WO2023185574A1 - 设备的运行控制方法和装置、存储介质及电子装置 - Google Patents

设备的运行控制方法和装置、存储介质及电子装置 Download PDF

Info

Publication number
WO2023185574A1
WO2023185574A1 PCT/CN2023/083035 CN2023083035W WO2023185574A1 WO 2023185574 A1 WO2023185574 A1 WO 2023185574A1 CN 2023083035 W CN2023083035 W CN 2023083035W WO 2023185574 A1 WO2023185574 A1 WO 2023185574A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
group
objects
target objects
candidate
Prior art date
Application number
PCT/CN2023/083035
Other languages
English (en)
French (fr)
Inventor
郁顺昌
梁鹤鸣
王文光
Original Assignee
追觅创新科技(苏州)有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 追觅创新科技(苏州)有限公司 filed Critical 追觅创新科技(苏州)有限公司
Publication of WO2023185574A1 publication Critical patent/WO2023185574A1/zh

Links

Classifications

    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/24—Floor-sweeping machines, motor-driven
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/28—Floor-scrubbing machines, motor-driven
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A47L11/4002—Installations of electric equipment
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A47L11/4011—Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
    • A47L2201/04—Automatic control of the travelling movement; Automatic obstacle detection
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
    • A47L2201/06—Control of the cleaning action for autonomous devices; Automatic detection of the surface condition before, during or after cleaning

