AI intelligent 3D spraying control system for surface treatment of urban art device

Abstract

The invention provides an AI intelligent 3D spraying control system for surface treatment of an urban art device, and belongs to the technical field of control, tracks of partial layers can be generated only through images through a trained neural network model in a multi-layer image spraying construction process, tracks of the rest layers are generated by adopting the neural network model, and the construction efficiency is improved. Therefore, the calculation power of directly generating the track according to the image is reduced, the total calculation time is shortened, and the efficiency of spraying work is further improved.

Description

Technical Field

[0001] The present application relates to the field of control technology, and in particular to an AI intelligent 3D spray control system for surface treatment of urban art installations. Background Art

[0002] The 3D equipment used for surface treatment of urban art installations can precisely control the spraying process to ensure uniform and beautiful coating. This advanced technology not only improves spraying efficiency, but also greatly enhances the visual effect of art installations. Through precise programming and real-time monitoring, the 3D spraying control system can adjust the spraying angle, speed and thickness according to different artistic needs, thereby achieving perfect reproduction of complex patterns and textures.

[0003] In the actual use of 3D spraying equipment, it is necessary to generate multiple spraying trajectories corresponding to the multiple layer images according to the multiple layer images of the original image to be sprayed. However, the computing power consumed in generating trajectories according to the individual layer images is large, which consumes more time in the trajectory planning process and the overall efficiency is low. Summary of the invention

[0004] The embodiment of the present application provides an AI intelligent 3D spray control system for surface treatment of urban art installations to improve the above-mentioned problems.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In the first aspect, the embodiment of the present application proposes an AI intelligent 3D spray control system for surface treatment of urban art installations, the system includes a controller and an execution terminal, and the system is configured as follows:

[0007] The controller obtains spraying data, the spraying data is image data to be sprayed, and the spraying data includes n layers and n layer images corresponding to the n layers, namely, the first layer image, the second layer image...the nth layer image, wherein n is a natural number greater than or equal to 3;

[0008] The controller obtains the mj-th layer image and the m+j-th layer image, and generates the mj-th layer trajectory and the m+j-th layer trajectory according to the mj-th layer image and the m+j-th layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j;

[0009] The controller obtains the trained neural network model, and inputs the mj-th layer trajectory and the m+j-th layer trajectory into the trained neural network model. The neural network model is used to output the predicted layer trajectory of the middle layer of the two-layer image according to the input two-layer layer trajectory;

[0010] The controller obtains the trajectory of the mth layer according to the output result of the neural network training model, and controls the execution terminal to spray the mth layer image according to the trajectory of the mth layer.

[0011] In conjunction with the first aspect, in some embodiments, the system is configured as follows:

[0012] The controller obtains the mj-th layer image and the m+j-th layer image, and generates the mj-th layer trajectory and the m+j-th layer trajectory according to the mj-th layer image and the m+j-th layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j, including:

[0013] The controller obtains the mj-th layer image, and divides the mj-th layer image into a plurality of sub-images, wherein the plurality of sub-images constitute the mj-th layer image;

[0014] If the controller determines that at least one side of a sub-image is not adjacent to another sub-image, the sub-image is determined to be a target sub-image:

[0015] The controller obtains all target sub-images, and uses the target sub-images as nodes and the lines between two adjacent target sub-images as paths to obtain multiple first Euler paths formed by the target sub-images;

[0016] The controller determines a plurality of target areas based on the positional relationship between the plurality of first Euler paths, wherein the target areas are areas separated and formed with the first Euler paths as boundaries;

[0017] The controller determines a filling area among the plurality of target areas based on the mj-th layer image, and determines the mj-th layer track according to the filling area.

[0018] In conjunction with the first aspect, in some embodiments, the system is configured as follows:

[0019] The controller determines a filling area in a plurality of target areas based on the mj-th layer image, and determines the mj-th layer track according to the filling area, including:

[0020] The controller obtains a sub-image in each filling area, and uses the sub-image as a node and a line between two adjacent sub-images as a path to obtain a plurality of second Euler paths formed by the sub-images;

[0021] The controller generates an mj-th layer trajectory based on the plurality of second Euler paths.

[0022] In conjunction with the first aspect, in some embodiments, the system is configured as follows:

[0023] The controller generates the mj-th layer trajectory based on multiple second Euler paths, including:

[0024] Based on the shortest path principle, the controller connects multiple second Euler paths to form the mj-th layer trajectory.

[0025] In conjunction with the first aspect, in some embodiments, the system is configured as follows:

[0026] The controller obtains the trained neural network model and inputs the mj-th layer trajectory and the m+j-th layer trajectory into the trained neural network model. The neural network model is used to output the predicted layer trajectory of the middle layer of the two-layer image according to the input two-layer layer trajectory, including:

[0027] The controller obtains a training set, wherein the training set includes k layers of adjacent layer trajectories, wherein k is a natural number greater than or equal to 3;

[0028] The controller imports the training set into the neural network model and performs iterative calculations. When the iterative calculation process meets the preset conditions, the calculation is stopped and the trained neural network training model is obtained.

