps: Before washing, the machine rotates for a certain period of time without adding water. During this waterless rotation, the machine uses a self-trained YOLOv5 object detection algorithm to detect pockets in the washing image, thus locating the pocket area. Within the located area, the machine performs binary classification and infrared sensor paper detection to determine whether there are any paper foreign objects. The two probabilities are weighted to obtain the final prediction result, thus determining whether there are any paper foreign objects. When a paper foreign object is detected, an alarm is immediately issued to remind the user and the washing process is stopped. If no paper foreign object is detected, the washing program begins. When the user finds that the washing machine has missed or false alarms for paper foreign objects, the service backend will optimize the detection algorithm and upgrade the detection algorithm online.

[0072] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0073] This application also provides a device for identifying foreign objects in a washing machine. It should be noted that this device can be used to execute the method for identifying foreign objects in a washing machine provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0074] The following describes the foreign object identification device in the washing machine provided in the embodiments of this application.

[0075] Figure 5 This is a schematic diagram of a foreign object identification device in a washing machine according to an embodiment of this application. Figure 5 As shown, the device includes: a positioning unit 10, a first acquisition unit 20, a second acquisition unit 30, and a determination unit 40. The positioning unit 10 is used to locate a first area on an object in the washing machine using a target detection algorithm; the first acquisition unit 20 is used to acquire real-time image data of the first area and determine the probability of the presence of a foreign object in the first area as a first predicted probability based on the real-time image data and a support vector machine model; the second acquisition unit 30 is used to acquire infrared sensing data of the first area and determine the probability of the presence of a foreign object in the first area as a second predicted probability based on the infrared sensing data and a deep neural network; the determination unit 40 is used to determine the final predicted probability of the presence of a foreign object in the first area based on the first predicted probability and the second predicted probability.

[0076] The foreign object identification device for washing machines described in this application includes a positioning unit, a first acquisition unit, a second acquisition unit, and a determination unit. The positioning unit is used to locate a first area on an object in the washing machine using a target detection algorithm. The first acquisition unit is used to acquire real-time image data of the first area and determine the probability of a foreign object in the first area as a first predicted probability based on the real-time image data and a support vector machine model. The second acquisition unit is used to acquire infrared sensing data of the first area and determine the probability of a foreign object in the first area as a second predicted probability based on the infrared sensing data and a deep neural network. The determination unit is used to determine the final predicted probability of a foreign object in the first area based on the first and second predicted probabilities. This device can detect paper foreign objects at the first moment, stop the washing program before they spread and are damaged, and analyze the collected false alarm and missed detection information data to optimize the detection algorithm online, continuously improve detection performance, and enhance user experience, thus solving the problem of existing washing machines being unable to distinguish foreign objects in clothes.

[0077] In some examples, the positioning unit includes a first positioning module, a second positioning module, and a third positioning module. The first positioning module controls the washing machine to enter a waterless rotation mode and acquires first image data of the object inside the washing machine. The second positioning module constructs a YOLO object detection algorithm based on a backbone network, a feature enhancement network, and an object detection head. This YOLO object detection algorithm is trained using multiple sets of training data, each set including historical image data of objects inside the washing machine acquired within a historical time period, and corresponding label data for those historical objects. The third positioning module inputs the first image data into the YOLO object detection algorithm to obtain the positioning result of the first region. The YOLO object detection algorithm is used to locate and crop the pocket area of ​​clothing, effectively narrowing the detection area for foreign object identification.

[0078] In some examples, the first acquisition unit includes a first acquisition module, a second acquisition module, and a third acquisition module. The first acquisition module is used to extract the second image data from the first image data. The second acquisition module is used to acquire a binary classification algorithm, which is one of the following: Support Vector Machine (SVM), Random Forest, or Decision Tree. The third acquisition module is used to determine the first predicted probability based on the second image data using the aforementioned binary classification algorithm. A trained SVM model is used to perform a binary classification to determine whether a paper object is present, and the probability of having a paper object is output.

