CN112749753B - Electrical equipment control method and device, electrical equipment and storage medium - Google Patents
Electrical equipment control method and device, electrical equipment and storage medium Download PDFInfo
- Publication number
- CN112749753B CN112749753B CN202110061859.3A CN202110061859A CN112749753B CN 112749753 B CN112749753 B CN 112749753B CN 202110061859 A CN202110061859 A CN 202110061859A CN 112749753 B CN112749753 B CN 112749753B
- Authority
- CN
- China
- Prior art keywords
- detected
- image
- features
- pollutant
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 136
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 81
- 231100000719 pollutant Toxicity 0.000 claims abstract description 81
- 238000004140 cleaning Methods 0.000 claims abstract description 42
- 239000000356 contaminant Substances 0.000 claims description 42
- 230000004927 fusion Effects 0.000 claims description 36
- 238000000605 extraction Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 238000002372 labelling Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 3
- 239000000428 dust Substances 0.000 description 10
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000002245 particle Substances 0.000 description 3
- 230000003749 cleanliness Effects 0.000 description 2
- -1 dirt Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B13/00—Accessories or details of general applicability for machines or apparatus for cleaning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Electromagnetism (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The application relates to an electrical equipment control method, an electrical equipment control device, electrical equipment and a storage medium. The method comprises the following steps: acquiring an image to be detected, which is acquired for an area to be detected of electrical equipment; extracting features of the image to be detected to obtain image features of the image to be detected, and performing target detection based on the image features to obtain a pollutant detection result in the area to be detected; and when the pollutant detection result meets the preset condition, sending out prompt information for prompting cleaning of the electrical equipment. By adopting the method, the pollutants in the electrical equipment can be automatically detected, and the user is intelligently prompted to perform cleaning treatment.
Description
Technical Field
The present application relates to the field of intelligent control technologies, and in particular, to an electrical apparatus control method, an electrical apparatus control device, an electrical apparatus, and a storage medium.
Background
After the electric appliance is used for a period of time, pollutants such as dust and the like can be attached to the electric appliance, and the use effect can be affected if the electric appliance is not cleaned. For example, as a common refrigeration/heating apparatus, in the operation process, pollutants such as dust and impurity particles in an external environment enter the air conditioner along with air flow, so that dirt is easily accumulated in the air conditioner, and the cleanliness of blown air is affected, which threatens the health of users, so that the air conditioner needs to be cleaned regularly.
At present, an air conditioner indoor unit is cleaned in a manual cleaning mode, but the cleaning time is required to be judged manually and automatically, and the cleaning time is often difficult to judge accurately, so that the following problems are caused: if the cleaning is frequently carried out, time and labor are wasted, and if the cleaning is carried out for a long time, the cleanliness is difficult to ensure.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an electrical device control method, apparatus, electrical device, and storage medium capable of providing a cleaning prompt.
An electrical device control method, the method comprising:
Acquiring an image to be detected, which is acquired for an area to be detected of electrical equipment;
extracting features of the image to be detected to obtain image features of the image to be detected, and performing target detection based on the image features to obtain a pollutant detection result in the area to be detected;
and when the pollutant detection result meets the preset condition, sending out prompt information for prompting the cleaning of the electrical equipment.
An electrical device control apparatus, the apparatus comprising:
The acquisition module is used for acquiring an image to be detected, which is acquired for a region to be detected of the electrical equipment;
The detection module is used for extracting the characteristics of the image to be detected, obtaining the image characteristics of the image to be detected, and carrying out target detection based on the image characteristics to obtain a pollutant detection result in the area to be detected;
and the control module is used for sending out prompt information for prompting the cleaning of the electrical equipment when the pollutant detection result meets the preset condition.
