A furniture contour spraying path planning method and system and an intelligent sofa

Abstract

The application discloses a kind of furniture contour spraying path planning method, system and intelligent sofa.Method includes: obtaining the collection image information of spraying contour;Intensity extraction is carried out to collection image information, and intensity gradient map is obtained, and based on collection image information, side wall mirror reflection bright band is grouped clustering, and false bright ring mark is obtained;Based on false bright ring mark and collection image information, the effective angle interval of contour closure determination is adjusted, and the curve position coordinates in intensity gradient map are filtered processing;Iterative optimization processing is carried out to the profile curve after filtering, and final contour closure curve is obtained, the planning scheme of contour spraying path is generated, and contour spraying path planning is completed.The application provides a kind of furniture contour spraying path planning method, system and intelligent sofa, to solve the technical problems that existing technology cannot distinguish real contour from optical artifact according to wall angle variation, leading to poor stability and accuracy of contour extraction.

Description

Technical Field

[0001] This invention relates to the field of automated spraying technology, and in particular to a method, system, and intelligent sofa for planning spraying paths for furniture contours. Background Technology

[0002] In the furniture manufacturing and surface treatment industry, especially for components such as door panels with complex carvings, image acquisition and contour analysis technology is key to achieving automated spraying and improving spraying accuracy. Its core objective is to accurately extract the true outer contour of the carved area in complex lighting conditions, providing a reliable data foundation for subsequent spraying path planning, thereby avoiding mis-spraying and missed spraying.

[0003] Currently, mainstream methods for furniture spraying image acquisition and contour analysis primarily employ machine vision technology based on fixed or single-structure light sources. These methods typically deploy coaxial ring or strip light sources, combined with an industrial camera, to acquire images of the sprayed area. Edge detection algorithms are then used to extract brightness gradients from the images, thereby identifying and fitting the contour closure curve of the carved area. However, this type of method has serious limitations when dealing with complex three-dimensional surfaces with grooves and sloping sidewalls, such as carved door panels. Specifically, the core flaw of this method lies in its inability to effectively handle the optical contradiction arising from the coupling between the illumination characteristics of the light source and the geometry of the groove. Conventionally, reducing the ratio of the inner and outer diameters of the coaxial ring light, i.e., narrowing the light band, can increase the proportion of axial light, theoretically suppressing shadows on the inner wall of the groove and enhancing bottom backlighting, thus improving contour closure. However, when the inclination angle of the groove sidewall is introduced, an excessively narrow ring light band can induce strong specular reflections on the sloping wall surface, generating a false closed loop with extremely high brightness in the image. Existing technologies lack the ability to adaptively adjust to this dynamic balance, often misjudging false bright central rings as genuine carved edges, while neglecting the true outer contour of the groove due to shadow coverage. Therefore, the biggest drawback of existing technologies is their inability to distinguish between the true contour and optical artifacts based on changes in the wall inclination angle, resulting in poor stability and accuracy of contour extraction. This leads to serious deviations in the generated spraying path, causing local overspray or underspray, making it difficult to meet the requirements of high-precision, high-quality automated spraying operations. Summary of the Invention

[0004] This invention provides a method, system, and smart sofa for planning furniture outline spraying paths, in order to solve the technical problem that existing technologies cannot distinguish between real outlines and optical artifacts based on changes in wall inclination angles, resulting in extremely poor stability and accuracy of outline extraction and serious deviations in the generated spraying paths.

[0005] The present invention discloses the following technical solutions: In a first aspect, embodiments of the present invention provide a method for planning a furniture outline spraying path, the method comprising: Acquire image information of the spraying outline; Brightness is extracted from the acquired image information to obtain a brightness gradient map, and the bright bands of the side wall specular reflection are grouped and clustered based on the acquired image information to obtain false bright ring identifiers; Based on the false bright ring markers and the acquired image information, the effective angle range for contour closure determination is adjusted, and the curve position coordinates in the brightness gradient map are filtered to obtain the filtered contour curve. The filtered contour curve is iteratively optimized to obtain the final contour closed curve, and a contour spraying path planning scheme is generated to complete the contour spraying path planning.

[0006] Optionally, the step of extracting brightness from the acquired image information to obtain a brightness gradient map includes: The brightness gradient value is obtained by extracting the backlight intensity distribution at the bottom of the groove and the attenuation degree of the shadow depth on the inner wall from the acquired image information. Based on the brightness gradient value, the boundary points of the potential contour closure curve are extracted, and the boundary points are enhanced by fusing texture and color gradient features to calculate the extended gradient distribution. Based on the extended gradient distribution, the boundary points are smoothed using Gaussian filtering to generate a brightness gradient map.

[0007] Optionally, the step of grouping and clustering the bright bands of the sidewall specular reflection based on the acquired image information to obtain false bright ring identifiers includes: Based on the acquired image information, reflection noise is filtered using a gradient threshold to obtain a set of filtered bright reflection bands. Based on the filtered set of reflective bright bands, the features of the filtered set of reflective bright bands are evaluated by calculating curvature index and continuity index, and the filtered reflective bright bands are grouped and clustered by a clustering algorithm to determine the group of bright bands after clustering. In the clustered bright band groups, the closed loop shape generated at the center of the groove is identified. Closed loops that meet the preset false loop criteria are judged as false closed loops, and corresponding false bright loop identifiers are generated.

[0008] Optionally, adjusting the effective angle range for contour closure determination based on the false bright ring marker and the acquired image information includes: The sidewall backlight intensity distribution is extracted based on the acquired image information; Based on the false bright ring markings and the sidewall backlight intensity distribution, the actual range of the sidewall tilt angle is determined by calculating the error value between the sidewall backlight intensity distribution curve and the ideal reference distribution curve; Based on the actual range of the sidewall inclination angle, the effective angle range for contour closure determination is adjusted to obtain the adjusted angle range. Based on the adjusted angle range, preliminary rules for contour closure are determined by comparing the consistency between the light source coordinates and the reflection path. The light source coordinates are obtained through light source position calibration, and the reflection path is calculated using Snell's law. Based on the preliminary rules, the angle threshold is optimized by calculating the peak offset of the sidewall backlight intensity distribution to generate the final judgment rule.

