A large complex workpiece space alignment real-time judgment method, system and device

Abstract

The application discloses a large complex workpiece space alignment real-time judgment method, system and device, wherein the method comprises the following steps: setting a preset marker at a preset position of a crane, collecting images of the preset marker in real time and screening, converting the clear and complete images of the preset marker, carrying out noise reduction processing on the HSV color space images to obtain preprocessed images; extracting V channel information from the preprocessed images through the HSV color space, calculating average brightness and dynamically adjusting the threshold range of the V channel corresponding color, segmenting the preset marker region according to the threshold range, and calculating the center region; using the corresponding relationship between the actual size of the preset marker and the pixel size in the image and the pre-set central baseline position information, calculating the offset of the preset marker relative to the central baseline, obtaining the position information of the preset marker corresponding to the main beam and the auxiliary beam, and judging whether the main beam and the auxiliary beam are aligned according to the position information. The method has high detection precision and strong environmental adaptability.

Description

Technical Field

[0001] This invention relates to the field of industrial crane equipment technology, and in particular to a method, system and device for real-time spatial alignment determination of large and complex workpieces. Background Technology

[0002] In industrial production, especially in heavy machinery manufacturing and shipbuilding involving the assembly of large crane equipment, the spatial alignment accuracy of large and complex components such as main beams and secondary beams directly affects the operational safety and service life of the equipment. Traditional spatial alignment determination techniques mainly rely on manual operation. Skilled workers use simple measuring tools such as plumb bobs and levels to perform multi-dimensional measurements. This method has significant technical drawbacks: First, manual measurement inevitably leads to low efficiency, especially for large workpieces exceeding 30 meters in length and weighing hundreds of tons, where a single full-size measurement can take 4-6 hours. Second, measurement accuracy is significantly affected by the operator's experience; repeated measurement errors by workers of different skill levels can reach ±3mm. Third, traditional optical measuring tools are prone to visual errors under complex lighting conditions, especially when strong light sources from the workshop ceiling are superimposed on the reflections from the workpiece surface, resulting in a significant error amplification effect. Furthermore, traditional methods struggle to achieve real-time and accurate determination given the complex structure of large and complex workpieces and diverse working environments.

[0003] With the development of machine vision and image processing technologies, it has become possible to determine workpiece spatial alignment using image acquisition and analysis. However, some existing vision-based methods suffer from insufficient detection accuracy and poor adaptability when dealing with complex lighting conditions and the detection of large targets on large workpieces. For example, in scenarios with significant lighting variations, it is difficult to accurately identify key feature targets, leading to deviations in alignment determination. Summary of the Invention

[0004] To address some or all of the technical problems existing in the prior art, this invention provides a method, system, and device for real-time spatial alignment determination of large and complex workpieces. It has the advantages of high detection accuracy, strong environmental adaptability, good real-time performance, and high degree of automation. It can effectively solve the problems existing in the current detection methods and has good application prospects.

[0005] The technical solution of the present invention is as follows:

[0006] Firstly, a real-time spatial alignment determination method for large and complex workpieces is provided for alignment between main beams and between secondary beams of a crane, the method comprising:

[0007] Pre-set markers are installed at predetermined locations on the crane, wherein the predetermined locations include the crane's first main beam, second main beam, and two auxiliary beams, and the predetermined markers include target devices;

[0008] Images of the preset markers are acquired in real time, and the acquired images are filtered to obtain clear and complete images of the preset markers;

[0009] The acquired images are converted using a color space conversion algorithm to obtain HSV color space images;

[0010] A noise reduction algorithm is applied to the HSV color space image to obtain a preprocessed image.

[0011] The V channel information of the obtained preprocessed image is extracted through the HSV color space, the average brightness of the corresponding color of the V channel is calculated and the threshold range of the corresponding color of the V channel is dynamically adjusted, the region of the preset marker is segmented according to the threshold range, and the center region of the preset marker is calculated through a geometric algorithm.

[0012] Using the known correspondence between the actual size of the preset marker and the pixel size in the image, and the pre-set central baseline position information, the offset of the preset marker relative to the central baseline is calculated to obtain the position information of the corresponding preset marker on the first main beam, the second main beam, and the two secondary beams. Based on the obtained position information, it is determined whether the first main beam and the second main beam, and the two secondary beams are aligned.

[0013] In some alternative implementations, the target device includes a circular target of a specific color.

[0014] In some alternative implementations, the specific color includes blue.

[0015] Furthermore, in the aforementioned method for real-time spatial alignment determination of large and complex workpieces, the process of extracting V channel information from the obtained preprocessed image using the HSV color space, calculating the average brightness of the corresponding color in the V channel, and dynamically adjusting the threshold range of the corresponding color in the V channel includes:

[0016] If the average brightness is greater than 110 and less than or equal to 145, then set the lower limit of HSV to (87, the value of average brightness - 5, the value of average brightness - 25), set the upper limit to (160, 255, 255), and extract the blue area to the mask.

[0017] If the average brightness is greater than 145, then set the lower limit of HSV to (87, 135, the value of average brightness - 5) and the upper limit to (160, 180, 255).