[0029] In conjunction with the first aspect, in some embodiments, the system is configured as follows:

[0030] The controller imports the training set into the neural network model and performs iterative calculations. When the iterative calculation process meets the preset conditions, the calculation is stopped and the trained neural network training model is obtained, including:

[0031] The controller selects the i-1th layer track, the i-th layer track and the i+1th layer track from the k-th layer track, where i is a natural number not equal to 0 and i <k;

[0032] The controller uses the data of the i-1th layer track and the data of the i+1th layer track as two different dimensional vectors to form a feature vector of the data of the i-th layer track and performs iterative calculation;

[0033] When the iterative calculation process meets the preset conditions, the calculation stops and the controller obtains the trained neural network training model.

[0034] In conjunction with the first aspect, in some embodiments, the system is configured as follows:

[0035] When the iterative calculation process meets the preset conditions, the calculation is stopped and the trained neural network training model is obtained, including:

[0036] The controller obtains k-2 error values ​​based on the training process of the neural network model according to the training set, and determines an average error value based on the k-2 error values;

[0037] The controller compares the average error value with the preset value. When the average error value is less than or equal to the preset value, the training is stopped and the trained neural network model is output.

[0038] In conjunction with the first aspect, in some embodiments, the system is configured as follows:

[0039] The controller obtains k-2 error values ​​based on the training process of the neural network model according to the training set, and determines the average error value based on the k-2 error values, including:

[0040] The controller inputs the data of the i-1th layer trajectory and the data of the i+1th layer trajectory into the neural network training model, and obtains the predicted layer trajectory output by the neural network training model;

[0041] The controller determines an error value based on the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory.

[0042] In conjunction with the first aspect, in some embodiments, the system is configured as follows:

[0043] The controller determines an error value based on the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory, satisfying:

[0044] If the data of the predicted layer trajectory is greater than the data of the i-th layer trajectory, the error value is determined as:

[0045] t=y(yx)

[0046] Among them, t is the error value, y is the data of the predicted layer trajectory, and x is the data of the i-th layer trajectory.

[0047] In conjunction with the first aspect, in some embodiments, the system is configured as follows:

[0048] The controller determines an error value based on the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory, satisfying:

[0049] If the data of the predicted layer trajectory is less than the data of the i-th layer trajectory, the error value is determined as:

[0050] t=y(xy)

[0051] Among them, t is the error value, y is the data of the predicted layer trajectory, and x is the data of the i-th layer trajectory.

[0052] The second aspect of the embodiment of the present invention proposes an AI intelligent 3D spraying control method for surface treatment of urban art devices, which is applicable to an AI intelligent 3D spraying control system for surface treatment of urban art devices. The system includes a controller and an execution terminal. The method includes:

[0053] The controller obtains spraying data, the spraying data is image data to be sprayed, and the spraying data includes n layers and n layer images corresponding to the n layers, namely, the first layer image, the second layer image...the nth layer image, wherein n is a natural number greater than or equal to 3;

[0054] The controller obtains the mj-th layer image and the m+j-th layer image, and generates the mj-th layer trajectory and the m+j-th layer trajectory according to the mj-th layer image and the m+j-th layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j;

[0055] The controller obtains the trained neural network model, and inputs the mj-th layer trajectory and the m+j-th layer trajectory into the trained neural network model. The neural network model is used to output the predicted layer trajectory of the middle layer of the two-layer image according to the input two-layer layer trajectory;

[0056] The controller obtains the trajectory of the mth layer according to the output result of the neural network training model, and controls the execution terminal to spray the mth layer image according to the trajectory of the mth layer.

[0057] In combination with the second aspect, in some implementations, the controller obtains the mj-th layer image and the m+j-th layer image, and generates the mj-th layer trajectory and the m+j-th layer trajectory according to the mj-th layer image and the m+j-th layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j, including:

[0058] The controller obtains the mj-th layer image, and divides the mj-th layer image into a plurality of sub-images, wherein the plurality of sub-images constitute the mj-th layer image;

[0059] If the controller determines that at least one side of a sub-image is not adjacent to another sub-image, then the sub-image is determined to be a target sub-image;

[0060] The controller obtains all target sub-images, and uses the target sub-images as nodes and the lines between two adjacent target sub-images as paths to obtain multiple first Euler paths formed by the target sub-images;

[0061] The controller determines a plurality of target areas based on the positional relationship between the plurality of first Euler paths, wherein the target areas are areas separated and formed with the first Euler paths as boundaries;

[0062] The controller determines a filling area among the plurality of target areas based on the mj-th layer image, and determines the mj-th layer track according to the filling area.