[0079] In some examples, the second acquisition unit includes a fourth acquisition module, a fifth acquisition module, a sixth acquisition module, and a seventh acquisition module. The fourth acquisition module is used to actively emit first infrared light towards the object in the washing machine using active infrared technology, and receive the second infrared light reflected by the object through a detector. The active infrared technology is a technology that uses an infrared light source to actively emit infrared light to detect objects. The fifth acquisition module is used to convert the second infrared light into an electrical signal to obtain the infrared sensing data, and to amplify and filter the infrared sensing data to obtain a processed digital signal. The sixth acquisition module is used to generate an infrared image of the object based on the processed digital signal using image processing technology. The seventh acquisition module is used to input the infrared image into the deep neural network to obtain the second predicted probability. Introducing an infrared sensing detection branch improves the accuracy of judgment, reduces false alarms, minimizes losses, and enhances the user experience.

[0080] In some instances, the determining unit includes a first determining module and a second determining module, wherein the first determining module is used to obtain the weighted average formula A = α. SVM ×0.5+α Infrared ×0.5, where A is the final predicted probability mentioned above, αSVM Let α be the first predicted probability mentioned above. Infrared The second prediction probability is given above; the second determining module is used to determine the final predicted probability of the presence of foreign objects in the first region based on the weighted average formula mentioned above. Compared to judging based on only one condition, this improves the accuracy of the prediction results and reduces false alarms.

[0081] In some instances, the determining unit further includes a third determining module and a fourth determining module. The third determining module is used to stop the washing machine's washing program and issue a warning message when the final predicted probability of a foreign object in the first area is greater than or equal to a preset probability. The fourth determining module is used to start the washing machine's washing program when the final predicted probability of a foreign object in the first area is less than the preset probability. When A is greater than 0.6, it is considered that a paper foreign object is present.

[0082] In some instances, the fourth determining module is also used to repeatedly execute the aforementioned positioning step, the aforementioned first acquisition step, the aforementioned second acquisition step, and the aforementioned determining step until the aforementioned final predicted probability is greater than or equal to the aforementioned preset probability or the washing machine finishes washing. By continuously upgrading the detection algorithm online, the washing machine's ability to identify paper foreign objects is enhanced, thereby improving the user experience.

[0083] The aforementioned foreign object identification device in the washing machine includes a processor and a memory. The aforementioned positioning units, etc., are all stored as program units in the memory, and the processor executes these program units stored in the memory to achieve the corresponding functions. All of the aforementioned modules are located in the same processor; alternatively, the aforementioned modules may be located in different processors in any combination.

[0084] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured; by adjusting kernel parameters, the problem of existing washing machines being unable to detect foreign objects in clothing can be solved.

[0085] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0086] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the foreign object identification method in the washing machine.

[0087] Specifically, methods for identifying foreign objects in a washing machine include:

[0088] Step S201 (Location Step): Obtain first image data of the object in the washing machine, and use a target detection algorithm to locate the first region on the object in the washing machine based on the first image data.

[0089] Specifically, visual sensors are used to monitor the laundry environment, and the YOLO object detection algorithm is used to locate and capture the pocket area of ​​clothing, effectively narrowing the detection area for identifying foreign objects.

[0090] Step S202 (first acquisition step): acquire the second image data of the first region, and determine the probability of the presence of foreign objects in the first region as the first predicted probability based on the second image data and the binary classification algorithm;

[0091] Specifically, the pocket area is classified into two categories based on whether there are paper foreign objects. If paper foreign objects are found, an alarm is triggered and the washing program is stopped to prevent paper scraps from contaminating clothes and causing them to be difficult to clean, thus improving the user experience.

[0092] Step S203 (Second Acquisition Step): Acquire the infrared sensing data of the first region, and determine the probability of the presence of foreign objects in the first region as the second predicted probability based on the infrared sensing data and the deep neural network.

[0093] Specifically, an infrared sensing detection branch is introduced to improve the accuracy of judgment, reduce false alarms, reduce losses, and improve the user experience.

