An automated modeling method based on spatial perception intelligent fusion

Abstract

The application relates to an automatic modeling method based on spatial perception intelligent fusion, and relates to the technical field of spatial modeling.The method comprises the following steps: collecting laser detection information and image detection information; based on the laser detection information, calling laser point cloud data corresponding to each detection position point; generating a laser space contour according to the laser point cloud data; combining the laser point cloud data and the image detection information to generate spatial image information; combining the laser space contour and the spatial image information to generate modeling comprehensive information; based on the modeling comprehensive information, performing modeling to generate modeling result information, and outputting the modeling result information.The application has the effect of improving the spatial modeling precision.

Description

Technical Field

[0001] This invention relates to the field of spatial modeling technology, and in particular to an automated modeling method based on spatial perception intelligent fusion. Background Technology

[0002] Spatial modeling refers to the techniques and methods used to construct abstract models based on geospatial data through mathematical, geometric, logical, or statistical methods to describe, analyze, simulate, or predict the morphology, distribution, relationships, and dynamic changes of geospatial entities. It is widely used in fields such as Geographic Information Science (GIS), remote sensing, urban planning, and environmental science.

[0003] Currently, when renovating a home, the dimensions of the room, such as length, width, height, wall thickness, and the size of door and window openings, are generally measured manually to obtain spatial dimension data. This data is then processed to create a spatial model.

[0004] Since spatial dimension data is currently generally acquired through manual measurement, manual measurement is easily affected by human factors such as reading deviation and improper measurement angle, resulting in low acquisition accuracy and consequently insufficient accuracy in spatial modeling. Summary of the Invention

[0005] To improve the accuracy of spatial modeling, this invention provides an automated modeling method based on spatial perception intelligent fusion.

[0006] This invention provides an automated modeling method based on spatial perception intelligent fusion, employing the following technical solution:

[0007] An automated modeling method based on spatial perception intelligent fusion includes:

[0008] S1: Acquire laser detection information and image detection information;

[0009] S2: Retrieve laser point cloud data corresponding to each detection location point based on laser detection information;

[0010] S3: Generate laser spatial contour based on laser point cloud data;

[0011] S4: Generate spatial image information by combining laser point cloud data and image detection information;

[0012] S5: Generate comprehensive modeling information by combining laser spatial contour and spatial image information;

[0013] S6: Model based on the comprehensive modeling information to generate modeling result information, and output the modeling result information.

[0014] By adopting the above technical solution, laser detection information and image detection information are collected sequentially, laser point cloud data is retrieved to generate laser spatial contours, and laser point cloud data and image detection information are fused to form spatial image information. Then, based on the laser spatial contours and spatial image information, comprehensive modeling information is generated and the modeling output is completed. This achieves the synergistic linkage of laser detection and image detection, giving full play to the complementary advantages of the two types of detection information, effectively improving the completeness and accuracy of the comprehensive modeling information, ensuring that the modeling results can comprehensively and accurately reflect the spatial features of the target, avoiding modeling deviations caused by single detection information, and improving the accuracy of spatial modeling.

[0015] Optionally, methods for generating spatial image information include:

[0016] S41: Retrieve single-position image information corresponding to each detection position point based on image detection information;

[0017] S42: Perform image recognition based on single-location image information to obtain the single-location image type;

[0018] S43: Determine the detection distance value corresponding to each detection location point based on the laser point cloud data;

[0019] S44: Calculate the ratio of adjacent detection distance values ​​and use it as the adjacent distance ratio;

[0020] S45: Based on the ratio of adjacent distances and the type of single-location image, combine the single-location image information to form comprehensive image information, and use the comprehensive image information as spatial image information.

[0021] By adopting the above technical solution, single-location image information is retrieved and the type of single-location image is identified. The adjacent distance ratio is calculated by combining the detection distance value determined by the laser point cloud data. Then, the single-location image information is combined to form spatial image information, thereby effectively correcting the distortion problem in the image acquisition process, improving the adaptability of spatial image information to the actual space, and providing high-quality image data support for the generation of subsequent modeling and comprehensive information.

[0022] Optionally, methods for forming image synthesis information include:

[0023] S451: Adjust the single-position image information according to the adjacent distance ratio to obtain the proportionally adjusted image information;

[0024] S452: Based on the type of single-location image, adjust the proportion of image information to extract the image information to obtain the image of the same type of region and the remaining region image;

[0025] S453: Retrieve the actual brightness value of the image based on images of the same type of region;

[0026] S454: Select images of the same type based on the actual brightness value of the image and use them as the selected area images;

[0027] S455: Combine the selected region image with the remaining region image and use it as comprehensive image information.

[0028] By adopting the above technical solution, the image information of a single location is adjusted by adjusting the adjacent distance ratio to obtain the proportional adjustment image information. After extracting the images of the same type of region and the remaining region images, the selected region images are selected based on the actual brightness value of the images and combined with the remaining region images to form comprehensive image information. This achieves accurate screening and optimization of image information, ensures the brightness consistency and effectiveness of the images of the same type of region in the comprehensive image information, eliminates invalid or poor quality image parts, improves the clarity and reliability of spatial image information, and lays a high-quality image foundation for the generation of comprehensive modeling information.

[0029] Optionally, the methods for selecting the region image include:

[0030] S4541: Collect ambient light levels;

[0031] S4542: Determine the image reference brightness value by combining the ambient light value and the detection distance value;

[0032] S4543: Determine whether the actual brightness values ​​of the image are all greater than the reference brightness values ​​of the image;

[0033] S4544: If yes, calculate the difference between the actual brightness value of the image and the reference brightness value of the image and use it as the brightness deviation value;

[0034] S4545: Combine the brightness deviation value with the type of image at a single location to determine the reference value for deviation selection;

[0035] S4546: Select the image of the same type of region corresponding to the larger value of the reference value of the deviation and use it as the selected region image;

[0036] S4547: If not, select the region image of the same type corresponding to the larger value of the actual brightness value of the image and use it as the selected region image.

[0037] By adopting the above technical solution, ambient light values ​​are collected, and a reference brightness value for the image is determined by combining the ambient light value with the detection distance value. The deviation is calculated by judging whether the actual brightness value of the image is greater than the reference brightness value, and a reference value is selected before selection, or the image of the same type with higher brightness is directly selected. This makes the selection of the selected area image adapt to the actual situation of ambient light and detection distance, avoids image quality problems caused by excessively strong or weak light, and ensures that the selected area image can accurately reflect the image characteristics of the corresponding detection location point, thereby improving the quality and adaptability of spatial image information.