[0063] In combination with the second aspect, in some implementations, the controller determines a filling area in a plurality of target areas based on the mj-th layer image, and determines the mj-th layer track according to the filling area, including:

[0064] The controller obtains a sub-image in each filling area, and uses the sub-image as a node and a line between two adjacent sub-images as a path to obtain a plurality of second Euler paths formed by the sub-images;

[0065] The controller generates an mj-th layer trajectory based on the plurality of second Euler paths.

[0066] In combination with the second aspect, in some implementations, the controller generates an mj-th layer trajectory based on the plurality of second Euler paths, including:

[0067] Based on the shortest path principle, the controller connects multiple second Euler paths to form the mj-th layer trajectory.

[0068] In combination with the second aspect, in some implementations, the controller obtains a trained neural network model, and inputs the mj-th layer trajectory and the m+j-th layer trajectory into the trained neural network model, and the neural network model is used to output a predicted layer trajectory of the middle layer of the two-layer image according to the input two-layer layer trajectory, including:

[0069] The controller obtains a training set, wherein the training set includes k layers of adjacent layer trajectories, wherein k is a natural number greater than or equal to 3;

[0070] The controller imports the training set into the neural network model and performs iterative calculations. When the iterative calculation process meets the preset conditions, the calculation is stopped and the trained neural network training model is obtained.

[0071] In conjunction with the second aspect, in some implementations, the controller imports the training set into the neural network model and performs iterative calculations, stops the calculations when the iterative calculation process meets a preset condition, and obtains the trained neural network training model, including:

[0072] The controller selects the i-1th layer track, the i-th layer track and the i+1th layer track from the k-th layer track, where i is a natural number not equal to 0 and i <k;

[0073] The controller uses the data of the i-1th layer track and the data of the i+1th layer track as two different dimensional vectors to form a feature vector of the data of the i-th layer track and performs iterative calculation;

[0074] When the iterative calculation process meets the preset conditions, the calculation stops and the controller obtains the trained neural network training model.

[0075] In conjunction with the second aspect, in some implementations, when the iterative calculation process meets a preset condition, the calculation is stopped, and a trained neural network training model is obtained, including:

[0076] The controller obtains k-2 error values ​​based on the training process of the neural network model according to the training set, and determines an average error value based on the k-2 error values;

[0077] The controller compares the average error value with the preset value. When the average error value is less than or equal to the preset value, the training is stopped and the trained neural network model is output.

[0078] In conjunction with the second aspect, in some implementations, the controller obtains k-2 error values ​​based on a training process of the neural network model according to the training set, and determines an average error value based on the k-2 error values, including:

[0079] The controller inputs the data of the i-1th layer trajectory and the data of the i+1th layer trajectory into the neural network training model, and obtains the predicted layer trajectory output by the neural network training model;

[0080] The controller determines an error value based on the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory.

[0081] In conjunction with the second aspect, in some implementations, the controller determines an error value based on the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory, satisfying:

[0082] If the data of the predicted layer trajectory is greater than the data of the i-th layer trajectory, the error value is determined as:

[0083] t=y(yx)

[0084] Among them, t is the error value, y is the data of the predicted layer trajectory, and x is the data of the i-th layer trajectory.

[0085] In conjunction with the second aspect, in some implementations, the controller determines an error value based on the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory, satisfying:

[0086] If the data of the predicted layer trajectory is less than the data of the i-th layer trajectory, the error value is determined as:

[0087] t=y(xy)

[0088] Among them, t is the error value, y is the data of the predicted layer trajectory, and x is the data of the i-th layer trajectory.

[0089] A third aspect of an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0090] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method proposed in the first aspect of the embodiment of the present invention.

[0091] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the embodiment of the present invention.

[0092] In summary, the above method and device have the following technical effects:

[0093] The embodiment of the present application proposes an AI intelligent 3D spray control system for surface treatment of urban art installations. First, the controller obtains spray data, which is image data to be sprayed. The spray data includes n layers and n layer images corresponding to the n layers, which are the first layer image, the second layer image...the nth layer image, respectively, wherein n is a natural number greater than or equal to 3. Then, the controller obtains the mjth layer image and the m+jth layer image, and generates the mjth layer trajectory and the m+jth layer trajectory according to the mjth layer image and the m+jth layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j. Then, the controller obtains a trained neural network model, and inputs the mjth layer trajectory and the m+jth layer trajectory into the trained neural network model. The neural network model is used to output a predicted layer trajectory of the middle layer of the two images according to the input two-layer layer trajectory. Finally, the controller obtains the mth layer trajectory according to the output result of the neural network training model, and controls the execution terminal to spray the mth layer image according to the mth layer trajectory. The present application proposes an AI intelligent 3D spray control system for surface treatment of urban art installations. Through a trained neural network model, during the multi-layer image spraying construction process, the trajectories of only some layers are generated through images, and the trajectories of the remaining layers are generated using the neural network model, which reduces the computing power when directly generating trajectories based on images, increases the total calculation time, and further improves the efficiency of the spraying work. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] Figure 1 A flow chart of an AI intelligent 3D spraying control method for surface treatment of urban art installations proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0095] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0096] The present application proposes an AI intelligent 3D spraying control method for surface treatment of urban art installations, which is applicable to an AI intelligent 3D spraying control system for surface treatment of urban art installations. The system includes a controller and an execution terminal. The execution terminal can be a printing device or a spraying device, which is not limited in the present application.

