WO2020077850A1

WO2020077850A1 - Method and apparatus for dividing and identifying indoor region, and terminal device

Info

Publication number: WO2020077850A1
Application number: PCT/CN2018/123779
Authority: WO
Inventors: 谭欢; 郭盖华; 谌鎏
Original assignee: 深圳乐动机器人有限公司
Priority date: 2018-10-18
Filing date: 2018-12-26
Publication date: 2020-04-23
Also published as: CN109522803B; CN109522803A

Abstract

The solution is applicable to the technical field of robots. Provided are a method and apparatus for dividing and identifying an indoor region, and a terminal device. The method comprises: obtaining an initial map; performing region division on the initial map by using a morphological image processing technology to obtain at least one room region of the indoor region image; and determining the region identification result corresponding to room regions according to graphic information of the room regions and preset identification information. According to the solution, the initial map is performed room division and the divided room regions are performed region identification to obtain the region identification result corresponding to room regions, which can provide more accurate cleaning data for a robot so that the robot can particularly clean according to the function type of the regions, the cleaning path is more clear, and the operation efficiency of the robot is improved.

Description

Indoor area division and recognition method, device and terminal equipment

Technical field

The invention belongs to the technical field of robots, and in particular relates to an indoor area division and identification method, device and terminal equipment.

Background technique

With the development of technology, mobile robots are widely used to assist or replace humans to complete some basic repetitive work. Among them, the cleaning robot is a typical application of the mobile robot. After the initial construction of the map through the sensor, the cleaning robot divides the map into several areas and plans the cleaning path of each area to clean the room.

At present, the cleaning robot always divides the area according to a fixed shape and a fixed size when planning the operation area. Usually, a room with an irregular shape or a room with a large area is always divided into several small areas, so that when the robot When the divided areas are cleaned, many unnecessary transition paths will be formed. This planning method makes the entire cleaning path appear chaotic on the map, resulting in low efficiency of the robot in the actual cleaning work.

technical problem

In view of this, embodiments of the present invention provide an indoor area division and identification method, device, and terminal device, to solve the problem of low work efficiency caused by a cleaning robot in the prior art due to a fixed work area and fixed path.

Technical solution

A first aspect of an embodiment of the present invention provides an indoor area division and identification method, including:

Get the initial map;

Morphological image processing technology is used to divide the initial map into regions to obtain at least one room region of the indoor region image;

According to the graphic information and preset identification information of each room area, the area identification result corresponding to each room area is determined.

A second aspect of an embodiment of the present invention provides an indoor area division and identification device, including:

The initial map acquisition module is used to acquire the initial map;

A room area acquisition module, configured to use morphological image processing technology to partition the initial map to obtain at least one room area of the indoor area image;

The area recognition result acquisition module is used to determine the area recognition result corresponding to each room area according to the graphic information and preset identification information of each room area.

A third aspect of the embodiments of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, when the processor executes the computer program The steps of the indoor area division and recognition method as described above are implemented.

A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium that stores a computer program, which when executed by a processor implements the indoor area division and recognition method described above step.

Beneficial effect

In the embodiment of the present invention, an initial map is first obtained; the initial map is divided into regions using morphological image processing technology to obtain at least one room area of the indoor area image; and determined according to the graphic information and preset identification information of each room area The area recognition results corresponding to each room area. The embodiment of the present invention obtains the area recognition result of each room area by performing area recognition on the room area divided according to the initial map, and the area recognition result of each room area can provide more accurate cleaning data for the work of the robot, so that the robot The type of function is targeted for cleaning, making the cleaning path more clear and improving the efficiency of the robot.

BRIEF DESCRIPTION

In order to more clearly explain the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only for the application In some embodiments, for those of ordinary skill in the art, without paying creative labor, other drawings may be obtained based on these drawings.

1 is a schematic diagram of an implementation process of an indoor area division and recognition method provided by an embodiment of the present invention;

2 is a schematic flowchart of a specific implementation of S102 in FIG. 1 provided by an embodiment of the present invention;

3 is a schematic diagram of an implementation process of an indoor area division and recognition method provided by an embodiment of the present invention;

4 is a schematic structural diagram of an indoor area division and identification device provided by an embodiment of the present invention;

5 is a schematic structural diagram of a room area acquisition module provided by an embodiment of the present invention;

6 is a schematic diagram of a terminal device provided by an embodiment of the present invention;

7 is an example diagram of a binary image provided by an embodiment of the present invention;

8 is an example diagram of an indoor area image subjected to an expansion process provided by an embodiment of the present invention.