[0094] Step S204 (Determination Step): Based on the first prediction probability and the second prediction probability, determine the final prediction probability that there is a foreign object in the first region.

[0095] Specifically, by using a weighted approach combining binary classification and infrared scanning to predict whether a paper foreign object is present in the pocket area, the results are more accurate compared to judging based on only one condition. This reduces false alarms, minimizes losses, and improves the user experience. Furthermore, feedback on false alarm data allows for continuous optimization of paper foreign object recognition performance.

[0096] Optionally, acquiring first image data of an object in the washing machine and using an object detection algorithm to locate a first region on the object in the washing machine based on the first image data includes: controlling the washing machine to enter a waterless rotation mode and acquiring first image data of the object in the washing machine; constructing a YOLO object detection algorithm based on a backbone network, a feature enhancement network, and an object detection head, wherein the YOLO object detection algorithm is trained using multiple sets of training data, each set of training data including: historical image data of historical objects in the washing machine and label data of the historical objects corresponding to the historical object image data acquired within a historical time period; inputting the first image data into the YOLO object detection algorithm to obtain the localization result of the first region.

[0097] Optionally, acquiring second image data of the first region and determining the probability of the presence of a foreign object in the first region as a first predicted probability based on the second image data and a binary classification algorithm includes: extracting the second image data from the first image data; acquiring a binary classification algorithm, wherein the binary classification algorithm is one of the following: support vector machine, random forest algorithm, decision tree algorithm; and using the binary classification algorithm to determine the first predicted probability based on the second image data.

[0098] Optionally, acquiring infrared sensing data of the first region and determining the probability of the presence of a foreign object in the first region as a second predicted probability based on the infrared sensing data and a deep neural network includes: actively emitting first infrared light towards the object in the washing machine using active infrared technology and receiving second infrared light reflected by the object through a detector; the active infrared technology being a technology that actively emits infrared light from an infrared light source to detect objects; converting the second infrared light into an electrical signal to obtain the infrared sensing data, and amplifying and filtering the infrared sensing data to obtain a processed digital signal; generating an infrared image of the object using image processing technology based on the processed digital signal; and inputting the infrared image into the deep neural network to obtain the second predicted probability.

[0099] Optionally, based on the first predicted probability and the second predicted probability, the final predicted probability of the presence of a foreign object in the first region is determined, including obtaining the weighted average formula A = α. SVM ×0.5+α Infrared ×0.5, where A is the final predicted probability mentioned above, and α SVM Let α be the first predicted probability mentioned above. Infrared The second predicted probability is given above; the final predicted probability of the presence of foreign objects in the first region is determined according to the weighted average formula mentioned above.

[0100] Optionally, after determining the final predicted probability of the presence of a foreign object in the first region based on the first predicted probability and the second predicted probability, the method further includes: stopping the washing program of the washing machine and issuing a warning message when the final predicted probability of the presence of a foreign object in the first region is greater than or equal to a preset probability; and entering the washing program of the washing machine when the final predicted probability of the presence of a foreign object in the first region is less than the preset probability.

[0101] Optionally, if the final predicted probability of the presence of a foreign object in the first region is less than the preset probability, after entering the washing program of the washing machine, the method further includes: repeatedly executing the positioning step, the first acquisition step, the second acquisition step, and the determination step until the final predicted probability is greater than or equal to the preset probability or the washing machine finishes washing.

[0102] This invention provides a processor for running a program, wherein the program executes the method for identifying foreign objects in the washing machine.

[0103] Specifically, methods for identifying foreign objects in a washing machine include:

[0104] Step S201 (Location Step): Obtain first image data of the object in the washing machine, and use a target detection algorithm to locate the first region on the object in the washing machine based on the first image data.

[0105] Specifically, visual sensors are used to monitor the laundry environment, and the YOLO object detection algorithm is used to locate and capture the pocket area of ​​clothing, effectively narrowing the detection area for identifying foreign objects.