[0018] If the average brightness does not meet the above conditions, it is considered low brightness, and a threshold range with a lower limit of HSV (90, 150, 50) and an upper limit of HSV (150, 255, 255) is used.

[0019] Furthermore, in the aforementioned real-time spatial alignment determination method for large and complex workpieces, the method utilizes the known correspondence between the actual size of preset markers and the pixel size in the image, as well as the pre-set central baseline position information, including:

[0020] If the offset of each preset marker relative to the central baseline is within the allowable error range, it indicates that the first main beam is aligned with the second main beam and the two secondary beams respectively.

[0021] If the offset of each preset marker relative to the central baseline exceeds the allowable error range, it indicates that the first main beam, the second main beam, and the two secondary beams are not aligned. At the same time, based on the offset direction and amount, the adjustment direction of the misaligned main beam or secondary beam is determined, and the corresponding movement is performed.

[0022] Secondly, a real-time spatial alignment determination system for large and complex workpieces is provided for alignment between main beams and between secondary beams of a crane. The system includes:

[0023] The marking module is used to set a preset marker at a preset position of the crane, wherein the preset position includes the first main beam, the second main beam and two auxiliary beams of the crane, and the preset marker includes a target device.

[0024] The image acquisition and filtering module is used to acquire images of the preset markers in real time, filter the acquired images, and obtain clear and complete images of the preset markers.

[0025] An image conversion module is used to convert the acquired image using a color space conversion algorithm to obtain an HSV color space image;

[0026] The image processing module is used to perform noise reduction processing on the HSV color space image using a noise reduction algorithm to obtain a preprocessed image;

[0027] The calculation and analysis module is used to extract V channel information from the obtained preprocessed image through the HSV color space, calculate the average brightness of the color corresponding to the V channel and dynamically adjust the threshold range of the color corresponding to the V channel, segment the region of the preset marker according to the threshold range, and calculate the center region of the preset marker through a geometric algorithm.

[0028] The determination module is used to calculate the offset of the preset marker relative to the central baseline by using the known correspondence between the actual size of the preset marker and the pixel size in the image and the preset central baseline position information, to obtain the position information of the corresponding preset marker on the first main beam, the second main beam and the two secondary beams, and to determine whether the first main beam and the second main beam and the two secondary beams are aligned based on the obtained position information.

[0029] Thirdly, a determination device is provided that applies the above-mentioned real-time spatial alignment determination method for large and complex workpieces, for alignment between main beams and between secondary beams of a crane, the device comprising:

[0030] Pre-set markers are provided on the main beam and secondary beam of the crane;

[0031] An image acquisition device is installed outside the crane. The range of the image acquired by the image acquisition device completely covers the preset markers on the main beam and the secondary beam, so that the image can be clearly acquired when the preset markers are at any angle on the main beam or the secondary beam of the crane.

[0032] The control module is pre-configured with a color space conversion algorithm and a noise reduction algorithm. The color space conversion algorithm converts the image acquired by the image acquisition device to obtain an HSV color space image, and the noise reduction algorithm is used to denoise the HSV color space image to obtain a pre-processed image. Simultaneously, the control module can extract V channel information from the obtained pre-processed image using the HSV color space, calculate the average brightness of the corresponding color in the V channel, dynamically adjust the threshold range of the corresponding color in the V channel, segment the region of the preset marker according to the threshold range, calculate the center region of the preset marker using a geometric algorithm, and calculate the offset of the preset marker relative to the central baseline using the known correspondence between the actual size of the preset marker and the pixel size in the image, as well as the pre-set central baseline position information. This yields the position information of the corresponding preset markers on the first main beam, the second main beam, and the two secondary beams. Based on the obtained position information, it determines whether the first and second main beams and the two secondary beams are aligned.

[0033] In some alternative implementations, the preset marker includes a circular target of a specific color.

[0034] In some alternative implementations, the image acquisition device includes one or more of the following: a camera, a digital camera, a scanner, an industrial camera, an image acquisition card, a light source device, and an adjustable image acquisition device.

[0035] Furthermore, the aforementioned real-time spatial alignment determination device for large and complex workpieces also includes an interactive module. The interactive module has a display interface that displays the actual status of preset markers on the main beam and secondary beam. It provides adjustment buttons for the exposure and gain parameters required by the image acquisition device, allowing users to adjust the parameters of the image acquisition device according to actual lighting conditions. The interface also includes a power switch and operating status display for the image acquisition device, and displays the alignment status, adjustment direction, and actual distance between each main beam and secondary beam in real time, providing intuitive information for the operator.

[0036] The main advantages of the technical solution of this invention are as follows:

[0037] This invention provides a method, system, and device for real-time spatial alignment determination of large and complex workpieces. It boasts advantages such as high detection accuracy, strong environmental adaptability, good real-time performance, and high automation, effectively solving the problems of existing detection methods and showing promising application prospects. Specifically, traditional methods rely on manual operation, resulting in low efficiency. In terms of accuracy and reliability, this invention utilizes a specific color circular target and advanced algorithms to accurately calculate the center position and offset, effectively reducing errors and ensuring stable and safe equipment operation. Facing complex lighting conditions, it dynamically adjusts thresholds to ensure accurate target identification in various environments, making it widely applicable. Simultaneously, an interactive window developed based on MFC intuitively displays various information, providing parameter adjustment and on / off buttons, facilitating flexible adjustments by operators and reducing operational difficulty. Compared to traditional alignment determination methods that rely on manual measurement and simple measuring tools, the real-time spatial alignment determination method for large and complex workpieces of this invention has significant advantages. Attached Figure Description

[0038] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and constitute a part of this invention, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0039] Figure 1 This is a flowchart illustrating a real-time spatial alignment determination method for large and complex workpieces according to an embodiment of the present invention.