Embodiments of the invention

In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structure and technology are proposed to thoroughly understand the embodiments of the present application. However, those skilled in the art should understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary details.

In order to explain the technical solutions described in the present application, the following will be described with specific embodiments.

Examples 1

FIG. 1 shows an implementation process of an indoor area division and identification method provided by an embodiment of the present invention. The detailed process is as follows:

In S101, an initial map is acquired.

In this embodiment, the main body of the process in this embodiment may be a robot or other computer equipment including a positioning sensor. The following uses a cleaning robot as an example to further explain the indoor area division and recognition method provided by this embodiment.

In this embodiment, the method for acquiring the initial map may be: scanning the indoor area, and generating the initial map according to the indoor area information obtained by the scan.

Specifically, when the indoor area is cleaned for the first time, the cleaning robot starts to move from an unknown position. During the movement, the indoor area is instantly located and constructed based on the sensor data obtained by the pose estimation and the sensors installed by the cleaning robot itself to obtain the indoor area Initial map.

In this embodiment, the method for obtaining the initial map may also be: calling the indoor area map stored inside the robot as the initial map, and the indoor area map stored inside the robot may be a map input by the user.

In this embodiment, the indoor area may be an indoor area of an ordinary family house, an indoor area of an office building, or other indoor areas. In this embodiment, an ordinary family house is taken as an example. The indoor area of an ordinary family house usually includes a living room, a bedroom, a kitchen, and Indoor areas for toilets and other areas.

In S102, the initial map is divided into regions using morphological image processing technology to obtain at least one room region of the indoor region image.

In this embodiment, after acquiring the initial map, the cleaning robot applies image corrosion expansion processing to the initial map to distinguish the map area corresponding to each area in the indoor area so that the map is displayed as at least one room area. For example, if The indoor area is an ordinary two-bedroom room. After the initial map is image-processed, the obtained room area may include a living room area, a bedroom area, a kitchen area, and a toilet area.

In S103, the area recognition result corresponding to each room area is determined according to the graphic information and preset identification information of each room area.

In this embodiment, the graphic information may include the area, shape, and topology of the room area, and the preset identification information may include area threshold, topology, and shape information corresponding to each area of various sample images. By comparing the graphic information of each room area with the preset identification information of the sample image, the function type that identifies each room area can be used as the area recognition result.

For example, when the area of a certain room area in the indoor area in this embodiment satisfies the area threshold condition of the bedroom in the sample image and is a topology structure connected to the living room through a door, it can be determined that the room area is a bedroom.

It can be known from the above embodiments that the embodiment of the present invention first obtains an initial map; uses morphological image processing technology to divide the initial map into regions to obtain at least one room area of the indoor area image; Preset identification information to determine the area identification result corresponding to each room area. In the embodiment of the present invention, by performing area recognition on the room areas divided according to the initial map, the area recognition results of each room area are obtained, which can provide more accurate cleaning data for the work of the robot, so that the robot can be targeted according to the function type of each area The cleaning work makes the cleaning path clearer and improves the working efficiency of the robot.

In an embodiment of the present invention, the specific implementation process of S101 in FIG. 1 is as follows:

In one embodiment, the positioning information of the robot in the indoor area is obtained.

In this embodiment, the cleaning robot acquires its positioning information in the indoor area through a sensor mounted on the robot. The sensor of the cleaning robot may include a laser ranging sensor and an ultrasonic sensor.

In one embodiment, the indoor area is constructed according to the real-time positioning and map construction algorithm and the positioning information to generate the initial map.

In this embodiment, the real-time positioning and map construction algorithm is SLAM ((simultaneous localization and mapping) algorithm, based on the positioning information obtained by the sensor, the SLAM algorithm is used to build an incremental map to achieve the autonomous positioning and map construction of the cleaning robot.

It can be seen from the above embodiments that, through the SLAM algorithm, the map construction of the entire indoor area can be completed in real time when the robot first works, thereby improving the accuracy of the initial map and providing map data support for subsequent precise cleaning.

As shown in FIG. 2, in one embodiment of the present invention, FIG. 2 shows the specific implementation process of S102 in FIG. 1, and the detailed process is as follows:

In S201, binarization processing is performed on the initial map to obtain a binarized image corresponding to the initial map.

As shown in FIG. 7, in this embodiment, FIG. 7 shows an example diagram of a binarized image.

In this embodiment, the initial map is first binarized to obtain a foreground area with a pixel value of 1 and a background area with a pixel value of 0, where the foreground area is an indoor area scanned by the robot.

