A multi-visual coding target layout optimization design method and system

Abstract

The present invention discloses a method and system for optimizing the layout of multiple visual coding targets. The method includes: fitting a quantitative relationship between positioning error and visual coding target size, and determining a first constraint condition that the visual coding target size and positioning error reference value should satisfy based on the fact that the actual positioning error does not exceed the positioning error reference value; determining a second constraint condition that the camera resolution and the visual coding target imaging size should satisfy, n≥1, to ensure that there are at least n visual coding targets in the field of view when the robot moves; and determining the visual coding target size by combining the first constraint condition and the second constraint condition. In this way, an effective design framework and method guidance are provided for the optimization design of the layout of multiple visual coding targets, ensuring the performance of the positioning system based on visual coding targets designed in a large-scale positioning scenario, thereby providing a guarantee for the autonomous positioning of mobile robots in a large-scale scenario and improving the degree of automation of mobile robots.

Description

Technical Field

[0001] The present invention belongs to the field of visual positioning technology, and more specifically, relates to a multi-visual coding target layout optimization design method and system. Background Art

[0002] Visual coding target-based positioning is a common visual positioning method that offers low cost, high accuracy, and ease of deployment, with the potential for application in a wide range of positioning scenarios. Designing the layout of visual coding target-based positioning systems is crucial and has a direct impact on their performance. However, there is currently no framework or method for optimizing the layout of multiple visual coding targets.

[0003] Therefore, this field urgently needs a multi-visual coding target layout optimization design method to provide effective method guidance for the layout design of multiple visual coding targets, fundamentally ensure the performance of the positioning system based on visual coding targets, and promote the application of the positioning system based on visual coding targets in a wide range of positioning scenarios. Summary of the Invention

[0004] In response to the defects of the existing technology and the need for improvement, the present invention provides a multi-visual coding target layout optimization design method and system, which aims to solve the multi-visual coding target layout design optimization problem in the design of visual coding target positioning system in large-scale positioning scenarios.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a multi-visual coding target layout optimization design method, comprising the following steps:

[0006] Fitting a quantitative relationship between the positioning error and the visual coding target size, and determining a first constraint condition that the visual coding target size and the positioning error reference value should satisfy based on the fact that the actual positioning error does not exceed the positioning error reference value;

[0007] In order to ensure that there are at least n visual coding targets in the field of view when the robot moves, the second constraint condition that the camera resolution and the visual coding target imaging size should meet is determined, n ≥ 1; the visual coding target size D and the visual coding target imaging size l meet Where k is the scaling factor, which depends on the design of the visual encoding target; K is the unit factor; L is the shortest distance between the camera and the visual encoding target; f is the focal length of the camera;

[0008] The visual encoding target size is determined by combining the first constraint and the second constraint.

[0009] Furthermore, a power approximation mathematical model or a polynomial model is used to fit the quantitative relationship between the positioning error and the size of the visual encoding target.

[0010] Furthermore, the second constraint condition is expressed as:

[0011]

[0012] Where W×H represents the camera resolution, W represents the image width, and H represents the image height.

[0013] Furthermore, n=4, and the second constraint condition is expressed as:

[0014]

[0015] Furthermore, the visual coding targets are all square visual coding targets.

[0016] Furthermore, the visual coding targets are all square visual coding targets, and each visual coding target has the same size, no gaps, and no relative rotation.

[0017] In a second aspect, the present invention provides a multi-visual coding target layout optimization design system, comprising: a computer-readable storage medium and a processor;

[0018] The computer-readable storage medium is used to store executable instructions;

[0019] The processor is used to read the executable instructions stored in the computer-readable storage medium and execute the multi-visual coding target layout optimization design method as described in the first aspect.

[0020] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects:

[0021] The present invention determines the size of the visual coding target by combining the first constraint condition that the visual coding target size should satisfy with the positioning error reference value, and the second constraint condition that the camera resolution and the imaging size of the visual coding target should satisfy. It provides a generalized design framework and method guidance for the layout design optimization of multiple visual coding targets, thereby improving the performance of the positioning system based on the visual coding target. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 1 is a flow chart of a multi-visual coding target layout optimization design method provided by an embodiment of the present invention;

[0023] Figure 2 Schematic diagram of various sizes of visual coding targets provided by an embodiment of the present invention;

[0024] Figure 3 This is a schematic diagram of a positioning scenario provided by an embodiment of the present invention;

[0025] Figure 4It is a schematic diagram of the visual coding target layout design provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0027] In the present invention, the terms "first", "second", etc. (if any) in the present invention and the drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0028] See Figure 1 The present invention provides a multi-visual coding target layout optimization design method, including operations S1 to S3.

[0029] Operation S1 is to fit a quantitative relationship between the positioning error and the visual coding target size, and determine a first constraint condition that the visual coding target size and the positioning error reference value should satisfy based on the fact that the actual positioning error does not exceed the positioning error reference value.

[0030] In this embodiment, the quantitative relationship between the positioning error and the visual encoding target size is generally expressed as follows:

[0031] E=f(D)=f(l,K,f,L,k)

[0032] Among them, f(*) can be including but not limited to power approximation mathematical model, polynomial model, and the specific form can be obtained by designing visual coding target size and positioning error experiments; E is the positioning error, which refers to the absolute translation error, defined as the root mean square error of the posture translation part, in units of m; l is the imaging size of the visual coding target, in pixels; K is the unit coefficient; f is the focal length of the camera, in units of mm; L is the shortest distance between the camera and the visual coding target, in units of m; k is the proportional coefficient, which depends on the design of the visual coding target; d is the effective size of the visual coding target, in units of m; D is the size of the visual coding target, in units of m.