[0009] Optionally, the step of filtering the curve position coordinates in the brightness gradient map to obtain the filtered contour curve includes: Based on the curve position coordinates in the brightness gradient map and the final judgment rule, the continuity and brightness change amplitude of the curve position coordinates are quantitatively evaluated, and coordinate points that do not meet the preset threshold are filtered out to obtain a first set of filtered coordinates. The continuity is quantified by the distance between adjacent points, and the brightness change amplitude is calculated by the gradient difference. Based on the first set of filtered coordinates, the second set of filtered coordinates is obtained by calculating the curve curvature and the ring closure index and removing the noise coordinates that belong to the false central bright ring. Based on the second set of filtered coordinates, the filtered contour curve is determined.

[0010] Optionally, the step of determining preliminary rules for contour closure based on the adjusted angle range by comparing the consistency between the light source coordinates and the reflection path includes: Obtain the actual trajectory of the light source position and reflection path; Based on Snell's law, the expected trajectory of the reflection path is calculated according to the actual range of the light source position and the sidewall tilt angle. Calculate the percentage deviation between the actual trajectory and the expected trajectory. When the percentage deviation is less than a preset deviation threshold, determine that the reflection paths corresponding to the actual trajectory and the expected trajectory are consistent, and determine the preliminary rules for contour closure.

[0011] Optionally, the iterative optimization of the filtered contour curve to obtain the final contour closure curve, generating a contour spraying path planning scheme, and completing the contour spraying path planning includes: The continuity of the filtered contour curve is evaluated to determine the breakpoints on the outer edge of the contour that are below a preset lower limit. The width of the light band of the coaxial ring light source is iteratively adjusted at the breakpoint of the outer edge of the contour to obtain an updated image sequence. The iterative adjustment is based on the continuity score as the objective function, and the adjustment amount is controlled by the step size coefficient until the continuity score exceeds a preset threshold or the maximum number of iterations is reached. Based on the updated image sequence, edge detection and clustering algorithms are iteratively applied until the cluster center points are closed, generating a final contour closure curve. The edge detection algorithm is used to extract the edge point set, and the cluster center points are determined by grouping the edge point set using the clustering algorithm. Based on the final contour closure curve, the spraying area is segmented and the spraying path is parametrically transformed to generate a contour spraying path planning scheme, thus completing the contour spraying path planning.

[0012] Secondly, embodiments of the present invention provide a planning system for furniture outline spraying paths, comprising: The data acquisition module is used to acquire image information of the spraying outline; The feature extraction module is used to extract brightness from the acquired image information to obtain a brightness gradient map, and to group and cluster the bright bands of the side wall specular reflection based on the acquired image information to obtain false bright ring identifiers. The contour filtering module is used to adjust the effective angle range for contour closure determination based on the false bright ring markers and the acquired image information, and to filter the curve position coordinates in the brightness gradient map to obtain the filtered contour curve. The path planning module is used to iteratively optimize the filtered contour curve to obtain the final contour closed curve, generate a contour spraying path planning scheme, and complete the contour spraying path planning.

[0013] Thirdly, another embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the furniture outline spraying path planning method as described above.

[0014] Another embodiment of the present invention provides a smart sofa, including a sofa and a computer program product disposed within the sofa. The computer program product includes a computer program or instructions, which, when executed by a device, implement the steps of a furniture outline spraying path planning method as described above.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention utilizes an adjustable coaxial ring light source with adjustable inner and outer diameters and a high dynamic range industrial camera to acquire multi-dimensional image information including backlight intensity, shadow attenuation, and specular reflection bright bands. This enables comprehensive perception of the complex optical characteristics of the carved grooves, providing a high-input-entropy data foundation for subsequent contour recognition. By introducing a joint analysis mechanism of edge detection and clustering algorithms, false closed loops are identified from two dimensions: brightness gradient and reflection bright band morphology. This resolves the fundamental contradiction of existing technologies being unable to distinguish between genuine carved edges and optical artifacts. By dynamically adjusting the effective angle range for contour closure determination, the determination rule is adaptively matched to changes in the groove sidewall inclination angle, suppressing the interference of false bright loops on contour extraction. Furthermore, through iterative optimization and adaptive adjustment of the light source band width, the breakpoint region of the carved outer edge is actively repaired, ultimately generating a continuous, realistic, and high-quality contour curve that can be directly used for path planning in painting robots. Attached Figure Description

[0016] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a method for planning a furniture outline spraying path according to an embodiment of the present invention. Figure 2 This is a schematic diagram illustrating the specific implementation process of a method for planning a furniture outline spraying path provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the brightness gradient map generation process of a furniture outline spraying path planning method provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the spraying path planning process of a furniture outline spraying path planning method provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of a furniture outline spraying path planning device provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the invention, are intended to cover non-exclusive inclusion.

[0020] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0021] See Figure 1 To address the technical problem that existing technologies cannot distinguish between real contours and optical artifacts based on changes in wall inclination angle, resulting in extremely poor stability and accuracy of contour extraction and serious deviations in the generated spraying path, an embodiment of the present invention provides a method for planning furniture contour spraying paths, comprising: S1, acquire image information of the spraying contour.

[0022] The process involves deploying an adjustable coaxial ring light source unit with adjustable inner and outer diameters and a high dynamic range industrial camera unit to acquire sprayed images of the grooved area of ​​the carved door panel. The acquired image information includes the backlight intensity distribution at the bottom of the groove, the attenuation degree of the shadow depth on the inner wall, and the position and shape of the specular reflection bright band on the side wall. The backlight intensity distribution at the bottom of the groove reflects the uniformity of the sprayed material coverage at the bottom; the attenuation degree of the shadow depth on the inner wall assesses the integrity of the inner wall spraying; and the position and shape of the specular reflection bright band on the side wall are used to identify false reflection features that may interfere with contour extraction. All of this information forms the initial data basis for subsequent contour analysis and judgment.

[0023] S2, extract the brightness of the acquired image information to obtain a brightness gradient map, and group and cluster the bright bands of the side wall specular reflection based on the acquired image information to obtain false bright ring identifiers.

[0024] Specifically, based on the backlight intensity distribution at the bottom of the groove and the attenuation degree of the shadow depth on the inner wall, an edge detection algorithm is used to extract the brightness gradient of the inner wall and bottom region of the groove. Specifically, the Canny edge detection operator is used to calculate the pixel brightness change rate, generating a brightness gradient map to characterize potential contour boundaries. Simultaneously, based on the position and shape of the specular reflection bright bands on the sidewalls, a clustering algorithm is used to group the reflective bright bands. By analyzing the curvature, continuity, and ring closure degree of each group of bright bands, false closed loops generated by specular reflection at the center of the groove are identified, thus obtaining false bright loop identifiers. These identifiers are used in subsequent contour determination rules to distinguish between the true outer edge of the carving and optical interference.