[0106] Step S202 (first acquisition step): acquire the second image data of the first region, and determine the probability of the presence of foreign objects in the first region as the first predicted probability based on the second image data and the binary classification algorithm;

[0107] Specifically, the pocket area is classified into two categories based on whether there are paper foreign objects. If paper foreign objects are found, an alarm is triggered and the washing program is stopped to prevent paper scraps from contaminating clothes and causing them to be difficult to clean, thus improving the user experience.

[0108] Step S203 (Second Acquisition Step): Acquire the infrared sensing data of the first region, and determine the probability of the presence of foreign objects in the first region as the second predicted probability based on the infrared sensing data and the deep neural network.

[0109] Specifically, an infrared sensing detection branch is introduced to improve the accuracy of judgment, reduce false alarms, reduce losses, and improve the user experience.

[0110] Step S204 (Determination Step): Based on the first prediction probability and the second prediction probability, determine the final prediction probability that there is a foreign object in the first region.

[0111] Specifically, by using a weighted approach combining binary classification and infrared scanning to predict whether a paper foreign object is present in the pocket area, the results are more accurate compared to judging based on only one condition. This reduces false alarms, minimizes losses, and improves the user experience. Furthermore, feedback on false alarm data allows for continuous optimization of paper foreign object recognition performance.

[0112] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0113] Step S201 (Location Step): Obtain first image data of the object in the washing machine, and use a target detection algorithm to locate the first region on the object in the washing machine based on the first image data.

[0114] Specifically, visual sensors are used to monitor the laundry environment, and the YOLO object detection algorithm is used to locate and capture the pocket area of ​​clothing, effectively narrowing the detection area for identifying foreign objects.

[0115] Step S202 (first acquisition step): acquire the second image data of the first region, and determine the probability of the presence of foreign objects in the first region as the first predicted probability based on the second image data and the binary classification algorithm;

[0116] Specifically, the pocket area is classified into two categories based on whether there are paper foreign objects. If paper foreign objects are found, an alarm is triggered and the washing program is stopped to prevent paper scraps from contaminating clothes and causing them to be difficult to clean, thus improving the user experience.

[0117] Step S203 (Second Acquisition Step): Acquire the infrared sensing data of the first region, and determine the probability of the presence of foreign objects in the first region as the second predicted probability based on the infrared sensing data and the deep neural network.

[0118] Specifically, an infrared sensing detection branch is introduced to improve the accuracy of judgment, reduce false alarms, reduce losses, and improve the user experience.

[0119] Step S204 (Determination Step): Based on the first prediction probability and the second prediction probability, determine the final prediction probability that there is a foreign object in the first region.

[0120] Specifically, by using a weighted approach combining binary classification and infrared scanning to predict whether a paper foreign object is present in the pocket area, the results are more accurate compared to judging based on only one condition. This reduces false alarms, minimizes losses, and improves the user experience. Furthermore, feedback on false alarm data allows for continuous optimization of paper foreign object recognition performance.

[0121] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0122] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0123] Step S201 (Location Step): Obtain first image data of the object in the washing machine, and use a target detection algorithm to locate the first region on the object in the washing machine based on the first image data.

[0124] Specifically, visual sensors are used to monitor the laundry environment, and the YOLO object detection algorithm is used to locate and capture the pocket area of ​​clothing, effectively narrowing the detection area for identifying foreign objects.

[0125] Step S202 (first acquisition step): acquire the second image data of the first region, and determine the probability of the presence of foreign objects in the first region as the first predicted probability based on the second image data and the binary classification algorithm;

[0126] Specifically, the pocket area is classified into two categories based on whether there are paper foreign objects. If paper foreign objects are found, an alarm is triggered and the washing program is stopped to prevent paper scraps from contaminating clothes and causing them to be difficult to clean, thus improving the user experience.

[0127] Step S203 (Second Acquisition Step): Acquire the infrared sensing data of the first region, and determine the probability of the presence of foreign objects in the first region as the second predicted probability based on the infrared sensing data and the deep neural network.

[0128] Specifically, an infrared sensing detection branch is introduced to improve the accuracy of judgment, reduce false alarms, reduce losses, and improve the user experience.

