WO2020019239A1

WO2020019239A1 - Positioning method and device, terminal and readable storage medium

Info

Publication number: WO2020019239A1
Application number: PCT/CN2018/097216
Authority: WO
Inventors: 林义闽; 廉士国; 易万鑫; 王超鹏
Original assignee: 深圳前海达闼云端智能科技有限公司
Priority date: 2018-07-26
Filing date: 2018-07-26
Publication date: 2020-01-30
Also published as: CN109691185A; CN109691185B

Abstract

The present application relates to the field of computer vision, in particular to a positioning method and device, a terminal and a readable storage medium. The positioning method is applied to a terminal or a cloud, and the positioning method comprises: acquiring a confidence coefficient of a scene where a terminal is located within a current time period, the confidence coefficient being used for representing a degree of difference between the scene where the terminal is located within the current time period and the scene where the terminal is located within a previous time period; adjusting a first positioning frequency according to the confidence coefficient of the scene where the terminal is located within the current time period, the confidence coefficient being inversely proportional to the first positioning frequency; according to the adjusted first positioning frequency, performing vision positioning in the scene within the current time period. The positioning method can reduce the power consumption of positioning and improve the endurance capability of the terminal, without reducing the positioning precision of the terminal.

Description

Positioning method, device, terminal and readable storage medium

Technical field

The present application relates to the field of computer vision, and in particular, to a positioning method, a device, a terminal, and a readable storage medium.

Background technique

With the rapid development of the performance of the terminal processor, the processing capacity of the terminal has been greatly improved, but because the development of battery technology is far from keeping up with the development of integrated circuits, when the battery capacity is very limited, the endurance of the terminal is subject to Impact of device power consumption. The current terminal integrates visual real-time map creation and positioning (Visual Simultaneous Localization and Mapping (referred to as "vSLAM") positioning algorithm, real-time terminal composition and positioning functions, such as intelligent robots, drones or AR / VR and other terminals.

technical problem

The inventor discovered during the research of the prior art that due to the high complexity of the vSLAM algorithm, the computing resources required on the terminal are very large, which reduces the effective working time of the terminal. At present, without reducing the stability of the vSLAM algorithm, the power consumption of vSLAM is usually reduced by reducing the positioning frequency of vSLAM. However, reducing the positioning frequency of vSLAM is prone to follow-up loss, which results in positioning failure and reduces the positioning accuracy of the terminal. .

It can be seen that how to reduce the power consumption of positioning without reducing the positioning accuracy of the terminal is a problem to be solved.

Technical solutions

A technical problem to be solved in some embodiments of the present application is to provide a positioning method, a device, a terminal, and a readable storage medium, so as to reduce the power consumption of positioning and improve the endurance of the terminal without reducing the positioning accuracy of the terminal.

An embodiment of the present application provides a positioning method, including: obtaining a confidence level of a scene in which a terminal is located in a current period, and the confidence level is used to represent a scene in which the terminal is located in the current period and a scene in a previous period. The degree of difference; adjusting the first positioning frequency according to the confidence of the scene in which the terminal is located in the current period, wherein the confidence is inversely proportional to the first positioning frequency; in the scene in the current period according to the adjusted first positioning frequency Visual positioning.

An embodiment of the present application further provides a positioning device, including: a confidence degree acquisition module, a frequency adjustment module, and a positioning module; the confidence degree acquisition module is used to obtain the confidence degree of the scene in which the terminal is located in the current period, and the confidence degree is used for Yu indicates the degree of difference between the scene in which the terminal is in the current period and the scene in the previous period; the frequency adjustment module is used to adjust the first positioning frequency according to the confidence of the scene in which the terminal is in the current period. It is inversely proportional to the first positioning frequency; the positioning module is configured to perform visual positioning in the scene where the current period is located according to the adjusted first positioning frequency.

An embodiment of the present application further provides a terminal, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor. The processor executes to enable at least one processor to perform the positioning method described above.