[0040] Figure 2 This is a schematic diagram of a real-time spatial alignment determination system for large and complex workpieces according to an embodiment of the present invention.

[0041] Figure 3 This is a schematic diagram of a real-time spatial alignment determination device for large and complex workpieces according to an embodiment of the present invention;

[0042] Explanation of reference numerals in the attached figures:

[0043] 10. Identification module; 20. Image acquisition and filtering module; 30. Image conversion module; 40. Image processing module; 50. Calculation analysis module and judgment module;

[0044] 100. Preset markers; 200. Image acquisition device; 300. Control module; 400. Interaction module; 401. Display interface. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0046] The following is in conjunction with the appendix Figure 1-3 The technical solutions provided in the embodiments of the present invention will be described in detail.

[0047] As attached Figure 1 As shown, this embodiment of the invention provides a real-time spatial alignment determination method for large and complex workpieces, used for the alignment between main beams and between secondary beams of a crane. The method includes the following steps:

[0048] Step S1: Set up preset markers at preset positions of the crane, wherein the preset positions include the first main beam, the second main beam and two auxiliary beams of the crane, and the preset markers include target devices;

[0049] In some optional implementations of this embodiment, the target device includes a circular target of a specific color. Preferably, the specific color is set to blue for the circular target.

[0050] Because the target devices have obvious geometric features and are easily identifiable, they are placed at predetermined locations on each beam as target objects for subsequent image detection. By setting target devices on each beam, clear detection markers are provided for image acquisition and processing, facilitating the subsequent extraction and analysis of beam position information. This setup, with its clearly defined pre-defined markers, makes subsequent image acquisition and processing more targeted, avoiding direct detection of complex beam structures, simplifying the detection process, and improving the feasibility of detection.

[0051] Step S2: Real-time acquisition of images of preset markers, filtering of acquired images to obtain clear and complete images of preset markers;

[0052] In some optional implementations of this embodiment, the image acquisition device includes one or more of the following: a camera, a digital camera, a scanner, an industrial camera, an image acquisition card, a light source device, and an adjustable image acquisition device.

[0053] In order to acquire images clearly, completely and accurately, the image acquisition device is set up outside the crane. However, it is necessary to ensure that the range of the image acquisition device completely covers the preset markers on the main beam and the secondary beam, so that the image can be clearly acquired when the preset markers are at any angle on the main beam or the secondary beam of the crane.

[0054] With this setup, image acquisition devices (such as cameras) can acquire image information containing preset markers in real time. Due to factors such as lighting variations and noise interference in the actual environment, the acquired images will inevitably have issues such as blurriness and incompleteness. Through image filtering algorithms, based on preset clarity and integrity standards (such as contrast and edge sharpness), the acquired images are filtered, removing those that do not meet the requirements and retaining clear and complete images, providing high-quality input data for subsequent image processing.

[0055] This setup ensures that the features of the preset markers in the subsequently processed images can be accurately identified and analyzed, avoiding detection errors caused by image quality issues and improving the accuracy and reliability of the detection.

[0056] Step S3: The acquired image is converted using a color space conversion algorithm to obtain an HSV color space image;

[0057] As is well known, conventional images are RGB images, and the images acquired in this embodiment of the invention are of this type. However, the common RGB color space has certain limitations in image processing, such as being quite sensitive to changes in lighting. The HSV color space, on the other hand, better matches the human visual perception of color, enabling the separation of color and brightness information. Therefore, in this embodiment of the invention, an RGB image is converted to an HSV image using a color space conversion algorithm, facilitating subsequent separate processing and analysis of the image's brightness information (V channel), and better adapting to image detection under different lighting conditions.

[0058] To more clearly illustrate the technical solutions of the embodiments of the present invention, a brief description of the HSV color space is provided below:

[0059] The HSV color model, also known as the Hexcone Model, is a color space created by A.S. Smith in 1978 based on the intuitive characteristics of color. It refers to a subset of visible light within the H, S, V three-dimensional color space, encompassing all colors within a specific color gamut. Here, H stands for Hue, S for Saturation, and V for Value. This approach provides a more suitable color space for subsequent noise reduction and thresholding, making brightness-based processing more effective and improving the accuracy of extracting pre-defined marker regions from images.

[0060] Step S4: Apply a noise reduction algorithm to the HSV color space image to obtain a preprocessed image;

[0061] Specifically, during image acquisition and transmission, various types of noise (such as Gaussian noise, salt-and-pepper noise, etc.) are inevitably introduced, which can interfere with the extraction of features from preset markers. Noise reduction algorithms (such as median filtering, Gaussian filtering, etc.) can remove noise from images, smooth image edges, and retain the main features of preset markers. Therefore, in this embodiment of the invention, by performing noise reduction processing on the V channel (luminance channel) in the HSV color space, the image quality can be improved without affecting color information, making the outline of the preset markers clearer. This reduces the interference of noise on subsequent image processing, improves the signal-to-noise ratio of the image, and lays the foundation for accurate segmentation of the preset marker region.