[0097] See also Figure 1 , the method comprises the following steps:

[0098] S101: The controller obtains spraying data, which is image data to be sprayed. The spraying data includes n layers and n layer images corresponding to the n layers, namely the first layer image, the second layer image...the nth layer image, wherein n is a natural number greater than or equal to 3.

[0099] It is understandable that before spraying, the controller needs to obtain spraying data and control the execution terminal to actually spray or print according to the spraying data. The working principle of 3D spraying has been disclosed in relevant patents and will not be repeated in this application. During the working process of 3D spraying, spraying construction needs to be carried out on each layer according to a predetermined route. In this application, the spraying data includes n layers and n layer images corresponding to the n layers, and n can be any natural number greater than or equal to 3.

[0100] S102: The controller obtains the mj-th layer image and the m+j-th layer image, and generates the mj-th layer trajectory and the m+j-th layer trajectory according to the mj-th layer image and the m+j-th layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j.

[0101] It is understandable that during the spraying process, the controller needs to design the actual spraying route according to the image of the layer, and designing the route directly according to the image requires a lot of computing power. In this embodiment, the path obtained by the neural network model is the layer trajectory of the mth layer, that is, the layer trajectory of the mth layer is between the image trajectory of the mjth layer and the image trajectory of the m+jth layer.

[0102] Specifically, in this embodiment, taking the image of the mjth layer as an example, the process of obtaining the spray path from the image may include the following steps:

[0103] S1021: The controller obtains the mj-th layer image, and divides the mj-th layer image into a plurality of sub-images, and the plurality of sub-images constitute the mj-th layer image.

[0104] It can be understood that in the process of segmenting the image, the smaller the sub-image, the less refined it is. The sub-image in this embodiment can be the minimum area during the actual spraying process of the execution terminal. Of course, it can also be some other calculation methods, which are not limited in this embodiment.

[0105] S1022: If the controller determines that at least one side of a sub-image is not adjacent to another sub-image, the sub-image is determined to be a target sub-image.

[0106] It can be understood that after the controller divides the image into multiple sub-images, if at least one side of a sub-image is not adjacent to another sub-image, it can be proved that the sub-image is located at the edge of the entire image. In this way, one side of the sub-image will not have any sub-image adjacent to it, while the other three sides or two sides are adjacent to other sub-images. In this way, it can be determined whether a sub-image is an edge sub-image. In this embodiment, for the convenience of explanation, the sub-image confirmed to be an edge is defined as a target sub-image.

[0107] S1023: The controller obtains all target sub-images, and uses the target sub-images as nodes and the lines between two adjacent target sub-images as paths to obtain multiple first Euler paths formed by the target sub-images.

[0108] After determining the target sub-image, it can be understood that multiple continuous sub-images are the boundaries of the part of the entire image that needs to be sprayed. Therefore, in this embodiment, the target sub-image is used as a node, and the line between two adjacent target sub-images is used as a path. Multiple first Euler paths formed by the target sub-image can be obtained. In this way, the first Euler path can be used as the boundary of the spraying area. These boundaries include, for example, the boundaries of the hollowed-out part of the image.

[0109] S1024: The controller determines a plurality of target areas based on the positional relationship between the plurality of first Euler paths, where the target areas are areas separated and formed with the first Euler paths as boundaries.

[0110] It can be understood that after multiple boundaries are determined, the entire area is divided into multiple areas according to the positional relationship of the multiple boundaries, such as whether they are nested, etc. These areas may be areas that need to be sprayed or may be hollow areas.

[0111] S1025: The controller determines a filling area among the plurality of target areas based on the mj-th layer image, and determines the mj-th layer track according to the filling area.

[0112] It can be understood that after determining multiple areas, the mjth layer image can be combined to determine whether the area is a filled area or a hollow area. After determining multiple filled areas, the image trajectory corresponding to the layer can be determined according to the distribution of the multiple filled areas.

[0113] It can be understood that in order to completely fill each filling area, in this embodiment, the sub-image in each filling area can also be obtained, and the sub-image is used as a node, and the connection between two adjacent sub-images is used as a path to obtain multiple second Euler paths formed by the sub-image. In this way, the second Euler path traverses the area where each word sub-image is located. In this way, connecting multiple second Euler paths can also generate the mj-th layer trajectory. It should be noted that in the generation process, based on the shortest path principle, multiple second Euler paths should be connected to form the mj-th layer trajectory.