An electrical device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
Acquiring an image to be detected, which is acquired for an area to be detected of electrical equipment;
extracting features of the image to be detected to obtain image features of the image to be detected, and performing target detection based on the image features to obtain a pollutant detection result in the area to be detected;
and when the pollutant detection result meets the preset condition, sending out prompt information for prompting the cleaning of the electrical equipment.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
Acquiring an image to be detected, which is acquired for an area to be detected of electrical equipment;
extracting features of the image to be detected to obtain image features of the image to be detected, and performing target detection based on the image features to obtain a pollutant detection result in the area to be detected;
and when the pollutant detection result meets the preset condition, sending out prompt information for prompting the cleaning of the electrical equipment.
According to the electrical equipment control method, the electrical equipment control device, the electrical equipment and the storage medium, the image to be detected, which is acquired for the area to be detected of the electrical equipment, is obtained, the feature extraction is carried out on the image to be detected, the image feature of the image to be detected is obtained, the target detection is carried out on the basis of the image feature, the pollutant detection result in the area to be detected is obtained, and when the pollutant detection result meets the preset condition, prompt information for prompting the cleaning of the electrical equipment is sent. Accordingly, the automatic detection can be performed on pollutants in the electrical equipment, the cleaning time is judged according to the pollutant detection result, and when the cleaning is judged to be needed, the user is intelligently prompted to perform cleaning treatment, so that the user does not need to judge the cleaning time by himself, and the labor consumption is reduced.
Drawings
FIG. 1 is an application environment diagram of an electrical device control method in one embodiment;
FIG. 2 is a flow chart of a method of controlling an electrical device in one embodiment;
FIG. 3 is a flow chart of a training method of the object detection model in one embodiment;
FIG. 4 is a schematic diagram of the structure of a target detection model in one embodiment;
Fig. 5 is a block diagram of an electrical device control apparatus in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The electrical equipment control method provided by the application can be applied to the electrical equipment 100 shown in fig. 1. The electrical equipment 100 comprises a control unit 101, an image acquisition unit 102 and a voice unit 103, wherein the image acquisition unit 102 and the voice unit 103 are respectively in communication connection with the control unit 101. The image acquisition unit 102 acquires an image of a region to be detected of the electrical equipment, the control unit 101 acquires the image acquired by the image acquisition unit 102 and detects pollutants in the image, and when a detection result meets a preset condition, a control instruction is sent to the voice unit 103 so that the voice unit 103 sends a cleaning prompt. The image capturing unit 102 may be a camera, and the voice unit 103 may be a speaker.
In one embodiment, the electrical apparatus 100 may further include a WIFI communication unit 104, where the WIFI communication unit 104 is communicatively connected to the control unit 101. WIFI communication unit 104 is also communicatively coupled to an internet of things (IOT) server 105, and user terminal 106 communicates with IOT server 105 via a network. When the detection result meets the preset condition, the control unit 101 may further send a control instruction to the WIFI communication unit 104, so that the WIFI communication unit 104 sends the cleaning prompt information to the user terminal 106 through the IOT server 105, and pushes relevant cleaning service information for the user through the user terminal 106.
In one embodiment, as shown in fig. 2, there is provided an electrical device control method, which is described as an example of application of the method to an electrical device, and includes the following steps S202 to S206.
S202, acquiring an image to be detected, which is acquired for an area to be detected of electrical equipment.
The electrical equipment in the present application may be, but not limited to, equipment that is prone to dust accumulation, such as an air conditioner and a dust collector. Taking an air conditioner as an example, the area to be detected may be an internal area of the air conditioner, and the image to be detected refers to an image of the area to be detected, specifically, a camera may be installed on an inner side of the air conditioner and used for acquiring the image of the area to be detected.
S204, extracting features of the image to be detected to obtain image features of the image to be detected, and performing target detection based on the image features to obtain a pollutant detection result in the area to be detected.
It can be understood that when pollutants such as dust appear in the to-be-detected area, the corresponding to-be-detected image contains pollutant information, target detection is performed on the to-be-detected image, so that the pollutants in the to-be-detected image can be identified, and the pollutant identification result in the to-be-detected image is used as the pollutant detection result in the to-be-detected area.