[0062] Step S5: Extract V channel information from the obtained preprocessed image using the HSV color space, calculate the average brightness of the corresponding color in the V channel and dynamically adjust the threshold range of the corresponding color in the V channel, segment the region of the preset marker according to the threshold range, and calculate the center region of the preset marker using a geometric algorithm.

[0063] In the real-time spatial alignment determination of large and complex workpieces, different lighting conditions can significantly affect the color representation of preset markers in the image. If a fixed threshold range is used for preset marker region segmentation, changes in lighting intensity can lead to inaccurate extraction of the preset marker regions, thus affecting the workpiece alignment determination result. Therefore, by calculating the average brightness of the color corresponding to the V channel and dynamically adjusting the threshold range, the aim is to enable the threshold range to adapt to the current image lighting conditions, ensuring accurate segmentation of the preset marker regions under different lighting conditions. This provides a reliable basis for subsequent accurate calculation of the center region of the preset markers and determination of workpiece alignment. In some optional implementations of this embodiment, to avoid the influence of factors such as lighting and achieve accurate extraction of preset markers, the V channel information is extracted from the obtained preprocessed image using the HSV color space. The average brightness of the color corresponding to the V channel and the threshold range of the color corresponding to the V channel are calculated and dynamically adjusted as follows:

[0064] If the average brightness is greater than 110 and less than or equal to 145, then set the lower limit of HSV to (87, the value of average brightness - 5, the value of average brightness - 25), set the upper limit to (160, 255, 255), and extract the blue area to the mask.

[0065] If the average brightness is greater than 145, then set the lower limit of HSV to (87, 135, the value of average brightness - 5) and the upper limit to (160, 180, 255).

[0066] If the average brightness does not meet the above conditions, it is considered low brightness, and a threshold range with a lower limit of HSV (90, 150, 50) and an upper limit of HSV (150, 255, 255) is used.

[0067] In this embodiment of the invention, based on the above analysis and explanation, the V channel represents the brightness information of the image. Calculating the average brightness of the color corresponding to the V channel can quantify the overall brightness of the current image and serve as an important basis for judging lighting conditions. This is the significance of average brightness in this embodiment of the invention.

[0068] Specifically, in this embodiment of the invention, after extracting the V channel information, the image only contains brightness information. Calculating the average brightness of the color corresponding to the V channel can reflect the overall brightness level of the current image. Since lighting conditions may change in the actual environment, a fixed threshold range is difficult to adapt to different situations. Therefore, a method of dynamically adjusting the threshold range is adopted, automatically adjusting the upper and lower limits of the threshold according to the average brightness, so that the preset marker area can be accurately segmented under different lighting conditions. In this embodiment of the invention, the preset marker is separated from the background through threshold segmentation to obtain its location. Then, a geometric algorithm (such as the centroid algorithm, the minimum bounding rectangle algorithm, etc.) is used to calculate the central region of the preset marker, so that the central region can accurately represent the position of the preset marker in the image.

[0069] Furthermore, in order to more clearly and completely explain the purpose and reasons for setting dynamic thresholds in the embodiments of the present invention, they will be described in detail as follows:

[0070] The purpose and reason for setting the average brightness between 87 and 145 is that when the average brightness is greater than 110 and less than or equal to 145, the light intensity is at a medium level. Under this lighting condition, the color distribution of the preset marker (taking the blue area as an example) in the HSV space follows a certain pattern. The lower limit of the HSV is set to (87, the value of average brightness - 5, the value of average brightness - 25), and the upper limit is set to (160, 255, 255). This is because as the average brightness changes, the hue (H) of the blue area remains relatively stable between 87 and 160, but the saturation (S) and brightness (V) are affected by the overall lighting. By reducing the lower limit of saturation by 5 and the lower limit of brightness by 25, the color variation range of the blue preset marker under medium lighting conditions can be more accurately captured, thus accurately extracting the blue area into the mask.

[0071] The purpose and reason for setting an average brightness greater than 145 is that when the average brightness is greater than 145, it indicates strong light intensity. At this time, the color of the preset marker will be brighter and the saturation may be reduced. The lower limit of HSV is set to (87, 135, average brightness - 5), and the upper limit is set to (160, 180, 255). By limiting the saturation upper limit to 180, we avoid color distortion caused by excessive brightness from interfering with area extraction. At the same time, the lower limit of brightness is still adjusted according to the average brightness to ensure that the range of the blue preset marker can still be accurately defined under strong light.

[0072] In cases of low average brightness: If the average brightness does not meet the above conditions, i.e., in a low-light environment, the preset marker color is darker. In this case, a fixed HSV lower limit of (90, 150, 50) and an upper limit of (150, 255, 255) are used as the threshold range. In this embodiment of the invention, this set of thresholds is derived from a large amount of image data testing under low-light conditions, which can effectively overcome the influence of low light on the preset marker color and accurately segment the target area.

