Circular target design and detection method for multi-task scene

Abstract

The invention provides a circular target design and detection method for a multi-task scene, and the method comprises the steps: image preprocessing, candidate contour extraction, affine transformation correction, circular contour recognition, arc segment recognition, central point positioning, and coding and decoding, and the target is composed of a central circle, a positioning ring, and 12 arc segments. 12-bit binary codes are constructed through black and white binary arc sections, rotation invariant recognition is achieved by adopting a minimum decimal numbering rule, in the recognition process, high-precision positioning of a center point is achieved through multi-circle contour weighted fusion, and screening of the arc sections is completed according to angle and radius variance features; according to the method, a plurality of circles of circular structures including the center circular contour, the positioning ring and the coding ring are designed in the circular coding mark target, and a multi-circle-center weighted fusion positioning strategy is introduced in the target center point calculation process, so that errors caused by local contour recognition deviation can be effectively counteracted, and the center point positioning precision of the target is improved.

Description

Technical Field

[0001] The present invention relates to the field of coded target detection technology, and in particular to a circular target design and detection method for multi-task scenarios. Background Art

[0002] Coded target detection is widely used in computer vision-related fields such as indoor test measurement, camera calibration, industrial vision inspection, and robot navigation. Automatically identifying and locating the target center, especially in environments with good lighting conditions, provides a stable geometric reference for other tasks. Therefore, obtaining the precise coordinates of the target center is crucial. To meet the requirements of recognition efficiency and stability, the target design must not only have good detection characteristics but also carry distinguishable coding information to enable multi-target recognition and numbering.

[0003] Currently, common coding markers are mainly divided into three categories: dot, square and circular. Dot coding markers are generally composed of small solid circles and were used in optical three-dimensional measurement and robot recognition scenarios in the early days. There are also disconnected elliptical rings that use redundant cyclic coding to ensure uniqueness, but such schemes perform better under small viewing angles and close-range shooting conditions and have limited versatility. Square coding markers are more common in augmented reality (AR) and planar machine vision systems. Circular coding markers are more popular in precision positioning tasks due to their good geometric symmetry, high anti-rotation and compact structure, and are the current research focus of circular vision target design.

[0004] Although there are a variety of coded or non-coded target detection methods in the existing technology, there are still limitations in multi-target recognition, target structure simplification, decoding stability and production cost control:

[0005] Prior art 1: Patent application number 202211047328.X, "Target, information detection method, device, terminal and storage medium", proposes a method for calculating the image center based on the intersection of the long axis of the circular ring and the base line of the triangle; this scheme determines the center position of the target in the image by identifying the pair of pixels with the farthest distance on the inner and outer circles, combined with the geometric structure of the triangle, which can improve the image data processing efficiency and target detection stability; however, this scheme has the following disadvantages: since the target used does not have the ability to be encoded, multi-target number recognition cannot be achieved, and it is only applicable to single target detection scenarios, and the target structure is relatively complex and the design is not universal, resulting in high production costs and limited promotion in actual applications.

[0006] Prior art 2: Patent application number 202111076814.X, "A target plate, target pattern detection method and device," discloses a target plate structure with a square blank area in the center and multiple circular or ring identification points arranged around it, which is suitable for camera geometric calibration tasks; the structure simplifies the calibration process by arranging the center points of the rings at non-collinear and unequal distances; however, this solution is mainly used for overall identification of the target plate, and cannot accurately and independently identify or encode a single target. The applicable scenarios are limited to a single calibration purpose, and the structure is still complex and the manufacturing cost is high, which is not suitable for large-scale or dynamic detection environments.

[0007] To this end, a circular target design and detection method for multi-task scenarios is proposed. Summary of the Invention

[0008] In view of this, the present invention provides a circular target design and detection method for multi-task scenarios to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0009] The technical solution of the present invention is implemented as follows: A circular target design and detection method for multi-task scenarios includes the following steps:

[0010] S1. Perform gamma illumination processing on the image to be recognized to balance the image brightness distribution, and perform grayscale conversion and binarization on the processed image to obtain a binarized image for subsequent recognition;

[0011] The gamma illumination processing performs brightness mapping on the original image by setting the nonlinear enhancement parameter γ. When there are underexposed areas in the image, the dark contrast is enhanced by adjusting γ<1, which is used to enhance the edge contour of the coded mark target, so that the high-frequency details in the subsequent binary image can be retained.