In one embodiment, a target detection model may be pre-established for detecting contaminants in the image, which may include, but is not limited to, dust, dirt, dust particles, and airborne contaminants, among other types of contaminants. Specifically, an image to be detected is input into a target detection model, the target detection model extracts image features of the image to be detected, mapping is carried out based on the image features, and position information of each detected pollutant in the image to be detected is obtained.
S206, when the pollutant detection result meets the preset condition, a prompt message for prompting cleaning of the electrical equipment is sent out.
The pollutant detection result meets the preset condition, and the pollutant in the area to be detected can be understood to reach the degree of cleaning, namely the cleaning time is reached, so that the electrical equipment sends out a cleaning prompt. The preset conditions may be set in combination with actual conditions, and are not limited thereto.
In one embodiment, the prompt information may be a voice prompt information, specifically, a voice prompt may be directly sent through a voice unit (such as a speaker) in the electrical apparatus to prompt the user to clean the electrical apparatus. In other embodiments, the prompt may also be sent to a user terminal installed with an associated Application (APP) through the IOT server to prompt the user to clean the appliance.
In the electrical equipment control method, the image to be detected, which is acquired for the area to be detected of the electrical equipment, is acquired, the image to be detected is subjected to feature extraction to obtain the image features of the image to be detected, target detection is performed based on the image features to obtain the pollutant detection result in the area to be detected, and when the pollutant detection result meets the preset condition, prompt information for prompting the cleaning of the electrical equipment is sent out. Accordingly, the automatic detection can be performed on pollutants in the electrical equipment, the cleaning time is judged according to the pollutant detection result, and when the cleaning is judged to be needed, the user is intelligently prompted to perform cleaning treatment, so that the user does not need to judge the cleaning time by himself, and the labor consumption is reduced.
In one embodiment, when the pollutant detection result meets the preset condition, the method further comprises: and sending the cleaning service related information to a terminal associated with the electrical equipment.
The cleaning service related information may include, but is not limited to, cleaning operation guide information, cleaning reservation service information, etc., to guide a user to better clean an electric device or to provide a professional clean-up service.
In one embodiment, the contaminant detection result includes a number of contaminants, and when the number of contaminants reaches a number threshold, it is determined that the contaminant detection result satisfies a preset condition.
The number of pollutants refers to the number of targets detected from an image to be detected, specifically, by performing target detection on the image to be detected, position information of each target in the image to be detected can be obtained, and the position information is used for representing the position of each target in the image to be detected, and the number of target positions is taken as the number of targets. The number of contaminants reaches a threshold number indicating that the number of contaminants is sufficiently high to the extent that cleaning is required. The number threshold may be set in combination with actual requirements, which is not limited.
In other embodiments, it may also be determined that the pollutant detection result meets the preset condition when the pollutant density in the area to be detected reaches the density threshold value. The pollutant density can be determined by the ratio of the pollutant quantity to the area of the area to be detected, and the pollutant density reaches a density threshold value, which indicates that the pollutant density is large enough to the extent that cleaning is needed. The density threshold may be set in combination with actual requirements, which is not limited.
In one embodiment, the step of extracting features of the image to be detected to obtain image features of the image to be detected, and performing target detection based on the image features to obtain a detection result of the contaminant in the area to be detected may specifically include: and extracting features of the image to be detected through the target detection model to obtain image features of the image to be detected, and carrying out target detection based on the image features to obtain a pollutant detection result in the area to be detected.
The object detection model is a model for detecting contaminant objects in an image. In one embodiment, as shown in fig. 3, the training method of the object detection model may include the following steps S302 to S306.
S302, acquiring a sample image acquired for a region to be detected and corresponding labeling information thereof, wherein the labeling information comprises: the position information and the category information of each contaminant marked in the sample image.