[0129] Step S204 (Determination Step): Based on the first prediction probability and the second prediction probability, determine the final prediction probability that there is a foreign object in the first region.

[0130] Specifically, by using a weighted approach combining binary classification and infrared scanning to predict whether a paper foreign object is present in the pocket area, the results are more accurate compared to judging based on only one condition. This reduces false alarms, minimizes losses, and improves the user experience. Furthermore, feedback on false alarm data allows for continuous optimization of paper foreign object recognition performance.

[0131] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0132] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0134] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0136] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0137] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0138] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0139] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0140] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0141] 1) The foreign object identification method in the washing machine described in this application firstly involves a positioning step, where first image data of an object in the washing machine is acquired, and a target detection algorithm is used to locate a first region on the object in the washing machine based on the first image data. Next, a first acquisition step is performed, acquiring second image data of the first region and determining the probability of a foreign object in the first region as a first predicted probability based on the second image data and a binary classification algorithm. Then, a second acquisition step is performed, acquiring infrared sensing data of the first region and determining the probability of a foreign object in the first region as a second predicted probability based on the infrared sensing data and a deep neural network. Finally, a determination step is performed, determining the final predicted probability of a foreign object in the first region based on the first and second predicted probabilities. This method can detect paper-based foreign objects in real time, stopping the washing program before they spread and become damaged. Furthermore, it analyzes the collected false alarm and missed detection data, optimizes the detection algorithm online, continuously improves detection performance, and enhances user experience, solving the problem of existing washing machines being unable to distinguish foreign objects in clothing.

[0142] 2) The foreign object identification device in the washing machine described in this application includes: a positioning unit, a first acquisition unit, a second acquisition unit, and a determination unit. The positioning unit is used to locate a first area on an object in the washing machine using a target detection algorithm. The first acquisition unit is used to acquire real-time image data of the first area and determine the probability of a foreign object in the first area as a first predicted probability based on the real-time image data and a support vector machine model. The second acquisition unit is used to acquire infrared sensing data of the first area and determine the probability of a foreign object in the first area as a second predicted probability based on the infrared sensing data and a deep neural network. The determination unit is used to determine the final predicted probability of a foreign object in the first area based on the first and second predicted probabilities. This device can detect paper foreign objects at the first moment, stop the washing program before they spread and are damaged, and analyze the collected missed and false alarm information data to optimize the detection algorithm online, continuously improve detection performance, and enhance user experience, thus solving the problem of existing washing machines being unable to distinguish foreign objects in clothes.

[0143] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for identifying foreign objects in a washing machine, characterized in that, include: The positioning step involves acquiring first image data of an object in the washing machine and using a target detection algorithm to locate a first region on the object in the washing machine based on the first image data. The first acquisition step involves acquiring second image data of the first region and determining the probability of the presence of a foreign object in the first region as a first predicted probability based on the second image data and a binary classification algorithm. The second acquisition step involves acquiring infrared sensing data of the first region and determining the probability of the presence of foreign objects in the first region as a second predicted probability based on the infrared sensing data and the deep neural network. The determination step involves determining the final predicted probability of the presence of a foreign object in the first region based on the first predicted probability and the second predicted probability. Acquire first image data of an object in the washing machine, and use an object detection algorithm to locate a first region on the object in the washing machine based on the first image data, including: Control the washing machine to enter a waterless rotation mode and acquire the first image data of the object in the washing machine; The YOLO object detection algorithm is constructed based on the backbone network, feature enhancement network, and object detection head. The YOLO object detection algorithm is trained using multiple sets of training data. Each set of training data includes: image data of historical objects in the washing machine and label data of the historical objects corresponding to the image data of the historical objects, acquired within a historical time period. The first image data is input into the YOLO target detection algorithm to obtain the localization result of the first region; Acquire infrared sensing data of the first region, and determine the probability of the presence of a foreign object in the first region as a second predicted probability based on the infrared sensing data and a deep neural network, including: Active infrared technology is used to actively emit first infrared light towards objects in the washing machine, and a detector receives the second infrared light reflected by the objects. The active infrared technology is a technology in which an infrared light source actively emits infrared light to detect objects. The second infrared light is converted into an electrical signal to obtain the infrared sensing data, and the infrared sensing data is amplified and filtered to obtain a processed digital signal. An infrared image of the object is generated using image processing technology based on the processed digital signal; The infrared image is input into the deep neural network to obtain the second predicted probability.