[0114] S103: The controller obtains a trained neural network model, and inputs the mj-th layer trajectory and the m+j-th layer trajectory into the trained neural network model. The neural network model is used to output a predicted layer trajectory of the middle layer of the two-layer image based on the input two-layer layer trajectory.

[0115] It can be understood that in this embodiment, by inputting the mj-th layer trajectory and the m+j-th layer trajectory into the trained neural network model, the m-th layer trajectory can be obtained. In this way, all layer trajectories except the 1st layer and the nth layer can be generated in this way. Therefore, combined with the actual usage scenario, the generated layer trajectory can also be input into the neural network training model as an input source, and the system needs to directly generate fewer layers. Of course, the proportion of which layers can be generated directly by images and which images can be generated by the neural network model can be determined according to the needs of the user, and is not limited in this embodiment.

[0116] As for how to obtain a trained neural network model, in this embodiment, steps S1031-S1032 can be used. Of course, in other embodiments, there may be other neural network models with different calculation methods or generation methods from those in this embodiment, which are not limited in this embodiment.

[0117] S1031: The controller obtains a training set, where the training set includes k layers of adjacent layer trajectories, where k is a natural number greater than or equal to 3.

[0118] Exemplarily, the training set is a trajectory generated by images in each layer, there are k layers in total, and the trajectories in each layer are adjacent trajectories.

[0119] S1032: The controller imports the training set into the neural network model and performs iterative calculations. When the iterative calculation process meets the preset conditions, the calculation stops, and a trained neural network training model is obtained.

[0120] Specifically, the controller selects the (i - 1)-th layer trajectory, the i-th layer trajectory, and the (i + 1)-th layer trajectory from the k layer trajectories. Here, i is a natural number other than 0, and i < k. Then, the controller uses the data of the (i - 1)-th layer trajectory and the data of the (i + 1)-th layer trajectory as two different dimensional vectors to form the feature vector of the data of the i-th layer trajectory and performs iterative calculations. When the iterative calculation process meets the preset conditions, the calculation stops, and the controller obtains a trained neural network training model.

[0121] As an implementation, for the determination of the error value, based on the process of training the neural network model according to the training set, k - 2 error values can be obtained, and the average error value is determined based on the k - 2 error values.

[0122] The controller can also adopt the method of cross-validation. Specifically, the training set is divided into several subsets, and one of the subsets is used as the validation set in turn, and the rest are used as the training set for model training. In this way, the overfitting phenomenon can be effectively avoided, and the generalization ability of the model on different data sets can be ensured.

[0123] Then, the controller compares the average error value with a preset value. When the average error value is less than or equal to the preset value, the training stops and the trained neural network model is output.

[0124] It can be understood that when the average error value is less than or equal to the preset value, the training stops and the trained neural network model is output. This not only improves the accuracy of the spraying effect but also greatly shortens the model training time and improves the overall work efficiency.

[0125] In summary, the AI intelligent 3D spraying control system provides an efficient, accurate, and personalized solution for the surface treatment of urban art installations, with broad application prospects and market potential.

[0126] As an implementation, if the data of the predicted layer trajectory is greater than the data of the i-th layer trajectory, the error value is determined as:

[0127] t = y(y - x)

[0128] If the data of the predicted layer trajectory is less than the data of the i-th layer trajectory, the error value is determined as:

[0129] t = y(x - y)

[0130] Where t is the error value, y is the data of the predicted layer trajectory, and x is the data of the i-th layer trajectory.

[0131] S104: The controller obtains the m-th layer trajectory according to the output result of the neural network training model, and controls the execution terminal to spray the m-th layer image according to the m-th layer trajectory.

[0132] It is understandable that all layer tracks except the first and nth layers can be generated in this way. Therefore, combined with the actual usage scenario, the generated layer tracks can also be used as input sources to the neural network training model, and the system needs to directly generate fewer layers.

[0133] The embodiment of the present application proposes an AI intelligent 3D spraying control method for surface treatment of urban art installations. First, the controller obtains spraying data, which is image data to be sprayed. The spraying data includes n layers and n layer images corresponding to the n layers, which are the first layer image, the second layer image...the nth layer image, respectively, wherein n is a natural number greater than or equal to 3. Then, the controller obtains the mjth layer image and the m+jth layer image, and generates the mjth layer trajectory and the m+jth layer trajectory according to the mjth layer image and the m+jth layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j. Then, the controller obtains a trained neural network model, and inputs the mjth layer trajectory and the m+jth layer trajectory into the trained neural network model. The neural network model is used to output a predicted layer trajectory of the middle layer of the two images according to the input two-layer layer trajectory. Finally, the controller obtains the mth layer trajectory according to the output result of the neural network training model, and controls the execution terminal to spray the mth layer image according to the mth layer trajectory. The present application proposes an AI intelligent 3D spray control method for surface treatment of urban art installations. Through a trained neural network model, during the multi-layer image spraying construction process, the trajectories of only some layers can be generated through images, and the trajectories of the remaining layers are generated using the neural network model, which reduces the computing power when directly generating trajectories based on images, increases the total calculation time, and further improves the efficiency of the spraying work.