Labeling each pollutant in the sample image, wherein the position information of the labeled pollutant represents the real position of the pollutant, and the category information of the labeled pollutant represents the real category of the pollutant. In one embodiment, the annotated class information may contain only one class, which is used to indicate that the annotated contaminant is a true contaminant, rather than an image background. In another embodiment, the labeled category information may contain a plurality of categories, such as dust, dirt, dust particles, airborne matter, etc., i.e., the contaminant category is subdivided to represent the actual subdivided category to which the labeled contaminant belongs.
S304, performing target detection on the sample image through a target detection model to be trained to obtain detection information corresponding to the sample image, wherein the detection information comprises: location information and category information of each contaminant detected from the sample image.
And inputting the sample image into a target detection model to be trained, extracting image features of the image to be detected by the target detection model, mapping based on the image features, and outputting detection information corresponding to the sample image. For a detected contaminant, its location information indicates the predicted location of the contaminant, and its category information includes the predicted category and its probability.
S306, adjusting parameters of the target detection model to be trained based on the labeling information and the detection information of the sample image until the training ending condition is met, and obtaining the target detection model.
The loss function may be established based on an error between the labeling information and the detection information of the sample image, and parameters of the target detection model may be adjusted according to a value of the loss function, and the training end condition may be that the value of the loss function is smaller than a preset threshold, or that the accuracy of the test sample meets a preset requirement, or that the iteration number reaches a preset number, where the preset threshold, the preset requirement and the preset number may be set in combination with an actual requirement, and the method is not limited herein.
In the above embodiment, the target detection model is trained, and after the training is completed, the image to be detected is input into the trained target detection model, so that the position information and the category information of each pollutant in the image to be detected can be obtained. Accordingly, the contaminant condition in the area to be detected is intelligently identified through the target detection technology in computer vision, so that the manpower consumption is reduced, and convenience is provided for users.
In one embodiment, the object detection model includes: a feature extraction network, a feature fusion network, and an identification network. The step of extracting features of the image to be detected through the target detection model to obtain image features of the image to be detected, and performing target detection based on the image features to obtain a pollutant detection result in the region to be detected specifically may include the following steps: extracting features of the image to be detected through a feature extraction network to obtain first features of at least two scales; extracting features of the image to be detected through a feature fusion network to obtain second features of at least two scales, wherein the scales of the second features correspond to the scales of the first features, the first features and the second features corresponding to the scales are fused to obtain fusion features of the scales, and the image features comprise the fusion features; and identifying each fusion characteristic through an identification network to obtain a pollutant detection result in the region to be detected.
As shown in fig. 4, a schematic structural diagram of the object detection model in one embodiment is provided, where the feature extraction network includes a convolution layer and 6 sets of residual layers, the feature fusion network includes 5 sets of convolution layers, and a Softmax function is used in the identification network. Specifically, the resolution (scale or size) of the image to be detected is adjusted to 256×256, and the image is input as an input image to the feature extraction network, and the input image is sequentially subjected to a first convolution process (convolution with 8 convolution kernels of 3×3 size) and a second convolution process (convolution with 16 convolution kernels of 3×3 size in steps of two pixels), and a feature map of 128×128 in scale is output. The 128×128 feature map is sequentially processed by six groups of residual layers (the execution times of each group of residual layers are respectively 2, 4 and 4), and the network depth is increased, so that a first feature map with the dimensions of 64×64, 32×32, 16×16, 8×8, 4×4 and 2×2 is obtained, in the six groups of residual layers, except for the difference of the number of convolution kernels and the resolution of the feature map, the structures of each group of residual layers are similar, and the two groups of residual layers are adjusted to achieve the same effect as a pooling layer by the step length of two pixels through the convolution kernels with the corresponding dimensions. In addition, the input image is further processed by 5 groups of convolution layers sequentially, so that second feature images with the scales of 2×2, 4×4, 8×8, 16×16 and 32×32 are obtained, the second feature images extracted by the convolution layers and the first feature images extracted by the residual layers are subjected to cascading operation to fuse feature information with corresponding scales, and in the process, the convolution layers are mainly used for carrying out up-sampling operation on the feature images, and fused features are divided into 5 groups (the scales are respectively 2×2, 4×4, 8×8, 16×16 and 32×32) according to different scales. The Softmax function identifies 5 groups of fusion features with different scales, and target position information and target category information are obtained.