An embodiment of the present application further provides a computer-readable storage medium storing a computer program, and the computer program implements the foregoing positioning method when executed by a processor.

Beneficial effect

Relative to the prior art, in some embodiments of the present application, since the first positioning frequency is inversely proportional to the confidence level, the confidence level indicates the degree of change of the scene in the current period and the scene in the previous period. When the confidence level is low, it indicates that the scene between the current period and the scene in the previous period has a large change and the scene is unstable. A high-frequency first positioning frequency is used to ensure the accuracy of the positioning. If the confidence level is high, it indicates that The scene does not change much and the scene is stable. The low-frequency first positioning frequency is used to locate the scene in the current period, which reduces the power consumption of positioning, and also greatly reduces the probability of follow-up loss. In this embodiment, the first positioning frequency is flexibly adjusted according to the degree of confidence, so that the power consumption of positioning is reduced without reducing the positioning accuracy of the terminal, and the endurance of the terminal is improved.

BRIEF DESCRIPTION OF THE DRAWINGS

One or more embodiments are exemplified by the pictures in the accompanying drawings. These exemplary descriptions do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the drawings in the drawings do not constitute a limitation on scale.

FIG. 1 is a schematic flowchart of a positioning method in a first embodiment of the present application; FIG.

2 is a schematic flowchart of a specific positioning method in a second embodiment of the present application;

FIG. 3 is a schematic diagram of a distribution of auxiliary positioning in a time period of T _N to T _{N + 1} in a positioning method according to a second embodiment of the present application; FIG.

4 is a schematic diagram of distribution of visual positioning and auxiliary positioning in a time period T1 to T2 in a positioning method in a second embodiment of the present application;

5 is a schematic structural diagram of a positioning device in a third embodiment of the present application;

FIG. 6 is a schematic structural diagram of a terminal in a fourth embodiment of the present application.

Embodiments of the invention

In order to make the purpose, technical solution, and advantages of the present application clearer, some embodiments of the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application. However, a person of ordinary skill in the art can understand that in the embodiments of the present application, many technical details are provided in order to make the reader better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solution claimed in this application can be implemented.

The first embodiment of the present application relates to a positioning method, which can be applied to a terminal or a cloud. The terminal may be a smart robot, an unmanned vehicle, a blind navigation device, or the like. The cloud communicates with the terminal to provide positioning results for the terminal. This embodiment uses the terminal as an example to describe the positioning process. For the process of executing the positioning method in the cloud, reference may be made to the content of the embodiment of the present application. The visual positioning in this embodiment is described by using the vSLAM positioning method as an example. Of course, other high-precision and high-energy-consuming visual positioning methods can also be used. This embodiment does not limit the visual positioning method of the terminal. The specific process of this positioning method is shown in Figure 1:

Step 101: Obtain the confidence of the scene in which the terminal is located in the current period. The confidence degree is used to indicate the degree of difference between the scene in which the terminal is located in the current period and the scene in the previous period.

In a specific implementation, image data of the scene where the terminal is located in the current period and angle information of the terminal are obtained; and based on the image data and angle information, the confidence level of the scene where the terminal is located in the current period is determined.

Specifically, the image data of the scene where the terminal is located in the current period can be obtained through a visual sensor, such as a camera, an infrared sensor, and the like. The angle information of the terminal in the current period can be obtained through an angle sensor, for example, an inclination sensor, a gyroscope, and the like. In this embodiment, there are no restrictions on the types of sensors that acquire image data, or the types of sensors that acquire terminal angle information.

In this step, the terminal may determine the confidence level of the scene in the current period according to the image data, determine the degree of texture quality change of the scene in the current period, and determine the lighting of the scene in the current period. Degree of change; Determine the degree of angle change of the scene in the current period according to the angle information; Calculate the average value of the texture quality change degree, lighting change degree and angle change degree, and use the average value as the terminal's The confidence of the scene.

The following will describe in detail the determination of the degree of change in texture quality, the degree of change in illumination, and the degree of change in angle, respectively.

