CN115640372A

CN115640372A - Method, device, system, equipment and medium for guiding area of indoor plane

Info

Publication number: CN115640372A
Application number: CN202211272825.XA
Authority: CN
Inventors: 王美钰
Original assignee: Agricultural Bank of China
Current assignee: Agricultural Bank of China
Priority date: 2022-10-18
Filing date: 2022-10-18
Publication date: 2023-01-24

Abstract

The invention discloses a region guiding method, a device, a system, equipment and a medium for an indoor plane. The method comprises the following steps: acquiring a regional position query instruction sent by a user side; the area position query instruction comprises an indoor plane number and user side query information; acquiring a target indoor plane graph corresponding to the indoor plane number in the area position query instruction, and determining a corresponding target position area in the target indoor plane graph according to user side query information; generating a target indoor plane graph and a target position area through a pre-trained target convolution neural semantic segmentation network PSPNet; and acquiring the position information of the target position area, and sending the position information of the target position area to a user side so as to guide the user to travel to the target position area. By the technical scheme, the area of the indoor plane can be quickly and accurately acquired, and the area guiding efficiency is improved.

Description

Method, device, system, equipment and medium for guiding area of indoor plane

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to a method, an apparatus, a system, a device, and a medium for guiding an area of an indoor plane.

Background

With the rapid development of the internet of things, in order to realize digital transformation of each enterprise unit, it is desirable to realize interconnection and intercommunication between devices or systems in a park by creating an enterprise park with informatization, visualization and intelligence, so as to provide intelligent processing for offices, businesses, guests and the like.

At present, buildings with multiple floors are arranged in a plurality of parks, and due to the fact that the layout of each building and even each floor is different, visitors cannot clearly know the indoor layout of the park and cannot quickly find a destination. Therefore, an important function of the intelligent park is indoor navigation, namely how to accurately find a target place according to a navigation route by inputting information.

Usually, the navigation route is displayed according to an indoor plan, and the traditional indoor plan construction method is to scan and map the indoor with a tape measure or a professional surveying and mapping tool. Or, the position information of the Ultra Wide Band (UWB) positioning device is collected and sent to the control terminal, and is connected in sequence to form an indoor plan. However, the method of scanning and drawing indoors with a tape measure or a professional surveying and mapping tool is inefficient and costly, and is difficult to implement; the mode of forming an indoor plan by using UWB positioning equipment requires the use of a large number of positioning equipment, and determining the placement position of the positioning equipment is time-consuming and labor-consuming. Therefore, how to rapidly and accurately obtain the area of the indoor plane and improve the efficiency of area guidance is a problem to be solved urgently at present.

Disclosure of Invention

The invention provides a method, a device, a system, equipment and a medium for guiding an indoor plane area, which can solve the problem of low efficiency of guiding the indoor plane area.

According to an aspect of the present invention, there is provided an indoor plane area guidance method, including:

acquiring a regional position query instruction sent by a user side; the area position query instruction comprises an indoor plane number and user side query information;

acquiring a target indoor plane graph corresponding to the indoor plane number in the area position query instruction, and determining a corresponding target position area in the target indoor plane graph according to user side query information; generating a target indoor plane graph and a target position area through a pre-trained target convolution neural semantic segmentation network PSPNet;

and acquiring the position information of the target position area, and sending the position information of the target position area to a user side so as to guide the user to travel to the target position area.

According to another aspect of the present invention, there is provided an indoor planar area directing apparatus comprising:

the instruction acquisition module is used for acquiring an area position query instruction sent by a user side; the area position query instruction comprises an indoor plane number and user side query information;

the position area acquisition module is used for acquiring a target indoor plane map corresponding to the indoor plane number in the area position query instruction and determining a corresponding target position area in the target indoor plane map according to the user side query information; generating a target indoor plane graph and a target position area through a pre-trained target convolution neural semantic segmentation network PSPNet;

and the position information acquisition module is used for acquiring the position information of the target position area and sending the position information of the target position area to the user side so as to guide the user to move to the target position area.