Definitions

  • This application relates to the field of smart home, specifically, to an operation control method and device for equipment, a storage medium and an electronic device.
  • the area to be cleaned is usually cleaned according to the set operating parameters.
  • the operation control method of the above equipment since the actual status of different areas is not exactly the same, cleaning the area according to the set operating parameters is prone to incomplete cleaning, resulting in the need for multiple cleanings and low cleaning efficiency. .
  • the purpose of this application is to provide an equipment operation control method and device, a storage medium and an electronic device, so as to at least solve the problem of low cleaning efficiency caused by incomplete cleaning in the equipment operation control method in the related art.
  • a method for controlling the operation of equipment includes: collecting images of the area to be cleaned through an image acquisition component on the cleaning equipment to obtain a target ground image; and performing object recognition on the target ground image. , obtain the object parameters of a group of target objects to be cleaned in the area to be cleaned, wherein the object parameters of the group of target objects include the object category of the group of target objects and the aggregation parameters of the group of target objects , the aggregation parameters of the group of target objects are used to represent the aggregation degree of the group of target objects in the area to be cleaned; according to the object category of the group of target objects and the aggregation parameters of the group of target objects , determine the target operating parameters of the cleaning equipment; control according to the target operating parameters The cleaning device cleans the group of target objects.
  • the image acquisition of the area to be cleaned through the image acquisition component on the cleaning device to obtain the target ground image includes: activating the light filling component on the cleaning device, wherein after activation, the The light-filling component is used to fill in the area to be cleaned; the image acquisition component collects images of the area to be cleaned to obtain the target ground image.
  • performing object recognition on the target ground image to obtain object parameters of a group of target objects to be cleaned in the area to be cleaned includes: identifying an object contained in the target ground image. Identify the object shadow of each candidate object in the group of candidate objects to obtain the object size of each candidate object; filter out the one candidate object from the group of candidate objects according to the object size of each candidate object. Group target objects, and obtain object parameters of the group of target objects, wherein the object size of each target object in the group of target objects is less than or equal to the first size threshold.
  • identifying the object shadow of each candidate object in a group of candidate objects contained in the target ground image and obtaining the object size of each candidate object includes: determining the According to the shadow area of the object shadow of each candidate object in the target ground image, the shadow area of each candidate object is obtained; according to the projection angle of each candidate object, the shadow area of each candidate object is The area is converted to the object size of each candidate object.
  • the group of target objects is filtered out from the group of candidate objects according to the object size of each candidate object, and the object parameters of the group of target objects are obtained, including : Determine the candidate object whose object size is less than or equal to the second size threshold in the group of candidate objects as the first target object, wherein the first target object belongs to the group of target objects; according to the first The degree of aggregation of target objects in the area to be cleaned determines the object parameters of the first target object, wherein the object category of the first target object is set to a preset category; for the group of candidate objects Identify the object categories of other candidate objects except the first target object to obtain the object categories of the other candidate objects; determine the candidate objects whose object categories among the other candidate objects belong to the category to be cleaned as the second target Object, wherein the second target object belongs to the group of target objects; according to the object category of the second target object and the aggregation process of the second target object in the area to be cleaned. degree, determining the object parameters of the second object.
  • determining the target operating parameters of the cleaning equipment according to the object category of the group of target objects and the aggregated parameters of the group of target objects includes: When multiple target objects are included, operating parameters corresponding to each target object are determined according to the object category of each target object in the multiple target objects and the aggregation parameters of each target object; A fusion operation is performed on the operating parameters corresponding to each target object to obtain the target operating parameters of the cleaning equipment.
  • the object parameters of the group of target objects further include: position information indicating the object positions of the group of target objects; in the step of controlling the cleaning device according to the target operating parameters, Before cleaning the group of target objects, the method further includes: controlling the cleaning device to move toward the object position of the group of target objects until the cleaning piece of the cleaning device is in contact with the group of target objects. The distance is less than or equal to the target distance threshold.
  • an operation control device for equipment including: a collection unit for collecting images of the area to be cleaned through the image collection component on the cleaning equipment to obtain a target ground image; and an identification unit , used to perform object recognition on the target ground image and obtain the object parameters of a group of target objects to be cleaned in the area to be cleaned, wherein the object parameters of the group of target objects include the object parameters of the group of target objects.
  • Object category and aggregation parameters of the group of target objects are used to represent the aggregation degree of the group of target objects in the area to be cleaned; a determination unit, configured to determine according to the The object category of a group of target objects and the aggregation parameters of the group of target objects determine the target operating parameters of the cleaning equipment; a first control unit is used to control the cleaning equipment to the one according to the target operating parameters.
  • Group target objects for cleaning are used to control the cleaning equipment to the one according to the target operating parameters.
  • the collection unit includes: a starting module for starting a light filling component on the cleaning device, wherein the started light filling component is used to fill the area to be cleaned.
  • Light a starting module for starting a light filling component on the cleaning device, wherein the started light filling component is used to fill the area to be cleaned.
  • acquisition module used to collect images of the area to be cleaned through the image acquisition component to obtain the target ground image.
  • the recognition unit includes: a recognition module, configured to recognize the object shadow of each candidate object in a set of candidate objects contained in the target ground image, and obtain the object shadow of each candidate object.
  • Object size of the object Object size of the object; filter module for each candidate as described Select the object size of the object, filter out the group of target objects from the group of candidate objects, and obtain the object parameters of the group of target objects, wherein the object of each target object in the group of target objects
  • the sizes are all less than or equal to the first size threshold.
  • the identification module includes: a first determination sub-module, used to determine the shadow area of the object shadow of each candidate object in the target ground image, and obtain the shadow area of each candidate object in the target ground image.
  • the shadow area of each candidate object; the conversion submodule is used to convert the shadow area of each candidate object into the object size of each candidate object according to the projection angle of each candidate object.
  • the screening module includes: a second determination sub-module, configured to determine candidate objects whose object size is less than or equal to the second size threshold in the group of candidate objects as the first target object, Wherein, the first target object belongs to the group of target objects; the third determination sub-module is used to determine the first target object according to the degree of aggregation of the first target object in the area to be cleaned.
  • Object parameters wherein the object category of the first target object is set to a preset category; the identification submodule is used to identify the object categories of other candidate objects in the group of candidate objects except the first target object.
  • the fourth determination submodule is used to determine the candidate objects whose object categories among the other candidate objects belong to the category to be cleaned as the second target object, wherein the third Two target objects belong to the group of target objects; a fifth determination submodule is used to determine the second target object according to the object category of the second target object and the degree of aggregation of the second target object in the area to be cleaned.
  • the object parameters of the second object are used to determine the candidate objects whose object categories among the other candidate objects belong to the category to be cleaned as the second target object, wherein the third Two target objects belong to the group of target objects; a fifth determination submodule is used to determine the second target object according to the object category of the second target object and the degree of aggregation of the second target object in the area to be cleaned. The object parameters of the second object.
  • the determining unit includes: a determining module, configured to, when the set of target objects includes a plurality of target objects, determine according to the object category and number of each target object in the plurality of target objects.
  • the aggregation parameters of each target object determine the operating parameters corresponding to each target object; the execution module is used to perform a fusion operation on the operating parameters corresponding to each target object to obtain the operating parameters of the cleaning equipment.
  • the target operating parameters configured to, when the set of target objects includes a plurality of target objects, determine according to the object category and number of each target object in the plurality of target objects.
  • the object parameters of the group of target objects further include: position information indicating the object positions of the group of target objects; the device further includes: a second control unit, configured to Before controlling the cleaning equipment to clean the group of target objects according to the target operating parameters, the cleaning equipment is controlled to move to the object position of the group of target objects until the cleaning member of the cleaning equipment The distance to the set of target objects is less than Or equal to the target distance threshold.
  • a computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the operation of the above device when running. Control Method.
  • an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned steps through the computer program.
  • Equipment operation control method including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned steps through the computer program.
  • the object category and aggregation degree of a group of target objects are used to set the operating parameters of the cleaning equipment, and the image acquisition component on the cleaning equipment collects images of the area to be cleaned to obtain the target ground image;
  • the image is used for object recognition to obtain object parameters of a group of target objects to be cleaned in the area to be cleaned.
  • the object parameters of a group of target objects include a group of object categories of target objects and a group of aggregation parameters of target objects.
  • a group of target objects The aggregation parameters of objects are used to represent the aggregation degree of a group of target objects in the area to be cleaned; the target operating parameters of the cleaning equipment are determined based on the object categories of a group of target objects and the aggregation parameters of a group of target objects; controlled according to the target operating parameters The cleaning equipment cleans a group of target objects.
  • the operating parameters of the cleaning equipment are determined according to the object category and aggregation degree of the objects to be cleaned, the operating parameters of the cleaning equipment can be flexibly adjusted to be suitable for the current objects to be cleaned, ensuring that the current The object to be cleaned can be completely cleaned, which can achieve the purpose of improving the integrity of regional cleaning and achieve the technical effect of improving regional cleaning efficiency, thereby solving the problem of incomplete cleaning caused by the operation control method of equipment in related technologies.
  • Figure 1 is a schematic diagram of the hardware environment of an optional device operation control method according to an embodiment of the present application
  • FIG. 2 is a flowchart of an optional device operation control method according to an embodiment of the present application. intention
  • Figure 3 is an optional mapping diagram according to an embodiment of the present application.
  • Figure 4 is a schematic flowchart of another optional device operation control method according to an embodiment of the present application.
  • Figure 5 is a structural block diagram of an optional equipment operation control device according to an embodiment of the present application.
  • Figure 6 is a structural block diagram of an optional electronic device according to an embodiment of the present application.
  • a method for controlling the operation of equipment is provided.
  • the above-mentioned device operation control method can be applied to the hardware environment composed of the cleaning device 102, the base station 104 and the cloud platform 106 as shown in FIG. 1 .
  • the cleaning device 102 can be connected to the base station 104 and/or the cloud platform 106 (for example, a voice cloud platform) through a network to realize interaction between the cleaning device 102 and the base station 104 and/or the cloud platform 106 .
  • the above-mentioned network may include but is not limited to at least one of the following: wired network, wireless network.
  • the above-mentioned wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, and local area network.
  • the above-mentioned wireless network may include at least one of the following: WIFI (Wireless Fidelity, Wireless Fidelity), Bluetooth, and infrared.
  • WIFI Wireless Fidelity, Wireless Fidelity
  • Bluetooth wireless Fidelity
  • the network used by the cleaning device 102 to communicate with the base station 104 and/or the cloud platform 106 may be the same as the network used by the base station 104 and the cloud platform 106, or may be different.
  • the cleaning equipment 102 may include but is not limited to: a sweeper, a floor washer, etc.
  • the operation control method of the equipment in the embodiment of the present application can be executed individually by the cleaning equipment 102, the base station 104 or the cloud platform 106, or can be executed jointly by at least two of the cleaning equipment 102, the base station 104 and the cloud platform 106.
  • the cleaning device 102 or the base station 104 may also execute the operation control method of the device according to the embodiment of the present application by a client installed thereon.
  • FIG. 2 is a schematic flowchart of an optional operation control method of the equipment according to the embodiment of the present application, such as As shown in Figure 2, the process of this method may include the following steps:
  • Step S202 Use the image acquisition component on the cleaning equipment to collect images of the area to be cleaned to obtain a target ground image.
  • the equipment operation control method in this embodiment can be applied to the scenario of controlling the operating status of the cleaning equipment.
  • the cleaning equipment may be equipment with area cleaning functions (for example, sweeping, cleaning, etc.), such as robots with area cleaning functions.
  • the above-mentioned robots may include but are not limited to one of the following: sweeping robots (i.e., floor sweepers), floor scrubbers Robot (i.e., floor washing machine) is a robot that integrates washing and mopping.
  • the cleaning equipment during the process of area cleaning, the cleaning equipment usually performs area cleaning according to set fixed operating parameters.
  • the operating parameters required to clean the area will vary depending on the objects to be cleaned in the area. If the fixed operating parameters are always the cleaning parameters corresponding to the cleaning dust, the cleaning equipment will be unable to clean some types of objects to be cleaned, and will produce a large amount of dust when cleaning other types of objects to be cleaned. Waste of resources.
  • the object to be cleaned is an object that is relatively easy to clean, such as dust
  • the object to be cleaned is an object with larger particles, or is sticky, which is difficult to clean
  • the cleaning equipment can first determine the object category and aggregation degree of the objects to be cleaned, determine the operating parameters of the cleaning equipment based on the determined object category and aggregation level, and operate according to the determined Parameter control of the cleaning equipment to clean the object to be cleaned can ensure that when the cleaning equipment cleans the current object to be cleaned, its operating parameters are suitable for the current object to be cleaned, which can improve the cleaning efficiency of the cleaning equipment while saving resource consumption.
  • the cleaning equipment can collect images of the area to be cleaned through the image acquisition component on the cleaning equipment to obtain a target ground image.
  • the above-mentioned image acquisition device may be a camera, a camera (for example, a macro camera), or other components with an image acquisition function, which is not limited in this embodiment.
  • a sweeper can use a macro camera to obtain ground images (the above-mentioned target ground An example of a surface image).
  • multiple image acquisition components can be installed on the cleaning equipment, and images of the area to be cleaned are collected through some or all of the multiple image acquisition components to obtain Multiple ground images.
  • the target ground image may be multiple ground images, or it may be one ground image obtained by processing multiple ground images.