It can be understood that the methods for determining the degree of texture quality change of the scene in the current period include, but are not limited to, the following two methods:

Method 1: Obtain characteristic pixel points in the image data, and count the number of characteristic pixel points, calculate a first ratio between the number of characteristic pixel points and the number of preset pixel points, and use the first ratio as the scene The degree of texture quality change.

Specifically, an image data is composed of one pixel, and feature pixels are extracted from the image data. There are multiple ways to extract feature pixels, for example, using scale-invariant feature transformation and accelerating robust features. Extraction of characteristic pixels of an image. Count the number of all characteristic pixel points extracted from the image data, and calculate the first ratio of the number of characteristic pixel points to the number of preset pixels. The number of preset pixels can be performed according to the actual situation. Setting, for example, the number of preset pixels can be 1000 or 10,000. The calculation of the first ratio is as follows: assuming that the number of characteristic feature pixels is F and the preset number of pixels is 1000, then the first ratio TF = F / 1000, and the first ratio is used as the texture quality of the scene Degree of change.

Method 2: Detect the pixels that belong to the edge in the image data, and count the number of pixels that belong to the edge, calculate the second ratio between the number of pixels that belong to the edge and the preset number of pixels, and set the second ratio The degree of change in the texture quality of the scene.

Specifically, the number of pixels belonging to the edge is extracted in the image data, and the extraction method may adopt an edge extraction method, which will not be repeated here. The preset number of image points is approximately the same as the setting method in the first method, which will not be described in detail here. The second ratio is calculated as follows: assuming that the number of pixels belonging to the edge is extracted as F ', and the preset number of pixels is 1000, then the second ratio is TF' = F '/ 1000, and the second ratio is used as the scene's The degree of texture quality change.

The following describes in detail the method of determining the degree of lighting change of the scene in the current period.

In a specific implementation, an average grayscale value in a preset area in the image data is calculated; and based on the average grayscale value and the preset grayscale value, the degree of lighting change of the scene in the current period is determined.

Specifically, the average gray value in a preset area in the image data is calculated. For example, the preset area may be the size of the entire image data, or it may be an intermediate area of the image data. The preset area may be based on the actual Need to be set. The average gray value in the preset area may be a sum of the gray value of each pixel in the preset area divided by the sum of all the pixels in the preset area. Of course, it may be determined by other This method calculates the average gray value in the preset area, which will not be exemplified here.

The calculated average gray value is compared with a preset gray value to determine the degree of lighting change of the scene in the current period. For example, if the preset gray value is 255 and the calculated average gray value is G, then the lighting change degree (TG) of the scene in the current period can be: TG = 1- G / 255, with TG as the current period. The lighting of the scene.

Of course, the lighting variation of the scene in which the scene is located can also be calculated in other manners, which will not be exemplified one by one in this embodiment.

The method of determining the degree of angle change of the scene in the current period is described in detail below.

In a specific implementation, a difference between the preset angle and the angle information is calculated; a third ratio between the difference and the preset angle is calculated, and the third ratio is used as the angle change degree of the scene in the current period.

For example, the angle information is A, and the preset angle can be 180 degrees or 360 degrees, which can be set according to the actual situation. Then the third ratio TA = 1-A / 180, and take TA as the degree of angle change of the scene in the current period.

After determining the texture quality change level, lighting change level, and angle change level in the scene in the current period, the average of the three can be obtained. For example, suppose the lighting change level is TG, the texture quality change level is TF, The degree of angle change is TA, then the confidence level of the scene in the current period is TH = (TF + TG + TA) / 3.

The confidence level of the scene in the current period in this embodiment is determined according to the degree of texture quality change, lighting change, and angle change. It can be understood that the confidence level of the scene in the current period can also be based on texture only. The degree of change in quality is determined either by the degree of change in lighting or the degree of change in angle; of course, the confidence of the scene in the current period can also be determined by the degree of change in texture quality, the degree of illumination, and the degree of change in angle The combination of any two of the two is determined, and this embodiment does not limit the method for determining the confidence of the scene in the current period.