According to another aspect of the present invention, there is provided an area guide system of an indoor plane, including:

the processor is used for acquiring a region position query instruction sent by a user side; the area position query instruction comprises an indoor plane number and user side query information; acquiring a target indoor plane graph corresponding to the indoor plane number in the area position query instruction, and determining a corresponding target position area in the target indoor plane graph according to user side query information; generating a target indoor plane graph and a target position area through a pre-trained target convolution neural semantic segmentation network PSPNet; acquiring position information of a target position area, and sending the position information of the target position area to a user side so as to guide the user to travel to the target position area;

and the user side is used for sending the area position query instruction to the processor and receiving the position information of the target position area sent by the processor.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform a method for area guidance of an indoor plane according to any one of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement a method for area guidance of an indoor plane according to any one of the embodiments of the present invention when executed.

According to the technical scheme, the target indoor plane map corresponding to the indoor plane number in the area position query instruction sent by the user side is obtained, the corresponding target position area is further determined in the target indoor plane map according to the query information of the user side, finally, the position information of the target position area is obtained, and the position information of the target position area is sent to the user side to guide the user to move to the target position area.

It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present invention, nor are they intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a region guidance method for an indoor plane according to an embodiment of the present invention;

fig. 2 is a flowchart of a region guidance method for an indoor plane according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of an indoor planar area directing device according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of an indoor planar area guidance system according to a fourth embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic device implementing the area guidance method for an indoor plane according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that, in the technical solution of the present application, the acquisition, storage, use, processing, etc. of data all conform to the relevant regulations of the national laws and regulations. The terms "first," "second," "target," and the like in the description and claims of the invention and in the foregoing description and drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a flowchart of an indoor plane area guidance method according to an embodiment of the present invention, where the present embodiment is applicable to a case where an indoor plane area guidance is provided for a user inside a building, and the method may be performed by an indoor plane area guidance device, which may be implemented in hardware and/or software, and the indoor plane area guidance device may be configured in an electronic device. As shown in fig. 1, the method includes:

s110, acquiring a region position query instruction sent by a user side.

The area location query instruction includes an indoor plane number and user side query information.

The area location query instruction may refer to an instruction initiated by the user terminal to query the location of an indoor planar area inside the building. The indoor plane number may refer to a number of each floor inside a building, and may be, for example, a number, an identity identifier, and the like, which is not limited in this embodiment of the present invention. The query information of the user side may refer to attribute information corresponding to an area to which the user needs to travel, and may be, for example, a number of an employee corresponding to a certain workstation or a room number of a certain conference room.

And S120, acquiring a target indoor plane graph corresponding to the indoor plane number in the area position query instruction, and determining a corresponding target position area in the target indoor plane graph according to the user side query information.

And generating a target indoor plane map and a target position area through a pre-trained target convolution neural semantic segmentation network PSPNet.

The target indoor plane map may refer to a location classification image that includes each location area classified in advance, and corresponds to the indoor plane number in the area location query instruction. The target location area may refer to a location area in the target indoor plane map corresponding to the user-side query information.

Specifically, if the area position query instruction sent by the user side is "conference room No. 01 on the second floor", the indoor plane number may be "second floor", the user side query information may be "conference room No. 01", and further, the position classification image including all the position areas in the "second floor" may be used as the target indoor plane map, and further, the area corresponding to "conference room No. 01" is screened out from the target indoor plane map and used as the target position area. Therefore, the location area which the user side needs to inquire can be efficiently acquired.

S130, obtaining the position information of the target position area, and sending the position information of the target position area to a user side so as to guide the user to move to the target position area.

The location information of the target location area may refer to location information of the target location area in a target indoor plan view. For example, the location information of the target location area may be generated from a landmark area in the target indoor plan. Specifically, taking the area location query instruction sent by the user terminal as "conference room No. 01 on the second floor" as an example, the location information of the target location area may be "on the left side of the tea room".

Example two

Fig. 2 is a flowchart of a region guidance method for an indoor plane according to a second embodiment of the present invention, where the present embodiment details based on the above embodiment, and in the present embodiment, specifically details an operation of obtaining a target indoor plane corresponding to an indoor plane number in a region location query instruction, where the method may specifically include: and screening out a target indoor plane graph matched with the indoor plane number in the region position query instruction from the prestored position classification images.