[0134] Based on the same inventive concept, the embodiment of the present application also proposes an AI intelligent 3D spray control system for surface treatment of urban art installations. The system includes a controller and an execution terminal. The system is configured as follows:

[0135] The controller obtains spraying data, the spraying data is image data to be sprayed, and the spraying data includes n layers and n layer images corresponding to the n layers, namely, the first layer image, the second layer image...the nth layer image, wherein n is a natural number greater than or equal to 3;

[0136] The controller obtains the mj-th layer image and the m+j-th layer image, and generates the mj-th layer trajectory and the m+j-th layer trajectory according to the mj-th layer image and the m+j-th layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j;

[0137] The controller obtains the trained neural network model, and inputs the mj-th layer trajectory and the m+j-th layer trajectory into the trained neural network model. The neural network model is used to output the predicted layer trajectory of the middle layer of the two-layer image according to the input two-layer layer trajectory;

[0138] The controller obtains the trajectory of the mth layer according to the output result of the neural network training model, and controls the execution terminal to spray the mth layer image according to the trajectory of the mth layer.

[0139] In some embodiments, the system is configured to:

[0140] The controller obtains the mj-th layer image and the m+j-th layer image, and generates the mj-th layer trajectory and the m+j-th layer trajectory according to the mj-th layer image and the m+j-th layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j, including:

[0141] The controller obtains the mj-th layer image, and divides the mj-th layer image into a plurality of sub-images, wherein the plurality of sub-images constitute the mj-th layer image;

[0142] If the controller determines that at least one side of a sub-image is not adjacent to another sub-image, then the sub-image is determined to be a target sub-image;

[0143] The controller obtains all target sub-images, and uses the target sub-images as nodes and the lines between two adjacent target sub-images as paths to obtain multiple first Euler paths formed by the target sub-images;

[0144] The controller determines a plurality of target areas based on the positional relationship between the plurality of first Euler paths, wherein the target areas are areas separated and formed with the first Euler paths as boundaries;

[0145] The controller determines a filling area among the plurality of target areas based on the mj-th layer image, and determines the mj-th layer track according to the filling area.

[0146] In some embodiments, the system is configured to:

[0147] The controller determines a filling area in a plurality of target areas based on the mj-th layer image, and determines the mj-th layer track according to the filling area, including:

[0148] The controller obtains a sub-image in each filling area, and uses the sub-image as a node and a line between two adjacent sub-images as a path to obtain a plurality of second Euler paths formed by the sub-images;

[0149] The controller generates an mj-th layer trajectory based on the plurality of second Euler paths.

[0150] In some embodiments, the system is configured to:

[0151] The controller generates the mj-th layer trajectory based on multiple second Euler paths, including:

[0152] Based on the shortest path principle, the controller connects multiple second Euler paths to form the mj-th layer trajectory.

[0153] In some embodiments, the system is configured to:

[0154] The controller obtains the trained neural network model and inputs the mj-th layer trajectory and the m+j-th layer trajectory into the trained neural network model. The neural network model is used to output the predicted layer trajectory of the middle layer of the two-layer image according to the input two-layer layer trajectory, including:

[0155] The controller obtains a training set, wherein the training set includes k layers of adjacent layer trajectories, wherein k is a natural number greater than or equal to 3;

[0156] The controller imports the training set into the neural network model and performs iterative calculations. When the iterative calculation process meets the preset conditions, the calculation is stopped and the trained neural network training model is obtained.

[0157] In some embodiments, the system is configured to:

[0158] The controller imports the training set into the neural network model and performs iterative calculations. When the iterative calculation process meets the preset conditions, the calculation is stopped and the trained neural network training model is obtained, including:

[0159] The controller selects the i-1th layer track, the i-th layer track and the i+1th layer track from the k-th layer track, where i is a natural number not equal to 0 and i <k;

[0160] The controller uses the data of the i-1th layer track and the data of the i+1th layer track as two different dimensional vectors to form a feature vector of the data of the i-th layer track and performs iterative calculation;

[0161] When the iterative calculation process meets the preset conditions, the calculation stops and the controller obtains the trained neural network training model.

[0162] In some embodiments, the system is configured to:

[0163] When the iterative calculation process meets the preset conditions, the calculation is stopped and the trained neural network training model is obtained, including:

[0164] The controller obtains k-2 error values ​​based on the training process of the neural network model according to the training set, and determines an average error value based on the k-2 error values;

[0165] The controller compares the average error value with the preset value. When the average error value is less than or equal to the preset value, the training is stopped and the trained neural network model is output.

[0166] In some embodiments, the system is configured to:

[0167] The controller obtains k-2 error values ​​based on the training process of the neural network model according to the training set, and determines the average error value based on the k-2 error values, including:

[0168] The controller inputs the data of the i-1th layer trajectory and the data of the i+1th layer trajectory into the neural network training model, and obtains the predicted layer trajectory output by the neural network training model;

[0169] The controller determines an error value based on the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory.