It should be noted that the image data of the scene where the terminal is located in the current period is the image data of the last frame collected in the current period or the image data of all frames collected in the current period. It can be understood that if the image data is image data of all frames collected in the current period, then the average texture quality change degree, average light change degree, and average angle change of the image data of all frames in the current period can be calculated. Degree, calculates the confidence level of the scene in the current period.

Step 102: Adjust the first positioning frequency according to the confidence of the scene in which the terminal is located in the current period. The confidence level is inversely proportional to the first positioning frequency.

Specifically, the higher the confidence level of the scene in the current period, the smaller the change between the scene in the current period and the scene in the previous period, and the more stable the scene, the terminal can reduce the first frequency to reduce Power consumption. The smaller the confidence level of the scene in the current period, the greater the change between the scene in the current period and the scene in the previous period, the more unstable the scene is. The terminal can increase the first positioning frequency to improve positioning. Precision.

It can be understood that, in order to facilitate the adjustment of the first positioning frequency, a correspondence relationship between the confidence level and the first positioning frequency may be stored in advance. When the confidence level of the scene in the current period is determined, the first positioning frequency required for the scene in the current period can be determined according to the pre-stored correspondence. For example, the pre-stored correspondence is shown in Table 1. In Table 1, Δt1> Δt2> Δt3; if the confidence level of the scene in the current period is 0.3, then the first frequency is adjusted to Δt2. Table 1 is only an example. In real life, the confidence is more than the number listed in Table 1.

置信度 Confidence	第一定位频率 First positioning frequency
0.1 0.1	△t1 T1
0.3 0.3	△t2 T2
0.9 0.9	△t3 T3

Table 1

It should be noted that if the terminal is turned on, the default current confidence is the minimum value, and the highest first frequency is used for positioning.

Step 103: Perform visual positioning in the scene where the current period is located according to the adjusted first positioning frequency.

Relative to the prior art, in some embodiments of the present application, since the first positioning frequency is inversely proportional to the confidence level, the confidence level indicates the degree of change of the scene in the current period and the scene in the previous period. When the confidence level is low, it indicates that the current period has a large change between the scene in which it is located and the scene in the previous period, and the scene is unstable. A high-frequency first positioning frequency is used to ensure the accuracy of the positioning. If the confidence level is high, It shows that the scene changes little and the scene is stable. The low-frequency first positioning frequency is used to locate the scene in the current period, which reduces the power consumption of positioning, and also greatly reduces the probability of follow-up loss. In this embodiment, the first positioning frequency is flexibly adjusted according to the degree of confidence, so that the power consumption of positioning is reduced without reducing the positioning accuracy of the terminal, and the endurance of the terminal is improved.

The second embodiment of the present application relates to a positioning method. The second embodiment is a further improvement on the first embodiment. The main improvement is that in this embodiment, auxiliary positioning is added during the visual positioning process. Positioning, while reducing power consumption, further ensures the accuracy of terminal positioning. In this embodiment, the visual positioning uses vSLAM positioning as an example, and the auxiliary positioning uses a visual inertial measurement / measurement unit (Visual-Inertial Odometry / Inertialmeasurement unit (referred to as "VIO / IMU") positioning is taken as an example for illustration. The specific process of this positioning method is shown in Figure 2:

Step 201: Obtain the confidence of the scene in which the terminal is located in the current period.

Step 202: Adjust the first positioning frequency according to the confidence of the scene in which the terminal is located in the current period.

It should be noted that steps 201 to 202 in this embodiment are substantially the same as steps 101 to 102 in the first embodiment, and will not be described in detail here.

Step 203: Perform the Nth visual positioning in the scene where the current period is located according to the adjusted first positioning frequency, and obtain the positioning result of the Nth visual positioning. N is an integer greater than 0.

Step 204: During the intermediate period between the Nth visual positioning and the N + 1th visual positioning, perform at least one auxiliary positioning based on the positioning results of the Nth visual positioning.