In S202, image erosion processing is performed on the binarized image to obtain the indoor area image, and the connected domain in the indoor area image is detected.

When the area scanned by the robot includes the bedroom and the living room, because the bedroom and the living room are connected, when creating the initial map, there are fewer pixel connections between the area corresponding to the bedroom and the area corresponding to the living room. If the two areas are connected, the robot It is impossible to accurately determine the function type of each area based on the connected areas. Therefore, the binary image needs to be eroded to delete pixels between two larger connected areas to divide the two areas.

This process specifically includes: first performing a predetermined number of image erosion processes on the binarized image. The image erosion process can delete the pixels on the edge of the binarized image to separate the connection parts of each area to obtain the indoor area image, and then scan the entire indoor In the area image, the connected area is detected on the indoor area image according to the pixel value of each pixel of the indoor area image, and at least one connected area in the indoor area image is acquired.

In S203, each connected domain in the indoor area image is subjected to an expansion process, and the region within the smallest circumscribed polygon of each connected domain after the expansion process is taken as the room region corresponding to the connected domain.

As shown in FIG. 8, in this embodiment, FIG. 8 shows an example diagram of an indoor area image subjected to an expansion process.

In this embodiment, since the image of the indoor area is corroded, the area of the area corresponding to each room will be reduced. Therefore, after each connected domain is segmented, it is necessary to separately perform a predetermined number of expansion processes on each connected domain to make each The connected domain corresponding to the room is restored to the corresponding area in the initial map, as shown in Figures 1 to 7 are the expanded connected domains in the indoor area image.

In this embodiment, for the single connected domain after expansion processing, the smallest circumscribed polygon of the single connected domain is selected so that the smallest circumscribed polygon surrounds the connected domain, and the area within the smallest circumscribed polygon is taken as the room area corresponding to the connected domain, Repeat the above process to get the room area corresponding to each connected domain.

In this embodiment, the smallest circumscribed polygon may be the smallest circumscribed rectangle.

In one embodiment of the present invention, the graphic information includes area area, area shape, and area connection topological relationship. S103 in FIG. 1 specifically includes:

According to the area area, area shape, area connection topology relationship and preset identification information corresponding to each room area, the function type of each room area is obtained.

In this embodiment, before the robot works, first obtain a large number of indoor structure diagrams of ordinary family houses as sample images, and count the area size, topological relationship and area shape of each area in the sample image to form preset identification information. Obtain the graphic information of the indoor area where the robot is located, and compare with the preset identification information to obtain the function type of each room area.

Taking a specific application scenario as an example, the topological relationship of the area connection of the living room in an ordinary family house is to communicate with the dining room, bedroom and kitchen, respectively. The shape of the kitchen area is a large rectangular channel. Determine the function type of the room area. For example, when it is detected that the area of the room area to be determined is within the area of the living room and it is connected to a plurality of other room areas, it can be determined that the function type of the room area to be determined is the living room.

As shown in FIG. 3, in an embodiment of the present invention, after S103 in FIG. 1, the indoor area division and recognition method provided by this embodiment further includes:

In S301, the area recognition result is sent to a user terminal, so that the user terminal displays the area recognition result.

In S302, receiving area identification result correction information sent by the preset terminal, and modifying the area identification result according to the area identification result correction information, the area identification result correction information is a user acquired by the user terminal Correction information input when it is checked that there is an error in the area recognition result.

In this embodiment, the cleaning robot can automatically perform area recognition based on the initial map generated by itself, and work in a corresponding working mode in each room area according to the area recognition result. At the same time, after obtaining the area recognition result, the cleaning robot may send the area recognition result to the user terminal, which may be a mobile phone or a computer.

The user terminal displays the area recognition result. The user views the area recognition result through the user terminal and corrects the area recognition result when the area recognition result is found to be incorrect. The user terminal obtains the correction information input by the user and generates the area recognition based on the correction information entered by the user Result correction information, and send the area recognition result correction information to the cleaning robot, the cleaning robot replaces the area recognition result with the area recognition result correction information, so that the cleaning robot will switch according to the corrected area recognition result in subsequent cleaning work Operating mode.

In an embodiment of the present invention, the user terminal may also generate an area identification sample according to the corrected area identification result, where the area identification sample includes the graphic information of each room area in the indoor area and the corresponding area identification result. The user terminal sends the area identification sample to the server, and the server adds the area identification sample to the preset identification information, thereby updating the preset identification information, and the server can periodically send the updated preset identification information to all the cleaners that communicate with the server Robot, so that the cleaning robot can more accurately identify the function of each area, and improve the accuracy of the area recognition results.