[0025] S3, based on the false bright ring marker and the acquired image information, adjust the effective angle range for contour closure determination, and filter the curve position coordinates in the brightness gradient map to obtain the filtered contour curve.

[0026] Specifically, based on the false bright ring markings and the backlight intensity distribution at the bottom of the groove, the actual range of the sidewall tilt angle is determined, and the effective angle range for contour closure determination is dynamically adjusted accordingly to correct the light reflection deviation caused by the tilted wall. Subsequently, according to the optimized determination rules, the curve position coordinates in the brightness gradient map are filtered. By quantifying the curve continuity, curvature, and ring closure, the difference between the real outer edge curve of the carving and the false central bright ring is identified, and the coordinates of the false closed ring formed by specular reflection interference are eliminated, thereby obtaining the filtered contour curve that reflects the actual carving boundary.

[0027] S4. The filtered contour curve is iteratively optimized to obtain the final contour closed curve, and a contour spraying path planning scheme is generated to complete the contour spraying path planning.

[0028] The process involves evaluating the continuity of the filtered contour curve. For breakpoints on the outer edge of the carving below a preset lower limit, the width of the coaxial ring light band is iteratively adjusted based on the shape of the bright band reflecting from the sidewall mirror. Image sequences are then re-acquired, and edge detection and clustering algorithms are repeatedly applied until a continuous, closed outer edge curve of the carving is extracted, resulting in the final contour closure curve. Based on this final contour closure curve, the spraying area is segmented, and a contour spraying path planning scheme is generated to complete the contour spraying path planning for the grooved area of ​​the carved door panel.

[0029] Furthermore, such as Figure 2As shown, this application provides a specific implementation process for a furniture contour spraying path planning method. First, by deploying an adjustable inner and outer diameter coaxial ring light source unit and a high dynamic range industrial camera unit, spraying images are acquired from the groove area of ​​the carved door panel, obtaining the backlight intensity distribution at the bottom of the groove, the attenuation degree of the inner wall shadow depth, and the position and shape of the specular reflection bright band on the side wall. Then, based on the backlight intensity distribution at the bottom of the groove and the attenuation degree of the inner wall shadow depth, an edge detection algorithm is used to extract the brightness gradient of the inner wall and bottom areas of the groove, determining the position coordinates of the potential contour closure curve, thus obtaining a brightness gradient map. Next, the position and shape of the specular reflection bright band on the side wall in the brightness gradient map are analyzed, and a clustering algorithm is used to group and cluster the reflective bright bands, identifying false closed loops generated at the center of the groove, thus obtaining false bright loop identifiers. Based on the false bright loop identifiers and the backlight intensity distribution, the actual range of the side wall tilt angle is determined, and the effective angle range for contour closure judgment is dynamically adjusted to obtain optimized judgment rules. According to the optimized judgment rules, the curve position coordinates in the brightness gradient map are filtered to identify the morphological differences between the real carved outer edge curve and the false central bright ring, thus obtaining the filtered contour curve. The continuity of the filtered contour curve is evaluated. For the breakpoints at the outer edge of the carving below the preset lower limit, the width of the coaxial ring light is iteratively adjusted based on the shape of the reflected bright band, resulting in the adjusted light source settings and updated image sequence. Finally, edge detection and clustering algorithms are repeatedly applied to this updated image to extract the final contour closure curve. The output data for the spraying path planning is then used as the planning scheme for the contour spraying path, thus completing the contour spraying path planning.

[0030] In one embodiment, brightness extraction is performed on the acquired image information to obtain a brightness gradient map, including steps S201 to S203, each step of which is as follows: S201, extract the backlight intensity distribution at the bottom of the groove and the degree of shadow depth attenuation on the inner wall from the acquired image information to obtain the brightness gradient value.

[0031] The algorithm uses the image of the backlight intensity distribution at the bottom of the groove and the image of the shadow depth attenuation on the inner wall as input. The Canny edge detection algorithm is employed. First, a Gaussian filter is applied to smooth the image to eliminate noise interference. Then, the brightness change rate in the horizontal and vertical directions of each pixel is calculated to obtain the gradient magnitude and direction. The final output is a brightness gradient value reflecting the degree of brightness abrupt change in the inner wall and bottom region of the groove. This gradient value is used to identify the location of potential contour boundaries.

[0032] S202, based on the brightness gradient value, extract the boundary points of the potential contour closure curve, fuse texture and color gradient features to enhance the boundary points, and calculate the extended gradient distribution.

[0033] In this process, pixels with brightness gradient values ​​exceeding a preset threshold are selected as candidate boundary points and organized into a boundary point sequence based on their spatial connectivity, forming a set of position coordinates for potential contour closure curves. Subsequently, for irregular boundary points in the groove, texture gradient features and color gradient features are fused for enhancement. The texture gradient features are obtained by calculating contrast and uniformity using the local gray-level co-occurrence matrix, while the color gradient features are calculated based on channel differences in the RGB or HSV color space. The two are then weighted and averaged according to preset weights to obtain an extended gradient distribution. This extended gradient distribution can more comprehensively depict the irregular boundary information generated by the changes in the carving shape in the inner wall and bottom area of ​​the groove.

[0034] S203, Based on the extended gradient distribution, the boundary points are smoothed by Gaussian filtering to generate a brightness gradient map.

[0035] The process involves using the expanded gradient distribution obtained by fusing texture and color gradient features as input. Gaussian filtering is applied to smooth the gradient distribution. By setting a preset standard deviation σ, weighted diffusion is performed on the gradient values ​​in the neighborhood of boundary points, effectively connecting and expanding isolated or discontinuous boundary points in space, thus enhancing the continuity and integrity of the contour. After Gaussian filtering expansion, a brightness gradient map, identified by pixel coordinates, is output. This map records the gradient intensity distribution at various locations on the inner wall and bottom of the groove, used for subsequent identification and determination of the contour closure curve.

[0036] This embodiment uses an edge detection algorithm to process the distribution of backlight intensity at the bottom of the groove and the attenuation of the shadow depth on the inner wall, accurately extracting brightness gradient values ​​and providing a quantitative basis for contour boundary localization. Based on this, texture gradient features and color gradient features are fused to enhance irregular boundary points of the groove, effectively addressing the irregular boundaries caused by the complex shape and varied surface texture of carved door panel grooves, improving the completeness and accuracy of boundary extraction. Furthermore, Gaussian filtering is used to expand the boundary points, smoothing the gradient distribution and connecting discontinuous boundary points, thereby generating a continuous, clear, and noise-resistant brightness gradient map. This lays a reliable data foundation for subsequent identification of potential contour closure curves and differentiation of false bright rings, significantly improving the accuracy and robustness of contour extraction under complex carved structures.