[0038] Optionally, methods for determining the image reference brightness value include:

[0039] S45421: Equipment specifications for image acquisition devices;

[0040] S45422: Determine the appropriate brightness range based on the equipment specifications;

[0041] S45423: Determine the distance-illuminance influence coefficient based on the detected distance value;

[0042] S45424: Calculate the product between the ambient illuminance value and the illuminance influence coefficient and use it as the distance-adjusted luminance value;

[0043] S45425: Determine whether the distance adjustment brightness value is within the specified brightness range;

[0044] S45426: If yes, then use the distance-adjusted brightness value as the image reference brightness value;

[0045] S45427: If not, then the end value of the specification-adapted brightness range is selected based on the image reference brightness value and used as the image reference brightness value.

[0046] By adopting the above technical solution, the brightness range suitable for the specifications is determined by the specifications of the acquisition equipment, and the distance-adjusted brightness value is calculated by combining the ambient light value and the distance-light influence coefficient. The image reference brightness value is determined according to the relationship between the distance-adjusted brightness value and the brightness range suitable for the specifications. This ensures that the image reference brightness value matches the performance parameters of the image acquisition equipment and fully considers the influence of the detection distance on the light, providing a reliable basis for the accurate selection of the selected area image and further ensuring the accuracy of spatial image information.

[0047] Optionally, methods for determining the reference value for deviation selection include:

[0048] S45451: Determine the allowable range of type deviation based on the type of single-location image;

[0049] S45452: Determine whether the brightness deviation value falls within the allowable range of type deviation;

[0050] S45453: If yes, then determine the category deviation coefficient based on the category of the single-location image;

[0051] S45454: Calculate the product between the type deviation coefficient and the brightness deviation value and use it as a reference value for deviation selection;

[0052] S45455: If not, then select the endpoint of the allowable range of type deviation based on the brightness deviation value to obtain the range selection endpoint;

[0053] S45456: Calculate the ratio between the brightness deviation value and the selected range value, and use it as a reference value for deviation selection.

[0054] By adopting the above technical solution, the allowable range of deviation for a single-location image is determined, and it is determined whether the brightness deviation value falls within the range and the corresponding deviation selection reference value is calculated. This ensures that the determination of the deviation selection reference value conforms to the characteristic requirements of the single-location image type, avoids the problem of insufficient regional image adaptability caused by uniform standard selection, and ensures that the selected regional image meets both the brightness deviation requirements and the characteristics of the corresponding image type, thereby improving the relevance and effectiveness of spatial image information.

[0055] Optional methods for generating modeling and comprehensive information include:

[0056] S51: Determine the spatial contour and texture information of the image based on the spatial image information;

[0057] S52: Determine contour similarity by combining image spatial contour and laser spatial contour;

[0058] S53: Determine whether the contour similarity is greater than the preset contour similarity benchmark value;

[0059] S54: If yes, the image texture information is fused with the laser spatial contour to form a comprehensive modeling information;

[0060] S55: If not, then combine the image spatial contour and the laser spatial contour to determine the contour difference region and the contour consistency region;

[0061] S56: Based on the contour differentiation region, retrieve the differentiation region image and the neighboring region image from the spatial image information;

[0062] S57: Combine the images of the distinguishing regions, the images of neighboring regions, and the regions with consistent contours to generate distinguishing adjustment modeling information, and use the distinguishing adjustment modeling information as the comprehensive modeling information.

[0063] By adopting the above technical solution, the spatial contour and texture information of the image are determined through spatial image information. The contour similarity is calculated and processed according to different cases. When the similarity meets the standard, the image texture information and the laser spatial contour are fused. When the similarity does not meet the standard, the contour difference area and the contour consistency area are identified and the difference adjustment modeling information is generated. This realizes the intelligent adaptation and fusion of laser spatial contour and image spatial contour. It not only retains the geometric accuracy advantage of laser spatial contour, but also incorporates the rich details of image texture information, effectively solves the problem of inconsistency between the two types of contours, and improves the completeness and accuracy of the comprehensive modeling information.

[0064] Optional methods for generating differentiated modeling information include:

[0065] S571: The image texture information is fused with the contour-consistent region to obtain contour-consistent modeling information;

[0066] S572: Identify the types of distinct regions based on the images of distinct regions, and identify the types of neighboring regions based on the images of neighboring regions;

[0067] S573: Determine the species deviation value by combining the species in the distinguishing region with the species in the neighboring region;

[0068] S574: When the species deviation value is less than the preset species baseline deviation value, determine the species texture adjustment information based on the species in the neighboring area;

[0069] S575: Merge the type texture adjustment information with the contour differentiation region to obtain contour differentiation modeling information;

[0070] S576: Combine contour consistency modeling information with contour difference modeling information as the basis for adjusting the modeling information.

[0071] By adopting the above technical solution, when the type deviation value is small, the type texture adjustment information is determined based on the type of neighboring regions. This information is then fused with the contour difference region to form contour difference modeling information. Finally, the difference adjustment modeling information is generated by combining the contour consistency modeling information. This achieves texture coordination and adaptation between the contour difference region and the contour consistency region, avoids the breakage or incoordination of modeling information caused by contour differences, ensures the continuity and rationality of the difference adjustment modeling information, and improves the overall quality of the comprehensive modeling information.

[0072] Optionally, methods for generating differentiated modeling information also include:

[0073] S5741: When the type deviation value is not less than the preset type reference deviation value, determine the image distance value and laser distance value based on the image of the distinguishing region;

[0074] S5742: Determine whether the image distance value is greater than the laser distance value;

[0075] S5743: If yes, then the image texture information and the image spatial contour are fused to form distinguishable adjustment modeling information;

[0076] S5744: If not, retrieve the brightness value of the distinguishing image based on the distinguishing region image;

[0077] S5745: Determine the contour change area by combining the distinguishing region type, the distinguishing image brightness value, and the type deviation value;

[0078] S5746: Combine image texture information with contour variation areas and use it as distinguishing adjustment modeling information.