In the above embodiment, the network depth is increased by using the residual layer, so that the contour, texture and other feature information of small-size targets such as dust can be extracted more accurately, and the fusion feature simultaneously contains the contour, texture and other feature information and position feature information of the targets by fusing the feature extracted by the residual layer and the feature extracted by the convolution layer with corresponding dimensions, thereby being beneficial to improving the accuracy of target detection.
In one embodiment, the step of identifying each fusion feature by identifying a network to obtain a detection result of the contaminant in the area to be detected may specifically include the following steps: identifying each fusion feature through an identification network to obtain an identification result and probability thereof corresponding to each fusion feature, wherein the identification result comprises position information and category information of each pollutant; and obtaining a pollutant detection result in the region to be detected according to the probability of each recognition result.
The recognition network is used for recognizing the fusion features of various scales to obtain recognition results and probabilities thereof corresponding to the fusion features of various scales, namely, the fusion features of each scale correspond to position information, class information and probability, and the class information and the position information corresponding to the maximum probability are output as detection results, so that the accuracy of target detection can be further improved.
In one embodiment, the pollutant detection result includes position information of each pollutant in the image to be detected, and the position information of each pollutant in the electrical equipment is obtained according to the position information of each pollutant in the image to be detected and a predetermined conversion relation.
Taking an air conditioner as an example, a camera is installed at the inner side of the air conditioner and used for collecting images of an area to be detected, a conversion relationship exists between a camera coordinate system where the camera is located and an image coordinate system where the images are located, and a conversion relationship also exists between the camera coordinate system and a world coordinate system, and the conversion relationship can be determined in advance in any possible way. Accordingly, after the position information of each contaminant in the image to be detected is obtained, the position information of each contaminant can be converted from the image coordinate system to the world coordinate system according to the predetermined conversion relation, and the position information of each contaminant in the air conditioner, such as the distances between the contaminant and the upper and lower surfaces, the left and right surfaces and the front and rear surfaces of the air conditioner, can be obtained, so that the contaminant position can be more accurately positioned. After the position information of each pollutant in the electrical equipment is obtained, the position information can be carried in the sent prompt information, so that the cleaning can be performed more specifically.
It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a part of the steps in the flowcharts related to the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages performed is not necessarily sequential, but may be performed alternately or alternately with at least a part of the steps or stages in other steps or other steps.
In one embodiment, as shown in fig. 5, there is provided an electrical device control apparatus 500, comprising: an acquisition module 510, a detection module 520, and a control module 530, wherein:
The acquiring module 510 is configured to acquire an image to be detected acquired for an area to be detected of an electrical device.
The detection module 520 is configured to perform feature extraction on an image to be detected, obtain image features of the image to be detected, and perform target detection based on the image features, so as to obtain a pollutant detection result in the area to be detected.
And the control module 530 is configured to send out a prompt message for prompting cleaning of the electrical equipment when the pollutant detection result meets a preset condition.
In one embodiment, the control module 530 is further configured to: and when the pollutant detection result meets the preset condition, sending cleaning service related information to a terminal associated with the electrical equipment.
In one embodiment, the contaminant detection result includes a contaminant number, and the control module 530 is further configured to: and when the number of pollutants reaches a number threshold, judging that the pollutant detection result meets a preset condition.
In one embodiment, the detection module 520 is specifically configured to, when performing feature extraction on an image to be detected to obtain image features of the image to be detected, perform object detection based on the image features, obtain a detection result of a contaminant in the area to be detected: and extracting features of the image to be detected through the target detection model to obtain image features of the image to be detected, and carrying out target detection based on the image features to obtain a pollutant detection result in the area to be detected.