As shown in fig. 2, the method includes:

s210, receiving the top-view images corresponding to all indoor planes shot by the camera, and labeling the top-view images according to contour coordinate information of all position areas in the top-view images to form a training data set.

Wherein, the camera can refer to the shooting equipment of building inside pre-installation. Along with the camera is more and more extensive in public area application, just can easily gather a large amount of data through the camera, from this, can be convenient for the acquisition of data, improve the efficiency that the region guided.

It is worth noting that the top view of each floor in the building can be efficiently collected by adjusting the shooting angle of the camera in order to increase the data set.

The training data set may refer to a data set for training a pre-established convolutional neural semantic segmentation Network (PSPNet). Illustratively, it may be a data set containing a plurality of annotation images. The annotation image may refer to an image obtained by an image annotation tool and containing coordinate information of the contour of the object in the top view image. It is noted that each pixel in the annotation image is fixed with a corresponding category identifier. The category identification needs to be determined according to the type of the identified location area, such as a corridor, a workstation, a chair or a cabinet, and the like, which is not limited by the embodiment of the present disclosure.

And S220, training the preset PSPNet by using the training data set to obtain the target PSPNet.

In an optional embodiment, the training the preset PSPNet by using the training data set to obtain the target PSPNet may include: initializing network parameters of a preset PSPNet, and extracting a feature map containing image features in a training data set by using a convolution module in the preset PSPNet; acquiring local features and global features in the feature map by using a pyramid pooling module in a preset PSPNet; connecting the local features and the global features in series by using a Full Convolution Network (FCN) in a preset PSPNet to obtain a predicted feature expression vector; and calculating the partial derivative of the loss function to each weight in the preset PSPNet according to the chain derivation of the back propagation algorithm by using the prediction characteristic expression vector, and updating each weight according to the partial derivative until the target iteration times is reached to obtain the target PSPNet.

The step of initializing the network parameters of the preset PSPNet may refer to performing an initialization process on each network parameter in the preset PSPNet. Illustratively, the network parameters may include: learning rate, batch size, optimization algorithm, number of iterations or weight decay, etc. The convolution module may refer to a module in which one of the two functions is inverted and shifted and then multiplied to obtain a product. The pyramid pooling module may refer to a module that performs downsampling. A local feature may refer to a shallow feature in a feature map. Global features may refer to deep features in a feature map. The prediction feature expression vector may refer to a prediction value obtained by forward propagation of a preset PSPNet. The target number of iterations may refer to a value set in advance for evaluating the number of iterations.

Specifically, a convolution module is utilized to extract image features in a training data set to generate a feature map; further, local features and global features in the feature map are obtained by using a pyramid pooling module, and the local features and the global features are connected in series by using a Full Convolution Network (FCN) to obtain a predicted feature expression vector; and finally, calculating the partial derivative of each weight in the preset PSPNet according to the prediction characteristic expression vector and the chain type derivative of the back propagation algorithm, and updating each weight according to the partial derivative until the target iteration times are reached to obtain the target PSPNet.

It should be noted that the generation process of the target PSPNet may be performed before the target PSPNet is used, and this is not specifically limited in the embodiment of the present invention.

And S230, receiving the indoor plan to be detected collected by the camera, inputting the indoor plan to be detected to the target PSPNet, and outputting a position classification image containing each position area.

The indoor plan to be measured can refer to an original plan inside a building actually shot by the camera. Each indoor plan to be measured is an actual shot image and does not contain a labeling result.

In an optional embodiment, after outputting the location classification image including the location areas, the method may further include: binding corresponding physical position information for each position area according to the geographical position information of each position area; and the geographical position information of each position area is pre-stored in a database. The geographic location information may refer to identification information of each location area. For example, if the location area is a workstation, the geographic location information may be a job number or a name of an employee corresponding to the workstation; if the location area is a conference room, the geographic location information may be a room number or the like. Therefore, the corresponding physical position information is bound for each position area in the position classification image, and convenience can be provided for follow-up user side query.

S240, acquiring a region position query instruction sent by a user side; the area position query instruction comprises an indoor plane number and user side query information.