[0079] By adopting the above technical solution, when the type deviation value is large, the contour change area is determined by comparing the image distance value and the laser distance value, or by combining the type of the distinguishing region, the brightness value of the distinguishing image, and the type deviation value. The distinguishing adjustment modeling information is generated in a targeted manner, which realizes the accurate processing of different type deviation scenarios, effectively avoids the modeling distortion problem caused by excessive type deviation, ensures that the distinguishing adjustment modeling information can accurately reflect the actual characteristics of the target space, and further improves the reliability of the modeling result information.

[0080] In summary, the present invention has at least one of the following beneficial technical effects:

[0081] 1. By sequentially collecting laser detection information and image detection information, laser point cloud data is retrieved to generate a laser spatial contour. The laser point cloud data and image detection information are then fused to form spatial image information. Finally, based on the laser spatial contour and spatial image information, comprehensive modeling information is generated and the modeling output is completed. This achieves the synergistic linkage between laser detection and image detection, fully leverages the complementary advantages of the two types of detection information, effectively improves the completeness and accuracy of the comprehensive modeling information, ensures that the modeling results can comprehensively and accurately reflect the spatial features of the target, avoids modeling deviations caused by single detection information, and improves the accuracy of spatial modeling.

[0082] 2. By retrieving single-location image information and identifying the types of single-location images, and combining the detection distance value determined by the laser point cloud data to calculate the adjacent distance ratio, the single-location image information is combined to form spatial image information, thereby effectively correcting the distortion problem in the image acquisition process, improving the adaptability of spatial image information to the actual space, and providing high-quality image data support for the subsequent generation of comprehensive modeling information;

[0083] 3. By determining the spatial contour and texture information of the image through spatial image information, the contour similarity is calculated and processed according to different cases. When the similarity meets the standard, the image texture information and the laser spatial contour are fused. When the similarity does not meet the standard, the contour difference area and the contour consistency area are identified and the difference adjustment modeling information is generated. This realizes the intelligent adaptation and fusion of laser spatial contour and image spatial contour. It not only retains the geometric accuracy advantage of laser spatial contour, but also incorporates the rich details of image texture information, effectively solving the problem of inconsistency between the two types of contours and improving the completeness and accuracy of the comprehensive modeling information. Attached Figure Description

[0084] Figure 1 This is a flowchart of an automated modeling method based on spatial perception and intelligent fusion.

[0085] Figure 2 This is a flowchart of the method for generating spatial image information;

[0086] Figure 3 This is a flowchart of the method for generating comprehensive modeling information. Detailed Implementation

[0087] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments.

[0088] An automated modeling method based on spatial perception intelligent fusion first collects laser detection information and image detection information, generates a laser spatial contour from laser point cloud data, and optimizes the generation of spatial image information by combining detection distance, image type, brightness, equipment specifications, and ambient light values. Then, it fuses the laser spatial contour, image spatial contour, and texture information according to contour similarity, and performs adaptation processing on contour difference regions based on type deviation, distance, etc., to generate comprehensive modeling information and output the modeling result. This achieves the synergistic linkage of laser detection and image detection, improving the accuracy of spatial modeling.

[0089] Reference Figure 1 This invention discloses an automated modeling method based on spatial perception intelligent fusion, which includes:

[0090] S1: Acquire laser detection information and image detection information.

[0091] Laser detection information refers to the collection of data, including three-dimensional geometric position (such as X, Y, Z coordinates) and reflection intensity, obtained by actively emitting laser beams at different locations using laser acquisition equipment and then reflecting them off the surface of a target object. Image detection information refers to image information acquired at different locations using image acquisition equipment.

[0092] Laser acquisition devices can be handheld modeling devices, laser modules of depth-sensing cameras, etc. Image acquisition devices can be vision modules of depth-sensing cameras. Laser acquisition devices and image acquisition devices can be integrated into the same handheld device or into devices such as drones, thus facilitating simultaneous detection.

[0093] S2: Retrieve laser point cloud data corresponding to each detection location point based on laser detection information.

[0094] The detection location point refers to the specific sampling point corresponding to the laser acquisition device and image acquisition device during the scanning of the target space. Laser point cloud data refers to data such as geometric position and reflection intensity acquired by the laser acquisition device. Laser detection information includes the detection location point and the corresponding laser point cloud data.

[0095] The detection location point and laser point cloud data are retrieved through laser detection information for convenient subsequent use.

[0096] S3: Generate laser spatial contours based on laser point cloud data.

[0097] Among them, laser spatial profile refers to the three-dimensional geometric boundary shape of the target space and object formed based on laser acquisition.

[0098] After preprocessing the laser point cloud data by removing noise and filling in sparse areas, the point cloud data is divided into point cloud subsets corresponding to different objects / regions (such as point cloud groups for walls, furniture, and shelves) according to spatial continuity and reflection intensity differences using a point cloud segmentation algorithm. Then, edge extraction and contour fitting are performed on each point cloud subset to construct the three-dimensional boundary of the object, form a contour, and serve as the laser spatial contour.

[0099] S4: Combine laser point cloud data with image detection information to generate spatial image information.

[0100] Spatial image information refers to the set of image data of the entire target space.

[0101] Spatial image information is obtained by stitching together individual images from the image detection information based on laser point cloud data, which facilitates subsequent use.

[0102] To further ensure the rationality of spatial image information, it is necessary to perform further separate analysis and calculation on the spatial image information, which will be explained in detail through the following steps.

[0103] Reference Figure 2 The method for generating spatial image information includes the following steps:

[0104] S41: Retrieve single-position image information corresponding to each detection location point based on image detection information.

[0105] Here, single-location image information refers to the image information corresponding to each detection location point. Image detection information includes the detection location point and its corresponding single-location image information.

[0106] The image detection information is used to retrieve the single-location image information corresponding to the detection location point, which is convenient for subsequent use.

[0107] S42: Perform image recognition based on single-location image information to obtain single-location image types.

[0108] Among them, single-location image category refers to the category to which an object belongs in an image at a single detection location point.

[0109] By performing image recognition on single-location image information and using the identified item types as single-location image types, it is convenient for subsequent use.

[0110] S43: Determine the detection distance value corresponding to each detection location point based on the laser point cloud data.

[0111] The detection distance value refers to the distance between the spatial location detected by the laser and the detection location point.