  • the above-mentioned process of processing multiple ground images may be splicing multiple ground images, or may be feature fusion of multiple ground images, which is not limited in this embodiment.
  • Multiple image acquisition components can be arranged at different positions of the cleaning equipment, or they can be arranged at the same position of the cleaning equipment.
  • an image acquisition component can be arranged on the bottom surface of the sweeping robot to collect images of the area to be cleaned at the bottom.
  • An image acquisition component may also be provided in front of the sweeping robot to collect images of the area to be cleaned in front, which is not limited in this embodiment.
  • the image acquisition component when used to collect images of the area to be cleaned, the image acquisition component can be used to collect images of the area to be cleaned multiple times to obtain multiple ground images.
  • the target ground image may be multiple ground images, or it may be one ground image obtained by processing multiple ground images.
  • Step S204 Perform object recognition on the target ground image to obtain object parameters of a group of target objects to be cleaned in the area to be cleaned, where the object parameters of a group of target objects include a group of object categories of target objects and a group of target objects.
  • Aggregation parameters, the aggregation parameters of a group of target objects are used to represent the degree of aggregation of a group of target objects in the area to be cleaned.
  • the cleaning device can perform object recognition on the target ground image to obtain object parameters of a group of target objects to be cleaned in the area to be cleaned.
  • a group of target objects can be dirt particles in the area.
  • the object parameters of a set of target objects may include: an object category of a set of target objects, aggregation parameters of a set of target objects, and may also include other parameters of a set of target objects, such as object positions, where the aggregation of a set of target objects Parameters are used to represent the degree of aggregation of a group of target objects in the area to be cleaned.
  • the process of object recognition on the target ground image may be: first perform object recognition on the target ground image, and determine the object position and location of each target object in a group of target objects included in the target ground image. The object's object class, and then based on each target object The object location and the object category of each target object determine the object parameters of a set of target objects.
  • the method of determining the object position of each target object may be: first determine the object position of each target object in the target ground image, and then determine the target object in the area to be cleaned based on the conversion relationship between the target ground image and the area to be cleaned. object position in .
  • the method of determining the object category of each target object may be: extracting the object characteristics of each target object, and determining the object category of each target object based on the object characteristics of each target object.
  • the object category with the largest number of target objects included in the group of target objects can be determined as the object category of the group of target objects, or the corresponding object category in a group of target objects can be determined. All object categories are determined as the object categories of a group of target objects. At this time, a group of target objects can have one or more object categories.
  • the distribution of a group of target objects in the area to be cleaned can be determined based on the object position of each target object (which can be expressed by density or other parameters), and based on a The distribution of a group of target objects in the area to be cleaned determines the aggregation parameters of a group of target objects.
  • the aggregation parameters of a group of target objects may be determined based on the brightness corresponding to the object positions of a group of target objects in the target ground image.
  • the brightness corresponding to the object positions of a group of target objects is lower, the higher the aggregation parameter of a group of target objects is (that is, the higher the aggregation degree of a group of target objects in the area to be cleaned).
  • Step S206 Determine the target operating parameters of the cleaning equipment based on the object categories of a group of target objects and the aggregation parameters of a group of target objects.
  • the cleaning device may determine the target of the cleaning device based on the object categories of a group of target objects and the aggregation parameters of a group of target objects.
  • Operating parameters For example, after determining that the object to be cleaned is cat litter and the aggregation parameters of the cat litter, the sweeping robot can determine the operating parameters used to clean the cat litter based on the determined aggregation parameters of the cat litter.
  • the cleaning device may store a mapping table of target operating parameters corresponding to different aggregation parameters under different object categories.
  • the above-mentioned process of determining the target operating parameters of the cleaning equipment may be: according to the object categories and aggregation parameters of a group of target objects, the corresponding operating parameters are found in the mapping table to obtain the target operating parameters.
  • the target operating parameters may include operating parameters of a plurality of equipment components on the cleaning equipment, and may include operating parameters of a liquid storage component (for example, a water tank),
  • the operating parameters of the cleaning parts eg, roller brush, mop, etc.
  • the sweeping robot determines that the object category of a group of objects to be cleaned is A and the aggregation parameter is B, it can find the operating parameters corresponding to the object category A and the aggregation parameter B in the mapping table ( That is, operating parameter C).
  • Step S208 Control the cleaning equipment to clean a group of target objects according to the target operating parameters.
  • the cleaning device can control the cleaning device to clean a group of target objects according to the target operating parameters.
  • the cleaning equipment can adjust the operating status of the cleaning parts in the cleaning equipment according to the target operating parameters, so that the cleaning parts clean a group of target objects at a rotation speed corresponding to the object category and aggregation parameters of the group of target objects.
  • the mop of the sweeping robot can be controlled to clean a group of objects to be cleaned according to the determined operating parameter C.
  • the cleaning equipment when controlling the cleaning equipment to clean a group of target objects according to the target operating parameters, can first move to the object position of the group of target objects in the area to be cleaned, and then control the cleaning equipment to clean a group of target objects according to the target operating parameters.
  • the target objects are cleaned to achieve personalized cleaning of a group of target objects (ie, targeted cleaning of a group of target objects).
  • the image acquisition component on the cleaning equipment collects images of the area to be cleaned to obtain a target ground image; object recognition is performed on the target ground image to obtain a group of target objects to be cleaned in the area to be cleaned.
  • Parameters, wherein the object parameters of a set of target objects include a set of object categories of the target objects and a set of aggregation parameters of the target objects.
  • the set of aggregation parameters of the target objects are used to represent the degree of aggregation of a set of target objects in the area to be cleaned.
  • the control method has the problem of low cleaning efficiency due to incomplete cleaning, and improves the efficiency of regional cleaning.
  • the image acquisition component on the cleaning equipment collects images of the area to be cleaned to obtain a target ground image, including:
  • S12 Use the image acquisition component to collect images of the area to be cleaned to obtain the target ground image.
  • the area to be cleaned in order to improve the image quality of the ground image, when it is necessary to collect images of the area to be cleaned, the area to be cleaned can be filled with light first, and then the image acquisition component can collect images of the area to be cleaned to obtain the target ground image. With the help of fill light, the clarity of collected ground images can be improved, thereby improving the accuracy of object recognition.
  • filling the area to be cleaned with light can be: activating the light filling component on the cleaning device.
  • the activated light filling component can be used to fill the area to be cleaned with light.
  • the image acquisition component collects images of the area to be cleaned. During the process, the fill light component can always be turned on.
  • the above-mentioned light-filling component may be a fill-light lamp provided on the cleaning equipment, or may be other light-filling components provided on the cleaning equipment, which is not limited in this embodiment.
  • the light-filling component may use white light, yellow light, or other colors of light to fill the area to be cleaned, which is not limited in this embodiment.
  • the light filling component can be turned off to stop filling the area to be cleaned.
  • the light filling component can be a fill light component with an adjustable angle to fill the area to be cleaned in different directions.
  • the cleaning equipment can record the light filling angle of the light filling component, that is, the target ground image can be accompanied by the angle information of the light filling component when the target ground image is collected.
  • the sweeping robot can start the fill light to fill in the area to be cleaned, and use the camera on the sweeping robot to take pictures of the area to be cleaned to obtain a ground image.
  • the image quality of the collected ground image can be improved, and the accuracy of object recognition can be improved.
  • object recognition is performed on the target ground image to obtain object parameters of a group of target objects to be cleaned in the area to be cleaned, including:
  • a group of target objects is selected from a group of candidate objects to obtain a group of object parameters of the target objects, wherein the object size of each target object in the group of target objects is smaller than Or equal to the first size threshold.
  • the target ground image may contain a group of candidate objects, and the group of candidate objects may be all objects in the area to be cleaned, and may or may not be objects to be cleaned.
  • object size recognition can be performed based on the object shadow, and the target objects to be cleaned can be filtered out based on the object size of the candidate objects.
  • the cleaning device may identify the object shadow of each candidate object in a set of candidate objects included in the target ground image, and obtain the object size of each candidate object.
  • the cleaning device may first determine the size of the object shadow of each candidate object, and then determine the object size of each candidate object based on the size of the object shadow of each candidate object.
  • the size of the object shadow of the candidate object may be the area of the object shadow of the candidate object, the perimeter of the object shadow of the candidate object, or the diameter of the object shadow of the candidate object, which is not limited in this embodiment.
  • the conversion ratio between the size of the object shadow of the candidate object and the object size of the candidate object is D.
  • the size of the object shadow of the candidate object is determined to be E
  • the object size E/D of the candidate object can be determined.
  • the cleaning device can filter out a group of target objects from a group of candidate objects according to the object size of each candidate object, and obtain a group of object parameters of the target objects.
  • a first size threshold that is, the maximum size of the object to be cleaned, and the object size of each filtered target object is less than or equal to the first size threshold.
  • the first size threshold is set to 20mm (only an example, the actual size threshold can be set according to actual needs), and the sizes of a group of candidate objects F1, F2, and F3 are 17mm, 18mm, and 24mm respectively.
  • the sweeping robot can determine candidate objects F1 and F2 as objects to be cleaned, and exclude F3 as an object to be cleaned.
  • the target ground image can be sharpened first to highlight the target. object shadow for each candidate object in the ground image, This facilitates the identification of object shadows for each candidate object.
  • the object size of the candidate object in the ground image is determined through the object shadow, and then the objects to be cleaned are filtered according to the object size of the candidate object, which can simplify the process of determining the object to be cleaned, thereby improving the efficiency of area cleaning.
  • the object shadow of each candidate object in a set of candidate objects contained in the target ground image is identified to obtain the object size of each candidate object, including:
  • S32 Convert the shadow area of each candidate object into the object size of each candidate object according to the projection angle of each candidate object.
  • the shadow area of the candidate object is also related to the projection angle of the candidate object.
  • the shadow area when the projection angle is vertical is smaller than the shadow area when the projection angle is oblique.
  • the object size of each candidate object may be determined according to the shadow area of each candidate object and the projection angle of each candidate object.
  • the cleaning equipment can first determine the shadow area of the object shadow of each candidate object in the target ground image to obtain the shadow area of each candidate object; then, according to the projection angle of each candidate object, convert the shadow area of each candidate object The object size for each candidate object.
  • the projection angle of each candidate object may be determined based on the light-filling angle of the light-filling component, or may be determined based on the shooting angle of the candidate object by the image acquisition component, which is not limited in this embodiment.
  • the process of converting the shadow area of each candidate object into the object size of each candidate object may be: determining the quotient of the shadow area (eg, s) and the cosine of the candidate object's projection angle (eg, ⁇ ) as the candidate
  • the object size of the object i.e., s/tan ⁇ ).
  • the object size of the candidate object is determined according to the projection angle and the shadow area, which can improve the accuracy of object size determination.
  • a group of target objects is screened out from a group of candidate objects according to the object size of each candidate object, and a group of object parameters of the target objects are obtained, including:
  • S41 Determine the candidate object whose object size is less than or equal to the second size threshold in a group of candidate objects as the first target object, where the first target object belongs to a group of target objects;
  • S44 Determine the candidate object whose object category belongs to the category to be cleaned among other candidate objects as the second target object, where the second target object belongs to a group of target objects;
  • S45 Determine the object parameters of the second object according to the object category of the second target object and the degree of aggregation of the second target object in the area to be cleaned.
  • candidate objects whose object size is less than or equal to the second size threshold can all be determined as objects to be cleaned without separately identifying them.
  • the object category of each candidate object is directly determined as the preset category (it can also be directly determined as an object to be cleaned without setting).
  • the cleaning device may determine a candidate object whose object size is less than or equal to the second size threshold in a group of candidate objects as the first target object, and the first target object belongs to a group of target objects.
  • the sweeping robot can determine objects with a size smaller than 10 mm as objects to be cleaned.
  • the cleaning device may determine the object parameters of the first target object according to the degree of aggregation of the first target object in the area to be cleaned.
  • the aggregation parameters of the first target object may be the same as in the previous embodiment.
  • the first target object can be directly set as a preset category, and the preset category can be a category to be cleaned, which is not limited in this embodiment.
  • the cleaning device can identify the object categories of the other candidate objects and obtain the object categories of the other candidate objects. For example, for candidate objects with an object size greater than 10 mm and less than 20 mm, the sweeping robot can perform object category recognition on these candidate objects to determine whether the object category of the candidate object is a category to be cleaned.
  • the cleaning device may determine a candidate object whose object category belongs to the category to be cleaned among the other candidate objects as the second target object, and the second target object belongs to a group of target objects.
  • the categories to be cleaned can be preset ones that need to be cleaned object category. For example, if the object category of the other candidate objects is identified as cat litter, it is determined that the other candidate objects belong to the objects to be cleaned. If the object category of the other candidate objects is identified to be small toys, it is determined that the other candidate objects do not belong to the objects to be cleaned. .
  • the cleaning device may determine the object parameters of the second target object according to the object category of the second target object and the degree of aggregation of the second target object in the area to be cleaned, where , the aggregation parameter of the second target object may be determined in the same or similar manner as in the previous embodiment, and the object category of the second target object is the aforementioned identified object category.
  • the target operating parameters of the cleaning equipment are determined based on the object categories of a group of target objects and the aggregated parameters of a group of target objects, including:
  • S52 Perform a fusion operation on the operating parameters corresponding to each target object to obtain the target operating parameters of the cleaning equipment.
  • the object category of a group of target objects may be one type or multiple types. If a group of target objects is a plurality of target objects, the cleaning device can determine the operating parameters corresponding to each target object according to the object category of each target object in the plurality of target objects and the aggregation parameters of each target object. The process of determining the operating parameters corresponding to each target object is similar to the method of determining the target operating parameters in the previous embodiments, and will not be described again here.