[0170] In some embodiments, the system is configured to:

[0171] The controller determines an error value based on the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory, satisfying:

[0172] If the data of the predicted layer trajectory is greater than the data of the i-th layer trajectory, the error value is determined as:

[0173] t=y(yx)

[0174] Among them, t is the error value, y is the data of the predicted layer trajectory, and x is the data of the i-th layer trajectory.

[0175] In some embodiments, the system is configured to:

[0176] The controller determines an error value based on the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory, satisfying:

[0177] If the data of the predicted layer trajectory is less than the data of the i-th layer trajectory, the error value is determined as:

[0178] t=y(xy)

[0179] Among them, t is the error value, y is the data of the predicted layer trajectory, and x is the data of the i-th layer trajectory.

[0180] The embodiment of the present application proposes an AI intelligent 3D spray control system for surface treatment of urban art installations. First, the controller obtains spray data, which is image data to be sprayed. The spray data includes n layers and n layer images corresponding to the n layers, which are the first layer image, the second layer image...the nth layer image, respectively, wherein n is a natural number greater than or equal to 3. Then, the controller obtains the mjth layer image and the m+jth layer image, and generates the mjth layer trajectory and the m+jth layer trajectory according to the mjth layer image and the m+jth layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j. Then, the controller obtains a trained neural network model, and inputs the mjth layer trajectory and the m+jth layer trajectory into the trained neural network model. The neural network model is used to output a predicted layer trajectory of the middle layer of the two images according to the input two-layer layer trajectory. Finally, the controller obtains the mth layer trajectory according to the output result of the neural network training model, and controls the execution terminal to spray the mth layer image according to the mth layer trajectory. The present application proposes an AI intelligent 3D spray control system for surface treatment of urban art installations. Through a trained neural network model, during the multi-layer image spraying construction process, the trajectories of only some layers are generated through images, and the trajectories of the remaining layers are generated using the neural network model, which reduces the computing power when directly generating trajectories based on images, increases the total calculation time, and further improves the efficiency of the spraying work.

[0181] Based on the same inventive concept, an embodiment of the present application further proposes an electronic device, the electronic device comprising:

[0182] At least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the AI ​​intelligent 3D spray control method for surface treatment of urban art installations according to an embodiment of the present application.

[0183] In addition, to achieve the above-mentioned purpose, an embodiment of the present application also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the AI ​​intelligent 3D spraying control method for surface treatment of urban art installations of an embodiment of the present application.

[0184] The following is a detailed introduction to the various components of electronic equipment:

[0185] The processor is the control center of the electronic device, which can be a processor or a general term for multiple processing elements. For example, the processor is one or more central processing units (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSP), or one or more field programmable gate arrays (field programmable gate arrays, FPGA).

[0186] Optionally, the processor can perform various functions of the electronic device by running or executing a software program stored in the memory, and calling data stored in the memory.

[0187] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0188] Optionally, the memory may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may be integrated with the processor, or may exist independently and be coupled to the processor through an interface circuit of the electronic device, which is not specifically limited in the embodiments of the present invention.

[0189] A transceiver is used to communicate with a network device or a terminal device.

[0190] Optionally, the transceiver may include a receiver and a transmitter, wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0191] Optionally, the transceiver may be integrated with the processor, or may exist independently and be coupled to the processor via an interface circuit of the router, which is not specifically limited in the embodiment of the present invention.

[0192] In addition, the technical effects of the electronic device can refer to the technical effects of the data transmission method in the above method embodiment, which will not be repeated here.

[0193] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0194] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0195] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0196] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0197] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0198] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0199] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

Claims

1. An Al intelligent 3D spraying control system for surface treatment of urban art installations, characterized in that: The system includes a controller and an execution terminal, and the system is configured as follows: The controller acquires spraying data, the spraying data is image data to be sprayed, the spraying data includes n layers and n layer images corresponding to the n layers, namely, a first layer image, a second layer image ... an nth layer image, wherein n is a natural number greater than or equal to 3; The controller obtains the mj-th layer image and the m+j-th layer image, and generates the mj-th layer trajectory and the m+j-th layer trajectory according to the mj-th layer image and the m+j-th layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j; The controller obtains a trained neural network model, and inputs the mj-th layer trajectory and the m+j-th layer trajectory into the trained neural network model, wherein the neural network model is used to output a predicted layer trajectory of a middle layer of two images according to the input two layer trajectories; The controller obtains the m-th layer trajectory according to the output result of the neural network training model, and controls the execution terminal to spray the m-th layer image according to the m-th layer trajectory.