[0037] Furthermore, such as Figure 3As shown, this application provides an implementation process for generating a brightness gradient map in a method for planning the spraying path of furniture contours. First, based on the distribution of backlight intensity at the bottom of the groove and the attenuation degree of the shadow depth on the inner wall, the Canny edge detection algorithm is used to process the inner wall and bottom areas of the groove to obtain brightness gradient values. For the brightness gradient values, the boundary points of the potential contour closure curve are extracted to determine the position coordinate sequence. From the position coordinate sequence, texture and color gradient features are fused to enhance the irregular boundary points of the groove; specifically, an extended gradient distribution is obtained through weighted average calculation. Texture features generally reflect the geometric structure of an object more stably than color features, especially when there are large changes in lighting, the paint color is close to the natural wood color, resulting in insignificant color gradients, or the contour structure is complex. Based on empirical values, the texture weight is usually higher than the color weight; for example, the initial texture weight is 0.6 and the initial color weight is 0.4. In specific applications, the texture weight and color weight can be adjusted according to the material, color, and other influencing factors of the actual sample. Based on the extended gradient distribution, Gaussian filtering is applied to extend the boundary points, smoothing noise in the gradient map and generating a brightness gradient map. The standard deviation σ is used to determine the degree of smoothing. In industrial image processing, a standard deviation σ of 1.0-2.0 is a common empirical range. For example, the initial standard deviation σ is 1.5. In specific applications, the standard deviation σ can be dynamically adjusted according to influencing factors such as the resolution and noise level of the actual image.

[0038] In one embodiment, the bright bands of specular reflection on the sidewall are grouped and clustered based on the acquired image information to obtain false bright ring identifiers, including steps S301 to S303, each step of which is as follows: S301, based on the acquired image information, the reflection noise is filtered by gradient threshold to obtain a set of filtered bright reflection bands.

[0039] The process involves extracting the location coordinates, width, curvature, and other morphological parameters of the bright reflective bands on the sidewalls from the acquired image information and brightness gradient map. The average pixel gradient in the gradient map is calculated, and a preset percentage of this average value is used as a gradient threshold to filter pixels within the reflective bright band region. Pixels with gradient values ​​below the threshold are identified as reflection noise and removed, while pixels with gradient values ​​above the threshold are retained, forming a filtered set of reflective bright bands. This set is used for subsequent clustering analysis and false closed-loop identification.

[0040] S302, based on the filtered set of reflective bright bands, the filtered set of reflective bright bands is evaluated by calculating curvature index and continuity index, and the filtered reflective bright bands are grouped and clustered by a clustering algorithm to determine the group of bright bands after clustering.

[0041] For each reflective bright band in the set, its pixel set is extracted, and the local curvature of each point is calculated, with the mean value used as the curvature index. The curvature calculation is: k = 1 / r, where r is the radius of curvature of the locally fitted circle. Simultaneously, the ratio of the number of consecutive pixels within the bright band to the total number of pixels is calculated as a continuity index. Based on the feature vector formed by the curvature and continuity index, the K-means clustering algorithm is used to group the reflective bright bands, grouping bright bands with similar morphological features into the same group. This group is then used to distinguish between genuine sidewall reflections and interfering false closed loops.

[0042] S303, in the clustered bright band groups, identify the closed loop shape generated at the center of the groove, determine the closed loop that meets the preset false loop standard as a false closed loop, and generate the corresponding false bright loop mark.

[0043] The process involves traversing each cluster of bright bands and checking for any connected annular structures that surround the central region of the groove. The area and perimeter of these annular structures are then extracted, and their irregularity is calculated using the following formula:

[0044] In the formula, Let S be the perimeter and S be the area.

[0045] If the area of ​​the ring is smaller than a preset pixel threshold and the irregularity is greater than a preset threshold, the closed ring is determined to be a false closed ring, and a binary identifier is assigned to it as a false bright ring identifier. This identifier is used to exclude optical interference in subsequent contour determination rules. In practical applications, the preset pixel threshold can be adjusted according to the actual contour sample. When the area of ​​the false bright ring in the contour sample is large, such as a wide-diameter groove, the preset pixel threshold can be adjusted accordingly.

[0046] This embodiment uses gradient thresholding to filter noise in reflective bright bands, effectively eliminating interfering pixels caused by scattering or low-intensity reflection, resulting in a pure set of reflective bright bands. Then, based on curvature and continuity indices, the bright bands are evaluated for features, and a clustering algorithm is used to group reflective bright bands with similar morphological characteristics, thus objectively distinguishing between genuine sidewall reflections and potential false bright ring structures. Finally, the closed loop shape generated at the center of the groove is identified in the clustered bright band groups. False closed loops are determined based on criteria such as area and irregularity, and corresponding identifiers are generated. This series of steps accurately identifies false bright rings induced by specular reflection at the center of the groove, preventing them from being confused with the outer edge of genuine carvings. This significantly reduces the false detection rate in contour interpretation, providing a reliable basis for subsequent dynamic adjustment of judgment rules and filtering of interference curves, and improving the accuracy and reliability of furniture spraying path planning.

[0047] In one embodiment, the effective angle range for contour closure determination is adjusted based on the false bright ring marker and the acquired image information, including steps S401 to S405, each step of which is as follows: S401, extract the sidewall backlight intensity distribution based on the acquired image information.

[0048] In this process, images are captured of the side wall area of ​​the groove in the carved door panel, and the reflection grayscale values ​​of each pixel on the side wall surface are extracted to form two-dimensional intensity distribution data mapped by spatial coordinates. This distribution is used to quantify the changes in light reflection intensity at different positions of the side wall, providing a basis for subsequent determination of the side wall tilt angle range and identification of false bright rings.

[0049] S402, based on the false bright ring mark and the side wall backlight intensity distribution, the actual range of the side wall tilt angle is determined by calculating the error value between the side wall backlight intensity distribution curve and the ideal reference distribution curve.