  • the operation parameter I1 corresponding to the object G to be cleaned can be determined based on the object category of the object to be cleaned G and the aggregation parameters of the object to be cleaned;
  • the object category of the cleaning object H and the aggregation parameters of the object H to be cleaned determine the operating parameters I2 corresponding to the object H to be cleaned.
  • the cleaning device can perform a fusion operation on the operating parameters corresponding to each target object to obtain the target operating parameters of the cleaning device.
  • the cleaning equipment can fuse the operating parameters I1 and I2 to obtain the final operating parameters (ie, the above target operating parameters).
  • the method of performing the fusion operation on the operating parameters corresponding to each target object may be: performing a superposition operation on the parameter values of the same operating parameters among the operating parameters corresponding to each target object, and adding the superimposed values.
  • the parameter value is used as the parameter value of the same operating parameter, or the maximum value among the parameter values of the same operating parameter is selected as the parameter value of the same operating parameter; all types of operating parameters corresponding to each target object are All operating parameters are stored in the target operating parameters, which are not limited in this embodiment.
  • the operating parameters of the cleaning equipment are obtained, which can improve the accuracy of operating parameter determination and improve the efficiency of regional cleaning.
  • the object parameters of a group of target objects also include: position information used to indicate the object positions of a group of target objects.
  • the object positions of a group of target objects are the positions of a group of target objects in the area to be cleaned. Object location.
  • the object position of a group of target objects may be a region range, or may be the position of a region center point, which is not limited in this embodiment.
  • the above method before controlling the cleaning equipment to clean a group of target objects according to the target operating parameters, the above method also includes:
  • S61 Control the cleaning device to move toward the object position of a group of target objects until the distance between the cleaning piece of the cleaning device and the group of target objects is less than or equal to the target distance threshold.
  • the cleaning device in order to better clean a group of target objects, can first move to the object position of the group of target objects until the distance between the cleaning piece of the cleaning device and the group of target objects is less than or equal to the target distance threshold.
  • the sweeping robot can be controlled to move near a group of objects to be cleaned, so that the cleaning parts of the sweeping robot can better clean the group of objects to be cleaned.
  • the cleaning device when the cleaning device is provided with a distance sensor, the cleaning device can determine the distance between the cleaning piece of the cleaning device and a group of target objects through the distance sensor.
  • the cleaning device can The device can determine the distance between the cleaning piece of the cleaning device and a group of target objects through the image acquisition component, which is not limited in this embodiment.
  • the cleaning equipment is a sweeper
  • the target object is particles (ie, dirt particles)
  • the above-mentioned fill light component is a fill light.
  • This optional example provides a solution for ground impurity identification.
  • the process of the equipment operation control method in this optional example may include the following steps:
  • Step S402 Use a fill light to illuminate the area near the ground, and use a macro camera to obtain a ground image.
  • the near-ground area can be an area 2-3cm from the ground. After using the fill light to illuminate the near-ground area, the camera can be used to obtain ground images.
  • Step S404 Determine the particle size through the ground particle projection, conduct preliminary classification according to the particle size, and perform type identification and positioning of the corresponding particles.
  • Step S406 automatically adjust the suction power and water volume of the sweeper according to the degree and type of particle aggregation, and use the adjusted sweeper to clean the particles to be cleaned. For example, after adjusting the suction force and water volume of the sweeper, the movement of the sweeper can be controlled. Get to where the particles are for precise cleaning of them.
  • the types of particulate impurities on the ground can be distinguished, and different cleaning methods can be used for different types of particulate impurities, which can satisfy personalized cleaning while cleaning the floor more effectively.
  • the method according to the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is Better implementation.
  • the technical solution of the present application essentially or the part that contributes to the existing technology can be implemented as software It is reflected in the form of a software product.
  • the computer software product is stored in a storage medium (such as ROM (Read-Only Memory)/RAM (Random Access Memory), magnetic disk, optical disk), including Several instructions are used to cause a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in various embodiments of this application.
  • FIG. 5 is a structural block diagram of an optional equipment operation control device according to an embodiment of the present application. As shown in Figure 5, the device may include:
  • the acquisition unit 502 is used to collect images of the area to be cleaned through the image acquisition component on the cleaning equipment to obtain the target ground image;
  • the identification unit 504 is connected to the acquisition unit 502 and is used to perform object identification on the target ground image and obtain object parameters of a group of target objects to be cleaned in the area to be cleaned, where the object parameters of a group of target objects include a group of target objects.
  • the object category and a group of target object aggregation parameters, a group of target object aggregation parameters are used to represent the aggregation degree of a group of target objects in the area to be cleaned;
  • the determination unit 506 is connected to the identification unit 504 and is used to determine the target operating parameters of the cleaning equipment according to the object categories of a group of target objects and the aggregate parameters of a group of target objects;
  • the first control unit 508 is connected to the determination unit 506 and is used to control the cleaning equipment to clean a group of target objects according to the target operating parameters.
  • the collection unit 502 in this embodiment can be used to perform the above step S202
  • the identification unit 504 in this embodiment can be used to perform the above step S204
  • the determination unit 506 in this embodiment can be used to perform the above step S202.
  • the first control unit 508 in this embodiment may be used to execute the above step S208.
  • the image acquisition component on the cleaning equipment collects images of the area to be cleaned to obtain the target ground image; performs object recognition on the target ground image to obtain the object parameters of a group of target objects to be cleaned in the area to be cleaned, where,
  • the object parameters of a group of target objects include an object category of a group of target objects and aggregation parameters of a group of target objects.
  • the aggregation parameters of a group of target objects are used to represent the degree of aggregation of a group of target objects in the area to be cleaned; according to a group of The object category of the target object and the aggregation parameters of a set of target objects determine the target of the cleaning device Operation parameters; the cleaning equipment is controlled according to the target operation parameters to clean a group of target objects, which solves the problem of low cleaning efficiency caused by incomplete cleaning in the equipment operation control methods in related technologies, and improves the efficiency of regional cleaning. .
  • the collection unit 502 includes:
  • a start-up module is used to start the light-filling component on the cleaning equipment, wherein the started light-filling component is used to fill the area to be cleaned with light;
  • the acquisition module is used to collect images of the area to be cleaned through the image acquisition component to obtain the target ground image.
  • identification unit 504 includes:
  • a recognition module used to identify the object shadow of each candidate object in a set of candidate objects contained in the target ground image, and obtain the object size of each candidate object
  • the filtering module is used to filter out a group of target objects from a group of candidate objects according to the object size of each candidate object, and obtain the object parameters of a group of target objects, wherein the object of each target object in the group of target objects The sizes are all less than or equal to the first size threshold.
  • the identification module includes:
  • the first determination sub-module is used to determine the shadow area of the object shadow of each candidate object in the target ground image, and obtain the shadow area of each candidate object;
  • the conversion submodule is used to convert the shadow area of each candidate object into the object size of each candidate object according to the projection angle of each candidate object.
  • the screening module includes:
  • the second determination sub-module is used to determine the candidate object whose object size is less than or equal to the second size threshold in a group of candidate objects as the first target object, wherein the first target object belongs to a group of target objects;
  • the third determination sub-module is used to determine the object parameters of the first target object according to the degree of aggregation of the first target object in the area to be cleaned, wherein the object category of the first target object is set as a preset category;
  • the identification submodule is used to identify the object categories of other candidate objects in a group of candidate objects except the first target object, and obtain the object categories of other candidate objects;
  • the fourth determination sub-module is used to determine the candidate object whose object category belongs to the category to be cleaned among other candidate objects as the second target object, wherein the second target object belongs to a group of target objects;
  • the fifth determination sub-module is used to determine the object parameters of the second object according to the object category of the second target object and the degree of aggregation of the second target object in the area to be cleaned.
  • the determining unit 506 includes:
  • a determination module configured to determine, when a group of target objects includes multiple target objects, the object corresponding to each target object based on the object category of each target object and the aggregation parameters of each target object. Operating parameters;
  • the execution module is used to perform a fusion operation on the operating parameters corresponding to each target object to obtain the target operating parameters of the cleaning equipment.
  • the object parameters of a group of target objects further include: position information used to indicate the object positions of a group of target objects; the above device further includes:
  • the second control unit is used to control the cleaning equipment to move to the object position of a group of target objects before controlling the cleaning equipment to clean a group of target objects according to the target operating parameters until the cleaning parts of the cleaning equipment are consistent with the group of target objects.
  • the distance is less than or equal to the target distance threshold.
  • the above module as part of the device, can run in the hardware environment as shown in Figure 1, and can be implemented by software or hardware, where the hardware environment includes a network environment.
  • a storage medium is also provided.
  • the above-mentioned storage medium can be used to execute the program code of the operation control method of any of the above-mentioned devices in the embodiment of the present application.
  • the above storage medium may be located on at least one network device among multiple network devices in the network shown in the above embodiment.
  • the storage medium is configured to store program codes for performing the following steps:
  • S1 collect images of the area to be cleaned through the image acquisition component on the cleaning equipment to obtain the target ground image
  • S2 perform object recognition on the target ground image to obtain object parameters of a group of target objects to be cleaned in the area to be cleaned, where the object parameters of a group of target objects include a group of object categories of target objects and a group of aggregation of target objects.
  • Parameters, a set of aggregate parameters for a target object used in the table Indicates the degree of aggregation of a group of target objects in the area to be cleaned;
  • S3 Determine the target operating parameters of the cleaning equipment based on the object categories of a group of target objects and the aggregation parameters of a group of target objects;
  • the above-mentioned storage medium may include but is not limited to: U disk, ROM, RAM, mobile hard disk, magnetic disk or optical disk and other various media that can store program codes.
  • an electronic device for implementing the operation control method of the above-mentioned device is also provided.
  • the electronic device may be a server, a terminal, or a combination thereof.
  • Figure 6 is a structural block diagram of an optional electronic device according to an embodiment of the present application. As shown in Figure 6, it includes a processor 602, a communication interface 604, a memory 606 and a communication bus 608. The processor 602, the communication interface 604 and memory 606 complete communication with each other through communication bus 608, where,
  • Memory 606 for storing computer programs
  • the processor 602 is used to implement the following steps when executing the computer program stored on the memory 606:
  • S1 collect images of the area to be cleaned through the image acquisition component on the cleaning equipment to obtain the target ground image
  • the object recognition on the target ground image to obtain object parameters of a group of target objects to be cleaned in the area to be cleaned, where the object parameters of a group of target objects include a group of object categories of target objects and a group of aggregation of target objects.
  • the aggregation parameter of a group of target objects is used to represent the degree of aggregation of a group of target objects in the area to be cleaned;
  • S3 Determine the target operating parameters of the cleaning equipment based on the object categories of a group of target objects and the aggregation parameters of a group of target objects;
  • the communication bus may be a PCI (Peripheral Component Interconnect, Peripheral Component Interconnect Standard) bus, or an EISA (Extended Industry Standard Architecture, Extended Industry Standard Architecture) bus, or the like.
  • the communication bus can be divided into address bus, Data bus, control bus, etc. For ease of presentation, only one thick line is used in Figure 6, but it does not mean that there is only one bus or one type of bus.
  • the communication interface is used for communication between the above-mentioned electronic device and other equipment.
  • the above-mentioned memory may include RAM or non-volatile memory (non-volatile memory), for example, at least one disk memory.
  • the memory may also be at least one storage device located remotely from the aforementioned processor.
  • the above-mentioned memory 606 may include, but is not limited to, the acquisition unit 502, the identification unit 504, the determination unit 506, and the first control unit 508 in the control device of the above-mentioned device.
  • it may also include but is not limited to other modular units in the control device of the above equipment, which will not be described again in this example.
  • the above-mentioned processor can be a general-purpose processor, which can include but is not limited to: CPU (Central Processing Unit, central processing unit), NP (Network Processor, network processor), etc.; it can also be a DSP (Digital Signal Processing, digital signal processor) ), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array, field programmable gate array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • CPU Central Processing Unit, central processing unit
  • NP Network Processor, network processor
  • DSP Digital Signal Processing, digital signal processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array, field programmable gate array
  • other programmable logic devices discrete gate or transistor logic devices, discrete hardware components.
  • the device that implements the operation control method of the above device can be a terminal device.
  • the terminal device can be a smart phone (such as an Android phone, iOS phone, etc.), a tablet Computers, handheld computers, and mobile Internet devices (Mobile Internet Devices, MID), PAD and other terminal equipment.
  • FIG. 6 does not limit the structure of the above-mentioned electronic device.
  • the electronic device may also include more or fewer components (such as network interfaces, display devices, etc.) than shown in FIG. 6 , or have a different configuration than that shown in FIG. 6 .
  • the program can be stored in a computer-readable storage medium, and the storage medium can Including: flash disk, ROM, RAM, magnetic disk or optical disk, etc.
  • the integrated unit in the above embodiment is implemented in the form of a software functional unit and serves as an independent When selling or using independent products, they can be stored in the above computer-readable storage media.
  • the technical solution of the present application is essentially or contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, It includes several instructions to cause one or more computer devices (which can be personal computers, servers or network devices, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.
  • the disclosed client can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division.
  • multiple units or components may be combined or may be Integrated into another system, or some features can be ignored, or not implemented.
  • the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the units or modules may be in electrical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.
  • each functional unit in each embodiment of the present application can be integrated into one processing unit, each unit can exist physically alone, or two or more units can be integrated into one unit.
  • the above integrated units can be implemented in the form of hardware or software functional units.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