The process of adding at least one auxiliary positioning during the intermediate period between the Nth visual positioning and the N + 1th visual positioning will be exemplified below.

For example, T _N indicates the time of the Nth visual positioning, and T _{N + 1} indicates the time of the N + 1th visual positioning. In the period of T _N ~ T _{N + 1} , the auxiliary positioning can be used to assist Positioning, to obtain the positioning result of the auxiliary positioning. The time for assisting positioning may be selected from the middle time of the period T _N ~ T _{N + 1} , or other time may be selected. It can be understood that auxiliary positioning can also be performed multiple times during the period of T _N ~ T _{N + 1} , wherein the auxiliary positioning is evenly distributed in the period of T _N ~ T _{N + 1} . As shown in FIG. 3, the auxiliary positioning is uniformly distributed twice during a period of T _N to T _{N + 1} (the auxiliary positioning is based on the VIO / IMU positioning method as an example).

In a specific implementation, the auxiliary positioning may also be performed according to the second positioning frequency.

Specifically, the second positioning frequency may be a fixed frequency. In order to improve the positioning accuracy of the auxiliary positioning, the fixed frequency may be a high frequency.

It can be understood that the second frequency can also be dynamically adjusted according to the confidence level. Before the terminal performs at least one auxiliary positioning based on the positioning results of the Nth visual positioning, the terminal obtains the second positioning frequency in the following manner: according to the confidence of the scene in which the terminal is located in the current period, and the confidence and proportion The corresponding relationship between them determines a second positioning frequency, where the ratio is a ratio of the first positioning frequency to the second positioning frequency.

Specifically, since the auxiliary positioning is used to assist visual positioning, when the first positioning frequency is high, the corresponding second positioning frequency should be reduced, and if the first positioning frequency is low, the corresponding second positioning frequency should be increased. The correspondence between confidence and proportion can be stored in advance, as shown in Table 2:

置信度 Confidence	占比（第一定位频率/第二定位频率） Percentage (first positioning frequency / second positioning frequency)
0.1 0.1	9：1 9: 1
0.3 0.3	7：3 7: 3
0.9 0.9	1：9 1: 9

Table 2

In order to list only the correspondence between the three kinds of confidence and proportion in Table 2, in practice, the correspondence between the confidence and proportion is not limited to those listed in Table 2.

A specific example is used to illustrate the process of obtaining the second positioning frequency: assuming that the reliability is 0.9 and the adjusted first positioning frequency is Δt1, then according to the corresponding relationship in Table 2, it can be determined that the second positioning frequency is 9 △ t1.

Step 205: According to the positioning result of the latest auxiliary positioning, perform the N + 1th positioning in the scene where the current period is located according to the adjusted first positioning frequency.

Specifically, when performing the N + 1th visual positioning, based on the positioning result of the latest auxiliary positioning, that is, the N + 1th visual positioning area can be determined by the positioning result of the latest auxiliary positioning to ensure the N + th 1-time visual positioning accuracy to prevent the target from being lost.

The following uses a specific example to describe the process of visual positioning according to the adjusted first frequency.

According to the confidence level, it is determined that the adjusted first positioning frequency is Δt1 and the second positioning frequency is Δh2. The time of the first visual positioning (using the vSLAM positioning method) according to the frequency of Δt1 is denoted as T1, the second time. The moment of visual positioning is represented as T2, then during the period of T1 ~ T2, the auxiliary positioning is performed according to the positioning frequency of △ h2 (using the VIO / IMU positioning method), as shown in Figure 4, within the time period of T1 ~ T2 According to △ h2 frequency, VIO / IMU positioning can be performed 3 times. Positioning result A of the first visual positioning of vSLAM, VIO / IMU positioning According to the positioning result A, and the acceleration and direction information of the terminal obtained by VIO / IMU, the first positioning result B of VIO / IMU positioning can be determined The second and third positioning of VIO / IMU positioning will not be repeated here, and the time of h3 is the time of the most recent positioning of the auxiliary positioning. By obtaining the positioning result D of this positioning, it can be determined that the first positioning at T2 is performed. The area of secondary video positioning is convenient for second visual positioning.