[0050] In this process, after removing the interference areas corresponding to false bright ring markers, the measured curve of the sidewall reflective intensity distribution is extracted. This curve is then compared with the target reference curve obtained by simulating the ideal vertical sidewall reflected light intensity distribution, and the error value between the two is calculated using the root mean square error formula. If the error value is less than a preset threshold, the sidewall tilt angle is determined to be close to vertical; otherwise, the error value is mapped to the corresponding tilt angle range to determine the actual range of the sidewall tilt angle. Specifically, when the sidewall tilts inward into the groove, i.e., the groove opening size is larger than the bottom size, forming a positive trapezoid or an inwardly contracting shape, it is defined as a positive tilt angle; when the sidewall tilts outward into the groove, i.e., the groove opening size is smaller than the bottom size, forming an inverted trapezoid or an outwardly expanding shape, it is defined as a negative tilt angle. This range is used to dynamically adjust the effective angle range for contour closure determination.

[0051] S403, based on the actual range of the sidewall inclination angle, adjust the effective angle range of the contour closure determination to obtain the adjusted angle range.

[0052] The process involves using the initial contour closure judgment angle range as a benchmark. Based on the determined actual range of sidewall inclination angles, a new upper and lower limit of the angle range is calculated using a linear adjustment formula. The inclination angle range is then multiplied by a preset proportional coefficient and added to or subtracted from the initial benchmark angle to obtain the widened or narrowed effective angle range. In practical applications, for positive inclination angles, false closed loops are more likely to appear in the center region of the groove, requiring an appropriate reduction in the effective angle range and enhanced filtering of false bright loops. For negative inclination angles, the true contour may extend towards the edge, requiring an appropriate expansion of the effective angle range and reduced suppression of edge bright bands. This adjusted angle range is used in subsequent contour judgment rules to adapt to different sidewall inclination degrees, avoiding misjudgment of the true contour or the intrusion of false contours due to fixed angle thresholds.

[0053] S404, based on the adjusted angle range, by comparing the consistency between the light source coordinates and the reflection path, a preliminary rule for contour closure is determined, wherein the light source coordinates are obtained through light source position calibration, and the reflection path is calculated using Snell's law.

[0054] This process includes a light source position calibration step, which uses the coordinates of a reference point to calculate the actual spatial coordinates of the coaxial ring light source. Simultaneously, based on Snell's law—the optical law that the ratio of the sine of the angle of incidence to the sine of the angle of refraction at the interface of two media is equal to the inverse relationship between the refractive indices of the two media—the expression is as follows:

[0055] In the formula, As the incident medium, As a reflective medium, The value of the sine of the incident angle is... The reflection angle is the sine value. The expected reflection path is calculated based on the angle between the incident light direction and the sidewall normal. The reflection path corresponding to the actual bright band position is compared with the expected reflection path, and the percentage deviation between the two is calculated. If the deviation is less than a preset threshold, the reflection mode is determined to be consistent. Based on this, a preliminary rule for contour closure is determined. This rule is used for subsequent validity screening of curves in the brightness gradient map.

[0056] S405, Based on the preliminary rules, the angle threshold is optimized by calculating the peak offset of the sidewall backlight intensity distribution to generate the final judgment rule.

[0057] The Gaussian fitting algorithm is used to detect the peak position of the sidewall backlight intensity distribution curve, obtaining the actual peak position. This position is then compared with the expected peak position under ideal vertical sidewall conditions, and the offset between the two is calculated. Based on this offset, the initial angle threshold is linearly corrected. The offset is multiplied by a preset coefficient and added to the base threshold to obtain the optimized angle threshold. This optimized angle threshold is integrated into the preliminary rules to form the final judgment rule, which includes angle range, peak offset compensation, and reflection consistency criteria. This rule is used for subsequent precise filtering of the contour curves in the brightness gradient map.

[0058] This embodiment obtains the sidewall backlight intensity distribution and, after eliminating interference based on false bright ring markers, uses the error value between the measured distribution curve and the ideal reference curve to determine the actual range of the sidewall tilt angle, thus objectively quantifying the tilt degree of the groove sidewall. Based on this tilt angle range, the effective angle interval for contour closure judgment is dynamically adjusted, enabling the judgment rule to adapt to the geometric characteristics of different carved door panels and avoiding misjudgment of the true contour or false contour entry caused by a fixed angle threshold. Furthermore, the reflection path is calculated through light source position calibration and Snell's law, comparing the consistency between the actual trajectory and the expected trajectory to ensure that the light source setting matches the sidewall shape. The angle threshold is optimized using the peak offset of the backlight intensity distribution, generating a final judgment rule that includes angle compensation and reflection consistency criteria. This series of steps significantly improves the robustness of contour closure judgment to optical interference from tilted walls, effectively reduces false bright ring misjudgments caused by changes in sidewall tilt angle, and provides an accurate and adaptive judgment benchmark for subsequent contour curve filtering, thereby improving the accuracy and reliability of spray path planning under complex carved structures.

[0059] In one embodiment, the curve position coordinates in the brightness gradient map are filtered to obtain a filtered contour curve, including steps S501 to S503, each step of which is as follows: S501, based on the curve position coordinates in the brightness gradient map and the final judgment rule, the continuity and brightness change amplitude of the curve position coordinates are quantitatively evaluated, and coordinate points that do not meet the preset threshold are filtered out to obtain a first set of filtered coordinates, wherein the continuity is quantified by the distance between adjacent points, and the brightness change amplitude is calculated by the gradient difference.

[0060] The process involves iterating through the coordinate sequence of each curve in the brightness gradient map, calculating the Euclidean distance between adjacent coordinate points as a continuity quantification indicator, and classifying a point as continuous if the distance is less than a preset pixel threshold. Simultaneously, the gradient difference at each coordinate point is calculated as the brightness change amplitude; if the gradient difference is greater than a preset gradient threshold, it is considered a valid edge. Based on the continuity threshold and brightness change amplitude threshold set in the final judgment rule, coordinate points that do not meet either condition are removed, and coordinate points that simultaneously meet both the continuity and brightness change amplitude requirements are retained, forming the first filtered coordinate set.

[0061] S502, based on the first set of filtered coordinates, by calculating the curve curvature and the ring closure index, noise coordinates belonging to false central bright rings are eliminated to obtain the second set of filtered coordinates.

[0062] In this process, for each curve in the first set of filtered coordinates, the local curvature at each point is calculated, and the average value is used as the curvature index. Simultaneously, the loop closure degree of the curve is calculated, which is the ratio of the square of the perimeter to four times π multiplied by the area. If the curvature is less than a preset curvature threshold and the loop closure degree is greater than a preset closure threshold, and the brightness of the curve's central region is higher than a preset difference in brightness from the surrounding area, then the curve is determined to be a false central bright loop, and its coordinates are removed from the first set of filtered coordinates. The remaining coordinates constitute the second set of filtered coordinates. This set is used for subsequent continuity evaluation and iterative optimization of the contour curves.