[0012] S2. Based on the binary image, extract all contours in the image using the Suzuki contour extraction algorithm;

[0013] Selecting a candidate contour that meets the structural characteristics of the coding mark target from the extracted contours, wherein the candidate contour must have an outer contour that is approximately elliptical and an inner structure consisting of a central circle contour and multiple arc segment contours;

[0014] For each closed contour, determine whether it contains:

[0015] An outer contour having a shape close to a circle or an ellipse;

[0016] At least one central circle outline for forming a center point;

[0017] At least eight arc segment profiles with angular intervals close to the set standard for code identification;

[0018] Only when all the above conditions are met, the closed contour is retained as the candidate contour of the coded mark target, and the remaining contours are eliminated.

[0019] S3, performing an affine transformation correction operation on the candidate contour to compensate for the distortion of the contour shape caused by the shooting angle or perspective deformation, so that the circular contour and the arc segment contour are restored to an approximately designed state;

[0020] In the process of performing affine transformation correction on the candidate contour, the major axis, minor axis and inclination information of the candidate contour are calculated using the least squares ellipse fitting method based on the outer contour point set of the candidate contour, and an affine transformation matrix is ​​established to perform geometric transformation on the overall contour image, so that the ellipse in the target structure is restored to an approximate standard circle to eliminate the deformation interference caused by the shooting perspective and retain the relative angle information of the internal arc structure.

[0021] S4. Analyzing the candidate contours after affine correction based on multiple contour features such as roundness, radius consistency, and fitting residuals, identifying contours that meet a set threshold and using them as the center circle contour and positioning ring contour of the coded mark target;

[0022] The criteria for identifying the center circle contour and the positioning ring contour include: calculating the roundness of each contour Among them, S represents the area enclosed by the contour, P represents the perimeter of the contour, and D represents the roundness of the contour;

[0023] When the roundness D is close to 1, it means that the contour is close to the ideal circle. At the same time, combined with the residual value of the contour point fitting, if the residual is lower than the preset threshold ε, the contour is determined to be a valid circular contour in the coding mark target structure;

[0024] S5. For each arc segment contour in the candidate contours, identify the contours based on the following features:

[0025] The central angle of the arc segment profile is an integer multiple of a fixed angle, wherein the fixed angle in the 12-bit coded target is 30 degrees;

[0026] The outer radius of the arc segment contour is calculated from the distance from the contour point to the target center point, and the variance of the outer radius is less than a set threshold;

[0027] For each contour point, determine whether it belongs to the outer arc segment or the inner arc segment based on the distance between it and the center point of the target, and select the valid arc segment contour accordingly;

[0028] Only when the arc segment contour satisfies all the above feature recognition conditions at the same time, it is determined to be a valid coded arc segment contour;

[0029] The variance of the outer radius is calculated as follows: for all pixel points on each arc segment contour, calculate the Euclidean distance from the target center point to obtain the average radius R and variance σ 2 , when the variance σ 2 When it is less than the threshold value θ, it indicates that the arc segment contour has a consistent outer contour curvature in space;

[0030] The method for determining whether a contour point belongs to an outer arc segment or an inner arc segment is:

[0031] Draw a ray from the center point of the target along the direction of each contour point, record the two intersection points of the ray and the contour, and if the distance between the current point and the center point is greater than the distance between the other intersection points, it is determined to be an outer arc segment;

[0032] When at least 80% of the contour points in the same arc segment contour meet the outer arc segment condition, the contour is retained as the coded arc segment contour.