In one embodiment, a training method of a target detection model includes: acquiring a sample image acquired for a region to be detected and corresponding labeling information thereof, wherein the labeling information comprises: the method comprises the steps of marking position information and category information of each pollutant in a sample image; performing target detection on the sample image through a target detection model to be trained to obtain detection information corresponding to the sample image, wherein the detection information comprises: position information and category information of each contaminant detected from the sample image; and adjusting parameters of the target detection model to be trained based on the labeling information and the detection information of the sample image until the training ending condition is met, so as to obtain the target detection model.
In one embodiment, the object detection model includes: a feature extraction network, a feature fusion network and an identification network; the step of extracting features of the image to be detected through the target detection model to obtain image features of the image to be detected, and performing target detection based on the image features to obtain a pollutant detection junction in the region to be detected specifically may include: extracting features of the image to be detected through a feature extraction network to obtain first features of at least two scales; extracting features of the image to be detected through a feature fusion network to obtain second features of at least two scales, wherein the scales of the second features correspond to the scales of the first features, the first features and the second features corresponding to the scales are fused to obtain fusion features of the scales, and the image features comprise the fusion features; and identifying each fusion characteristic through an identification network to obtain a pollutant detection result in the region to be detected.
In one embodiment, the step of identifying each fusion feature by identifying a network to obtain a detection result of the contaminant in the area to be detected may specifically include: identifying each fusion feature through an identification network to obtain an identification result and probability thereof corresponding to each fusion feature, wherein the identification result comprises position information and category information of each pollutant; and obtaining a pollutant detection result in the region to be detected according to the probability of each recognition result.
In one embodiment, the contaminant detection result includes positional information of each contaminant in the image to be detected, the apparatus further comprising: and the position determining module is used for obtaining the position information of each pollutant in the electrical equipment according to the position information of each pollutant in the image to be detected and a predetermined conversion relation.
The specific limitation of the electrical equipment control device may be referred to the limitation of the electrical equipment control method hereinabove, and will not be described herein. The above-mentioned respective modules in the electrical equipment control device may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, an electrical device is provided, including a memory having a computer program stored therein and a processor, which when executing the computer program performs the steps of the method embodiments described above.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.
In one embodiment, a computer program product or computer program is provided that includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-described method embodiments.
It should be appreciated that the terms "first," "second," and the like in the above embodiments are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. The term "plurality" is understood with respect to a description of a range of values as equal to or greater than two.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. An electrical device control method, the method comprising:
Acquiring an image to be detected, which is acquired for an area to be detected of electrical equipment;
Extracting features of the image to be detected through a target detection model to obtain image features of the image to be detected, and performing target detection based on the image features to obtain a pollutant detection result in the region to be detected, wherein the target detection model comprises: a feature extraction network, a feature fusion network and an identification network;
Extracting features of the image to be detected through the feature extraction network to obtain first features of at least two scales; the characteristic extraction network comprises a convolution layer and 6 groups of residual layers, the structures of each group of residual layers are similar, and the two groups of residual layers are adjusted by the convolution kernel with corresponding size in the step length of two pixels to achieve the same effect as the pooling layer;
Extracting features of the image to be detected through the feature fusion network to obtain second features of at least two scales, wherein the scales of the second features correspond to the scales of the first features, the first features and the second features corresponding to the scales are fused to obtain fusion features of the scales, and the image features comprise the fusion features; the feature fusion network comprises 5 groups of convolution layers;
Identifying each fusion characteristic through the identification network to obtain a pollutant detection result in the region to be detected;
and when the pollutant detection result meets the preset condition, sending out prompt information for prompting the cleaning of the electrical equipment.
2. The method according to claim 1, wherein when the pollutant detection result satisfies a preset condition, further comprising: and sending the cleaning service related information to a terminal associated with the electrical equipment.
3. The method of claim 1, wherein the contaminant detection result includes a contaminant number, and the contaminant detection result is determined to satisfy a preset condition when the contaminant number reaches a number threshold.