[0073] The method of dynamically adjusting the threshold in the embodiments of the present invention has at least the following beneficial effects:

[0074] 1. Improved Segmentation Accuracy: By dynamically adjusting the threshold range, the segmentation of the preset marker area closely matches its actual color performance under different lighting conditions, avoiding missed or false detections due to changes in lighting, and greatly improving the accuracy of preset marker area extraction. For example, under medium lighting conditions, a traditional fixed threshold may miss some slightly darker edge areas of the preset marker, while dynamic threshold adjustment can extract them completely.

[0075] 2. Enhanced environmental adaptability: The method of this invention fully considers the influence of light intensity on image color. Whether in strong light, medium light or low light environment, it can achieve accurate segmentation of the preset marker area through reasonable threshold setting, which significantly enhances the adaptability of the real-time spatial alignment determination method for large and complex workpieces in different environments, ensures the reliability and stability of alignment detection results, and provides a guarantee for the high-precision installation and real-time monitoring of large and complex workpieces.

[0076] This configuration, by dynamically adjusting the threshold range, improves the adaptability of the method in this embodiment of the invention to different lighting environments, ensuring the accuracy of the segmentation of the preset marker area. Accurate calculation of the central region provides precise positional coordinates for subsequent offset calculations, improving detection precision.

[0077] Step S6: Using the known correspondence between the actual size of the preset marker and the pixel size in the image, and the preset central baseline position information, calculate the offset of the preset marker relative to the central baseline, and obtain the position information of the corresponding preset marker on the first main beam, the second main beam, and the two secondary beams. Based on the obtained position information, determine whether the first main beam and the second main beam, and the two secondary beams are aligned.

[0078] In the installation and use of large and complex workpieces, ensuring precise alignment between key components (such as the main beam and secondary beams of a crane) is crucial for guaranteeing the safe and stable operation of the equipment and maximizing its design performance. In this embodiment of the invention, the alignment status of the first and second main beams and the two secondary beams is accurately determined by quantifying the offset of each preset marker relative to the central baseline. Furthermore, when misalignment is detected, the offset information provides clear direction and data support for subsequent adjustments, thereby improving the efficiency and quality of workpiece installation and maintenance, and reducing safety hazards and equipment failure risks caused by component misalignment.

[0079] Specifically, in this embodiment of the invention, the use of the known correspondence between the actual size of a preset marker and the pixel size in the image, and the preset central baseline position information, includes:

[0080] If the offset of each preset marker relative to the central baseline is within the allowable error range, it indicates that the first main beam is aligned with the second main beam and the two secondary beams respectively.

[0081] If the offset of each preset marker relative to the central baseline exceeds the allowable error range, it indicates that the first main beam, the second main beam, and the two secondary beams are not aligned. At the same time, based on the offset direction and amount, the adjustment direction of the misaligned main beam or secondary beam is determined, and the corresponding movement is performed.

[0082] It should be noted that the central baseline is an ideal alignment reference line pre-set based on the workpiece design requirements, representing the ideal positional relationship of each beam. The central baseline serves as a reference line for judging whether each beam is aligned. It is pre-set in the crane's design drawings or actual structure. In this embodiment of the invention, it is only used as a reference to determine whether the main beam and secondary beam of the crane are aligned, and its specific setting method is not described or studied.

[0083] Furthermore, it can be considered that once the preset markers are determined, their actual size is known and fixed. Calibration can determine the ratio between the pixel size in the image and the actual size (i.e., pixel resolution). In practical applications, based on the coordinates of the preset markers' center region in the image, combined with the pixel resolution, they can be converted into actual physical coordinates. By calculating the offset of the physical coordinates of the preset markers on each beam relative to the central baseline, the positional information of each beam can be obtained. If the offset of the preset markers on the first and second main beams relative to the central baseline is within the allowable error range, it indicates that the two main beams are aligned; similarly, the alignment of the two secondary beams can be determined.

[0084] Specifically, in this embodiment of the invention, the correspondence between the actual size of the preset marker and the pixel size in the image (i.e., pixel resolution) is determined through prior system calibration, establishing a connection between the image space and the actual physical space. By calculating the coordinates of the center region of the preset marker in the image and converting them to actual physical coordinates using pixel resolution, the actual physical coordinates of the preset markers on each beam are compared with the coordinates of the central baseline; the difference obtained is the offset. Setting an allowable error range takes into account unavoidable minor deviations during actual manufacturing, installation, and testing. If the offset is within the allowable error range, it indicates that the beam position is within acceptable accuracy, meaning the first main beam, the second main beam, and the two secondary beams are aligned; otherwise, it is determined to be misaligned.

[0085] When the offset exceeds the allowable error range, the offset direction (e.g., horizontally to the left or right, vertically upward or downward, etc.) directly reflects the deviation trend of the misaligned beam relative to the ideal position. The magnitude of the offset reflects the degree of deviation. In this embodiment of the invention, based on this information, combined with the structural characteristics of the beam and the working principle of the adjustment mechanism, the specific adjustment direction of the misaligned main beam or secondary beam can be determined.

[0086] It should also be noted that the allowable error range in the embodiments of the present invention is set according to actual needs, so that when determining the offset according to the allowable error range, the aligned devices can be accurately aligned without affecting the accuracy of the devices, and the safety of the devices can be guaranteed.