[0033] S6. Calculating the target center point using a weighted fusion algorithm using the geometric center coordinates of the center circle contour, the positioning ring contour, and the encoding ring contour;

[0034] The center coordinates of the minimum circumscribed circles of the positioning ring contour and the coding ring contour are calculated respectively, and the three are weighted averaged according to a preset weight coefficient to calculate the center point coordinates of the coding mark target.

[0035] S7. For the identified coded arc segment contour, read the color information of each arc segment in sequence from any starting position in a clockwise direction, set black to represent "1" and white to represent "0", and construct a 12-bit binary code;

[0036] Performing cyclic shift on the 12-bit binary code to generate all 12 combinations, converting each combination into a decimal number, and selecting the smallest decimal value as the unique identification code value of the coding mark target;

[0037] The order of reading the arc segment color information is determined by sorting the polar angles corresponding to the line connecting the target center point to the center point of each arc segment from small to large; among all the cyclic shift combinations of the 12-bit code, the corresponding decimal minimum value is selected as the unique number of the final coding mark target.

[0038] The embodiment of the present invention adopts the above technical solution, which has the following advantages:

[0039] 1. The present invention designs a multi-circle circular structure in the circular coded mark target, including a central circle contour, a positioning ring and a coding ring, and introduces a multi-circle center weighted fusion positioning strategy in the target center point calculation process, which can effectively offset the error caused by local contour recognition deviation and improve the target center point positioning accuracy.

[0040] 2. The present invention designs the coding ring to consist of 12 high-density and equiangularly distributed arc segments. Each segment can encode a binary value, which is combined to form complete coding information. It is supplemented by a rotation-invariant minimum decimal code selection strategy to achieve unique identification of the target in any orientation. It not only supports simultaneous detection and identification of multiple targets, but also ensures the stability and robustness of the target numbering, significantly expanding the practical application capabilities of the target structure in multiple scenarios and multiple tasks.

[0041] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1 is a flow chart of the steps of the present invention;

[0044] Figure 2 This is an example diagram of the coded target of the present invention. DETAILED DESCRIPTION

[0045] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are to be considered as illustrative in nature and not restrictive.

[0046] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0047] like Figure 1-2 As shown, the embodiment of the present invention provides a circular target design and detection method for multi-task scenarios, which mainly includes two core components: one is the structural design of the coded mark target, and the other is the processing flow of image recognition, information positioning, and encoding and decoding of the target;

[0048] In terms of target structure design, the coding mark target used in the present invention has a ring structure and is composed of two types of geometric elements: a circular structure for center positioning and an arc coding structure for information expression. The coding ring is composed of 12 equally divided arc segments, each covering a 30-degree angle. The colors are encoded in a black and white binary format, with black representing binary "1" and white representing "0". When arranged in sequence, they form a 12-bit binary number. Due to the uncontrollable rotation angle of this ring arrangement during the shooting process,

[0049] The present invention adopts a cyclic shift matching method to select the one with the smallest corresponding decimal value from 12 possible starting positions as the unique identification ID. For example, when the code "001100110000" is read, all its rotation combinations will be automatically converted into decimal and the minimum value "102" will be selected as the recognition result to ensure the uniqueness and rotation invariance of the extracted code; a center circle and a positioning ring are provided inside the encoding ring to assist in locating the geometric center of the target and enhance the center point positioning accuracy.

[0050] Entering the recognition and decoding part, the whole process consists of seven steps, specifically, including:

[0051] Step S1 is image preprocessing. Since the captured image has problems of uneven illumination and abnormal grayscale distribution, the present invention uses a gamma correction method to balance the brightness of the original image. By setting the γ value (usually less than 1), the image is nonlinearly enhanced to make the dark details more prominent, which is beneficial for edge detection and contour recognition. The adjusted image is then converted into a grayscale image and binarized using an adaptive or fixed threshold method to obtain a high-contrast black and white image, providing clear basic data for subsequent contour extraction.