In an embodiment of the present invention, the area recognition method provided by the embodiment of the present invention further includes:

According to the area recognition results corresponding to each room area, the working mode corresponding to each room area is determined.

In this embodiment, due to the different types of functions in each area of the ordinary family house, the floor cleaning conditions are also different. Setting different working modes for the cleaning robot according to the rooms with different functions can make the cleaning robot more targeted Carry out cleaning work to improve the cleaning level and efficiency of the robot.

In an embodiment of the present invention, the area recognition result includes a kitchen, a living room, and a bedroom. The area recognition method provided in the embodiment of the present invention further specifically includes:

If the result of the area recognition is a kitchen, adjust the working module to a super pollution purification mode;

If the area recognition result is a living room, adjust the working mode to a strong cleaning mode;

If the area recognition result is a bedroom, the working mode is adjusted to a regular cleaning mode.

In this embodiment, different working modes may include different cleaning powers and cleaning frequencies. Therefore, different cleaning powers and cleaning frequencies are adopted for areas with different functions. For example, the cleaning frequency of the living room and kitchen may be greater than the cleaning frequency of the bedroom. In this way, the cleaning robot can not only keep the entire indoor space clean, but also shorten the time of cleaning work and prolong the service life of the cleaning robot.

Taking a specific application as an example, in the indoor area of a common family house, the kitchen needs to process ingredients, and the ground is usually dirty and accompanied by oil stains. Therefore, the working mode of the robot in the kitchen can adopt a super-cleaning mode, so that the cleaning robot can Remove ground rubbish and oil stains; because there are frequent people in and out of the living room, the ground is dirty, so a powerful cleaning mode can be used for the living room, so that the cleaning robot can remove the dust and garbage in the living room; because there are fewer people in and out of the bedroom, you can choose regular Clean mode.

Obtain the forbidden area entered by the user, and compare the area identification result with the forbidden area; if the area identification result is consistent with the forbidden area, adjust the working mode to the forbidden cleaning mode.

In this embodiment, the user can set a certain room area in the recognized area recognition result as a prohibited area, which includes multiple edges. In the prohibited cleaning mode, when the robot reaches the outer edge of the prohibited area , Then stop advancing and turn to continue to work in other areas outside the prohibited area. For example, if the prohibited area is a kitchen, the robot does not enter the kitchen and turns when it reaches the edge of the kitchen, and only cleans the room area that is not set as a no-entry area.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Examples 2 :

As shown in FIG. 4, an indoor area dividing and identifying device 100 provided by an embodiment of the present invention is used to execute the method steps in the embodiment corresponding to FIG. 1, which includes:

The initial map acquisition module 110 is used to acquire an initial map;

The room area acquisition module 120 is configured to use morphological image processing technology to perform area division on the initial map to obtain at least one room area of the indoor area image;

The area recognition result obtaining module 130 is used to determine the area recognition result corresponding to each room area according to the graphic information and preset identification information of each room area.

It can be known from the above embodiments that the embodiment of the present invention first obtains an initial map; uses morphological image processing technology to divide the initial map into regions to obtain at least one room area of the indoor area image; according to the graphic information of each room area and Preset identification information to determine the area identification result corresponding to each room area. In the embodiment of the present invention, by performing area recognition on the room areas divided according to the initial map, the area recognition results of each room area are obtained, which can provide more accurate cleaning data for the work of the robot, so that the robot can be targeted according to the function type of each area The cleaning work makes the cleaning path clearer and improves the working efficiency of the robot.

In an embodiment of the present invention, the initial map acquisition module 110 in the embodiment corresponding to FIG. 4 specifically includes:

The positioning information acquiring unit is used to acquire positioning information of the robot in the indoor area.

An initial map acquisition unit is used to construct a map of the indoor area according to the real-time positioning and map construction algorithm and the positioning information to generate the initial map.

It can be seen from the above embodiment that, through the SLAM algorithm, the map construction of the entire indoor area can be completed in real time when the cleaning robot first works, thereby improving the accuracy of the initial map and providing map data support for subsequent accurate cleaning.

As shown in FIG. 5, in an embodiment of the present invention, the room area acquisition module 120 in FIG. 4 further includes a structure for executing the method steps in the embodiment corresponding to FIG. 2, which includes:

A binarized image acquisition unit 121, configured to perform binarization processing on the initial map to obtain a binarized image corresponding to the initial map;

The indoor area image acquisition unit 122 is configured to perform image erosion processing on the binarized image to obtain the indoor area image, and detect the connected domain in the indoor area image.