[0063] S503, Based on the second set of filtered coordinates, determine the filtered contour curve.

[0064] In this process, the coordinate points in the second set of filtered coordinates are connected sequentially according to spatial connectivity to form several curve segments. The small gaps in the curve segments caused by the removal of noise coordinates are smoothed by linear interpolation or spline interpolation, and finally a continuous filtered contour curve that reflects the true outer edge of the carving is generated. This curve is used for subsequent continuity evaluation and spraying path planning.

[0065] This embodiment quantifies the continuity and brightness variation of the curve position coordinates based on the final judgment rules, filtering out coordinate points that do not meet the preset threshold. This effectively eliminates isolated points caused by noise or weak edges, resulting in a first set of filtered coordinates. Based on this, the curve curvature and annular closure index are further calculated to accurately identify and eliminate noise coordinates belonging to false central bright rings, resulting in a second set of filtered coordinates. This achieves a secondary screening of false closed loops. Finally, the filtered contour curve is determined based on the second set of filtered coordinates. This two-step filtering mechanism systematically eliminates interference from false bright rings caused by specular reflection or uneven lighting, while retaining the irregular continuous curve of the true sculpted outer edge. This significantly improves the accuracy and authenticity of the contour curve, providing high-quality, low-interference input data for subsequent continuity assessment and spray path planning, effectively reducing the risk of mis-spraying and missed spraying.

[0066] In one embodiment, based on the adjusted angle range, preliminary rules for contour closure are determined by comparing the consistency between the light source coordinates and the reflection path, including steps S601 to S603, each step of which is as follows: S601, obtain the actual trajectory of the light source position and reflection path.

[0067] The process involves acquiring the actual spatial coordinates of the light source as its position. Simultaneously, the pixel coordinate sequence of the centerline of the reflected bright band is extracted from the acquired image information and transformed into its actual spatial trajectory, which serves as the actual trajectory of the reflection path. This actual trajectory is then used for consistency comparison with the expected reflection path calculated using Snell's law.

[0068] S602, based on the Snell's Law, the expected trajectory of the reflection path is calculated according to the actual range of the light source position and the sidewall tilt angle.

[0069] In this study, the obtained spatial coordinates of the light source are taken as the starting point of the incident light. The actual range of the sidewall tilt angle is used to determine the direction of the sidewall normal. The reflection direction of the light on the sidewall surface is calculated according to Snell's law, which states that when light is refracted at the interface of two media, the ratio of the sine of the incident angle to the sine of the refraction angle is equal to the inverse relationship between the refractive indices of the two media. The reflection direction is calculated as follows:

[0070] In the formula, As the incident medium, As a reflective medium, The value of the sine of the incident angle is... The reflection angle is the sine value. Based on this sine value, the reflection direction is determined, and the propagation path of the light in space is traced along this direction to generate a sequence of expected trajectory coordinates for the reflected light. This expected trajectory is compared with the actual acquired reflected bright band trajectory to verify the degree of matching between the light source setup and the sidewall geometry.

[0071] S603, calculate the percentage deviation between the actual trajectory and the expected trajectory. When the percentage deviation is less than a preset deviation threshold, determine that the reflection paths corresponding to the actual trajectory and the expected trajectory are consistent, and determine the preliminary rules for contour closure.

[0072] The process involves comparing the actual reflection path trajectory with the expected trajectory calculated based on Snell's Law point by point. The spatial distance between corresponding points on both the actual and expected trajectories is calculated, and the average of these distances is then divided by the total length of the expected trajectory to obtain the percentage deviation. If this percentage deviation is less than a preset threshold, the actual reflection behavior is determined to be consistent with the theoretical reflection model, indicating that the current light source position matches the sidewall tilt angle range. Based on this, preliminary rules for contour closure are determined. These rules include the allowable angle range, reflection path consistency conditions, and the basic basis for subsequent contour determination.

[0073] This embodiment obtains the actual trajectory of the light source position and reflection path, and calculates the expected trajectory of the reflection path based on Snell's law and the range of the light source coordinates and sidewall tilt angle. The deviation percentage between the actual trajectory and the expected trajectory is calculated, and the reflection path is determined to be consistent only when the deviation is less than a preset threshold, thus establishing a preliminary rule for contour closure. This process achieves quantitative verification between the light source setting and the geometry of the groove sidewall, ensuring that only areas whose reflection behavior conforms to the laws of physical optics are included in the contour determination, effectively eliminating false reflection interference caused by light source position deviation or tilt angle estimation errors. Simultaneously, this consistency determination provides a reliable prerequisite for subsequent angle threshold optimization and final determination rule generation, significantly enhancing the physical rationality and anti-interference capability of contour closure determination, and further improving the accuracy and robustness of complex carved door panel spraying path planning.

[0074] In one embodiment, the filtered contour curve is iteratively optimized to obtain the final contour closed curve, generating a contour spraying path planning scheme to complete the contour spraying path planning, including steps S701 to S704, each step as follows: S701, perform a continuity assessment on the filtered contour curve to determine the contour outer edge breakpoints that are below a preset lower limit.

[0075] The process involves iterating through the sequence of coordinate points on the filtered contour curve, calculating the Euclidean distance and angular change between adjacent points, and generating a continuity score for each curve segment. If the continuity score is lower than a preset lower threshold, the area corresponding to that curve segment is marked as a breakpoint on the outer edge of the contour. This breakpoint is used for subsequent iterative adjustments of the light source parameters based on the shape of the reflected bright band.

[0076] S702, iteratively adjust the width of the light band of the coaxial ring light source at the breakpoint of the outer edge of the contour to obtain an updated image sequence. The iterative adjustment is based on the continuity score as the objective function, and the adjustment amount is controlled by the step size coefficient until the continuity score exceeds a preset threshold or the maximum number of iterations is reached.

[0077] The continuity score of the filtered contour curve is used as the objective function. Based on the difference between the average width and intensity of the reflected bright band and the target value, the step size coefficient is used to calculate the adjustment amount of the light band width in each iteration. The iteration formula is as follows:

[0078] In the formula, k is the step size coefficient, 0.5. Let I represent the target intensity and I represent the average grayscale value. The step size coefficient k controls the magnitude of the light band width adjustment in each iteration, and its value is obtained through pre-experimental calibration. This fixed step size coefficient is suitable for most furniture painting scenarios, such as common wood, paint, and groove sizes. However, for extreme cases, such as highly reflective metallic paint surfaces or extremely deep carved grooves, users or the system can configure other k values, such as those in the range of 0.3-0.8, without affecting the overall algorithm framework.