[0052] Step S2 is candidate contour extraction. This step uses the boundary tracking algorithm proposed by Suzuki for contour detection. The algorithm is based on pixel adjacency and scans all closed areas in the image layer by layer to obtain a complete contour list. Due to the presence of various noises or non-coded graphic interference in the scene, candidate coded mark target contours need to be screened out from all contours. The screening criteria include: the overall external contour is close to a circle, the internal structure contains a central circle contour, and at least 8 regularly distributed arc segment contours. Contours that do not meet the above characteristics will be directly excluded.

[0053] Step S3 is affine transformation correction. This step adopts the method of ellipse fitting and affine matrix correction. In the specific operation, ellipse least squares fitting is performed on the outer contour to obtain the parameters of the major axis, minor axis, and inclination angle; then, an affine transformation matrix is ​​established based on these parameters, and the entire candidate target area is corrected so that the arcs and circular structures in the contour are closer to their original design forms after correction, thereby improving the geometric consistency and accuracy of subsequent recognition.

[0054] Step S4 is circle contour recognition. This step confirms the center circle and positioning ring contours in the target structure from the corrected candidate contours. The recognition indicators mainly include:

[0055] The roundness of the contour (calculated as D = 4πS / P 2 ), fitting residual value (i.e., the average distance from the contour point to the minimum fitting circle) and contour radius consistency. When a contour satisfies the conditions of circularity close to 1, fitting residual value lower than the set threshold, and radius variance being stable, it can be identified as a valid circle contour.

[0056] Step S5 is arc segment contour recognition. This step determines the arc segment structural features based on the following criteria:

[0057] 1) The included angle of each arc must be an integer multiple of a fixed value, which is 30 degrees for a 12-bit target;

[0058] 2) The variance of the outer radius should be stable, that is, the distance set from the target center to each pixel on the arc segment has a small variance;

[0059] 3) The contour should have good continuity, that is, there should be no large breaks or discrete points;

[0060] 4) The outer / inner belonging of each arc segment must be determined, that is, by drawing a ray from the center to the two intersection points of the contour, and distinguishing the outer arc from the inner arc based on the distance;

[0061] 5) The number of arc segments should be consistent with the number of coding bits, and the angle arrangement should meet the polar coordinate symmetry requirements;

[0062] The arc segments that meet all the conditions will be recorded and sorted as coding input.

[0063] Step S6 is to locate the target center point. The present invention adopts a multi-circle center fusion strategy, that is, the coordinates of the minimum circumscribed circle center of the central circle contour, positioning ring contour and encoding ring contour are calculated respectively, and weighted average is performed according to the preset weights. Since single contour recognition is offset due to local noise or deformation, by fusing multi-layer geometric center information, the error is effectively suppressed, and a more accurate target geometric center is obtained, thereby improving recognition stability and positioning accuracy.

[0064] Step S7 is the coding value decoding. After completing the arc segment identification and sorting, start from any arc segment in a clockwise direction, read its color value in turn, and set black to "1" and white to "0" to form a complete 12-bit binary number. Then, 12 combinations are generated in turn through cyclic shift and converted into decimal numbers respectively. Finally, the one with the smallest value is selected as the unique coding value of the target. The biggest advantage of this coding method is that it is naturally invariant to rotation transformation. Regardless of the image shooting angle, the extracted coding value remains logically consistent.

[0065] Application examples:

[0066] Suppose a camera captures an image, which is then gamma corrected to obtain a clear image. After performing Suzuki contour extraction, a candidate contour consisting of a central circle and 12 arc segments is screened out. Affine transformation restores the contour structure to its standard shape. Contour detection identifies the central circle contour, positioning ring contour, and 12 equally spaced arc segments. Arc segment screening and code reading are then completed based on the five geometric features. At this point, the read code is "100100110001." A loop generates 12 combinations and calculates the corresponding decimal values. The minimum value "73" is selected as the unique identification number, completing the entire recognition process.

[0067] The following describes some of the technical terms and key algorithms involved in this embodiment:

[0068] Gamma lighting processing: Gamma lighting processing is a nonlinear transformation method of image brightness, which is used to adjust the grayscale contrast between bright and dark areas in an image.