2. The method according to claim 1, characterized in that, Acquire second image data of the first region, and determine the probability of the presence of a foreign object in the first region as a first predicted probability based on the second image data and a binary classification algorithm, including: Extract the second image data from the first image data; Obtain a binary classification algorithm, wherein the binary classification algorithm is one of the following: support vector machine, random forest algorithm, decision tree algorithm; The binary classification algorithm is used to determine the first predicted probability based on the second image data.

3. The method according to claim 1, characterized in that, Based on the first predicted probability and the second predicted probability, the final predicted probability of the presence of a foreign object in the first region is determined, including: Formula for obtaining weighted average Where A is the final predicted probability. The first predicted probability, This is the second predicted probability; The final predicted probability of the presence of foreign objects in the first region is determined based on the weighted average formula.

4. The method according to claim 1, characterized in that, After determining the final predicted probability of the presence of a foreign object in the first region based on the first predicted probability and the second predicted probability, the method further includes: If the final predicted probability of the presence of a foreign object in the first area is greater than or equal to the preset probability, the washing machine's washing program will be stopped and a warning message will be issued. If the final predicted probability of the presence of a foreign object in the first area is less than the preset probability, the washing machine will proceed with the washing program.

5. The method according to claim 4, characterized in that, If the final predicted probability of a foreign object being present in the first area is less than the preset probability, after entering the washing program of the washing machine, the method further includes: Repeat the positioning step, the first acquisition step, the second acquisition step, and the determination step until the final predicted probability is greater than or equal to the preset probability or the washing machine finishes washing.

6. A device for identifying foreign objects in a washing machine, characterized in that, include: The positioning unit is used to locate a first area on an object in the washing machine using a target detection algorithm; The first acquisition unit is used to acquire real-time image data of the first region, and determine the probability of the presence of foreign objects in the first region as a first predicted probability based on the real-time image data and the support vector machine model. The second acquisition unit is used to acquire infrared sensing data of the first region, and determine the probability of the presence of foreign objects in the first region as a second predicted probability based on the infrared sensing data and the deep neural network. The determining unit is configured to determine the final predicted probability of the presence of a foreign object in the first region based on the first predicted probability and the second predicted probability. The positioning unit includes a first positioning module, a second positioning module, and a third positioning module. The first positioning module is used to control the washing machine to enter a waterless rotation mode and acquire first image data of the object in the washing machine. The second positioning module is used to construct a YOLO object detection algorithm based on a backbone network, a feature enhancement network, and an object detection head. The YOLO object detection algorithm is trained using multiple sets of training data. Each set of training data includes image data of historical objects in the washing machine acquired within a historical time period, as well as label data of the historical objects corresponding to the image data. The third positioning module is used to input the first image data into the YOLO object detection algorithm to obtain the positioning result of the first region. The second acquisition unit includes a fourth acquisition module, a fifth acquisition module, a sixth acquisition module, and a seventh acquisition module. The fourth acquisition module is used to actively emit first infrared light towards the object in the washing machine using active infrared technology, and receive the second infrared light reflected by the object through a detector. The active infrared technology is a technology in which an infrared light source actively emits infrared light to detect objects. The fifth acquisition module is used to convert the second infrared light into an electrical signal to obtain the infrared sensing data, and to amplify and filter the infrared sensing data to obtain a processed digital signal; the sixth acquisition module is used to generate an infrared image of the object based on the processed digital signal using image processing technology; the seventh acquisition module is used to input the infrared image into the deep neural network to obtain the second prediction probability.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the foreign object identification method in the washing machine according to any one of claims 1 to 5.

8. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a method for performing the identification of foreign objects in a washing machine according to any one of claims 1 to 5.

Images