[0112] The spatial location is retrieved by laser point cloud data, and the average distance between the location and the corresponding detection location is calculated as the detection distance value for subsequent use.

[0113] S44: Calculate the ratio of adjacent detection distance values ​​and use it as the adjacent distance ratio.

[0114] The adjacent distance ratio refers to the ratio between the detection distance values ​​corresponding to adjacent detection location points.

[0115] The ratio between the detection distance values ​​corresponding to adjacent detection locations is calculated, and the calculation result is used as the adjacent distance ratio for convenient subsequent use.

[0116] S45: Based on the ratio of adjacent distances and the type of single-location image, combine the single-location image information to form comprehensive image information, and use the comprehensive image information as spatial image information.

[0117] Image composite information refers to the image set data corresponding to the composite stitching of images from various locations.

[0118] By combining the ratio of adjacent distances with the types of single-location images, the individual images in the single-location image information are stitched together, and the stitched image is used as comprehensive image information. This comprehensive image information is then used as spatial image information, thereby improving the accuracy of the acquired spatial image information.

[0119] To further ensure the rationality of the image synthesis information, it is necessary to perform further separate analysis and calculation on the image synthesis information, which will be explained in detail through the following steps.

[0120] The method for forming image composite information includes the following steps:

[0121] S451: Adjust the image information at a single location based on the ratio of adjacent distances to obtain proportionally adjusted image information.

[0122] Among them, the scale-adjusted image information refers to the image information corresponding to the scale adjustment of the single-position image information.

[0123] By adjusting the image information at a single location according to the ratio of adjacent distances, proportionally adjusted image information with consistent image proportions is obtained, which facilitates subsequent use.

[0124] S452: Based on the image type at a single location, adjust the image information proportionally to extract the image information to obtain images of the same type of region and the remaining region images.

[0125] Among them, images of the same type of region refer to images of the corresponding region of the same single location (such as walls, doors and windows, shelves, goods, etc.). Remaining region images refer to the corresponding images remaining after removing images of the same type of region from the scaled image information.

[0126] By extracting images of the same type from the scaled image information according to the single-location image type, images of the same type of region are obtained, and the remaining images are used as the remaining region images for convenient subsequent use.

[0127] S453: Retrieve the actual brightness value of the image based on images of the same type of region.

[0128] The actual brightness value of an image refers to the quantized data of the true brightness of each pixel or region in an image of the same type.

[0129] The brightness conversion formula is used to calculate the brightness value of each pixel in the same type of image region, and then the average brightness of the region is calculated as the actual brightness value of the image. The brightness conversion formula is existing technology and will not be described in detail.

[0130] S454: Select images of the same type based on the actual brightness value of the image and use them as the selected area images.

[0131] Among them, the selected region image refers to the image corresponding to the selected region images of the same type.

[0132] By selecting images of the same type of region according to their actual brightness values, and using the selected images as the selected region images, it is convenient for subsequent use.

[0133] To further ensure the rationality of the selected region image, it is necessary to perform further separate analysis and calculation on the selected region image, which will be explained in detail through the steps shown below.

[0134] The method for selecting a region of image includes the following steps:

[0135] S4541: Collect ambient light levels.

[0136] Among them, ambient light value refers to the quantitative data of the actual light intensity existing in the environment of the target space.

[0137] Ambient light levels are obtained by detecting light sensors pre-installed on laser acquisition devices or image acquisition devices.

[0138] S4542: Determine the image reference brightness value by combining the ambient light value and the detection distance value.

[0139] Among them, the image reference brightness value refers to the reference standard used to judge whether the brightness of images in the same type of area meets the standard.

[0140] By combining and analyzing ambient light values ​​and detection distance values, a baseline brightness value for the image can be determined, facilitating subsequent use.

[0141] To further ensure the rationality of the image reference brightness value, it is necessary to perform a further separate analysis and calculation on the image reference brightness value, which will be explained in detail through the steps shown below.

[0142] The method for determining the reference brightness value of an image includes the following steps:

[0143] S45421: Equipment specifications for image acquisition devices.

[0144] Among them, equipment specifications refer to the set of core technical parameters of image acquisition equipment. Equipment specifications include sensor size, ISO range, aperture size, exposure time adjustment range, image resolution, supported image formats, etc.

[0145] Equipment specifications can be obtained by pre-entering them by the operator, or by querying the nameplate or built-in storage data of the image acquisition device.

[0146] S45422: Determine the appropriate brightness range based on the equipment specifications.

[0147] Among them, the specification adaptation brightness range refers to the range of brightness values ​​that allow the image acquisition device to stably acquire clear, low-noise images without overexposure or underexposure.

[0148] By inputting the device specifications into a preset specification database, a suitable brightness range can be obtained, which facilitates subsequent use.

[0149] The specification database pre-stores a table of different equipment specifications and their corresponding brightness ranges. The specification database is obtained by the operator after querying the manufacturer's technical manual for different equipment specifications and inputting the information.

[0150] S45423: Determine the distance-illuminance influence coefficient based on the detection distance value.

[0151] Among them, the distance-lighting influence coefficient refers to the dimensionless coefficient that quantifies the effect of the detection distance value on the attenuation effect of ambient light intensity.

[0152] By inputting the detected distance value into a preset distance illumination influence database, a distance illumination influence coefficient is obtained for convenient subsequent use.

[0153] The distance-light-influence database pre-stores a table of different detection distance values ​​and their corresponding distance-light-influence coefficients. The distance-light-influence database is obtained by the operator detecting the actual light value at different detection distances and calculating the coefficient between it and the preset theoretical output light value.

[0154] S45424: Calculate the product of ambient light value and light influence coefficient and use it as the distance-adjusted brightness value.

[0155] Among them, the distance-adjusted brightness value refers to the brightness value corresponding to the attenuation of light intensity after the detected distance value.

[0156] The product of ambient light value and light influence coefficient is calculated, and the result is used as the distance adjustment brightness value for convenient subsequent use.

[0157] S45425: Determine whether the distance adjustment brightness value is within the specified brightness range. If yes, proceed to S45426; if no, proceed to S45427.

[0158] Specifically, the system determines whether the distance-adjusted brightness value can be directly used by judging whether it falls within the specified brightness range.

[0159] S45426: Use the distance-adjusted brightness value as the image reference brightness value.