本申请提供了一种设备的运行控制方法和装置、存储介质及电子装置，上述方法包括：通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；对目标地面图像进行对象识别，得到待清洁区域内待清洁的一组目标对象的对象参数，其中，一组目标对象的对象参数包括一组目标对象的对象类别和一组目标对象的聚集参数，一组目标对象的聚集参数用于表示一组目标对象在待清洁区域中的聚集程度；根据一组目标对象的对象类别和一组目标对象的聚集参数，确定清洁设备的目标运行参数；按照目标运行参数控制清洁设备对一组目标对象进行清洁。通过本申请，解决了相关技术中的设备的运行控制方法存在由于易出现清洁不完全导致的清洁效率低的问题。

Description

设备的运行控制方法和装置、存储介质及电子装置
本申请要求如下专利申请的优先权：于2022年04月01日提交中国专利局、申请号为202210340030.1、发明名称为“设备的运行控制方法和装置、存储介质及电子装置”的中国专利申请，上述专利申请的全部内容通过引用结合在本申请中。
【技术领域】
本申请涉及智能家居领域，具体而言，涉及一种设备的运行控制方法和装置、存储介质及电子装置。
【背景技术】
目前，在控制清洁设备进行区域清洁的过程中，通常按照设置的运行参数对待清洁区域进行清洁。然而，采用上述设备的运行控制方式，由于不同区域的实际状态并不完全相同，按照设定的运行参数进行区域清洁，易出现清洁不完全的情况，导致需要多次清洁，清洁的效率较低。
由此可见，相关技术中的设备的运行控制方法，存在由于易出现清洁不完全导致的清洁效率低的问题。
【发明内容】
本申请的目的在于提供一种设备的运行控制方法和装置、存储介质及电子装置，以至少解决相关技术中的设备的运行控制方法存在由于易出现清洁不完全导致的清洁效率低的问题。
本申请的目的是通过以下技术方案实现：
根据本申请实施例的一个方面，提供了一种设备的运行控制方法，包括：通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；对所述目标地面图像进行对象识别，得到所述待清洁区域内待清洁的一组目标对象的对象参数，其中，所述一组目标对象的对象参数包括所述一组目标对象的对象类别和所述一组目标对象的聚集参数，所述一组目标对象的聚集参数用于表示所述一组目标对象在所述待清洁区域中的聚集程度；根据所述一组目标对象的对象类别和所述一组目标对象的聚集参数，确定所述清洁设备的目标运行参数；按照所述目标运行参数控制 所述清洁设备对所述一组目标对象进行清洁。
在一个示例性实施例中，所述通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像，包括：启动所述清洁设备上的补光部件，其中，启动后的所述补光部件用于对所述待清洁区域进行补光；通过所述图像采集部件对所述待清洁区域进行图像采集，得到所述目标地面图像。
在一个示例性实施例中，所述对所述目标地面图像进行对象识别，得到所述待清洁区域内待清洁的一组目标对象的对象参数，包括：对所述目标地面图像中包含的一组候选对象中的每个候选对象的对象阴影进行识别，得到所述每个候选对象的对象尺寸；按照所述每个候选对象的对象尺寸，从所述一组候选对象中筛选出所述一组目标对象，得到所述一组目标对象的对象参数，其中，所述一组目标对象中的每个目标对象的对象尺寸均小于或者等于第一尺寸阈值。
在一个示例性实施例中，所述对所述目标地面图像中包含的一组候选对象中的每个候选对象的对象阴影进行识别，得到所述每个候选对象的对象尺寸，包括：确定所述每个候选对象在所述目标地面图像中的对象阴影的阴影面积，得到所述每个候选对象的阴影面积；根据所述每个候选对象的投影角度，将所述每个候选对象的阴影面积转换为所述每个候选对象的对象尺寸。
在一个示例性实施例中，所述按照所述每个候选对象的对象尺寸，从所述一组候选对象中筛选出所述一组目标对象，得到所述一组目标对象的对象参数，包括：将所述一组候选对象中对象尺寸小于或者等于第二尺寸阈值的候选对象，确定为第一目标对象，其中，所述第一目标对象属于所述一组目标对象；根据所述第一目标对象在所述待清洁区域中的聚集程度，确定所述第一目标对象的对象参数，其中，所述第一目标对象的对象类别被设置为预设类别；对所述一组候选对象中除了所述第一目标对象以外的其他候选对象的对象类别进行识别，得到所述其他候选对象的对象类别；将所述其他候选对象中对象类别属于待清洁类别的候选对象，确定为第二目标对象，其中，所述第二目标对象属于所述一组目标对象；根据所述第二目标对象的对象类别和所述第二目标对象在所述待清洁区域中的聚集程 度，确定所述第二对象的对象参数。
在一个示例性实施例中，所述根据所述一组目标对象的对象类别和所述一组目标对象的聚集参数，确定所述清洁设备的目标运行参数，包括：在所述一组目标对象包含多种目标对象的情况下，根据所述多种目标对象中的每种目标对象的对象类别和所述每种目标对象的聚集参数，确定与所述每种目标对象对应的运行参数；对与所述每种目标对象对应的运行参数执行融合操作，得到所述清洁设备的所述目标运行参数。
在一个示例性实施例中，所述一组目标对象的对象参数还包括：用于指示所述一组目标对象的对象位置的位置信息；在所述按照所述目标运行参数控制所述清洁设备对所述一组目标对象进行清洁之前，所述方法还包括：控制所述清洁设备向所述一组目标对象的对象位置进行移动，直到所述清洁设备的清洁件与所述一组目标对象的距离小于或者等于目标距离阈值。
根据本申请实施例的另一个方面，还提供了一种设备的运行控制装置，包括：采集单元，用于通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；识别单元，用于对所述目标地面图像进行对象识别，得到所述待清洁区域内待清洁的一组目标对象的对象参数，其中，所述一组目标对象的对象参数包括所述一组目标对象的对象类别和所述一组目标对象的聚集参数，所述一组目标对象的聚集参数用于表示所述一组目标对象在所述待清洁区域中的聚集程度；确定单元，用于根据所述一组目标对象的对象类别和所述一组目标对象的聚集参数，确定所述清洁设备的目标运行参数；第一控制单元，用于按照所述目标运行参数控制所述清洁设备对所述一组目标对象进行清洁。
在一个示例性实施例中，所述采集单元包括：启动模块，用于启动所述清洁设备上的补光部件，其中，启动后的所述补光部件用于对所述待清洁区域进行补光；采集模块，用于通过所述图像采集部件对所述待清洁区域进行图像采集，得到所述目标地面图像。
在一个示例性实施例中，所述识别单元包括：识别模块，用于对所述目标地面图像中包含的一组候选对象中的每个候选对象的对象阴影进行识别，得到所述每个候选对象的对象尺寸；筛选模块，用于按照所述每个候 选对象的对象尺寸，从所述一组候选对象中筛选出所述一组目标对象，得到所述一组目标对象的对象参数，其中，所述一组目标对象中的每个目标对象的对象尺寸均小于或者等于第一尺寸阈值。
在一个示例性实施例中，所述识别模块包括：第一确定子模块，用于确定所述每个候选对象在所述目标地面图像中的对象阴影的阴影面积，得到所述每个候选对象的阴影面积；转换子模块，用于根据所述每个候选对象的投影角度，将所述每个候选对象的阴影面积转换为所述每个候选对象的对象尺寸。
在一个示例性实施例中，所述筛选模块包括：第二确定子模块，用于将所述一组候选对象中对象尺寸小于或者等于第二尺寸阈值的候选对象，确定为第一目标对象，其中，所述第一目标对象属于所述一组目标对象；第三确定子模块，用于根据所述第一目标对象在所述待清洁区域中的聚集程度，确定所述第一目标对象的对象参数，其中，所述第一目标对象的对象类别被设置为预设类别；识别子模块，用于对所述一组候选对象中除了所述第一目标对象以外的其他候选对象的对象类别进行识别，得到所述其他候选对象的对象类别；第四确定子模块，用于将所述其他候选对象中对象类别属于待清洁类别的候选对象，确定为第二目标对象，其中，所述第二目标对象属于所述一组目标对象；第五确定子模块，用于根据所述第二目标对象的对象类别和所述第二目标对象在所述待清洁区域中的聚集程度，确定所述第二对象的对象参数。
在一个示例性实施例中，确定单元包括：确定模块，用于在所述一组目标对象包含多种目标对象的情况下，根据所述多种目标对象中的每种目标对象的对象类别和所述每种目标对象的聚集参数，确定与所述每种目标对象对应的运行参数；执行模块，用于对与所述每种目标对象对应的运行参数执行融合操作，得到所述清洁设备的所述目标运行参数。
在一个示例性实施例中，所述一组目标对象的对象参数还包括：用于指示所述一组目标对象的对象位置的位置信息；所述装置还包括：第二控制单元，用于在所述按照所述目标运行参数控制所述清洁设备对所述一组目标对象进行清洁之前，控制所述清洁设备向所述一组目标对象的对象位置进行移动，直到所述清洁设备的清洁件与所述一组目标对象的距离小于 或者等于目标距离阈值。
根据本申请实施例的又一方面，还提供了一种计算机可读的存储介质，该计算机可读的存储介质中存储有计算机程序，其中，该计算机程序被设置为运行时执行上述设备的运行控制方法。
根据本申请实施例的又一方面，还提供了一种电子装置，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，上述处理器通过计算机程序执行上述的设备的运行控制方法。
在本申请实施例中，采用一组目标对象的对象类别和聚集程度设置清洁设备的运行参数的方式，通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；对目标地面图像进行对象识别，得到待清洁区域内待清洁的一组目标对象的对象参数，其中，一组目标对象的对象参数包括一组目标对象的对象类别和一组目标对象的聚集参数，一组目标对象的聚集参数用于表示一组目标对象在待清洁区域中的聚集程度；根据一组目标对象的对象类别和一组目标对象的聚集参数，确定清洁设备的目标运行参数；按照目标运行参数控制清洁设备对一组目标对象进行清洁，由于根据待清洁对象的对象类别和聚集程度确定清洁设备的运行参数，可以灵活对清洁设备的运行参数进行调整，以适用于当前的待清洁对象，保证当前待清洁对象可以被完全清洁，可以实现提高区域清洁的完整性的目的，达到提高区域清洁效率的技术效果，进而解决了相关技术中的设备的运行控制方法存在由于易出现清洁不完全导致的清洁效率低的问题。
【附图说明】
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本申请的实施例，并与说明书一起用于解释本申请的原理。
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是根据本申请实施例的一种可选的设备的运行控制方法的硬件环境的示意图；
图2是根据本申请实施例的一种可选的设备的运行控制方法的流程示 意图；
图3是根据本申请实施例的一种可选的映射表示意图；
图4是根据本申请实施例的另一种可选的设备的运行控制方法的流程示意图；
图5是根据本申请实施例的一种可选的设备的运行控制装置的结构框图；
图6是根据本申请实施例的一种可选的电子装置的结构框图。
【具体实施方式】
下文中将参考附图并结合实施例来详细说明本申请。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
根据本申请实施例的一个方面，提供了一种设备的运行控制方法。可选地，在本实施例中，上述设备的运行控制方法可以应用于如图1所示的由清洁设备102、基站104和云平台106所构成的硬件环境中。如图1所示，清洁设备102可以通过网络与基站104和/或云平台106(例如，语音云平台)进行连接，以实现清洁设备102与基站104和/或云平台106之间的交互。
上述网络可以包括但不限于以下至少之一：有线网络，无线网络。上述有线网络可以包括但不限于以下至少之一：广域网，城域网，局域网，上述无线网络可以包括但不限于以下至少之一：WIFI(Wireless Fidelity，无线保真)，蓝牙，红外。清洁设备102与基站104和/或云平台106进行通信所使用的网络与基站104与云平台106进行通信所使用的网络可以是相同的，也可以是不同的。清洁设备102可以包括但不限于：扫地机，洗地机等。
本申请实施例的设备的运行控制方法可以由清洁设备102、基站104或者云平台106单独来执行，也可以由清洁设备102、基站104和云平台106中的至少两个共同执行。其中，清洁设备102或者基站104执行本申请实施例的设备的运行控制方法也可以是由安装在其上的客户端来执行。
以由清洁设备102来执行本实施例中的设备的运行控制方法为例，图2是根据本申请实施例的一种可选的设备的运行控制方法的流程示意图，如 图2所示，该方法的流程可以包括以下步骤：
步骤S202，通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像。
本实施例中的设备的运行控制方法可以应用于对清洁设备的运行状态进行控制的场景。清洁设备可以是具备区域清洁功能(例如，清扫、清洗等)的设备，例如，具备区域清洁功能的机器人，上述机器人可以包括但不限于以下之一：扫地机器人(即，扫地机)，洗地机器人(即，洗地机)，集洗拖于一体的机器人。
相关技术中，在进行区域清洁的过程中，清洁设备通常会按照设置的固定运行参数进行区域清洁。但是，区域内的待清洁对象不同时，将区域清洁干净所需的运行参数会有所不同。如果采用固定运行参数一直为清洁灰尘所对应的清洁参数时，清洁设备则会存在在清洁某些种类的待清洁对象时无法清理干净，而在清洁另一些种类的待清洁对象时会产生大量的资源浪费。
例如，在待清洁对象为灰尘这类比较容易清洁的对象时，只需要设定比较小的运行参数就可以将区域清洁干净；在待清洁对象为颗粒较大、或者有粘性等比较难清洁的对象时，需要设定比较大的运行参数才能将待清洁区域清洁干净。
在本实施例中，在进行区域清洁的过程中，清洁设备可以首先确定待清洁对象的对象类别和聚集程度，根据确定出的对象类别和聚集程度确定清洁设备的运行参数，并按照确定的运行参数控制清洁设备对待清洁对象进行清洁，可以保证清洁设备在清洁当前的待清洁对象时，其运行参数适用于当前的待清洁对象，可以在节约资源消耗的同时，提高清洁设备的清洁效率。
对于当前的待清洁区域，在清洁设备对当前的待清洁区域进行区域清洁时，清洁设备可以通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像。上述图像采集设备可以是摄像头，也可以是照相机(例如，微距相机)，或者其他具有图像采集功能的部件，本实施例中对此不做限定。
例如，可以通过扫地机可以利用微距相机获取地面图像(上述目标地 面图像的一种示例)。
可选地，为了更好地对待清洁区域进行图像采集，可以在清洁设备上安装多个图像采集部件，通过多个图像采集部件中的部分或者全部图像采集部件，对待清洁区域进行图像采集，得到多张地面图像。目标地面图像可以是多张地面图像，也可以是通过对多张地面图像进行处理，得到的一张地面图像。上述对多张地面图像进行处理的过程，可以是对多张地面图像进行拼接，也可以是对多张地面图像进行特征融合，本实施例中对此不做限定。