[0087] For example, if the preset marker on the first main beam is offset to the right by a certain distance in the horizontal direction relative to the central baseline, in order to achieve alignment, the first main beam needs to be moved to the left by a corresponding distance. It can be understood that the greater the offset, the greater the distance that needs to be moved, so as to gradually reduce the gap with the ideal position and achieve precise alignment of the beam.

[0088] Therefore, the method described in this embodiment of the invention enables rapid and accurate determination of whether the first main beam, the second main beam, and the two secondary beams are aligned, through a clear offset judgment standard and allowable error range setting. This avoids the subjectivity and ambiguity of manual judgment, greatly improving the accuracy and reliability of alignment detection results and providing a scientific and objective basis for workpiece installation, acceptance, and daily maintenance. Simultaneously, based on the adjustment direction suggestions given by the offset direction and amount, operators can quickly formulate targeted adjustment plans, avoiding blind adjustments and significantly improving the efficiency of adjustment work. Furthermore, precise offset data ensures the accuracy of adjustments, reduces the number of repeated adjustments, lowers labor and time costs, helps to quickly restore the workpiece to its normal operating state, and ensures the continuity of production operations. In addition, it can promptly detect and correct beam misalignment problems, effectively avoiding potential risks such as uneven stress and increased vibration caused by component misalignment, significantly improving the safety and stability of large and complex workpiece operation, extending equipment lifespan, and reducing the probability of equipment failure and safety accidents, thus possessing significant economic and safety value.

[0089] With this configuration, in this embodiment of the invention, by converting the pixel coordinates in the image into actual physical coordinates, accurate measurement of the position of each beam can be achieved. Simultaneously, based on the offset calculation of the central baseline, the alignment between each beam can be intuitively determined, providing an accurate basis for the installation, commissioning, and maintenance of the crane.

[0090] Secondly, such as Figure 2 As shown, this embodiment of the invention also provides a real-time spatial alignment determination system for large and complex workpieces, used for alignment between main beams and between secondary beams of a crane. The system includes: an identification module 10, an image acquisition and filtering module 20, an image conversion module 30, an image processing module 40, a calculation and analysis module, and a determination module 50, wherein:

[0091] The marking module 10 is used to set a preset marker 100 at a preset position of the crane, wherein the preset position includes the first main beam, the second main beam and two auxiliary beams of the crane, and the preset marker 100 includes a target device.

[0092] The image acquisition and filtering module 20 is used to acquire images of the preset marker 100 in real time, filter the acquired images, and obtain clear and complete images of the preset marker 100. The image conversion module 30 is used to convert the acquired images using a color space conversion algorithm to obtain an HSV color space image. The image processing module 40 is used to perform noise reduction processing on the HSV color space image using a noise reduction algorithm to obtain a preprocessed image. The calculation and analysis module is used to extract V channel information from the obtained preprocessed image through the HSV color space, calculate the average brightness of the corresponding color of the V channel and dynamically adjust the threshold range of the corresponding color of the V channel, segment the region of the preset marker 100 according to the threshold range, and calculate the central region of the preset marker 100 through a geometric algorithm. The judgment module is used to calculate the offset of the preset marker 100 relative to the central baseline using the known correspondence between the actual size of the preset marker 100 and the pixel size in the image and the pre-set central baseline position information, to obtain the position information of the preset marker 100 on the first main beam, the second main beam and the two secondary beams, and to determine whether the first main beam and the second main beam and the two secondary beams are aligned based on the obtained position information.

[0093] Thirdly, such as Figure 3 As shown, this embodiment of the invention also provides a determination device for applying the above-mentioned real-time spatial alignment determination method for large and complex workpieces, used for alignment between main beams and between secondary beams of a crane. The device includes: a preset marker 100, an image acquisition device 200, and a control module 300, wherein:

[0094] Preset markers 100 are installed on the main beam and secondary beam of the crane; image acquisition device 200 is installed outside the crane, and the range of the image acquired by image acquisition device 200 completely covers the preset markers 100 on the main beam and secondary beam, so that clear images can be acquired when the preset markers 100 are at any angle on the main beam or secondary beam of the crane; the control module 300 is pre-set with a color space conversion algorithm and a noise reduction algorithm, which are used to convert the image acquired by image acquisition device 200 to obtain an HSV color space image using the color space conversion algorithm, and to perform noise reduction processing on the HSV color space image using the noise reduction algorithm to obtain a preprocessed image. At the same time, the control module 300 can also process the obtained image. The preprocessed image extracts V channel information through the HSV color space, calculates the average brightness of the corresponding color in the V channel, and dynamically adjusts the threshold range of the corresponding color in the V channel. Based on the threshold range, the region of the preset marker 100 is segmented, and the central region of the preset marker 100 is calculated through a geometric algorithm. Using the known correspondence between the actual size of the preset marker 100 and the pixel size in the image, as well as the pre-set central baseline position information, the offset of the preset marker 100 relative to the central baseline is calculated to obtain the position information of the preset marker 100 on the first main beam, the second main beam, and the two secondary beams. Based on the obtained position information, it is determined whether the first main beam and the second main beam, and the two secondary beams are aligned.