[0160] When the distance adjustment brightness value is within the specified brightness range, it means that the distance adjustment brightness value can be used directly. Therefore, the distance adjustment brightness value is used as the image reference brightness value to improve the accuracy of the obtained image reference brightness value.

[0161] S45427: Select the end value of the specification-adaptive brightness range based on the image reference brightness value and use it as the image reference brightness value.

[0162] When the distance adjustment brightness value is not within the specified brightness range, it means that the distance adjustment brightness value cannot be used directly. Therefore, the difference between the two extreme values ​​of the specified brightness range and the image reference brightness value is calculated, and the extreme value with the smaller difference is selected as the image reference brightness value for convenient use later.

[0163] S4543: Determine whether the actual brightness values ​​of the image are all greater than the image reference brightness values. If yes, proceed to S4544; if no, proceed to S4547.

[0164] Specifically, the method involves determining whether the actual brightness value of the image is greater than the reference brightness value, thereby determining whether the image can be selected directly based on its brightness.

[0165] S4544: Calculate the difference between the actual brightness value of the image and the reference brightness value of the image, and use it as the brightness deviation value.

[0166] Among them, the brightness deviation value refers to the deviation value corresponding to the existence of a brightness deviation.

[0167] When the actual brightness value of the image is greater than the reference brightness value, it means that the selection cannot be made directly based on the brightness. Therefore, the difference between the actual brightness value and the reference brightness value is calculated and the result is used as the brightness deviation value for subsequent use.

[0168] S4545: Combine the brightness deviation value with the type of image at a single location to determine the reference value for deviation selection.

[0169] Among them, the deviation selection reference value refers to the reference value corresponding to the selection based on brightness and type.

[0170] By combining the brightness deviation value with the type of image at a single location, a reference value for deviation selection can be determined to facilitate subsequent use.

[0171] To further ensure the rationality of the selected reference value for deviation, it is necessary to perform a further separate analysis and calculation on the selected reference value for deviation, which will be explained in detail through the steps shown below.

[0172] The method for determining the reference value for deviation includes the following steps:

[0173] S45451: Determine the allowable range of type deviation based on the type of single-location image.

[0174] Among them, the permissible range of type deviation refers to the pre-defined allowable range of brightness deviation for a specific single-location image type (such as wall, glass, furniture, shelf, etc.).

[0175] By inputting the single-location image type into a preset type database to obtain the allowable range of type deviation, it is convenient for subsequent use.

[0176] The category database pre-stores a table of different single-location image categories and their corresponding allowable deviation ranges. The category database is obtained by the operator after combining industry modeling accuracy standards and statistical analysis of reasonable deviation ranges from a large number of data collection experiments.

[0177] For example, the category database can be set such that the category deviation tolerance range is [-20, +20] when the single-location image category is wall, [-50, +50] when the single-location image category is glass, and [-30, +30] when the single-location image category is decorative painting.

[0178] S45452: Determine whether the brightness deviation value falls within the allowable range of the type deviation. If yes, proceed to S45453; if no, proceed to S45455.

[0179] Among them, by judging whether the brightness deviation value falls within the allowable range of the type deviation, different methods are selected to determine the reference value for the deviation.

[0180] S45453: Determine the type deviation coefficient based on the type of single-location image.

[0181] The category deviation coefficient refers to a dimensionless weighted coefficient set for a specific single-location image category (such as wall, glass, shelf, goods, etc.). Different single-location image categories have different reflective characteristics, and therefore the corresponding images have different sensitivities to brightness deviations. Thus, different single-location image categories correspond to different category deviation coefficients.

[0182] When the brightness deviation value falls within the allowable range of category deviation, the category deviation coefficient is obtained by inputting the single-location image category into the preset category database for matching, which is convenient for subsequent use.

[0183] The category database pre-stores a table of different single-position image categories and their corresponding category deviation coefficients. The category database is pre-set by the operator according to their needs.

[0184] For example, the category deviation coefficient is 1.3 when the single-position image type is wall, 1.0 when the single-position image type is glass, and 0.7 when the single-position image type is decorative painting.

[0185] S45454: Calculate the product between the type deviation coefficient and the brightness deviation value and use it as a reference value for deviation selection.

[0186] In this process, the product between the type deviation coefficient and the brightness deviation value is calculated, and the calculation result is used as a reference value for deviation selection, thereby improving the accuracy of the obtained deviation selection reference value.

[0187] S45455: Based on the brightness deviation value, the end value of the allowable range of type deviation is selected to obtain the range selection end value.

[0188] Among them, the selected endpoint value refers to the endpoint value corresponding to the selected endpoint value of the allowable range of type deviation.

[0189] When the brightness deviation value does not fall within the allowable range of category deviation, the difference between the two endpoints of the allowable range of category deviation and the brightness deviation value is calculated, and the endpoint corresponding to the smaller value of the difference is selected as the endpoint of the range selection for convenient subsequent use.

[0190] S45456: Calculate the ratio between the brightness deviation value and the selected range value, and use it as a reference value for deviation selection.

[0191] Specifically, by calculating the ratio between the brightness deviation value and the selected range value, and using the calculation result as the deviation selection reference value, the accuracy of the obtained deviation selection reference value is improved.

[0192] S4546: Select the image of the same type of region corresponding to the larger value of the deviation reference value and use it as the selected region image.

[0193] Specifically, by selecting images of the same type corresponding to the larger value of the deviation reference value, and using the selected images as the selected region images, the accuracy of the obtained selected region images is improved.

[0194] S4547: Select the region image of the same type corresponding to the larger value of the actual brightness value of the image and use it as the selected region image.

[0195] When the actual brightness value of the image is not greater than the reference brightness value, it means that the selection can be made directly based on the brightness. Therefore, the image of the same type corresponding to the larger value of the actual brightness value is selected and the selected image is used as the selection area image to improve the accuracy of the obtained selection area image.

[0196] S455: Combine the selected region image with the remaining region image and use it as comprehensive image information.

[0197] Specifically, by mapping the selected region image and the remaining region image to the same three-dimensional spatial coordinate system, aligning the spatial coordinates, and performing boundary smoothing processing, the selected region image and the remaining region image are stitched together and fused to form the final image synthesis information, thereby improving the accuracy of the acquired image synthesis information.

[0198] S5: Generate comprehensive modeling information by combining laser spatial contour and spatial image information.