The room area acquisition unit 123 is configured to perform expansion processing on each connected domain in the indoor area image, and use the area within the smallest circumscribed polygon of each connected domain after the expansion processing as the room area corresponding to the connected domain.

In one embodiment of the present invention, the graphic information includes area area, area shape, and area connection topology relationship. The area recognition result acquisition module in FIG. 4 specifically includes:

In an embodiment of the present invention, the indoor area division and recognition device 100 further includes a structure for executing the method steps in the embodiment corresponding to FIG. 3, which includes:

An area recognition result sending module, configured to send the area recognition result to a user terminal, so that the user terminal displays the area recognition result;

An area recognition result correction module, configured to receive area recognition result correction information sent by the preset terminal, and correct the area recognition result according to the area recognition result correction information, and the area recognition result correction information is the user terminal The obtained correction information that the user inputs when checking that the area recognition result has an error.

It can be seen from the above embodiment that the user corrects the area recognition result automatically recognized by the robot through the user terminal, which can further improve the accuracy of the area recognition result, so that the cleaning robot can perform the switching work according to the corrected area recognition result in the subsequent cleaning work mode.

In an embodiment of the present invention, the indoor area division and identification device further includes:

The working mode confirmation module is used to determine the working mode corresponding to each room area according to the area recognition result corresponding to each room area.

In an embodiment of the invention, the working mode confirmation module specifically includes:

A super strong pollution purification mode confirmation unit, used to adjust the working module to a super strong pollution purification mode if the area recognition result is a kitchen;

A powerful cleaning mode confirmation unit, configured to adjust the working mode to a powerful cleaning mode if the area recognition result is a living room;

The normal cleaning mode confirmation unit is used to adjust the working mode to the normal cleaning mode if the area recognition result is a bedroom.

In an embodiment of the invention, the working mode confirmation module further includes:

A forbidden area acquisition unit, configured to acquire a forbidden area input by a user, and compare the area identification result with the forbidden area;

The forbidden working module confirmation unit is configured to adjust the working mode to a forbidden cleaning mode if the area recognition result is consistent with the forbidden area.

In this embodiment, due to the different functions of each area of an ordinary family house, the ground cleanliness is also different. Setting different working modes for the cleaning robot according to the rooms with different functions can make the cleaning robot more targeted for cleaning Work, thereby improving the cleaning level and working efficiency of the robot.

In one embodiment, the indoor area division and identification device 100 further includes other functional modules / units for implementing the method steps in each of the embodiments.

Examples 3 :

An embodiment of the present invention further provides a terminal device 6, including a memory 61, a processor 60, and a computer program 62 stored in the memory 61 and executable on the processor 60, and the processor 60 executes the computer program 62 The steps in each of the embodiments described in Embodiment 1 are implemented, for example, steps S101 to S103 shown in FIG. 1. Alternatively, when the processor 60 executes the computer program 62, the functions of each module in each device embodiment described in Embodiment 2 are realized, for example, the functions of the modules 110 to 130 shown in FIG. 4.

The terminal device 6 may be a computing device such as a desktop computer, a notebook, a palmtop computer and a cloud server. The terminal device 6 may include, but is not limited to, a processor 60 and a memory 61. For example, the terminal device 6 may further include input and output devices, network access devices, buses, and the like.

The so-called processor 60 may be a central processing unit (Central Processing Unit (CPU), can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (Application Specific Integrated Circuit (ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 61 may be an internal storage unit of the terminal device 6, such as a hard disk or a memory of the terminal device 6. The memory 61 may also be an external storage device of the terminal device 6, such as a plug-in hard disk equipped on the terminal device 6, a smart memory card (Smart Media Card, SMC), and secure digital (SD) Flash card Card) etc. Further, the memory 61 may also include both an internal storage unit of the terminal device 6 and an external storage device. The memory 61 is used to store the computer program 62 and other programs and data required by the terminal device 6. The memory 61 can also be used to temporarily store data that has been or will be output.

Examples 4 :

An embodiment of the present invention also provides a computer-readable storage medium that stores a computer program 62, and when the computer program 62 is executed by the processor 60, the steps in the embodiments described in Embodiment 1 are implemented. , For example, steps S101 to S103 shown in FIG. 1. Alternatively, when the computer program 62 is executed by the processor 60, the functions of the modules in the device embodiments described in Embodiment 2 are implemented, for example, the functions of the modules 110 to 130 shown in FIG.