2. The Al intelligent 3D spraying control system for surface treatment of urban art installations according to claim 1 is characterized in that: The system is configured to: The controller obtains the mj-th layer image and the m+j-th layer image, and generates the mj-th layer trajectory and the m+j-th layer trajectory according to the mj-th layer image and the m+j-th layer image, wherein m and j are both natural numbers not equal to 0, and n>m, m>j, including: The controller acquires the mj-th layer image, and divides the mj-th layer image into a plurality of sub-images, wherein the plurality of sub-images constitute the mj-th layer image; If the controller determines that at least one side of one of the sub-images is not adjacent to another of the sub-images, then determining the sub-image to be a target sub-image; The controller acquires all the target sub-images, and uses the target sub-images as nodes and the lines between two adjacent target sub-images as paths to acquire a plurality of first Euler paths formed by the target sub-images; The controller determines a plurality of target areas based on the positional relationship between the plurality of first Euler paths, wherein the target areas are areas separated and formed with the first Euler paths as boundaries; The controller determines a filling area among the plurality of target areas based on the mj-th layer image, and determines the mj-th layer track according to the filling area.

3. The Al intelligent 3D spraying control system for surface treatment of urban art installations according to claim 2 is characterized in that: The system is configured to: The controller determines a filling area in the plurality of target areas based on the mj-th layer image, and determines the mj-th layer track according to the filling area, including: The controller obtains the sub-image in each of the filling areas, and uses the sub-image as a node and a line between two adjacent sub-images as a path to obtain a plurality of second Euler paths formed by the sub-images; The controller generates the mj-th layer trajectory based on a plurality of the second Euler paths.

4. The Al intelligent 3D spraying control system for surface treatment of urban art installations according to claim 3 is characterized in that: The system is configured to: The controller generates the mj-th layer trajectory based on the plurality of the second Euler paths, including: The controller connects a plurality of the second Euler paths based on the shortest path principle to form the mj-th layer trajectory.

5. The Al intelligent 3D spraying control system for surface treatment of urban art installations according to claim 1 is characterized in that: The system is configured to: The controller obtains a trained neural network model, and inputs the mj-th layer trajectory and the m+j-th layer trajectory into the trained neural network model, wherein the neural network model is used to output a predicted layer trajectory of a middle layer of two layers of images according to the input two layers of layer trajectory, including: The controller obtains a training set, wherein the training set includes k layers of adjacent layer trajectories, wherein k is a natural number greater than or equal to 3; The controller imports the training set into the neural network model and performs iterative calculations, stops the calculations when the iterative calculation process meets preset conditions, and obtains the trained neural network training model.

6. The Al intelligent 3D spraying control system for surface treatment of urban art installations according to claim 5 is characterized in that: The system is configured to: The controller imports the training set into the neural network model and performs iterative calculation, stops the calculation when the iterative calculation process meets the preset conditions, and obtains the trained neural network training model, including: The controller selects the i-1th layer track, the i-th layer track and the i+1th layer track from the k-th layer track, wherein i is a natural number not equal to 0, and i <k; The controller uses the data of the i-1th layer track and the data of the i+1th layer track as two different dimensional vectors to form a feature vector of the data of the i-th layer track and performs iterative calculation; When the iterative calculation process meets the preset conditions, the calculation is stopped, and the controller obtains the trained neural network training model.

7. The Al intelligent 3D spraying control system for surface treatment of urban art installations according to claim 6 is characterized in that: The system is configured to: When the iterative calculation process meets the preset conditions, the calculation is stopped, and the trained neural network training model is obtained, including: The controller obtains k-2 error values ​​based on the training process of the neural network model according to the training set, and determines an average error value based on the k-2 error values; The controller compares the average error value with a preset value, and when the average error value is less than or equal to the preset value, stops training and outputs the trained neural network model.

8. The Al intelligent 3D spraying control system for surface treatment of urban art installations according to claim 6 is characterized in that: The system is configured to: The controller obtains k-2 error values ​​based on the training process of the neural network model according to the training set, and determines an average error value based on the k-2 error values, including: The controller inputs the data of the i-1th layer trajectory and the data of the i+1th layer trajectory into the neural network training model, and obtains the predicted layer trajectory output by the neural network training model; The controller determines the error value according to the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory.

9. The Al intelligent 3D spraying control system for surface treatment of urban art installations according to claim 8 is characterized in that: The system is configured to: The controller determines an error value according to the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory, satisfying: If the data of the predicted layer track is greater than the data of the i-th layer track, the error value is determined as: t=y(yx) Among them, t is the error value, y is the data of the predicted layer trajectory, and x is the data of the i-th layer trajectory.

10. The AI ​​intelligent 3D spray control system for surface treatment of urban art installations according to claim 8, characterized in that: The system is configured to: The controller determines an error value according to the data of the predicted layer trajectory output by the neural network training model and the data of the i-th layer trajectory, satisfying: If the data of the predicted layer track is less than the data of the i-th layer track, the error value is determined as: t=y(xy) Among them, t is the error value, y is the data of the predicted layer trajectory, and x is the data of the i-th layer trajectory.

Images