多个图像采集部件可以设置在清洁设备的不同位置上，也可以设置在清洁设备的同一位置上，例如，可以在扫地机器人的底面设置图像采集部件，以对底部的待清洁区域进行图像采集，也可以在扫地机器人的前方设置图像采集部件，以对前方的待清洁区域进行图像采集，本实施例中对此不做限定。
在本实施例中，在通过图像采集部件对待清洁区域进行图像采集时，可以通过图像采集部件对待清洁区域进行多次图像采集，得到多张地面图像。与前述类似的，目标地面图像可以是多张地面图像，也可以是通过对多张地面图像进行处理，得到的一张地面图像。
步骤S204，对目标地面图像进行对象识别，得到待清洁区域内待清洁的一组目标对象的对象参数，其中，一组目标对象的对象参数包括一组目标对象的对象类别和一组目标对象的聚集参数，一组目标对象的聚集参数用于表示一组目标对象在待清洁区域中的聚集程度。
在本实施例中，在得到目标地面图像之后，清洁设备可以对目标地面图像进行对象识别，得到待清洁区域内待清洁的一组目标对象的对象参数，这里，一组目标对象可以是待清洁区域内的脏污颗粒。一组目标对象的对象参数可以包括：一组目标对象的对象类别，一组目标对象的聚集参数，还可以包括一组目标对象的其他参数，例如，对象位置，其中，一组目标对象的聚集参数用于表示一组目标对象在待清洁区域中的聚集程度。
可选地，对目标地面图像进行对象识别的过程可以是：先对目标地面图像进行对象识别，确定出目标地面图像中包括的一组目标对象中的每个目标对象的对象位置以及每个目标对象的对象类别，再根据每个目标对象 的对象位置以及每个目标对象的对象类别，确定一组目标对象的对象参数。
确定每个目标对象的对象位置的方式可以是：先确定每个目标对象在目标地面图像中的对象位置，再根据目标地面图像与待清洁区域之间的转换关系，确定目标对象在待清洁区域中的对象位置。确定每个目标对象的对象类别的方式可以是：提取每个目标对象的对象特征，根据每个目标对象的对象特征，确定每个目标对象的对象类别。
在确定一组目标对象的对象参数时，可以将一组目标对象中包含的目标对象的对象数量最多的对象类别，确定为一组目标对象的对象类别，也可以将一组目标对象中对应的所有对象类别，确定为一组目标对象的对象类别，此时，一组目标对象的对象类别可以有一种或多个。在确定一组目标对象的聚集参数时，可以根据每个目标对象的对象位置，确定一组目标对象在待清洁区域中的分布(可以通过密度表示，也可以通过其他参数表示)，并基于一组目标对象在待清洁区域中的分布，确定一组目标对象的聚集参数。
可选地，一组目标对象的聚集参数可以是根据目标地面图像中与一组目标对象的对象位置所对应的明暗度确定的，当与一组目标对象的对象位置所对应的明暗度越低时，一组目标对象的聚集参数越高(即，一组目标对象在待清洁区域中的聚集程度越高)。
步骤S206，根据一组目标对象的对象类别和一组目标对象的聚集参数，确定清洁设备的目标运行参数。
在本实施例中，在确定一组目标对象的对象类别和一组目标对象的聚集参数之后，清洁设备可以根据一组目标对象的对象类别和一组目标对象的聚集参数，确定清洁设备的目标运行参数。例如，在确定待清洁对象为猫砂、以及猫砂的聚集参数之后，扫地机器人可以根据确定出的猫砂的聚集参数，确定清洁猫砂所使用的运行参数。
可选地，清洁设备上可以保存有不同对象类别下，不同聚集参数所对应的目标运行参数的映射表。上述确定清洁设备的目标运行参数的过程可以是：根据一组目标对象的对象类别以及聚集参数，在映射表中查找出相对应的运行参数，得到目标运行参数。目标运行参数可以包括清洁设备上的多个设备部件的运行参数，可以包括储液件(例如，水箱)的运行参数， 清洁件(例如，滚刷、拖布等)的运行参数，也可以包括电机(例如，负压发生器)的运行参数，还可以包括其他部件的运行参数，本实施例中对此不做限定。
例如，如图3所示，扫地机器人在确定一组待清洁对象的对象类别为A，且聚集参数为B后，可以在映射表中查找与对象类别A以及聚集参数B所对应的运行参数(即，运行参数C)。
步骤S208，按照目标运行参数控制清洁设备对一组目标对象进行清洁。
在确定目标运行参数之后，清洁设备可以按照目标运行参数控制清洁设备对一组目标对象进行清洁。比如，清洁设备可以按照目标运行参数对清洁设备中的清洁件的运行状态进行调节，以使得清洁件按照与一组目标对象的对象类别和聚集参数相对应的转速对一组目标对象进行清洁。例如，可以按照确定出的运行参数C控制扫地机器人的拖布对一组待清洁对象进行清洁。
可选地，在按照目标运行参数控制清洁设备对一组目标对象进行清洁时，清洁设备可以首先移动到一组目标对象在待清洁区域的对象位置，再按照目标运行参数控制清洁设备对一组目标对象进行清洁，以实现对一组目标对象的个性化清扫(即，对一组目标对象的定向清洁)。
通过上述步骤S202至步骤S208，通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；对目标地面图像进行对象识别，得到待清洁区域内待清洁的一组目标对象的对象参数，其中，一组目标对象的对象参数包括一组目标对象的对象类别和一组目标对象的聚集参数，一组目标对象的聚集参数用于表示一组目标对象在待清洁区域中的聚集程度；根据一组目标对象的对象类别和一组目标对象的聚集参数，确定清洁设备的目标运行参数；按照目标运行参数控制清洁设备对一组目标对象进行清洁，解决了相关技术中的设备的运行控制方法存在由于易出现清洁不完全导致的清洁效率低的问题，提高了区域清洁的效率。
在一个示例性实施例中，通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像，包括：
S11，启动清洁设备上的补光部件，其中，启动后的补光部件用于对待清洁区域进行补光；
S12，通过图像采集部件对待清洁区域进行图像采集，得到目标地面图像。
在本实施例中，为了提高地面图像的图像质量，在需要对待清洁区域进行图像采集时，可以首先对待清洁区域进行补光，再通过图像采集部件对待清洁区域进行图像采集，得到目标地面图像，借助补光，可以提高采集地面图像的清晰度，进而提高对象识别的准确度。
可选地，对待清洁区域进行补光可以是：启动清洁设备上的补光部件，启动后的补光部件可以用于对待清洁区域进行补光，在通过图像采集部件对待清洁区域进行图像采集的过程中，补光部件可以一直处于开启状态。上述补光部件可以是设置于清洁设备上的补光灯，也可以是设置于清洁设备上的其他补光部件，本实施例中对此不做限定。补光部件对待清洁区域进行补光采用的可以是白光，也可以是黄光，还可以是其他颜色的光，本实施例中对此不做限定。
可选地，为了避免资源浪费，可以在通过图像采集部件对待清洁区域进行图像采集，得到目标地面图像之后，将补光部件关闭，以停止对待清洁区域进行补光。
需要说明的是，为了更好地对待清洁区域进行补光，补光部件可以为角度可调的补光部件，以对不同方位的待清洁区域进行补光，在上述补光部件对待清洁区域进行补光的过程中，清洁设备可以记录补光部件的补光角度，即，在目标地面图像上可以附带有采集该目标地面图像时，补光部件的角度信息。
例如，扫地机器人可以在调整补光灯的角度之后，启动补光灯对待清洁区域进行补光，并通过扫地机器人上的摄像头对待清洁区域进行拍摄，得到地面图像。
通过本实施例，在通过补光部件对待清洁区域进行补光之后，再对待清洁区域进行图像采集，可以提高采集到的地面图像的图像质量，提高对象识别的准确度。
在一个示例性实施例中，对目标地面图像进行对象识别，得到待清洁区域内待清洁的一组目标对象的对象参数，包括：
S21，对目标地面图像中包含的一组候选对象中的每个候选对象的对象 阴影进行识别，得到每个候选对象的对象尺寸；
S22，按照每个候选对象的对象尺寸，从一组候选对象中筛选出一组目标对象，得到一组目标对象的对象参数，其中，一组目标对象中的每个目标对象的对象尺寸均小于或者等于第一尺寸阈值。
目标地面图像中可以包含一组候选对象，一组候选对象可以是待清洁区域上的全部对象，其可以是待清洁的对象，也可以不是待清洁的对象。为了识别出目标地面图像中包含的候选对象，可以基于对象阴影进行对象尺寸识别，并基于候选对象的对象尺寸，筛选出待清洁的目标对象。
在本实施例中，在得到目标地面图像之后，清洁设备可以对目标地面图像中包含的一组候选对象中的每个候选对象的对象阴影进行识别，得到每个候选对象的对象尺寸。在进行候选对象的对象尺寸识别时，清洁设备可以先确定每个候选对象的对象阴影的大小，再根据每个候选对象的对象阴影的大小，确定每个候选对象的对象尺寸。
候选对象的对象阴影的大小可以为候选对象的对象阴影的面积，也可以是候选对象的对象阴影的周长，还可以是候选对象的对象阴影的直径，本实施例中对此不做限定。例如，对于一个候选对象，候选对象的对象阴影的大小与候选对象的对象尺寸的换算比例为D，在确定候选对象的对象阴影的大小为E时，可以确定候选对象的对象尺寸E/D。
在本实施例中，在确定每个候选对象的对象尺寸之后，清洁设备可以按照每个候选对象的对象尺寸，从一组候选对象中筛选出一组目标对象，得到一组目标对象的对象参数。对于一些尺寸较大的物体并不适宜通过清洁设备进行清洁，可以设置第一尺寸阈值，即，待清洁对象的最大尺寸，筛选出的每个目标对象的对象尺寸均小于或者等于第一尺寸阈值。
例如，第一尺寸阈值设置为20mm(仅为实例，实际的尺寸阈值可以根据实际需要进行设定)，一组候选对象F1、F2、F3的尺寸分别为17mm、18mm和24mm。扫地机器人可以将候选对象F1、F2确定为待清洁的对象，而排除F3，不将其作为待清洁的对象。
需要说明的是，考虑到在对象阴影不够明显时，可能无法准确识别出对象阴影，即，无法确定出其是否为候选对象的对象阴影，可以先对目标地面图像进行锐化处理，以突出目标地面图像中每个候选对象的对象阴影， 进而方便对每个候选对象的对象阴影进行识别。
通过本实施例，通过对象阴影确定地面图像中的候选对象的对象尺寸，进而根据候选对象的对象尺寸筛选待清洁的对象，可以简化确定待清洁对象的过程，进而提升区域清洁的效率。
在一个示例性实施例中，对目标地面图像中包含的一组候选对象中的每个候选对象的对象阴影进行识别，得到每个候选对象的对象尺寸，包括：
S31，确定每个候选对象在目标地面图像中的对象阴影的阴影面积，得到每个候选对象的阴影面积；
S32，根据每个候选对象的投影角度，将每个候选对象的阴影面积转换为每个候选对象的对象尺寸。
候选对象的阴影面积与候选对象的对象尺寸呈正相关关系，即，候选对象的对象尺寸越大，候选对象的阴影面积也越大。同时，除了与候选对象的对象尺寸有关之外，候选对象的阴影面积还与候选对象的投影角度有关，投影角度为垂直时的阴影面积小于投影角度为倾斜时的阴影面积。
在本实施例中，可以根据每个候选对象的阴影面积以及每个候选对象的投影角度，确定每个候选对象的对象尺寸。清洁设备可以首先确定每个候选对象在目标地面图像中的对象阴影的阴影面积，得到每个候选对象的阴影面积；然后，根据每个候选对象的投影角度，将每个候选对象的阴影面积转换为每个候选对象的对象尺寸。
每个候选对象的投影角度可以是根据补光部件的补光角度确定的，也可以是根据图像采集部件对候选对象的拍摄角度确定的，本实施例中对此不做限定。将每个候选对象的阴影面积转换为每个候选对象的对象尺寸的过程可以是：将阴影面积(比如，s)与候选对象的投影角度(比如，α)的余弦值的商，确定为候选对象的对象尺寸(即，s/tanα)。
通过本实施例，根据投影角度和阴影面积确定候选对象的对象尺寸，可以提高对象尺寸确定的精确度。
在一个示例性实施例中，按照每个候选对象的对象尺寸，从一组候选对象中筛选出一组目标对象，得到一组目标对象的对象参数，包括：
S41，将一组候选对象中对象尺寸小于或者等于第二尺寸阈值的候选对象，确定为第一目标对象，其中，第一目标对象属于一组目标对象；
S42，根据第一目标对象在待清洁区域中的聚集程度，确定第一目标对象的对象参数，其中，第一目标对象的对象类别被设置为预设类别；
S43，对一组候选对象中除了第一目标对象以外的其他候选对象的对象类别进行识别，得到其他候选对象的对象类别；
S44，将其他候选对象中对象类别属于待清洁类别的候选对象，确定为第二目标对象，其中，第二目标对象属于一组目标对象；
S45，根据第二目标对象的对象类别和第二目标对象在待清洁区域中的聚集程度，确定第二对象的对象参数。
在本实施例中，在按照每个候选对象的对象尺寸筛选待清洁的对象时，对于对象尺寸小于或者等于第二尺寸阈值的候选对象，可以均确定为待清洁的对象，而不需要分别识别每个候选对象的对象类别，而直接将其对象类别确定为预设类别(也可以不设置，直接将其确定为待清洁的对象)。清洁设备可以将一组候选对象中对象尺寸小于或者等于第二尺寸阈值的候选对象，确定为第一目标对象，第一目标对象属于一组目标对象。
例如，第二尺寸阈值为10mm(仅为实例，实际的尺寸阈值可以根据实际需要进行设定)，扫地机器人可以将对象尺寸小于10mm的对象，均确定为待清洁的对象。
在确定第一目标对象之后，清洁设备可以根据第一目标对象在待清洁区域中的聚集程度，确定第一目标对象的对象参数，这里，第一目标对象的聚集参数可以是采用与前述实施例中相同或者类似的方式确定的，第一目标对象可以直接被设置为预设类别，预设类别可以是待清洁类别，本实施例中对此不做限定。
对于一组候选对象中除了第一目标对象以外的其他候选对象，清洁设备可以对其他候选对象的对象类别进行识别，得到其他候选对象的对象类别。例如，对于对象尺寸大于10mm且小于20mm的候选对象，扫地机器人可以对这些候选对象进行对象类别识别，以判断候选对象的对象类别是否为待清洁类别。
在确定其他候选对象的对象类别之后，清洁设备可以将其他候选对象中，对象类别属于待清洁类别的候选对象，确定为第二目标对象，第二目标对象属于一组目标对象。这里，待清洁类别可以是预设的需要进行清洁 的对象类别。例如，如果识别出其他候选对象的对象类别为猫砂，则确定其他候选对象属于待清洁的对象，如果识别出其他候选对象的对象类别为小型玩具，则确定其他候选对象不属于待清洁的对象。
在本实施例中，在确定第二目标对象之后，清洁设备可以根据第二目标对象的对象类别、以及第二目标对象在待清洁区域中的聚集程度，确定第二目标对象的对象参数，这里，第二目标对象的聚集参数可以是采用与前述实施例中相同或者类似的方式确定的，第二目标对象的对象类别是前述识别出的对象类别。
通过本实施例，根据对象尺寸的不同采用不同的方式确定待清洁对象的对象参数，可以提高待清洁对象的对象参数确定的精准度。
在一个示例性实施例中，根据一组目标对象的对象类别和一组目标对象的聚集参数，确定清洁设备的目标运行参数，包括：
S51，在一组目标对象包含多种目标对象的情况下，根据多种目标对象中的每种目标对象的对象类别和每种目标对象的聚集参数，确定与每种目标对象对应的运行参数；
S52，对与每种目标对象对应的运行参数执行融合操作，得到清洁设备的目标运行参数。
在本实施例中，一组目标对象的对象类别可以是一种，也可以是多种。如果一组目标对象为多种目标对象，清洁设备可以根据多种目标对象中的每种目标对象的对象类别和每种目标对象的聚集参数，分别确定与每种目标对象对应的运行参数。确定与每种目标对象对应的运行参数的过程与前述实施例中确定目标运行参数的方式类似，在此不做赘述。
例如，当一组目标对象的对象类别包含G，H两种时，可以根据待清洁对象G的对象类别和待清洁对象G的聚集参数，确定与待清洁对象G对应的运行参数I1；根据待清洁对象H的对象类别和待清洁对象H的聚集参数，确定与待清洁对象H对应的运行参数I2。