[0069] Suzuki Contour Extraction Algorithm: This is a boundary tracing method for binary image contour extraction proposed by Suzuki and Abe. It recursively constructs a boundary hierarchy through pixel adjacency relationships and can completely extract the contour structure of closed areas. It is often used in contour recognition modules in computer vision libraries such as OpenCV.

[0070] Affine transformation: Affine transformation is a two-dimensional geometric transformation that maintains the linearity and parallelism between points. It is used to perform translation, rotation, scaling and tilt. In the present invention, it is used to restore the elliptical distortion caused by the shooting angle to a circular contour.

[0071] Ellipse least squares fitting: used to fit the ellipse geometry to the contour point set, minimize the sum of squared errors, and obtain the major axis, minor axis, center, and inclination parameters of the ellipse. The results are used to generate an affine transformation matrix to achieve contour affine correction.

[0072] Contour fitting residual: It is used to measure the average distance error between the contour points and their fitting curves (such as circles). The smaller the residual, the closer the fitting result is to the actual structure. It is used to assist in determining the validity of the circle contour.

[0073] Outer radius variance: This parameter characterizes the consistency of the arc segment in spatial curvature by calculating the distance from all pixels on the arc segment to the target center and finding its variance. A small variance indicates a regular and stable shape, which is the basis for screening valid arc segment contours.

[0074] Polar angle sorting: During the code reading process, the polar angle (polar coordinate angle) value of each arc segment center point relative to the target center point is sorted from small to large, standardizing the clockwise order of code extraction to avoid coding errors caused by sequence confusion.

[0075] Circular shift matching: This decoding strategy is designed to solve the target rotation problem. It performs cyclic shifts on all 12 starting bits of the read 12-bit binary code, converts it to decimal, and selects the minimum value as the unique number.

[0076] Grayscale threshold determination: During the arc segment color extraction process, the average grayscale or adaptive threshold method is used to count the grayscale of pixels in the local area, and the current arc segment color is judged as "black" (1) or "white" (0) according to the threshold to construct a complete binary code.

[0077] Weighted fusion algorithm: During the center point positioning process, multiple circles (center circle, positioning ring, encoding ring) are used to fit the center point coordinates and are assigned preset weights respectively. Weighted averaging is performed to obtain the final fused center point position, thereby suppressing the overall positioning error caused by local contour offset.

[0078] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various modifications and substitutions within the technical scope disclosed in the present invention, and such modifications and substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A circular target design and detection method for multi-task scenarios, characterized by: The following steps are involved: S1. Perform gamma illumination processing on the image to be recognized to balance the image brightness distribution, and perform grayscale conversion and binarization on the processed image to obtain a binarized image for subsequent recognition; S2. Based on the binary image, extract all contours in the image using the Suzuki contour extraction algorithm; Selecting a candidate contour that meets the structural characteristics of the coding mark target from the extracted contours, wherein the candidate contour must have an outer contour that is approximately elliptical and an inner structure consisting of a central circle contour and multiple arc segment contours; S3, performing an affine transformation correction operation on the candidate contour to compensate for the distortion of the contour shape caused by the shooting angle or perspective deformation, so that the circular contour and the arc segment contour are restored to an approximately designed state; S4. Analyzing the candidate contours after affine correction based on multiple contour features such as roundness, radius consistency, and fitting residuals, identifying contours that meet a set threshold and using them as the center circle contour and positioning ring contour of the coded mark target; S5. For each arc segment contour in the candidate contours, identify the contours based on the following features: The central angle of the arc segment profile is an integer multiple of a fixed angle, wherein the fixed angle in the 12-bit coded target is 30 degrees; The outer radius of the arc segment contour is calculated from the distance from the contour point to the target center point, and the variance of the outer radius is less than a set threshold; For each contour point, determine whether it belongs to the outer arc segment or the inner arc segment based on the distance between it and the center point of the target, and select the valid arc segment contour accordingly; Only when the arc segment contour satisfies all the above feature recognition conditions at the same time, it is determined to be a valid coded arc segment contour; S6. Calculating the target center point using a weighted fusion algorithm using the geometric center coordinates of the center circle contour, the positioning ring contour, and the encoding ring contour; S7. For the identified coded arc segment contour, read the color information of each arc segment in sequence from any starting position in a clockwise direction, set black to represent "1" and white to represent "0", and construct a 12-bit binary code; Circular shift is performed on the 12-bit binary code to generate all 12 combinations, and each combination is converted into a decimal number, and the smallest decimal value is selected as the unique identification code value of the coding mark target.