[0033] Among them, the relationship between the effective size d of the visual coding target and the imaging size l of the visual coding target is:

[0034]

[0035] The relationship between the visual coding target size D and the visual coding target effective size d is:

[0036] D=kd

[0037] In this embodiment, the first constraint condition is:

[0038] E=f(D)≤e,

[0039] Where, e is the positioning error reference value, the unit is m.

[0040] Operation S2, to ensure that there are at least n visual coding targets in the field of view when the robot moves, determine the second constraint condition that the camera resolution and the visual coding target imaging size should meet, n ≥ 1; the visual coding target size D and the visual coding target imaging size l meet Where k is the scaling factor, which depends on the design of the visual encoding target; K is the unit factor; L is the shortest distance between the camera and the visual encoding target; and f is the focal length of the camera.

[0041] In this embodiment, in order to ensure that there are at least n visual coding targets in the field of view of the robot when it moves, it is necessary to meet After the transformation, the second constraint is obtained, which is expressed as:

[0042]

[0043] Where W×H represents the camera resolution, W represents the image width, and H represents the image height.

[0044] It should be noted that the basic positioning condition is that the number of visual coding targets in the robot's field of view during movement is at least 1, which ensures uninterrupted positioning information. The optimal positioning condition is that the number of visual coding targets in the robot's field of view is at least 4 during movement, which achieves a good balance between positioning accuracy and positioning stability.

[0045] When n=1, the second constraint is expressed as:

[0046]

[0047] When n=4, the second constraint is expressed as:

[0048]

[0049] Operation S3: Determine the size of the visual encoding target by combining the first constraint and the second constraint.

[0050] Furthermore, the visual coding target layout can be described using the visual coding target layout density, which is defined as the maximum number of visual coding targets of the same size per square meter, in units of pcs / m 2 .

[0051] The present invention is further described in detail below with reference to a specific implementation case.

[0052] An embodiment of the present invention provides a multi-visual coding target layout optimization design method, which is related to factors such as the visual coding target type, the established positioning error and visual coding target layout relationship model, camera hardware parameters, positioning requirement scenarios, the range of distance variation between the camera and the visual coding target during robot movement, and the layout range, among which:

[0053] The visual coding target selected is AprilTag, and the scaling factor k is 1.25;

[0054] The camera hardware has a resolution W×H of 2448×2048 pixels and a focal length f of 12 mm;

[0055] The positioning requirements are: the absolute translation error E is less than 0.03m, and the positioning information is stable and continuous;

[0056] The shortest distance L1 between the camera and the visual encoding target during the robot's movement is 1.58m;

[0057] The visual coding target size is defined as Figure 2 As shown, D is the visual coding target size, in m; l is the visual coding target imaging size, in pixels; d is the visual coding target effective size, in m.

[0058] S1, the quantitative relationship between the fitting positioning error and the visual encoding target size is:

[0059]

[0060] The first constraint is:

[0061]

[0062] S2, to ensure that there are at least four visual coding targets in the robot's field of view when it moves, the second constraint is expressed as:

[0063]

[0064] S3, combining the first constraint and the second constraint, the relationship between the visual coding target size D and the distance L1 is obtained as follows:

[0065] D=0.2125L1

[0066] According to the spatial range of the layout, the constraint relationship between multiple visual coding targets, and the relationship between the optimized size and distance of the visual coding targets, the optimal layout design of the visual coding targets in this scenario is: 9 / m 2 .

[0067] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A multi-visual coding target layout optimization design method, characterized in that: The following steps are involved: Fitting a quantitative relationship between the positioning error and the visual coding target size, and determining a first constraint condition that the visual coding target size and the positioning error reference value should satisfy based on the fact that the actual positioning error does not exceed the positioning error reference value; In order to ensure that there are at least n visual coding targets in the field of view when the robot moves, the second constraint condition that the camera resolution and the visual coding target imaging size should meet is determined, n ≥ 1; the visual coding target size D and the visual coding target imaging size l meet Where k is the scaling factor, which depends on the design of the visual encoding target; K is the unit factor; L is the shortest distance between the camera and the visual encoding target; f is the focal length of the camera; The visual encoding target size is determined by combining the first constraint and the second constraint.

2. The multi-visual coding target layout optimization design method according to claim 1, characterized in that: The quantitative relationship between the positioning error and the visual encoding target size is fitted through a power approximation mathematical model or a polynomial model.

3. The multi-visual coding target layout optimization design method according to claim 1, characterized in that: The second constraint is expressed as: Where W×H represents the camera resolution, W represents the image width, and H represents the image height.

4. The multi-visual coding target layout optimization design method according to claim 3, characterized in that: When n=4, the second constraint condition is expressed as:

5. The multi-visual coding target layout optimization design method according to claim 1, characterized in that: The visual coding targets are all square visual coding targets.

6. The multi-visual coding target layout optimization design method according to claim 1, characterized in that: The visual coding targets are all square visual coding targets, and each visual coding target has the same size, no gaps, and no relative rotation.

7. A multi-visual coding target layout optimization design system, characterized in that: include: Computer-readable storage medium and processor; The computer-readable storage medium is used to store executable instructions; The processor is used to read the executable instructions stored in the computer-readable storage medium and execute the multi-visual coding target layout optimization design method as described in any one of claims 1-6.

Images