在本实施例中，在确定与每种目标对象对应的运行参数之后，清洁设备可以对与每种目标对象对应的运行参数执行融合操作，得到清洁设备的目标运行参数。例如，清洁设备可以将运行参数I1和运行参数I2进行融合，得到最终的运行参数(即，上述目标运行参数)。
可选地，对与每种目标对象对应的运行参数执行融合操作的方式可以是：将与每种目标对象对应的运行参数中，相同的运行参数的参数值执行叠加操作，并将叠加后的参数值，作为该相同的运行参数的参数值，或者，选取相同的运行参数的参数值中的最大值，作为该相同的运行参数的参数值；将每种目标对象对应的运行参数中所有种类的运行参数全部保存在目标运行参数中，本实施例中对此不做限定。
通过本实施例，通过对与每种待清洁对象对应的运行参数执行融合操作，得到清洁设备的运行参数，可以提升运行参数确定的精准性，提升区域清洁的效率。
在一个示例性实施例中，一组目标对象的对象参数还包括：用于指示一组目标对象的对象位置的位置信息，一组目标对象的对象位置为一组目标对象在待清洁区域中的对象位置。这里，一组目标对象的对象位置可以是一个区域范围，也可以是区域中心点的位置，本实施例中对此不做限定。
对应地，在按照目标运行参数控制清洁设备对一组目标对象进行清洁之前，上述方法还包括：
S61，控制清洁设备向一组目标对象的对象位置进行移动，直到清洁设备的清洁件与一组目标对象的距离小于或者等于目标距离阈值。
在本实施例中，为了更好地对一组目标对象进行清洁，清洁设备可以首先向一组目标对象的对象位置进行移动，直到清洁设备的清洁件与一组目标对象的距离小于或者等于目标距离阈值。例如，可以控制扫地机器人移动到一组待清洁对象的对象位置附近，以便于扫地机器人的清洁件可以更好地对一组待清洁对象进行清洁。
可选地，在清洁设备上设置有距离传感器的情况下，清洁设备可以通过距离传感器确定清洁设备的清洁件与一组目标对象的距离，在清洁设备上未设置有距离传感器的情况下，清洁设备可以通过图像采集部件确定清洁设备的清洁件与一组目标对象的距离，本实施例中对此不做限定。
通过本实施例，通过先控制清洁设备移动到待清洁对象附近，再对待清洁对象进行清洁，可以实现对待清洁对象的定向清洁，提升区域清洁的效率。
下面结合可选示例对本申请实施例中的设备的运行控制方法进行解释 说明。在本可选示例中，清洁设备为扫地机，目标对象为微粒(即，脏污颗粒)，上述补光部件为补光灯。
本可选示例提供了一种地面杂质识别的方案，结合图4所示，本可选示例中的设备的运行控制方法的流程可以包括以下步骤：
步骤S402，利用补光灯向近地面区域进行打光，利用微距相机获取地面图像。
近地面区域可以为距离地面2-3cm的区域，在利用补光灯向近地面区域进行打光之后，可以利用相机获取地面图像。
步骤S404，通过地面微粒投影判断微粒大小，并根据微粒尺寸进行初步分类，对相应的微粒进行类型识别和定位。
通过地面微粒投影判断微粒大小，并根据微粒尺寸进行初步分类。对于较小的微粒，可以直接将其确定为待清洁的微粒，对于较大的微粒，可以先识别其类型，在为待清洁的类型时，将其确定为待清洁的微粒。对于待清洁的微粒，还可以对其进行定位，确定微粒位置。
步骤S406，根据微粒聚集程度和类别自动地调整扫地机的吸力和水量，并使用调整后的扫地机对待清洁的微粒进行清洁，比如，在调整扫地机的吸力和水量之后，可以控制扫地机移动到微粒所在的位置，以对微粒进行精确清洁。
通过本可选示例，可以区分地面上微粒杂质的类型，并对不同类型的微粒杂质采用不同的清洁方式，可以在满足个性化清扫的同时，更为有效的对地面进行清洁。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软 件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM(Read-Only Memory，只读存储器)/RAM(Random Access Memory，随机存取存储器)、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
根据本申请实施例的另一个方面，还提供了一种用于实施上述设备的运行控制方法的设备的运行控制装置。图5是根据本申请实施例的一种可选的设备的运行控制装置的结构框图，如图5所示，该装置可以包括：
采集单元502，用于通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；
识别单元504，与采集单元502相连，用于对目标地面图像进行对象识别，得到待清洁区域内待清洁的一组目标对象的对象参数，其中，一组目标对象的对象参数包括一组目标对象的对象类别和一组目标对象的聚集参数，一组目标对象的聚集参数用于表示一组目标对象在待清洁区域中的聚集程度；
确定单元506，与识别单元504相连，用于根据一组目标对象的对象类别和一组目标对象的聚集参数，确定清洁设备的目标运行参数；
第一控制单元508，与确定单元506相连，用于按照目标运行参数控制清洁设备对一组目标对象进行清洁。
需要说明的是，该实施例中的采集单元502可以用于执行上述步骤S202，该实施例中的识别单元504可以用于执行上述步骤S204，该实施例中的确定单元506可以用于执行上述步骤S206，该实施例中的第一控制单元508可以用于执行上述步骤S208。
通过上述模块，通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；对目标地面图像进行对象识别，得到待清洁区域内待清洁的一组目标对象的对象参数，其中，一组目标对象的对象参数包括一组目标对象的对象类别和一组目标对象的聚集参数，一组目标对象的聚集参数用于表示一组目标对象在待清洁区域中的聚集程度；根据一组目标对象的对象类别和一组目标对象的聚集参数，确定清洁设备的目标 运行参数；按照目标运行参数控制清洁设备对一组目标对象进行清洁，解决了相关技术中的设备的运行控制方法存在由于易出现清洁不完全导致的清洁效率低的问题，提高了区域清洁的效率。
在一个示例性实施例中，采集单元502包括：
启动模块，用于启动清洁设备上的补光部件，其中，启动后的补光部件用于对待清洁区域进行补光；
采集模块，用于通过图像采集部件对待清洁区域进行图像采集，得到目标地面图像。
在一个示例性实施例中，识别单元504包括：
识别模块，用于对目标地面图像中包含的一组候选对象中的每个候选对象的对象阴影进行识别，得到每个候选对象的对象尺寸；
筛选模块，用于按照每个候选对象的对象尺寸，从一组候选对象中筛选出一组目标对象，得到一组目标对象的对象参数，其中，一组目标对象中的每个目标对象的对象尺寸均小于或者等于第一尺寸阈值。
在一个示例性实施例中，识别模块包括：
第一确定子模块，用于确定每个候选对象在目标地面图像中的对象阴影的阴影面积，得到每个候选对象的阴影面积；
转换子模块，用于根据每个候选对象的投影角度，将每个候选对象的阴影面积转换为每个候选对象的对象尺寸。
在一个示例性实施例中，筛选模块包括：
第二确定子模块，用于将一组候选对象中对象尺寸小于或者等于第二尺寸阈值的候选对象，确定为第一目标对象，其中，第一目标对象属于一组目标对象；
第三确定子模块，用于根据第一目标对象在待清洁区域中的聚集程度，确定第一目标对象的对象参数，其中，第一目标对象的对象类别被设置为预设类别；
识别子模块，用于对一组候选对象中除了第一目标对象以外的其他候选对象的对象类别进行识别，得到其他候选对象的对象类别；
第四确定子模块，用于将其他候选对象中对象类别属于待清洁类别的候选对象，确定为第二目标对象，其中，第二目标对象属于一组目标对象；
第五确定子模块，用于根据第二目标对象的对象类别和第二目标对象在待清洁区域中的聚集程度，确定第二对象的对象参数。
在一个示例性实施例中，确定单元506包括：
确定模块，用于在一组目标对象包含多种目标对象的情况下，根据多种目标对象中的每种目标对象的对象类别和每种目标对象的聚集参数，确定与每种目标对象对应的运行参数；
执行模块，用于对与每种目标对象对应的运行参数执行融合操作，得到清洁设备的目标运行参数。
在一个示例性实施例中，一组目标对象的对象参数还包括：用于指示一组目标对象的对象位置的位置信息；上述装置还包括：
第二控制单元，用于在按照目标运行参数控制清洁设备对一组目标对象进行清洁之前，控制清洁设备向一组目标对象的对象位置进行移动，直到清洁设备的清洁件与一组目标对象的距离小于或者等于目标距离阈值。
此处需要说明的是，上述模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在如图1所示的硬件环境中，可以通过软件实现，也可以通过硬件实现，其中，硬件环境包括网络环境。
根据本申请实施例的又一个方面，还提供了一种存储介质。可选地，在本实施例中，上述存储介质可以用于执行本申请实施例中上述任一项设备的运行控制方法的程序代码。
可选地，在本实施例中，上述存储介质可以位于上述实施例所示的网络中的多个网络设备中的至少一个网络设备上。
可选地，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：
S1，通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；
S2，对目标地面图像进行对象识别，得到待清洁区域内待清洁的一组目标对象的对象参数，其中，一组目标对象的对象参数包括一组目标对象的对象类别和一组目标对象的聚集参数，一组目标对象的聚集参数用于表 示一组目标对象在待清洁区域中的聚集程度；
S3，根据一组目标对象的对象类别和一组目标对象的聚集参数，确定清洁设备的目标运行参数；
S4，按照目标运行参数控制清洁设备对一组目标对象进行清洁。
可选地，本实施例中的具体示例可以参考上述实施例中所描述的示例，本实施例中对此不再赘述。
可选地，在本实施例中，上述存储介质可以包括但不限于：U盘、ROM、RAM、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
根据本申请实施例的又一个方面，还提供了一种用于实施上述设备的运行控制方法的电子装置，该电子装置可以是服务器、终端、或者其组合。
图6是根据本申请实施例的一种可选的电子装置的结构框图，如图6所示，包括处理器602、通信接口604、存储器606和通信总线608，其中，处理器602、通信接口604和存储器606通过通信总线608完成相互间的通信，其中，
存储器606，用于存储计算机程序；
处理器602，用于执行存储器606上所存放的计算机程序时，实现如下步骤：
S1，通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；
S2，对目标地面图像进行对象识别，得到待清洁区域内待清洁的一组目标对象的对象参数，其中，一组目标对象的对象参数包括一组目标对象的对象类别和一组目标对象的聚集参数，一组目标对象的聚集参数用于表示一组目标对象在待清洁区域中的聚集程度；
S3，根据一组目标对象的对象类别和一组目标对象的聚集参数，确定清洁设备的目标运行参数；
S4，按照目标运行参数控制清洁设备对一组目标对象进行清洁。
可选地，在本实施例中，通信总线可以是PCI(Peripheral Component Interconnect，外设部件互连标准)总线、或EISA(Extended Industry Standard Architecture，扩展工业标准结构)总线等。该通信总线可以分为地址总线、 数据总线、控制总线等。为便于表示，图6中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。通信接口用于上述电子装置与其他设备之间的通信。
上述的存储器可以包括RAM，也可以包括非易失性存储器(non-volatile memory)，例如，至少一个磁盘存储器。可选地，存储器还可以是至少一个位于远离前述处理器的存储装置。
作为一种示例，上述存储器606中可以但不限于包括上述设备的控制装置中的采集单元502、识别单元504、确定单元506、以及第一控制单元508。此外，还可以包括但不限于上述设备的控制装置中的其他模块单元，本示例中不再赘述。
上述处理器可以是通用处理器，可以包含但不限于：CPU(Central Processing Unit，中央处理器)、NP(Network Processor，网络处理器)等；还可以是DSP(Digital Signal Processing，数字信号处理器)、ASIC(Application Specific Integrated Circuit，专用集成电路)、FPGA(Field－Programmable Gate Array，现场可编程门阵列)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。
可选地，本实施例中的具体示例可以参考上述实施例中所描述的示例，本实施例在此不再赘述。
本领域普通技术人员可以理解，图6所示的结构仅为示意，实施上述设备的运行控制方法的设备可以是终端设备，该终端设备可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。图6其并不对上述电子装置的结构造成限定。例如，电子装置还可包括比图6中所示更多或者更少的组件(如网络接口、显示装置等)，或者具有与图6所示的不同的配置。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令终端设备相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、ROM、RAM、磁盘或光盘等。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
上述实施例中的集成的单元如果以软件功能单元的形式实现并作为独 立的产品销售或使用时，可以存储在上述计算机可读取的存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在存储介质中，包括若干指令用以使得一台或多台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。
在本申请的上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的客户端，可通过其它的方式实现。其中，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，单元或模块的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例中所提供的方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
以上所述仅是本申请的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本申请原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本申请的保护范围。