And S250, screening out a target indoor plane graph matched with the indoor plane number in the region position query instruction from the prestored position classification images.

Specifically, the location classification image matched with the indoor plane number in the area location query command is screened out from each pre-stored location classification image, and the location classification image can be used as a target indoor plane map. Thereby, an effective basis for subsequent further location area identification can be provided.

S260, screening out a target position area matched with the user side query information from the target indoor plane graph.

Specifically, after the target indoor plane map is obtained, a location area matched with the user side query information is screened out from the target indoor plane map, and the location area can be used as the target location area. Thereby, an effective basis for acquiring the position information of the target position area can be provided.

S270, obtaining the position information of the target position area, and sending the position information of the target position area to the user side so as to guide the user to move to the target position area.

According to the technical scheme of the embodiment of the invention, the contour coordinate information of each position area in the overlook image shot by the camera is marked to form a training data set, and the preset PSPNet is trained by utilizing the training data set to obtain the target PSPNet; further, processing an indoor plan to be measured acquired by the camera by using the target PSPNet, and outputting a position classification image containing each position area; and when acquiring a regional position query instruction sent by a user terminal, screening out a target indoor plane map matched with the indoor plane number in the regional position query instruction from the pre-stored position classification image, further screening out a target position region matched with the query information of the user terminal from the target indoor plane map, finally acquiring the position information of the target position region, and sending the position information of the target position region to the user terminal to guide the user to move to the target position region, so that the problem of low guide efficiency of the indoor plane region is solved, the region of the indoor plane can be quickly and accurately acquired, and the region guide efficiency is improved.

EXAMPLE III

Fig. 3 is a schematic structural diagram of an indoor planar area directing device according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes: an instruction obtaining module 310, a location area obtaining module 320, and a location information obtaining module 330;

the instruction obtaining module 310 is configured to obtain an area location query instruction sent by a user end; the area position query instruction comprises an indoor plane number and user side query information;

a location area obtaining module 320, configured to obtain a target indoor plane map corresponding to the indoor plane number in the area location query instruction, and determine a corresponding target location area in the target indoor plane map according to the user side query information; generating a target indoor plane graph and a target position area through a pre-trained target convolution neural semantic segmentation network PSPNet;

the location information acquiring module 330 is configured to acquire location information of a target location area, and send the location information of the target location area to a user side, so as to guide the user to travel to the target location area.

According to the technical scheme of the embodiment of the invention, the target indoor plane map corresponding to the indoor plane number in the area position query instruction sent by the user terminal is obtained, the corresponding target position area is further determined in the target indoor plane map according to the query information of the user terminal, finally, the position information of the target position area is obtained, and the position information of the target position area is sent to the user terminal to guide the user to move to the target position area, so that the problem of low guide efficiency of the indoor plane area is solved, the area of the indoor plane can be quickly and accurately obtained, and the area guide efficiency is improved.

Optionally, the area directing device for the indoor plane may further include: the position classification image generation module is used for receiving overlook images corresponding to all indoor planes shot by a camera before acquiring a target indoor plane image corresponding to an indoor plane number in a region position query instruction and determining a corresponding target position region in the target indoor plane image according to user side query information, and marking the overlook images according to contour coordinate information of all position regions in the overlook images to form a training data set; training a preset PSPNet by utilizing the training data set to obtain a target PSPNet; and receiving an indoor plan to be detected collected by a camera, inputting the indoor plan to be detected into a target PSPNet, and outputting a position classification image containing each position area.

Optionally, the location classification image generation module may be specifically configured to: initializing network parameters of a preset PSPNet, and extracting a feature map containing image features in a training data set by using a convolution module in the preset PSPNet; acquiring local features and global features in the feature map by using a pyramid pooling module in a preset PSPNet; connecting the local features and the global features in series by using a Full Convolution Network (FCN) in a preset PSPNet to obtain a predicted feature expression vector; and calculating the partial derivative of the loss function to each weight in the preset PSPNet according to the chain derivation of the back propagation algorithm by using the prediction characteristic expression vector, and updating each weight according to the partial derivative until the target iteration times is reached to obtain the target PSPNet.