[0079] Reacquire the image sequence according to the adjusted light source settings, and re-evaluate the continuity score of the contour curve. Repeat the above process until the continuity score exceeds the preset threshold or reaches the preset maximum number of iterations, thereby obtaining the optimized light source settings and the updated image sequence.

[0080] S703, based on the updated image sequence, the edge detection algorithm and clustering algorithm are iteratively applied until the cluster center points are closed, generating the final contour closure curve. The edge detection is used to extract the edge point set, and the cluster center points are determined by grouping the edge point set using the clustering algorithm.

[0081] The process involves using the updated image sequence as input, employing an edge detection algorithm to extract edge point sets from the image, and then using a clustering algorithm to spatially group these edge point sets, determining the corresponding cluster center points for each group. The closure indicator for each cluster center point is a Boolean value; the distance between the first and last points of a cluster center point set is calculated, and if this distance is less than 1 pixel, the cluster is considered closed; otherwise, it is considered unclosed. If the current cluster center points do not yet form a closed shape, the clustering result is fed back to the edge detection stage for image enhancement or re-detection, and edge point sets are extracted and clustered again. This process is iterated repeatedly until the cluster center points form a continuous closed loop structure. The output closed curve at this point is the final contour closure curve.

[0082] S704, based on the final contour closed curve, the spraying area is segmented and the spraying path is parametrically transformed to generate a contour spraying path planning scheme, thus completing the contour spraying path planning.

[0083] The process involves using the final closed contour curve as the spatial boundary and employing region growing or polygon filling algorithms to segment the spraying area of ​​the carved door panel's groove region, determining the target area to be sprayed and the areas to be avoided. Subsequently, the segmented boundary curve is converted into motion trajectory parameters for the spraying robot through spline fitting or equidistant offset, generating a planning scheme containing information such as path point coordinates, spraying speed, and spray gun angle, thereby completing the contour spraying path planning for the carved door panel's groove region.

[0084] This embodiment accurately locates the outer edge breakpoints below a preset lower limit by evaluating the continuity of the filtered contour curve. Based on the morphological characteristics of the reflected bright band, it iteratively adjusts the width of the coaxial ring light source using a continuity score as the objective function and a step size coefficient. This adaptively optimizes lighting conditions and effectively compensates for edge breaks caused by insufficient illumination or poor angles. After acquiring updated image sequences, edge detection and clustering algorithms are repeatedly applied until the cluster center points close, generating the final contour closure curve, significantly improving the continuity and integrity of the complex carved outer edge. Finally, the spraying area is segmented and path parameterized based on the final contour closure curve, generating a planning scheme that can be directly used for automated spraying. This series of iterative optimization processes not only solves the problems of outer edge breakpoints and false bright ring interference that are difficult to overcome in existing technologies, but also enables the extraction of the contour closure curve to have self-correcting capabilities. This significantly reduces mis-spraying and missed spraying caused by contour recognition errors while improving the accuracy of spraying path planning, providing an efficient and reliable solution for automated furniture spraying.

[0085] Furthermore, such as Figure 4 As shown, this application provides a method for planning the spraying path of furniture contour painting. First, an updated image is acquired and processed using an edge detection algorithm to obtain a preliminary set of edge points. Then, a clustering algorithm is used to group the preliminary edge point set and determine the cluster centers. If the cluster centers do not form a closed loop, the edge detection algorithm and clustering algorithm are repeatedly applied to the cluster centers to obtain the final contour closure curve. Next, the spraying area is segmented using the final contour closure curve. Finally, the input data for spraying path planning is output as the planning scheme for the contour spraying path, completing the contour spraying path planning.

[0086] Based on the same inventive concept, this application also provides a planning system for realizing the above-mentioned furniture outline spraying path. The solution provided by this system is similar to the solution described in the above method. Therefore, the specific limitations of one or more furniture outline spraying path planning device embodiments provided below can be found in the limitations of the furniture outline spraying path planning method above, and will not be repeated here.

[0087] In one exemplary embodiment, such as Figure 5 As shown, a system for planning the spraying path of furniture outlines is provided, including: The data acquisition module 801 is used to acquire image information of the spraying outline; The feature extraction module 802 is used to extract brightness from the acquired image information to obtain a brightness gradient map, and to group and cluster the bright bands of the side wall specular reflection based on the acquired image information to obtain false bright ring identifiers. The filtering contour module 803 is used to adjust the effective angle range of the contour closure determination based on the false bright ring marker and the acquired image information, and to filter the curve position coordinates in the brightness gradient map to obtain the filtered contour curve. The path planning module 804 is used to iteratively optimize the filtered contour curve to obtain the final contour closed curve, generate a contour spraying path planning scheme, and complete the contour spraying path planning.

[0088] In one embodiment, a smart sofa is provided, including a sofa and a computer program product disposed within the sofa. The computer program product includes a computer program or instructions that, when executed by a device, implement the steps of a furniture outline spraying path planning method as described above.

[0089] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0090] This technical solution utilizes an adjustable coaxial ring light source unit with adjustable inner and outer diameters and a high dynamic range industrial camera, along with a brightness gradient map and clustering analysis algorithm, to construct a dedicated image acquisition and contour analysis system for the grooved areas of carved door panels. Its core advantage lies in overcoming the limitations of existing technologies in handling false bright ring interference under varying groove sidewall inclination angles. It enables dynamic and interactive extraction and judgment of contour closure curves in a three-dimensional, adjustable lighting environment. Users can intuitively iterate and adjust the light source to actively optimize acquisition parameters or judgment rules, and observe in real-time the impact of different lighting settings on the elimination of false closure loops and the continuity of the true carved outer edge. This provides accurate decision-making basis for spraying path planning, achieving a leap from passive image acquisition to active light source control and contour recognition. Simultaneously, this solution fully leverages the respective advantages of the adjustable ring light source in illumination optimization, the high dynamic range camera in detail capture, and the edge detection and clustering algorithms in image analysis, solving the problems of traditional single-vision systems being susceptible to specular reflection interference and having poor contour closure stability under inclined wall conditions.