[0095] In some optional implementations of this embodiment, the preset marker 100 includes a circular target of a specific color. Preferably, the specific color is set to a blue circular target.

[0096] Because the target device has obvious geometric features and is easily identifiable, it is placed at predetermined positions on each beam as the target object for subsequent image detection. By setting target devices on each beam, clear detection markers can be provided for image acquisition and processing, facilitating the subsequent extraction and analysis of the positional information of each beam. This setup, with clear predetermined markers 100, makes subsequent image acquisition and processing more targeted, avoiding direct detection of complex beam structures, simplifying the detection process, and improving the feasibility of detection.

[0097] In some optional implementations of this embodiment, the image acquisition device 200 includes one or more of a camera, digital camera, scanner, industrial camera, image acquisition card, light source device, and adjustable image acquisition device 200. It is understood that, in addition to the optional devices mentioned above, the embodiments of the present invention also include the control module 300, light source device, and storage device corresponding to the acquisition device, etc. In the embodiments of the present invention, these are only illustrative examples and are not the only limitations thereof.

[0098] In addition, to facilitate users in adjusting the parameters of the image acquisition device 200 according to actual lighting conditions, and to set the on / off buttons and working status of the image acquisition device 200, and to display the alignment status, adjustment direction, and actual distance between each main beam and secondary beam in real time, providing intuitive information for operators, an interactive module 400 is also provided on a large and complex workpiece spatial alignment real-time determination device according to an embodiment of the present invention. The interactive module 400 is connected to the preset marker 100, the image acquisition device 200, and the control module 300, and a display interface 401 is provided on the interactive module 400 so that the actual status of the preset marker 100 on the main beam and secondary beam can be displayed through the display interface 401, and adjustment buttons for the exposure parameters and gain parameters required by the image acquisition device 200 are provided.

[0099] Therefore, the real-time spatial alignment determination method, system, and apparatus for large and complex workpieces of the present invention have the following technical advantages compared with the prior art:

[0100] 1. Improve detection accuracy: Through steps such as color space conversion, noise reduction processing, dynamic threshold segmentation, and geometric algorithm calculation of the center area, the accuracy of extracting the position information of the preset markers is effectively improved, thereby accurately judging the alignment of the beam.

[0101] 2. Adaptability to different environments: The method of dynamically adjusting the threshold range of the V channel enables the detection process to adapt to different lighting conditions, thus improving the environmental adaptability of the method.

[0102] 3. Real-time detection: Real-time image acquisition and processing enables the acquisition of beam position information in real time, facilitating the timely detection and resolution of beam alignment issues, and improving the safety and reliability of crane operation.

[0103] 4. Automated inspection: It reduces the workload of manual inspection, automates the inspection process, improves inspection efficiency, and reduces inspection costs.

[0104] In summary, this invention provides a real-time spatial alignment determination method, system, and device for large and complex workpieces. It boasts advantages such as high detection accuracy, strong environmental adaptability, good real-time performance, and high automation, effectively addressing the problems of existing detection methods. Compared to existing technologies, for example, the multi-view vision alignment system proposed in patent ZLCN20181034567.X attempts to solve large-size detection problems, but its fixed camera array scheme is difficult to adapt to the dynamic detection needs of mobile hoisting equipment in workshops. While the laser-assisted vision method disclosed in US20210063215A1 improves detection accuracy in some scenarios, its complex opto-mechatronics integrated system increases deployment costs by more than 300%, and reduces maintenance cycles to one-third of conventional systems. These technical deficiencies severely restrict the practical application value of visual inspection technology in industrial settings. The embodiments of this invention, however, possess a spatial alignment determination method with strong environmental adaptability, high-precision real-time processing capabilities, and strong scalability, breaking through existing technological bottlenecks and showing promising application prospects.

[0105] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Additionally, the terms "front," "back," "left," "right," "upper," and "lower" in this document refer to the placement shown in the accompanying drawings.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A real-time spatial alignment determination method for large and complex workpieces, characterized in that, The method for aligning main beams and secondary beams of a crane includes: Pre-set markers are installed at predetermined locations on the crane, wherein the predetermined locations include the crane's first main beam, second main beam, and two auxiliary beams, and the predetermined markers include target devices; Images of the preset markers are acquired in real time, and the acquired images are filtered to obtain clear and complete images of the preset markers; The acquired images are converted using a color space conversion algorithm to obtain HSV color space images; A noise reduction algorithm is applied to the HSV color space image to obtain a preprocessed image. The V channel information of the obtained preprocessed image is extracted through the HSV color space, the average brightness of the corresponding color of the V channel is calculated and the threshold range of the corresponding color of the V channel is dynamically adjusted, the region of the preset marker is segmented according to the threshold range, and the center region of the preset marker is calculated through a geometric algorithm. Using the known correspondence between the actual size of the preset marker and the pixel size in the image, and the pre-set central baseline position information, the offset of the preset marker relative to the central baseline is calculated to obtain the position information of the corresponding preset marker on the first main beam, the second main beam, and the two secondary beams. Based on the obtained position information, it is determined whether the first main beam and the second main beam, and the two secondary beams are aligned.