Optionally, the location area obtaining module 320 may be specifically configured to: and screening out a target indoor plane graph matched with the indoor plane number in the region position query instruction from the prestored position classification images.

Optionally, the location area obtaining module 320 may be specifically configured to: and screening out a target position area matched with the user side query information from the target indoor plane graph.

Optionally, the area directing device for the indoor plane may further include: the position information binding module is used for binding corresponding physical position information for each position area according to the geographical position information of each position area after the position classification image containing each position area is output; and the geographical position information of each position area is pre-stored in a database.

The area guidance device of the indoor plane provided by the embodiment of the invention can execute the area guidance method of the indoor plane provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

Example four

Fig. 4 is a schematic structural diagram of an indoor planar area guidance system according to a fourth embodiment of the present invention. As shown in fig. 4, the system includes: a processor 410 and a client 420;

the processor 410 is configured to obtain an area location query instruction sent by the user end 420; the area position query instruction comprises an indoor plane number and user side query information; acquiring a target indoor plane graph corresponding to the indoor plane number in the area position query instruction, and determining a corresponding target position area in the target indoor plane graph according to user side query information; generating a target indoor plane graph and a target position area through a pre-trained target convolution neural semantic segmentation network PSPNet; acquiring the location information of a target location area, and sending the location information of the target location area to a user terminal 420, so as to guide the user to travel to the target location area;

the user end 420 is configured to send the area location query instruction to the processor 410, and receive the location information of the target location area sent by the processor 410.

According to the technical scheme of the embodiment of the invention, the target indoor plane map corresponding to the indoor plane number in the area position query instruction sent by the user terminal 420 is obtained, the corresponding target position area is further determined in the target indoor plane map according to the query information of the user terminal, finally, the position information of the target position area is obtained, and the position information of the target position area is sent to the user terminal 420, so that the user is guided to move to the target position area, the problem of low guidance efficiency of the indoor plane area is solved, the area of the indoor plane can be quickly and accurately obtained, and the area guidance efficiency is improved.

Optionally, the processor 410 may be further configured to: the method comprises the steps that a target indoor plane graph corresponding to indoor plane numbers in a region position query instruction is obtained, before a corresponding target position region is determined in the target indoor plane graph according to user side query information, top-view images corresponding to indoor planes and shot by a camera are received, the top-view images are marked according to contour coordinate information of the position regions in the top-view images, and a training data set is formed; training a preset PSPNet by utilizing the training data set to obtain a target PSPNet; and receiving an indoor plan to be detected collected by a camera, inputting the indoor plan to be detected into a target PSPNet, and outputting a position classification image containing each position area.

Optionally, the processor 410 may be specifically configured to: initializing network parameters of a preset PSPNet, and extracting a feature map containing image features in a training data set by using a convolution module in the preset PSPNet; acquiring local features and global features in the feature map by using a pyramid pooling module in a preset PSPNet; connecting the local features and the global features in series by using a Full Convolution Network (FCN) in a preset PSPNet to obtain a predicted feature expression vector; and calculating the partial derivative of the loss function to each weight in the preset PSPNet according to the chain derivation of the back propagation algorithm by using the prediction characteristic expression vector, and updating each weight according to the partial derivative until the target iteration times is reached to obtain the target PSPNet.

Optionally, the processor 410 may be specifically configured to: and screening out a target indoor plane graph matched with the indoor plane number in the region position query command from the prestored position classification images.

Optionally, the processor 410 may be specifically configured to: and screening out a target position area matched with the user side query information from the target indoor plane graph.

Optionally, the processor 410 may be further configured to: after the position classification image containing each position area is output, binding corresponding physical position information for each position area according to the geographical position information of each position area; and the geographical position information of each position area is pre-stored in a database.

The area guidance system of the indoor plane provided by the embodiment of the invention can execute the area guidance method of the indoor plane provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

EXAMPLE five

FIG. 5 illustrates a block diagram of an electronic device 510 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 5, the electronic device 510 includes at least one processor 520, and a memory communicatively coupled to the at least one processor 520, such as a Read Only Memory (ROM) 530, a Random Access Memory (RAM) 540, and so on, where the memory stores computer programs executable by the at least one processor, and the processor 520 may perform various suitable actions and processes according to the computer programs stored in the Read Only Memory (ROM) 530 or the computer programs loaded from the storage unit 590 into the Random Access Memory (RAM) 540. In the RAM540, various programs and data required for the operation of the electronic device 510 can also be stored. The processor 520, the ROM 530, and the RAM540 are connected to each other through a bus 550. An input/output (I/O) interface 560 is also connected to bus 550.