Compared with the prior art, the positioning method provided in this embodiment adds auxiliary positioning in the process of visual positioning, further improving the accuracy of visual positioning, and avoiding the occurrence of targets and losses in visual positioning.

The third embodiment of the present application relates to a positioning device 50, which includes a confidence obtaining module 501, a frequency adjustment module 502, and a positioning module 503. The specific structure is shown in FIG.

The confidence degree acquisition module 501 is used to obtain the confidence degree of the scene in which the terminal is located in the current period, and the confidence degree is used to indicate the degree of difference between the scene in which the terminal is located in the current period and the scene in the previous period; the frequency adjustment module 502 is used to The first positioning frequency is adjusted according to the confidence of the scene in which the terminal is located in the current period, where the confidence is inversely proportional to the first positioning frequency; the positioning module 503 is configured to be located in the current period according to the adjusted first positioning frequency. Visual positioning within the scene.

This embodiment is an embodiment of a virtual device corresponding to the foregoing positioning method. The technical details in the foregoing method embodiment are still applicable in this embodiment, and details are not described herein again.

It should be noted that the device embodiments described above are only schematic and do not limit the scope of protection of this application. In practical applications, those skilled in the art may select some or all of the modules according to actual needs. To achieve the purpose of the solution of this embodiment, there is no limitation here.

A fourth embodiment of the present application relates to a terminal. As shown in FIG. 6, the terminal includes at least one processor 601; and a memory 602 communicatively connected to the at least one processor 601. The memory 602 stores instructions executable by the at least one processor 601, and the instructions are executed by the at least one processor 601, so that the at least one processor 601 can execute the positioning method.

In the fourth embodiment, the processor uses a central processing unit (CPU) as an example, and the memory uses a readable and writable memory (Random Access Memory, RAM) as an example. The processor and the memory may be connected through a bus or other methods. In FIG. 6, the connection through the bus is taken as an example. As a non-volatile computer-readable storage medium, the memory can be used to store non-volatile software programs, non-volatile computer executable programs, and modules. The processor executes various functional applications and data processing of the device by running non-volatile software programs, instructions, and modules stored in the memory, that is, the above positioning method is implemented.

The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system and an application program required for at least one function; the storage data area may store a list of options and the like. In addition, the memory may include a high-speed random access memory, and may further include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely set with respect to the processor, and these remote memories may be connected to an external device through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

One or more modules are stored in the memory, and when executed by one or more processors, the positioning method in any of the foregoing method embodiments is executed.

The above products can execute the method provided in the embodiment of the present application, and have the corresponding functional modules and beneficial effects of the execution method. For technical details not described in this embodiment, refer to the method provided in the embodiment of the present application.

A fifth embodiment of the present application relates to a computer-readable storage medium storing a computer program. When the computer program is executed by the processor, the positioning method described in any of the above method embodiments is implemented.

That is, those skilled in the art can understand that all or part of the steps in the method of the above embodiments can be implemented by a program instructing related hardware. The program is stored in a storage medium and includes several instructions for making a device ( It may be a single-chip microcomputer, a chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes .

Those of ordinary skill in the art can understand that the foregoing embodiments are specific embodiments for implementing the present application, and in practical applications, various changes can be made in form and details without departing from the spirit and range.

Claims

A positioning method, including:

Obtaining a confidence level of a scene in which the terminal is located in the current period, where the confidence level is used to indicate a degree of difference between a scene in which the terminal is located in the current period and a scene in a previous period;

Adjusting a first positioning frequency according to the confidence level of the scene in which the terminal is located in the current period, wherein the confidence level is inversely proportional to the first positioning frequency;

Visual positioning is performed in the scene where the current period is located according to the adjusted first positioning frequency.
The positioning method according to claim 1, wherein the visual positioning in the scene where the current period is located according to the adjusted first positioning frequency specifically comprises:

Perform the Nth visual positioning in the scene where the current period is located according to the adjusted first positioning frequency, and obtain the positioning result of the Nth visual positioning, where N is an integer greater than 0;

Performing at least one auxiliary positioning on the basis of the positioning results of the Nth visual positioning during an intermediate period between the Nth visual positioning and the N + 1th visual positioning;

According to the positioning result of the latest auxiliary positioning, the N + 1th positioning is performed in the scene where the current period is located according to the adjusted first positioning frequency.
The positioning method according to claim 2, wherein performing at least one auxiliary positioning based on the positioning result of the Nth visual positioning, specifically comprising:

Based on the positioning results of the Nth visual positioning, the auxiliary positioning is performed according to the second positioning frequency.
The positioning method according to claim 3, wherein before performing at least one auxiliary positioning based on the positioning result of the Nth visual positioning, the positioning method further comprises:

Determining the second positioning frequency according to the confidence level of the scene in which the terminal is located in the current period, and the correspondence between the confidence level and the ratio, where the ratio is

The ratio of the first positioning frequency to the second positioning frequency.
The positioning method according to any one of claims 1 to 4, wherein the obtaining the confidence of the scene in which the terminal is located in the current period specifically includes:

Acquiring image data of a scene where the terminal is located in the current period, and acquiring angle information of the terminal;

According to the image data and the angle information, a confidence level of a scene in which the terminal is located in a current period is determined.
The positioning method according to claim 5, wherein determining the confidence of the scene in which the terminal is located in the current period according to the image data and the angle information specifically includes:

Determining, according to the image data, a degree of change in texture quality of a scene in the current period, and determining a degree of change in lighting of the scene in the current period;

Determining, according to the angle information, the degree of change in the angle of the scene in the current period;

Calculate an average value of the texture quality change degree, the lighting change degree, and the angle change degree, and use the average value as the confidence level of the scene in which the terminal is located in the current period.
The positioning method according to claim 6, wherein determining the degree of texture quality change of the scene in the current period according to the image data specifically includes:

Obtain characteristic pixel points in the image data, and count the number of characteristic pixel points, calculate a first ratio between the number of characteristic pixel points and a preset number of pixel points, and set the first ratio As the degree of texture quality change of the scene;

or,

Detecting the pixels belonging to the edge in the image data, and counting the number of pixels belonging to the edge, calculating a second ratio between the number of pixels belonging to the edge and the number of preset pixels, and The second ratio is used as a texture quality change degree of the scene.
The positioning method according to claim 6 or 7, wherein determining the degree of lighting change of the scene in the current period according to the image data specifically includes:

Calculating an average gray value within a preset area in the image data;

According to the average grayscale value and a preset grayscale value, a degree of lighting change of the scene in the current period is determined.
The positioning method according to any one of claims 6 to 8, wherein determining a degree of a change in angle of a scene in a current period according to the angle information specifically includes:

Calculating a difference between a preset angle and the angle information;

Calculate a third ratio between the difference and the preset angle, and use the third ratio as the degree of angle change of the scene in the current period.
The positioning method according to any one of claims 5 to 8, wherein the image data of the scene in which the terminal is located in the current period is the image data of the last frame collected in the current period or acquired in the current period Image data for all frames.
A positioning device, comprising: a confidence obtaining module, a frequency adjustment module, and a positioning module;

The confidence degree acquisition module is used to obtain the confidence degree of the scene in which the terminal is located in the current period, and the confidence degree is used to indicate the difference between the scene in which the terminal is located in the current period and the scene in the previous period;

The frequency adjustment module is configured to adjust the first positioning frequency according to the confidence of the scene in which the terminal is located in the current period, where the confidence is inversely proportional to the first positioning frequency;

The positioning module is configured to perform visual positioning in the scene where the current period is located according to the adjusted first positioning frequency.
A terminal comprising: at least one processor; and

A memory connected in communication with the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the method according to any one of claims 1 to 11. Positioning method.
A computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the positioning method according to any one of claims 1 to 11 is implemented.