[0091] For the device embodiments, since they basically correspond to the method embodiments, the relevant details can be found in the descriptions of the method embodiments. The device embodiments described above are merely illustrative; components described as separate parts may or may not be physically separate, and components shown as units may or may not be physical units, meaning they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0092] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for planning the spraying path of furniture outline, characterized in that, include: Acquire image information of the spraying outline; Brightness is extracted from the acquired image information to obtain a brightness gradient map, and the bright bands of the side wall specular reflection are grouped and clustered based on the acquired image information to obtain false bright ring identifiers; Based on the false bright ring markers and the acquired image information, the effective angle range for contour closure determination is adjusted, and the curve position coordinates in the brightness gradient map are filtered to obtain the filtered contour curve. The filtered contour curve is iteratively optimized to obtain the final contour closed curve, and a contour spraying path planning scheme is generated to complete the contour spraying path planning.

2. The method for planning a furniture outline spraying path as described in claim 1, characterized in that, The step of extracting brightness from the acquired image information to obtain a brightness gradient map includes: The brightness gradient value is obtained by extracting the backlight intensity distribution at the bottom of the groove and the attenuation degree of the shadow depth on the inner wall from the acquired image information. Based on the brightness gradient value, the boundary points of the potential contour closure curve are extracted, and the boundary points are enhanced by fusing texture and color gradient features to calculate the extended gradient distribution. Based on the extended gradient distribution, the boundary points are smoothed using Gaussian filtering to generate a brightness gradient map.

3. The method for planning a furniture outline spraying path as described in claim 2, characterized in that, The step of grouping and clustering the bright bands of the sidewall specular reflection based on the acquired image information to obtain false bright ring identifiers includes: Based on the acquired image information, reflection noise is filtered using a gradient threshold to obtain a set of filtered bright reflection bands. Based on the filtered set of reflective bright bands, the features of the filtered set of reflective bright bands are evaluated by calculating curvature index and continuity index, and the filtered reflective bright bands are grouped and clustered by a clustering algorithm to determine the group of bright bands after clustering. In the clustered bright band groups, the closed loop shape generated at the center of the groove is identified. Closed loops that meet the preset false loop criteria are judged as false closed loops, and corresponding false bright loop identifiers are generated.

4. The method for planning a furniture outline spraying path as described in claim 1, characterized in that, The adjustment of the effective angle range for contour closure determination based on the false bright ring marker and the acquired image information includes: The sidewall backlight intensity distribution is extracted based on the acquired image information; Based on the false bright ring markings and the sidewall backlight intensity distribution, the actual range of the sidewall tilt angle is determined by calculating the error value between the sidewall backlight intensity distribution curve and the ideal reference distribution curve; Based on the actual range of the sidewall inclination angle, the effective angle range for contour closure determination is adjusted to obtain the adjusted angle range. Based on the adjusted angle range, preliminary rules for contour closure are determined by comparing the consistency between the light source coordinates and the reflection path. The light source coordinates are obtained through light source position calibration, and the reflection path is calculated using Snell's law. Based on the preliminary rules, the angle threshold is optimized by calculating the peak offset of the sidewall backlight intensity distribution to generate the final judgment rule.

5. The method for planning a furniture outline spraying path as described in claim 4, characterized in that, The step of filtering the curve position coordinates in the brightness gradient map to obtain the filtered contour curve includes: Based on the curve position coordinates in the brightness gradient map and the final judgment rule, the continuity and brightness change amplitude of the curve position coordinates are quantitatively evaluated, and coordinate points that do not meet the preset threshold are filtered out to obtain a first set of filtered coordinates. The continuity is quantified by the distance between adjacent points, and the brightness change amplitude is calculated by the gradient difference. Based on the first set of filtered coordinates, the second set of filtered coordinates is obtained by calculating the curve curvature and the ring closure index and removing the noise coordinates that belong to the false central bright ring. Based on the second set of filtered coordinates, the filtered contour curve is determined.

6. The method for planning a furniture outline spraying path as described in claim 4, characterized in that, Based on the adjusted angle range, the preliminary rules for contour closure are determined by comparing the consistency between the light source coordinates and the reflection path, including: Obtain the actual trajectory of the light source position and reflection path; Based on Snell's law, the expected trajectory of the reflection path is calculated according to the actual range of the light source position and the sidewall tilt angle. Calculate the percentage deviation between the actual trajectory and the expected trajectory. When the percentage deviation is less than a preset deviation threshold, determine that the reflection paths corresponding to the actual trajectory and the expected trajectory are consistent, and determine the preliminary rules for contour closure.

7. The method for planning a furniture outline spraying path as described in claim 1, characterized in that, The filtered contour curve is iteratively optimized to obtain the final contour closed curve, generating a contour spraying path planning scheme, and completing the contour spraying path planning, including: The continuity of the filtered contour curve is evaluated to determine the breakpoints on the outer edge of the contour that are below a preset lower limit. The width of the light band of the coaxial ring light source is iteratively adjusted at the breakpoint of the outer edge of the contour to obtain an updated image sequence. The iterative adjustment is based on the continuity score as the objective function, and the adjustment amount is controlled by the step size coefficient until the continuity score exceeds a preset threshold or the maximum number of iterations is reached. Based on the updated image sequence, edge detection and clustering algorithms are iteratively applied until the cluster center points are closed, generating a final contour closure curve. The edge detection algorithm is used to extract the edge point set, and the cluster center points are determined by grouping the edge point set using the clustering algorithm. Based on the final contour closure curve, the spraying area is segmented and the spraying path is parametrically transformed to generate a contour spraying path planning scheme, thus completing the contour spraying path planning.

8. A system for planning the spraying path of furniture outlines, characterized in that, The system includes: The data acquisition module is used to acquire image information of the spraying outline; The feature extraction module is used to extract brightness from the acquired image information to obtain a brightness gradient map, and to group and cluster the bright bands of the side wall specular reflection based on the acquired image information to obtain false bright ring identifiers. The contour filtering module is used to adjust the effective angle range for contour closure determination based on the false bright ring markers and the acquired image information, and to filter the curve position coordinates in the brightness gradient map to obtain the filtered contour curve. The path planning module is used to iteratively optimize the filtered contour curve to obtain the final contour closed curve, generate a contour spraying path planning scheme, and complete the contour spraying path planning.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions, which, when executed by a communication device, implement the method for planning the furniture outline spraying path as described in any one of claims 1-7.

10. A smart sofa, comprising a sofa and a computer program product disposed within the sofa, the computer program product comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by the communication device, the method for planning the furniture outline spraying path as described in any one of claims 1-7 is implemented.

Images