[0199] Among them, the modeling integrated information refers to the standardized modeling core data set formed by fusing the three-dimensional geometric accuracy of the laser spatial contour with the spatial image.

[0200] The laser spatial contour and spatial image information are aligned and fused in the same three-dimensional space to generate the data, which is convenient for subsequent use.

[0201] To further ensure the rationality of the modeling and synthesis information, it is necessary to perform further separate analysis and calculation on the modeling and synthesis information, which will be explained in detail through the following steps.

[0202] Reference Figure 3 The method for generating comprehensive modeling information includes the following steps:

[0203] S51: Determine the spatial contour and texture information of the image based on the spatial image information.

[0204] Image spatial contour refers to the two-dimensional or three-dimensional contour data that reflects the boundaries of various objects (such as walls, shelves, and goods) within the target space. Image texture information refers to the set of visual feature data of object surfaces in an image, including the texture structure of objects (such as the graininess of walls and the metallic texture of shelves), color distribution (such as the color of goods packaging and the color of wall paint), and light and dark details.

[0205] By preprocessing spatial image information and using semantic segmentation algorithms (such as U-Net network) to label the object type of each pixel in the spatial image, and then using edge detection algorithms (such as Canny algorithm) to extract the boundary contours of pixels with the same label, the image spatial contours corresponding to the actual spatial locations are formed after coordinate calibration. Then, for each object region divided by the image spatial contours, the texture structure, color distribution and other data within the region are extracted by feature extraction algorithms (such as gray-level co-occurrence matrix, color histogram), and combined with pixel brightness values ​​and RGB channel information to form image texture information, which is convenient for subsequent use.

[0206] S52: Determine contour similarity by combining image spatial contour and laser spatial contour.

[0207] Contour similarity refers to a dimensionless index that quantifies the degree of geometric matching between the spatial contour of an image and the spatial contour of a laser beam.

[0208] By aligning the image spatial contour and the laser spatial contour with the same spatial reference, the influence of coordinate deviation is eliminated. Then, key features such as key points (e.g., vertices, inflection points, arc centers), contour line parameters (e.g., line segment length, curve curvature, angular relationships), and regional topology (e.g., relative positions between objects) are extracted for both types of contours. Key point matching rate and shape similarity are then calculated, and finally, a weighted average is used to obtain the contour similarity score for subsequent use. The specific weights of key point matching rate, shape similarity, and other indicators are preset by the operator according to actual needs.

[0209] S53: Determine whether the contour similarity is greater than the preset contour similarity benchmark value. If yes, proceed to S54; if no, proceed to S55.

[0210] The contour similarity benchmark value refers to the threshold used to define whether the image spatial contour and the laser spatial contour are properly matched. The contour similarity benchmark value is obtained after being pre-input by the operator.

[0211] By judging whether the contour similarity is greater than the preset contour similarity benchmark value, it can be determined whether the image texture information or laser spatial contour needs to be adjusted.

[0212] S54: Integrate image texture information with laser spatial contours to form comprehensive modeling information.

[0213] When the contour similarity is greater than the preset contour similarity benchmark value, it means that there is no need to adjust the image texture information or the laser spatial contour. Therefore, the pixel coordinates of the image texture information are directly converted to the three-dimensional coordinate system of the laser spatial contour, and the texture is covered according to the contour to form the modeling comprehensive information and improve the accuracy of the obtained modeling comprehensive information.

[0214] S55: Combine the image spatial contour and the laser spatial contour to determine the contour differentiation region and the contour consistency region.

[0215] The contour-distinguishing region refers to the contour region where the image space contour differs from the laser space contour. The contour-consistent region refers to the contour region where the image space contour and the laser space contour are consistent.

[0216] When the contour similarity is greater than the preset contour similarity benchmark value, it means that there is no need to adjust the image texture information or laser spatial contour. Therefore, by comparing the image spatial contour and the laser spatial contour, the areas with differences are taken as contour difference areas, and the areas with similarity are taken as contour consistency areas, which is convenient for subsequent use.

[0217] S56: Based on the contour differentiation region, retrieve the differentiation region image and the neighboring region image from the spatial image information.

[0218] Among them, the distinguishing region image refers to the image corresponding to the contour distinguishing region, and the neighboring region image refers to the image corresponding to the region adjacent to the contour distinguishing region.

[0219] By retrieving the image corresponding to the contour differentiation region from the spatial image information and using it as the differentiation region image, and retrieving the image next to the differentiation region image as the neighboring region image, it is convenient for subsequent use.

[0220] S57: Combine the images of the distinguishing regions, the images of neighboring regions, and the regions with consistent contours to generate distinguishing adjustment modeling information, and use the distinguishing adjustment modeling information as the comprehensive modeling information.

[0221] Among them, the differentiated adjustment modeling information refers to the core modeling data set corresponding to the adjustments made based on the differences in the contours.

[0222] By combining and analyzing images of different regions, neighboring regions, and regions with consistent contours, differential adjustment modeling information is generated. This differential adjustment modeling information is then used as comprehensive modeling information to improve the accuracy of the acquired comprehensive modeling information.

[0223] To further ensure the rationality of the differentiation adjustment modeling information, it is necessary to perform further separate analysis and calculation on the differentiation adjustment modeling information, which will be explained in detail through the steps shown below.

[0224] The methods for generating modeling information to differentiate and adjust include the following steps:

[0225] S571: The image texture information is fused with the contour-consistent region to obtain contour-consistent modeling information.

[0226] Among them, the contour-consistent modeling information refers to the core data set corresponding to the modeling after texture fusion of regions with consistent contours.

[0227] By transforming the pixel coordinates of image texture information to the three-dimensional coordinate system of the contour-consistent region, and then applying texture overlay according to the contour, contour-consistent modeling information is formed, which is convenient for subsequent use.

[0228] S572: Identify the types of distinct regions based on the images of distinct regions, and identify the types of neighboring regions based on the images of neighboring regions.

[0229] Among them, the distinguishable region type refers to the type of object in the distinguishable region image, and the neighboring region type refers to the type of object in the neighboring region image.

[0230] By identifying the types of objects in the distinguishing regions of the image, the types of the distinguishing regions are obtained. Similarly, by identifying the types of objects in the neighboring regions of the image, the types of the neighboring regions are obtained, which facilitates subsequent use.