The computer program 62 can be stored in a computer-readable storage medium. When the computer program 62 is executed by the processor 60, the steps of the foregoing method embodiments can be implemented. Wherein, the computer program 62 includes computer program code, and the computer program code may be in a source code form, an object code form, an executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunication signals, and software distribution media. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in jurisdictions. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media Excluded are electrical carrier signals and telecommunications signals.

The steps in the method of the embodiment of the present invention may be adjusted, merged, and deleted sequentially according to actual needs.

The modules or units in the system of the embodiment of the present invention may be combined, divided, and deleted according to actual needs.

The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modification, equivalent replacement and improvement made within the spirit and principle of the present invention should be included in the protection of the present invention Within range.

Claims

An indoor area division and identification method, which is characterized by including:

Get the initial map;

Morphological image processing technology is used to divide the initial map into regions to obtain at least one room region of the indoor region image;

According to the graphic information and preset identification information of each room area, the area identification result corresponding to each room area is determined.
The indoor area division and recognition method according to claim 1, wherein the morphological image processing technology is used to divide the initial map to obtain at least one room area of the indoor area image, including:

Performing binary processing on the initial map to obtain a binary image corresponding to the initial map;

Performing image erosion processing on the binary image to obtain an indoor area image, and detecting connected domains in the indoor area image;

Each connected domain in the indoor area image is subjected to expansion processing, and the area within the smallest circumscribed polygon of each connected domain after the expansion processing is taken as the room area corresponding to the connected domain.
The indoor area division and identification method according to claim 1, wherein the graphic information includes an area area, an area shape and an area connection topological relationship, and the determination is based on the graphic information of each room area and preset identification information The area recognition results corresponding to each room area include:

According to the area area, area shape, area connection topology relationship and preset identification information corresponding to each room area, the function type of each room area is obtained.
The indoor area division and identification method according to claim 1, wherein after determining the area identification result corresponding to each room area according to the graphic information and preset identification information of each room area, further comprising:

Sending the area recognition result to the user terminal, so that the user terminal displays the area recognition result;

Receiving the area identification result correction information sent by the preset terminal, and correcting the area identification result according to the area identification result correction information, the area identification result correction information is for the user acquired by the user terminal Correction information entered when there is an error in the area recognition result.
The indoor area division and recognition method according to any one of claims 1 to 4, wherein after determining the area recognition result corresponding to each room area according to the graphic information and preset identification information of each room area, Also includes:

According to the area recognition results corresponding to each room area, the working mode corresponding to each room area is determined.
The indoor area division and recognition method according to claim 5, wherein the area recognition result includes a kitchen, a living room, and a bedroom; and the work mode corresponding to each room area is determined according to the area recognition result corresponding to each room area ,Also includes:

If the result of the area recognition is a kitchen, adjust the working module to a super pollution purification mode;

If the area recognition result is a living room, adjust the working mode to a strong cleaning mode;

If the area recognition result is a bedroom, the working mode is adjusted to a regular cleaning mode.
The indoor area division and identification method according to claim 5, wherein the determining the working mode corresponding to each room area according to the area identification result corresponding to each room area further comprises:

Obtain the forbidden area entered by the user, and compare the area identification result with the forbidden area;

If the result of the area recognition is consistent with the forbidden area, the working mode is adjusted to the no-cleaning mode.
An indoor area division and identification device, characterized in that it includes:

The initial map acquisition module is used to acquire the initial map;

A room area acquisition module, configured to use morphological image processing technology to partition the initial map to obtain at least one room area of the indoor area image;

The area recognition result acquisition module is used to determine the area recognition result corresponding to each room area according to the graphic information and preset identification information of each room area.
The indoor area division and identification device according to claim 8, wherein the room area acquisition module comprises:

A binary image acquisition unit, configured to perform binary processing on the initial map to obtain a binary image corresponding to the initial map;

An indoor area image acquisition unit, configured to perform image erosion processing on the binary image to obtain an indoor area image, and detect a connected domain in the indoor area image;

The room area acquisition unit is configured to perform expansion processing on each connected domain in the indoor area image, and use the area within the smallest circumscribed polygon of each connected domain after the expansion processing as the room area corresponding to the connected domain.
A terminal device, including a memory, a processor, and a computer program stored in the memory and runable on the processor, characterized in that the processor implements the computer program as claimed in claims 1 to 7 The steps of any one of the methods.
A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.