4. The method of claim 1, wherein the training method of the object detection model comprises:
Acquiring a sample image acquired for the region to be detected and corresponding labeling information thereof, wherein the labeling information comprises: the position information and the category information of each pollutant marked in the sample image;
performing target detection on the sample image through a target detection model to be trained to obtain detection information corresponding to the sample image, wherein the detection information comprises: position information and category information of each contaminant detected from the sample image;
And adjusting parameters of the target detection model to be trained based on the labeling information and the detection information of the sample image until the training ending condition is met, so as to obtain the target detection model.
5. The method of claim 1, wherein identifying each of the fused features via the identification network to obtain a contaminant detection result in the area to be detected comprises:
identifying each fusion feature through the identification network to obtain an identification result and probability thereof corresponding to each fusion feature, wherein the identification result comprises position information and category information of each pollutant;
and obtaining a pollutant detection result in the region to be detected according to the probability of each identification result.
6. The method according to any one of claims 1 to 5, wherein the contaminant detection result includes positional information of each contaminant in the image to be detected, the method further comprising:
And obtaining the position information of each pollutant in the electrical equipment according to the position information of each pollutant in the image to be detected and a predetermined conversion relation.
7. An electrical device control apparatus, the apparatus comprising:
The acquisition module is used for acquiring an image to be detected, which is acquired for a region to be detected of the electrical equipment;
The detection module is used for extracting the characteristics of the image to be detected through a target detection model, obtaining the image characteristics of the image to be detected, carrying out target detection based on the image characteristics, and obtaining the pollutant detection result in the area to be detected, wherein the target detection model comprises: a feature extraction network, a feature fusion network and an identification network; extracting features of the image to be detected through the feature extraction network to obtain first features of at least two scales; the characteristic extraction network comprises a convolution layer and 6 groups of residual layers, the structures of each group of residual layers are similar, and the two groups of residual layers are adjusted by the convolution kernel with corresponding size in the step length of two pixels to achieve the same effect as the pooling layer; extracting features of the image to be detected through the feature fusion network to obtain second features of at least two scales, wherein the scales of the second features correspond to the scales of the first features, the first features and the second features corresponding to the scales are fused to obtain fusion features of the scales, and the image features comprise the fusion features; the feature fusion network comprises 5 groups of convolution layers; identifying each fusion characteristic through the identification network to obtain a pollutant detection result in the region to be detected;
and the control module is used for sending out prompt information for prompting the cleaning of the electrical equipment when the pollutant detection result meets the preset condition.
8. The apparatus of claim 7, wherein the control module is further configured to send cleaning service related information to a terminal associated with the electrical device when the contaminant detection result meets a preset condition.
9. An electrical device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 6 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110061859.3A CN112749753B (en) | 2021-01-18 | 2021-01-18 | Electrical equipment control method and device, electrical equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110061859.3A CN112749753B (en) | 2021-01-18 | 2021-01-18 | Electrical equipment control method and device, electrical equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112749753A CN112749753A (en) | 2021-05-04 |
CN112749753B true CN112749753B (en) | 2024-04-26 |
Family
ID=75652345
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110061859.3A Active CN112749753B (en) | 2021-01-18 | 2021-01-18 | Electrical equipment control method and device, electrical equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112749753B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115469086A (en) * | 2021-06-11 | 2022-12-13 | 广东美的白色家电技术创新中心有限公司 | Electrical equipment, microorganism detection module thereof and microorganism detection method |