[0231] S573: Determine the species deviation value by combining the species in the distinguishing region with the species in the neighboring region.

[0232] Among them, the species deviation value refers to the quantitative index that quantifies the degree of difference between species in the distinguishing region and species in neighboring regions in terms of core characteristics (reflectivity, light transmittance, texture complexity, and material density).

[0233] The type of the distinguishing region and the type of the neighboring region are input into a preset type deviation database to obtain the type deviation value, which is convenient for subsequent use.

[0234] The species deviation database pre-stores a table of different distinguishing regions, neighboring regions, and their corresponding species deviation values. The species deviation database is pre-set by the operator according to actual needs.

[0235] For example, the category deviation database can set a category deviation value of 2 when the category of the distinguishing area and the category of the adjacent area are glass and wall respectively, a category deviation value of 1 when they are decorative painting and wall respectively, and a category deviation value of 3 when they are glass and decorative painting respectively.

[0236] S574: When the species deviation value is less than the preset species baseline deviation value, determine the species texture adjustment information based on the species in the neighboring area.

[0237] The category baseline deviation value refers to the deviation value corresponding to when only texture adjustment is required. The category baseline deviation value is obtained after pre-input by the operator. In this embodiment, the category baseline deviation value can be set to 1.

[0238] When the type deviation value is less than the preset type baseline deviation value, it means that the type of the distinguishing region and the type of the neighboring region are the same type. Therefore, the type texture adjustment information is obtained by inputting the type of the neighboring region into the preset type texture database for matching, which is convenient for subsequent use.

[0239] The type texture database pre-stores a lookup table of different neighboring region types and their corresponding type texture adjustment information, which is obtained after the operator pre-inputs the information.

[0240] S575: Merge the type texture adjustment information with the contour differentiation region to obtain contour differentiation modeling information.

[0241] Among them, contour differentiation modeling information refers to the core data set corresponding to the modeling after texture fusion of regions with contour differences.

[0242] By transforming the pixel coordinates of the texture adjustment information to the three-dimensional coordinate system of the contour differentiation region, and then applying texture overlay according to the contour, contour differentiation modeling information is obtained, which is convenient for subsequent use.

[0243] S576: Combine contour consistency modeling information with contour difference modeling information as the basis for adjusting the modeling information.

[0244] Specifically, by combining contour consistency modeling information with contour difference modeling information, a core dataset for overall contour modeling is formed and merged as difference adjustment modeling information, thereby improving the accuracy of the obtained difference adjustment modeling information.

[0245] To further ensure the rationality of the differentiation adjustment modeling information, it is necessary to perform further separate analysis and calculation on the differentiation adjustment modeling information, which will be explained in detail through the steps shown below.

[0246] The method for generating modeling information to differentiate and adjust also includes the following steps:

[0247] S5741: When the type deviation value is not less than the preset type reference deviation value, determine the image distance value and laser distance value based on the image of the distinguishing region.

[0248] The image distance value refers to the distance between the image acquisition location and the detection location. The laser distance value refers to the distance between the laser acquisition location and the detection location.

[0249] When the type deviation value is not less than the preset type baseline deviation value, it indicates that the type of the distinguishing region and the type of the neighboring region are not the same type. Therefore, the laser point cloud data corresponding to the distinguishing region image is retrieved to obtain the laser distance value. By using the perspective law of near objects being larger and far objects being smaller in the distinguishing region image, combined with the external parameters (shooting posture) of the image acquisition device, the relative distance between each pixel and the device is calculated, and the average value of the region is taken as the image distance value, which facilitates subsequent use.

[0250] S5742: Determine whether the image distance value is greater than the laser distance value. If yes, proceed to S5743; if no, proceed to S5744.

[0251] Specifically, by judging whether the image distance value is greater than the laser distance value, it can be determined whether the image is captured through the glass and onto the wall / furniture behind it, while the laser captures the glass.

[0252] S5743: Integrate image texture information with image spatial contours to form differentiated adjustment modeling information.

[0253] When the image distance value is greater than the laser distance value, it indicates that the image is capturing the wall / furniture behind the glass, while the laser is capturing the glass. Therefore, the only difference is due to the laser being affected by the glass. By transforming the pixel coordinates of the image texture information to the three-dimensional coordinate system of the image space contour and applying texture overlay according to the contour, differential adjustment modeling information is formed, improving the accuracy of the acquired differential adjustment modeling information.

[0254] S5744: Retrieve brightness values ​​of different regions based on different regions of the image.

[0255] Among them, the distinguishing image brightness value refers to the quantized brightness data in the distinguishing region of the image.

[0256] When the image distance value is not greater than the laser distance value, it indicates that the image is not being captured through the glass to see the wall / furniture behind it, but rather the laser is capturing the glass. Therefore, the brightness value of the differentiated image is retrieved by distinguishing the different regions for later use.

[0257] S5745: Determine the contour change area by combining the distinguishing region type, the distinguishing image brightness value, and the type deviation value.

[0258] The contour change area refers to the area corresponding to the contour after it has been changed and adjusted.

[0259] By inputting the type of distinguishing region, the brightness value of the distinguishing image, and the type deviation value into the contour enlargement database to obtain the contour enlargement value, the contour distinguishing region is enlarged according to the contour enlargement value. At this time, the contour consistent region is correspondingly shrunk, and the contour region corresponding to the overall contour adjustment is taken as the contour change region for convenient subsequent use.

[0260] The contour enlargement database pre-stores a table of different types of distinguishing regions, distinguishing image brightness values, type deviation values, and corresponding contour enlargement values. The contour enlargement database obtains the average distance value that can be enlarged by conducting experiments on different types of distinguishing regions according to different distinguishing image brightness values ​​and different type deviation values, and then uses this average distance value as the contour enlargement value.

[0261] S5746: Combine image texture information with contour variation areas and use it as distinguishing adjustment modeling information.

[0262] Specifically, by transforming the pixel coordinates of image texture information to the three-dimensional coordinate system of the contour change region and applying texture coverage according to the contour, differential adjustment modeling information is formed, thereby improving the accuracy of the acquired differential adjustment modeling information.

[0263] S6: Model based on the comprehensive modeling information to generate modeling result information, and output the modeling result information.

[0264] Among them, the modeling result information refers to a standardized three-dimensional model data set that fully restores the physical form and surface details of the target space.