Claims (20)

  1. 一种设备的运行控制方法，其特征在于，包括：
    通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；
    对所述目标地面图像进行对象识别，得到所述待清洁区域内待清洁的一组目标对象的对象参数，其中，所述一组目标对象的对象参数包括所述一组目标对象的对象类别和所述一组目标对象的聚集参数，所述一组目标对象的聚集参数用于表示所述一组目标对象在所述待清洁区域中的聚集程度；
    根据所述一组目标对象的对象类别和所述一组目标对象的聚集参数，确定所述清洁设备的目标运行参数；
    按照所述目标运行参数控制所述清洁设备对所述一组目标对象进行清洁。
  2. 根据权利要求1所述的方法，其特征在于，所述通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像，包括：
    启动所述清洁设备上的补光部件，其中，启动后的所述补光部件用于对所述待清洁区域进行补光；
    通过所述图像采集部件对所述待清洁区域进行图像采集，得到所述目标地面图像。
  3. 根据权利要求1所述的方法，其特征在于，所述对所述目标地面图像进行对象识别，得到所述待清洁区域内待清洁的一组目标对象的对象参数，包括：
    对所述目标地面图像中包含的一组候选对象中的每个候选对象的对象阴影进行识别，得到所述每个候选对象的对象尺寸；
    按照所述每个候选对象的对象尺寸，从所述一组候选对象中筛选出所述一组目标对象，得到所述一组目标对象的对象参数。
  4. 根据权利要求3所述的方法，其特征在于，所述一组目标对象中的每个目标对象的对象尺寸均小于或者等于第一尺寸阈值。
  5. 根据权利要求3所述的方法，其特征在于，所述对所述目标地面图像中包含的一组候选对象中的每个候选对象的对象阴影进行识别，得到所述每个候选对象的对象尺寸，包括：
    确定所述每个候选对象在所述目标地面图像中的对象阴影的阴影面积，得到所述每个候选对象的阴影面积；
    根据所述每个候选对象的投影角度，将所述每个候选对象的阴影面积转换为所述每个候选对象的对象尺寸。
  6. 根据权利要求3或4所述的方法，其特征在于，所述按照所述每个候选对象的对象尺寸，从所述一组候选对象中筛选出所述一组目标对象，得到所述一组目标对象的对象参数，包括：
    将所述一组候选对象中对象尺寸小于或者等于第二尺寸阈值的候选对象，确定为第一目标对象，其中，所述第一目标对象属于所述一组目标对象；
    根据所述第一目标对象在所述待清洁区域中的聚集程度，确定所述第一目标对象的对象参数，其中，所述第一目标对象的对象类别被设置为预设类别；
    对所述一组候选对象中除了所述第一目标对象以外的其他候选对象的对象类别进行识别，得到所述其他候选对象的对象类别；
    将所述其他候选对象中对象类别属于待清洁类别的候选对象，确定为第二目标对象，其中，所述第二目标对象属于所述一组目标对象；
    根据所述第二目标对象的对象类别和所述第二目标对象在所述待清洁区域中的聚集程度，确定所述第二目标对象的对象参数。
  7. 根据权利要求1所述的方法，其特征在于，所述根据所述一组目标对象的对象类别和所述一组目标对象的聚集参数，确定所述清洁设备的目标运行参数，包括：
    在所述一组目标对象包含多种目标对象的情况下，根据所述多种目标对象中的每种目标对象的对象类别和所述每种目标对象的聚集参数，确定与所述每种目标对象对应的运行参数；
    对与所述每种目标对象对应的运行参数执行融合操作，得到所述清洁设备的所述目标运行参数。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述一组目标对象的对象参数还包括：用于指示所述一组目标对象的对象位置的位置信息。
  9. 根据权利要求8所述的方法，其特征在于，在所述按照所述目标运行参数控制所述清洁设备对所述一组目标对象进行清洁之前，所述方法还包括：
    控制所述清洁设备向所述一组目标对象的对象位置进行移动，直到所述清洁设备的清洁件与所述一组目标对象的距离小于或者等于目标距离阈值。
  10. 根据权利要求1所述的方法，其特征在于，所述一组目标对象的聚集参数采用下述方式确定：
    根据所述一组目标对象中每个目标对象的对象位置，确定所述一组目标对象在待清洁区域中的分布；
    基于所述一组目标对象在待清洁区域中的分布，确定一组目标对象的聚集参数。
  11. 根据权利要求1所述的方法，其特征在于，所述一组目标对象的聚集参数采用下述方式确定：
    根据所述目标地面图像中与所述一组目标对象的对象位置所对应的明暗度，确定所述一组目标对象的聚集参数。
  12. 根据权利要求5所述的方法，其特征在于，所述每个候选对象的投影角度根据所述清洁设备上的补光部件的补光角度或所述图像采集部件对所述候选对象的拍摄角度确定。
  13. 根据权利要求5所述的方法，其特征在于，所述根据所述每个候选对象的投影角度，将所述每个候选对象的阴影面积转换为所述每个候选对象的对象尺寸，包括：
    将所述候选对象的阴影面积与相应的候选对象的投影角度的余弦值的商，确定为相应的候选对象的对象尺寸。
  14. 根据权利要求7所述的方法，其特征在于，所述对与所述每种目标对象对应的运行参数执行融合操作，得到所述清洁设备的所述目标运行参数，包括；
    将与每种目标对象对应的运行参数中，相同种类的运行参数的参数值执行叠加操作，并将叠加后的参数值作为该相同种类的运行参数融合后的参数值。
  15. 根据权利要求7所述的方法，其特征在于，所述对与所述每种目标对象对应的运行参数执行融合操作，得到所述清洁设备的所述目标运行参数，包括；
    从与每种目标对象对应的运行参数中，选取相同种类的运行参数的参数值的最大值，作为该相同种类的运行参数融合后的参数值。
  16. 根据权利要求4所述的方法，其特征在于，所述第一尺寸阈值为20mm。
  17. 根据权利要求6所述的方法，其特征在于，所述第二尺寸阈值为10mm。
  18. 一种设备的运行控制装置，其特征在于，包括：
    采集单元，用于通过清洁设备上的图像采集部件对待清洁区域进行图像采集，得到目标地面图像；
    识别单元，用于对所述目标地面图像进行对象识别，得到所述待清洁区域内待清洁的一组目标对象的对象参数，其中，所述一组目标对象的对象参数包括所述一组目标对象的对象类别和所述一组目标对象的聚集参数，所述一组目标对象的聚集参数用于表示所述一组目标对象在所述待清洁区域中的聚集程度；
    确定单元，用于根据所述一组目标对象的对象类别和所述一组目标对象的聚集参数，确定所述清洁设备的目标运行参数；
    第一控制单元，用于按照所述目标运行参数控制所述清洁设备对所述一组目标对象进行清洁。
  19. 一种计算机可读的存储介质，其特征在于，所述计算机可读的存储介质包括存储的程序，其中，所述程序运行时执行权利要求1至7中任一项所述的方法。
  20. 一种电子装置，包括存储器和处理器，其特征在于，所述存储器中存储有计算机程序，所述处理器被设置为通过所述计算机程序执行权利要求1至17中任一项所述的方法。
PCT/CN2023/083035 2022-04-01 2023-03-22 设备的运行控制方法和装置、存储介质及电子装置 WO2023185574A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210340030.1A CN116935205A (zh) 2022-04-01 2022-04-01 设备的运行控制方法和装置、存储介质及电子装置
CN202210340030.1 2022-04-01

Publications (1)

Publication Number Publication Date
WO2023185574A1 true WO2023185574A1 (zh) 2023-10-05

Family

ID=88199198

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/083035 WO2023185574A1 (zh) 2022-04-01 2023-03-22 设备的运行控制方法和装置、存储介质及电子装置

Country Status (2)

Country Link
CN (1) CN116935205A (zh)
WO (1) WO2023185574A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111035327A (zh) * 2019-12-31 2020-04-21 深圳飞科机器人有限公司 清洁机器人、地毯检测方法及计算机可读存储介质
CN112633384A (zh) * 2020-12-25 2021-04-09 北京百度网讯科技有限公司 基于图像识别模型的对象识别方法、装置和电子设备
CN112716376A (zh) * 2020-12-25 2021-04-30 北京小狗吸尘器集团股份有限公司 基于扫地机的清洁方法、装置、可读存储介质及电子设备
CN112741555A (zh) * 2019-10-31 2021-05-04 深圳拓邦股份有限公司 一种清扫方法、***及清扫设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112741555A (zh) * 2019-10-31 2021-05-04 深圳拓邦股份有限公司 一种清扫方法、***及清扫设备
CN111035327A (zh) * 2019-12-31 2020-04-21 深圳飞科机器人有限公司 清洁机器人、地毯检测方法及计算机可读存储介质
CN112633384A (zh) * 2020-12-25 2021-04-09 北京百度网讯科技有限公司 基于图像识别模型的对象识别方法、装置和电子设备
CN112716376A (zh) * 2020-12-25 2021-04-30 北京小狗吸尘器集团股份有限公司 基于扫地机的清洁方法、装置、可读存储介质及电子设备

Also Published As

Publication number Publication date
CN116935205A (zh) 2023-10-24

Similar Documents

Publication Publication Date Title
WO2023051227A1 (zh) 清洁设备的控制方法及装置
RU2624737C2 (ru) Способ и устройство для уборки мусора
CN110693397B (zh) 清洁机器人的控制方法、清洁机器人及介质
CN111476459B (zh) 清洁机集群协同工作方法、装置、设备及计算机可读介质
WO2022007590A1 (zh) 清洁机构的脏污程度确定方法、装置及存储介质
CN108416271A (zh) 清扫方法及清扫***
WO2020107622A1 (zh) 一种清洁地面的方法、扫地机器人及拖地机器人
WO2022267795A1 (zh) 区域地图的处理方法及装置、存储介质及电子装置
CN109358546B (zh) 家用电器的控制方法、装置和***
WO2023025023A1 (zh) 移动机器人的清扫方法及装置、存储介质、电子装置
CN112043206A (zh) 一种扫拖一体机及其清洁方法
WO2020253163A1 (zh) 机器人的控制方法及装置、视觉设备的控制方法及装置
WO2020019944A1 (zh) 一种智能分析***、方法及装置
WO2023185574A1 (zh) 设备的运行控制方法和装置、存储介质及电子装置
CN112036272B (zh) 一种楼宇的幕墙清洁控制方法、服务器和存储介质
CN111084589A (zh) 清洁方法及相关产品
WO2023131246A1 (zh) 清洁设备的控制方法及装置、存储介质及电子装置
WO2023131161A1 (zh) 清洁设备的运行控制方法及装置、存储介质及电子装置
CN111050027B (zh) 镜头畸变补偿方法、装置、设备和存储介质
CN109363578B (zh) 清洁监控方法、装置及吸尘器和移动终端
CN115399697A (zh) 清洁设备的自清洁方法和装置、存储介质及电子装置
CN115550638A (zh) 一种摄像头状态检测***及方法
CN114617478B (zh) 一种清洁控制方法、装置、扫地机器人及存储介质
CN212698736U (zh) 一种扫拖一体机
WO2023185247A1 (zh) 区域清洁的控制方法和装置、存储介质及电子装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23777945

Country of ref document: EP

Kind code of ref document: A1