2. The method for real-time spatial alignment determination of large and complex workpieces according to claim 1, characterized in that, The target device includes a circular target of a specific color.

3. The method for real-time spatial alignment determination of large and complex workpieces according to claim 2, characterized in that, The specific color includes blue.

4. The method for real-time spatial alignment determination of large and complex workpieces according to claim 1, characterized in that, The preprocessed image is processed by extracting the V channel information using the HSV color space. The average brightness of the corresponding color in the V channel is calculated, and the threshold range for the corresponding color in the V channel is dynamically adjusted, including: If the average brightness is greater than 110 and less than or equal to 145, then set the lower limit of HSV to (87, the value of average brightness - 5, the value of average brightness - 25), set the upper limit to (160, 255, 255), and extract the blue area to the mask. If the average brightness is greater than 145, then set the lower limit of HSV to (87, 135, the value of average brightness - 5) and the upper limit to (160, 180, 255). If the average brightness does not meet the above conditions, it is considered low brightness, and a threshold range with a lower limit of HSV (90, 150, 50) and an upper limit of HSV (150, 255, 255) is used.

5. The method for real-time spatial alignment determination of large and complex workpieces according to claim 1, characterized in that, The known correspondence between the actual size of preset markers and the pixel size in the image, along with pre-defined central baseline position information, includes: If the offset of each preset marker relative to the central baseline is within the allowable error range, it indicates that the first main beam is aligned with the second main beam and the two secondary beams respectively. If the offset of each preset marker relative to the central baseline exceeds the allowable error range, it indicates that the first main beam, the second main beam, and the two secondary beams are not aligned. At the same time, based on the offset direction and amount, the adjustment direction of the misaligned main beam or secondary beam is determined, and the corresponding movement is performed.

6. A real-time spatial alignment determination system for large and complex workpieces, characterized in that, The system is used for alignment between main beams and between secondary beams of a crane, and includes: The marking module is used to set a preset marker at a preset position of the crane, wherein the preset position includes the first main beam, the second main beam and two auxiliary beams of the crane, and the preset marker includes a target device. The image acquisition and filtering module is used to acquire images of the preset markers in real time, filter the acquired images, and obtain clear and complete images of the preset markers. An image conversion module is used to convert the acquired image using a color space conversion algorithm to obtain an HSV color space image; The image processing module is used to perform noise reduction processing on the HSV color space image using a noise reduction algorithm to obtain a preprocessed image; The calculation and analysis module is used to extract V channel information from the obtained preprocessed image through the HSV color space, calculate the average brightness of the color corresponding to the V channel and dynamically adjust the threshold range of the color corresponding to the V channel, segment the region of the preset marker according to the threshold range, and calculate the center region of the preset marker through a geometric algorithm. The determination module is used to calculate the offset of the preset marker relative to the central baseline by using the known correspondence between the actual size of the preset marker and the pixel size in the image and the preset central baseline position information, to obtain the position information of the corresponding preset marker on the first main beam, the second main beam and the two secondary beams, and to determine whether the first main beam and the second main beam and the two secondary beams are aligned based on the obtained position information.

7. A determination device for applying the real-time spatial alignment determination method for large and complex workpieces according to any one of claims 1-5, characterized in that, The device for aligning main beams and secondary beams of a crane, comprising: Pre-set markers are installed on the main beam and secondary beam of the crane; An image acquisition device is installed outside the crane. The range of the image acquired by the image acquisition device completely covers the preset markers on the main beam and the secondary beam, so that the image can be clearly acquired when the preset markers are at any angle on the main beam or the secondary beam of the crane. The control module is pre-configured with a color space conversion algorithm and a noise reduction algorithm. The color space conversion algorithm converts the image acquired by the image acquisition device to obtain an HSV color space image, and the noise reduction algorithm is used to denoise the HSV color space image to obtain a pre-processed image. Simultaneously, the control module can extract V channel information from the obtained pre-processed image using the HSV color space, calculate the average brightness of the corresponding color in the V channel, dynamically adjust the threshold range of the corresponding color in the V channel, segment the region of the preset marker according to the threshold range, calculate the center region of the preset marker using a geometric algorithm, and calculate the offset of the preset marker relative to the central baseline using the known correspondence between the actual size of the preset marker and the pixel size in the image, as well as the pre-set central baseline position information. This yields the position information of the corresponding preset markers on the first main beam, the second main beam, and the two secondary beams. Based on the obtained position information, it determines whether the first and second main beams and the two secondary beams are aligned.

8. The determining device according to claim 7, characterized in that, The preset markers include circular targets of a specific color.

9. The determining device according to claim 7, characterized in that, The image acquisition device includes one or more of the following: camera, digital camera, scanner, industrial camera, image acquisition card, light source device, and adjustable image acquisition device.

10. The determining device according to any one of claims 7-9, characterized in that, It also includes an interactive module with a display interface that allows the display of the actual status of preset markers on the main beam and secondary beam. The display interface provides adjustment buttons for the exposure and gain parameters required by the image acquisition device, allowing users to adjust the parameters of the image acquisition device according to actual lighting conditions. It also sets the power button and working status of the image acquisition device, and displays the alignment status, adjustment direction, and actual distance between each main beam and secondary beam in real time, providing intuitive information for operators.

Images