[0265] By inputting the comprehensive modeling information into a preset 3D modeling system to perform 3D modeling, the modeling result information is obtained and output, thereby realizing the synergistic linkage of laser detection and image detection and improving the accuracy of spatial modeling.

[0266] Based on the same inventive concept, embodiments of the present invention provide an automated modeling system based on spatial perception intelligent fusion, comprising:

[0267] The data acquisition module is used to acquire laser detection information, image detection information, ambient light levels, and equipment specifications.

[0268] The memory stores a program for implementing an automated modeling method based on spatial perception intelligent fusion, as described above.

[0269] The processor loads and executes programs stored in memory.

[0270] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0271] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. An automated modeling method based on spatial perception intelligent fusion, characterized in that, The method comprises the following steps: S1: collecting laser detection information and image detection information; S2: calling laser point cloud data corresponding to each detection position point based on the laser detection information; S3: generating a laser space profile according to the laser point cloud data; S4: generating space image information by combining the laser point cloud data and the image detection information; S5: generating modeling comprehensive information by combining the laser space profile and the space image information; S6: modeling based on the modeling comprehensive information to generate modeling result information, and outputting the modeling result information; The method for generating space image information comprises the following steps: S41: calling unit position image information corresponding to each detection position point based on the image detection information; S42: performing image recognition based on the unit position image information to obtain unit position image categories; S43: determining detection distance values corresponding to each detection position point according to the laser point cloud data; S44: calculating the proportion value of adjacent detection distance values as an adjacent distance proportion value; S45: combining unit position image information according to the adjacent distance proportion value and the unit position image categories to form image comprehensive information, and taking the image comprehensive information as the space image information; The method for forming image comprehensive information comprises the following steps: S451: adjusting unit position image information according to the adjacent distance proportion value to obtain proportionally adjusted image information; S452: extracting proportionally adjusted image information according to the unit position image categories to obtain same category region image and remaining region image; S453: calling image actual brightness values based on the same category region image; S454: selecting the same category region image as selected region image based on the image actual brightness values; S455: combining the selected region image and the remaining region image as the image comprehensive information.

2. The automated modeling method based on spatial perception intelligent fusion according to claim 1, characterized in that, The method for selecting the selected region image comprises the following steps: S4541: collecting ambient light value; S4542: determining image reference brightness value by combining the ambient light value and the detection distance value; S4543: determining whether the image actual brightness values are all greater than the image reference brightness value; S4544: if yes, calculating the difference value between the image actual brightness value and the image reference brightness value as brightness deviation value; S4545: determining deviation selection reference value by combining the brightness deviation value and the unit position image categories; S4546: selecting the same category region image corresponding to the larger value of the deviation selection reference value as the selected region image; S4547: if no, selecting the same category region image corresponding to the larger value of the image actual brightness value as the selected region image. 3.The automatic modeling method based on spatial perception intelligent fusion according to claim 2, characterized in that, The method for determining the image reference brightness value comprises the following steps: S45421: collecting the equipment specifications of an image acquisition device; S45422: determining specification adaptive brightness interval according to the equipment specifications; S45423: determining distance light influence coefficient according to the detection distance value; S45424: calculating the product value between the ambient light value and the distance light influence coefficient as distance adjusted brightness value; S45425: determining whether the distance adjusted brightness value is located in the specification adaptive brightness interval; S45426: if yes, taking the distance adjusted brightness value as the image reference brightness value; S45427: If no, then the end value of the specification adaptive luminance interval is selected based on the image reference luminance value and taken as the image reference luminance value.

4. The automatic modeling method based on spatial perception intelligent fusion according to claim 2, characterized in that, The method for determining the deviation selection reference value comprises: S45451: determining a category deviation allowable interval according to the unit position image category; S45452: determining whether the luminance deviation value falls within the category deviation allowable interval; S45453: if yes, then determining a category deviation coefficient according to the unit position image category; S45454: calculating the product value between the category deviation coefficient and the luminance deviation value and taking the product value as the deviation selection reference value; S45455: if no, then selecting the end value of the category deviation allowable interval based on the luminance deviation value to obtain an interval selection end value; S45456: calculating the ratio value between the luminance deviation value and the interval selection end value and taking the ratio value as the deviation selection reference value.

5. The automated modeling method based on spatial perception intelligent fusion according to claim 1, characterized in that, The method for generating the modeling comprehensive information comprises: S51: determining image space contour and image texture information according to the space image information; S52: determining contour similarity by combining the image space contour and the laser space contour; S53: determining whether the contour similarity is greater than a preset contour similarity reference value; S54: if yes, then fusing the image texture information and the laser space contour to form the modeling comprehensive information; S55: if no, then determining contour difference region and contour consistent region by combining the image space contour and the laser space contour; S56: based on the contour difference region, calling the difference region image and the adjacent region image from the space image information; S57: generating the difference adjustment modeling information by combining the difference region image, the adjacent region image and the contour consistent region, and taking the difference adjustment modeling information as the modeling comprehensive information.

6. The automatic modeling method based on spatial perception intelligent fusion according to claim 5, characterized in that, The method for generating the difference adjustment modeling information comprises: S571: fusing the image texture information and the contour consistent region to obtain contour consistent modeling information; S572: identifying the difference region category based on the difference region image and identifying the adjacent region category based on the adjacent region image; S573: determining a category deviation value by combining the difference region category and the adjacent region category; S574: when the category deviation value is less than a preset category reference deviation value, determining category texture adjustment information according to the adjacent region category; S575: fusing the category texture adjustment information and the contour difference region to obtain contour difference modeling information; S576: combining the contour consistent modeling information and the contour difference modeling information to take the combination as the difference adjustment modeling information.

7. The automatic modeling method based on spatial perception intelligent fusion according to claim 6, characterized in that, The method for generating the difference adjustment modeling information further comprises: S5741: when the category deviation value is not less than the preset category reference deviation value, determining an image distance value and a laser distance value according to the difference region image; S5742: determining whether the image distance value is greater than the laser distance value; S5743: if yes, then fusing the image texture information and the image space contour to form the difference adjustment modeling information; S5744: if no, then calling a difference image luminance value based on the difference region image; S5745: determining a contour change region by combining the difference region category, the difference image luminance value and the category deviation value; S5746: combine image texture information with the contour change region and use as a distinct adjustment modeling information.

Images