A number of components in the electronic device 510 are connected to the I/O interface 560, including: an input unit 570 such as a keyboard, a mouse, and the like; an output unit 580 such as various types of displays, speakers, and the like; a storage unit 590 such as a magnetic disk, optical disk, or the like; and a communication unit 5100 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 5100 allows the electronic device 510 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

Processor 520 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of processor 520 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 520 performs the various methods and processes described above, such as the area-directed approach to indoor planes.

The method comprises the following steps:

and acquiring the position information of the target position area, and sending the position information of the target position area to a user side so as to guide the user to move to the target position area.

In some embodiments, the area directing method of the indoor plane may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 590. In some embodiments, part or all of the computer program can be loaded and/or installed onto the electronic device 510 via the ROM 530 and/or the communication unit 5100. When the computer program is loaded into RAM540 and executed by processor 520, one or more steps of the above-described area-directing method of the indoor plane may be performed. Alternatively, in other embodiments, the processor 520 may be configured by any other suitable means (e.g., by means of firmware) to perform the area direction method for the indoor plane.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method of area guidance of an indoor plane, comprising:

2. The method according to claim 1, wherein before the obtaining of the target indoor plane map corresponding to the indoor plane number in the area location query instruction and determining the corresponding target location area in the target indoor plane map according to the user-side query information, further comprising:

receiving the top-view images corresponding to all indoor planes shot by the camera, and labeling the top-view images according to the contour coordinate information of all position areas in the top-view images to form a training data set;

training a preset PSPNet by utilizing the training data set to obtain a target PSPNet;

and receiving an indoor plan to be detected collected by a camera, inputting the indoor plan to be detected into a target PSPNet, and outputting a position classification image containing each position area.

3. The method as claimed in claim 2, wherein the training of the predetermined PSPNet with the training data set to obtain the target PSPNet comprises:

initializing network parameters of a preset PSPNet, and extracting a feature map containing image features in a training data set by using a convolution module in the preset PSPNet;

acquiring local features and global features in the feature map by using a pyramid pooling module in a preset PSPNet;

connecting the local features and the global features in series by using a Full Convolution Network (FCN) in a preset PSPNet to obtain a predicted feature expression vector;

and calculating the partial derivative of the loss function to each weight in the preset PSPNet according to the chain derivation of the back propagation algorithm by using the prediction characteristic expression vector, and updating each weight according to the partial derivative until the target iteration times is reached to obtain the target PSPNet.

4. The method according to claim 1, wherein the obtaining the target indoor plane map corresponding to the indoor plane number in the area location query command comprises:

and screening out a target indoor plane graph matched with the indoor plane number in the region position query instruction from the prestored position classification images.

5. The method of claim 1, wherein the determining a corresponding target location area in the target indoor plane according to the user-side query information comprises:

and screening out a target position area matched with the user side query information from the target indoor plane graph.

6. The method according to claim 2, further comprising, after the outputting the position classification image containing the position areas:

binding corresponding physical position information for each position area according to the geographical position information of each position area; and the geographical position information of each position area is pre-stored in a database.

7. An indoor planar area directing apparatus, comprising:

the position area acquisition module is used for acquiring a target indoor plane graph corresponding to the indoor plane number in the area position query instruction and determining a corresponding target position area in the target indoor plane graph according to the user side query information; generating a target indoor plane graph and a target position area through a pre-trained target convolution neural semantic segmentation network PSPNet;

8. An indoor planar area guidance system, comprising:

and the user side is used for sending the regional position query instruction to the processor and receiving the position information of the target position region sent by the processor.

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the area directing method of the indoor plane of any one of claims 1-6.

10. A computer-readable storage medium, having stored thereon computer instructions for causing a processor to execute a method of area guidance of an indoor plane according to any one of claims 1 to 6.