2. The circular target design and detection method for multi-task scenarios according to claim 1, characterized in that: In step S1, the gamma illumination processing performs brightness mapping on the original image by setting the nonlinear enhancement parameter γ. When there is an underexposed area in the image, the dark contrast is enhanced by adjusting γ<1, which is used to enhance the edge contour of the coding mark target so that the high-frequency details in the subsequent binary image can be retained.

3. The circular target design and detection method for multi-task scenarios according to claim 1, characterized in that: In step S2, for each closed contour, it is determined whether it contains: An outer contour having a shape close to a circle or an ellipse; At least one central circle outline for forming a center point; At least eight arc segment profiles with angular intervals close to the set standard for code identification; Only when all the above conditions are met, the closed contour is retained as the candidate contour of the coded mark target, and the remaining contours are eliminated.

4. The circular target design and detection method for multi-task scenarios according to claim 1, characterized in that: In step S3, during the process of performing affine transformation correction on the candidate contour, the major axis, minor axis and inclination information of the candidate contour are calculated using the least squares ellipse fitting method based on the outer contour point set of the candidate contour, and an affine transformation matrix is ​​established to perform a geometric transformation on the overall contour image, so that the ellipse in the target structure is restored to an approximate standard circle to eliminate the deformation interference caused by the shooting perspective and retain the relative angle information of the internal arc structure.

5. The circular target design and detection method for multi-task scenarios according to claim 1, characterized in that: In step S4, the criteria for identifying the center circle contour and the positioning ring contour include: calculating the roundness of each contour D = 4πS / P2, where S represents the area enclosed by the contour, P represents the perimeter of the contour, and D represents the roundness of the contour; When the roundness D is close to 1, it means that the contour is close to the ideal circle. At the same time, combined with the residual value of the contour point fitting, if the residual is lower than the preset threshold ε, the contour is determined to be a valid circular contour in the coding mark target structure.

6. The circular target design and detection method for multi-task scenarios according to claim 1, characterized in that: In step S5, the variance of the outer radius is calculated as follows: for all pixel points on the contour of each arc segment, the Euclidean distance from the target center is calculated to obtain the average radius R and variance σ 2 , when the variance σ 2 When it is less than the threshold value θ, it indicates that the arc segment contour has a consistent outer contour curvature in space.

7. The circular target design and detection method for multi-task scenarios according to claim 1, characterized in that: In step S5, the method for determining whether the contour point belongs to the outer arc segment or the inner arc segment is: Draw a ray from the center point of the target along the direction of each contour point, record the two intersection points of the ray and the contour, and if the distance between the current point and the center point is greater than the distance between the other intersection points, it is determined to be an outer arc segment; When at least 80% of the contour points in the same arc segment contour meet the outer arc segment condition, the contour is retained as the coded arc segment contour.

8. The circular target design and detection method for multi-task scenarios according to claim 1, characterized in that: In step S6, the center coordinates of the minimum circumscribed circles of the positioning ring contour and the coding ring contour are calculated respectively, and the three are weighted averaged according to a preset weight coefficient to calculate the center point coordinates of the coding mark target.

9. The circular target design and detection method for multi-task scenarios according to claim 1, characterized in that: In step S7, the order of reading the arc segment color information is determined by sorting the polar angles corresponding to the lines connecting the target center point to the center point of each arc segment from small to large.

10. The circular target design and detection method for multi-task scenarios according to claim 1, characterized in that: In step S7, the corresponding decimal minimum value among all cyclic shift combinations of the 12-bit code is selected as the unique number of the final code mark target.

Images