CN116274170B (en) * | 2023-03-27 | 2023-10-13 | 中建三局第一建设工程有限责任公司 | Control method, system and related device of laser cleaning equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107606744A (en) * | 2017-10-09 | 2018-01-19 | 珠海格力电器股份有限公司 | Monitoring device and method for air conditioner and air conditioner |
CN108253587A (en) * | 2017-11-29 | 2018-07-06 | 珠海格力电器股份有限公司 | Air cleanliness adjusting method and device |
WO2019100289A1 (en) * | 2017-11-23 | 2019-05-31 | Harman International Industries, Incorporated | Method and system for speech enhancement |
JP2020072311A (en) * | 2018-10-29 | 2020-05-07 | オリンパス株式会社 | Information acquisition device, information acquisition method, information acquisition program, and information acquisition system |
CN111442472A (en) * | 2020-04-10 | 2020-07-24 | 青岛海尔空调器有限总公司 | Air conditioner filter screen cleaning prompting method and air conditioner |
CN111780349A (en) * | 2020-07-15 | 2020-10-16 | 珠海格力电器股份有限公司 | Self-cleaning method and device for air conditioner heat exchanger and air conditioner |
-
2021
- 2021-01-18 CN CN202110061859.3A patent/CN112749753B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107606744A (en) * | 2017-10-09 | 2018-01-19 | 珠海格力电器股份有限公司 | Monitoring device and method for air conditioner and air conditioner |
WO2019100289A1 (en) * | 2017-11-23 | 2019-05-31 | Harman International Industries, Incorporated | Method and system for speech enhancement |
CN108253587A (en) * | 2017-11-29 | 2018-07-06 | 珠海格力电器股份有限公司 | Air cleanliness adjusting method and device |
JP2020072311A (en) * | 2018-10-29 | 2020-05-07 | オリンパス株式会社 | Information acquisition device, information acquisition method, information acquisition program, and information acquisition system |
CN111442472A (en) * | 2020-04-10 | 2020-07-24 | 青岛海尔空调器有限总公司 | Air conditioner filter screen cleaning prompting method and air conditioner |
CN111780349A (en) * | 2020-07-15 | 2020-10-16 | 珠海格力电器股份有限公司 | Self-cleaning method and device for air conditioner heat exchanger and air conditioner |
Also Published As
Publication number | Publication date |
---|---|
CN112749753A (en) | 2021-05-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112749753B (en) | Electrical equipment control method and device, electrical equipment and storage medium | |
CN110705405B (en) | Target labeling method and device | |
CN109800697B (en) | Transformer target detection and appearance defect identification method based on VGG-net style migration | |
CN111680746B (en) | Vehicle damage detection model training, vehicle damage detection method, device, equipment and medium | |
CN111080693A (en) | Robot autonomous classification grabbing method based on YOLOv3 | |
CN110610483B (en) | Crack image acquisition and detection method, computer equipment and readable storage medium | |
CN110991222B (en) | Object state monitoring and sow oestrus monitoring method, device and system | |
CN111814905A (en) | Target detection method, target detection device, computer equipment and storage medium | |
CN111223129A (en) | Detection method, detection device, monitoring equipment and computer readable storage medium | |
CN110307903B (en) | Method for dynamically measuring non-contact temperature of specific part of poultry | |
CN113516651A (en) | Welding joint defect detection method and device based on residual error network | |
CN115359239A (en) | Wind power blade defect detection and positioning method and device, storage medium and electronic equipment | |
CN112837308A (en) | Building crack detection method, device, equipment and storage medium | |
CN111010079A (en) | Multi-sensor-based photovoltaic intelligent cleaning control system and method | |
CN111723723A (en) | Image detection method and device | |
CN110827263B (en) | Magnetic shoe surface defect detection system and detection method based on visual identification technology | |
CN114581419A (en) | Transformer insulating sleeve defect detection method, related equipment and readable storage medium | |
CN110704459B (en) | Cleaning method, medium and system for zombie vehicle data in parking lot | |
CN114596243A (en) | Defect detection method, device, equipment and computer readable storage medium | |
CN116485749A (en) | Self-encoder-based method for identifying dirt in lens module | |
CN110660000A (en) | Data prediction method, device, equipment and computer readable storage medium | |
CN115937492A (en) | Transformer equipment infrared image identification method based on feature identification | |
CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
CN110189301B (en) | Foreign matter detection method for generator stator core steel sheet stacking platform | |
JP2021119802A (en) | Sweeping control method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |