Novel data type for n-dimensional representation of objects with ultra-rich contents

Abstract

To provide punch forming of composite charges.SOLUTION: Generation of data enriched voxels is provided. A method of the present invention includes a step of receiving image data of a three-dimensional (3D) object. A number of key vertices are detected within the 3D object, and a bill of materials (BOM) is created for each key vertex. The BOM for each key vertex is then enriched with production data and sensor data, wherein the enriched BOM for each key vertex describes environmental conditions within a defined area around the 3D object. The enriched BOM for each key vertex is then fed into a respective neural network that generates a two-dimensional (2D) pixel containing all data from the enriched BOM, wherein the 2D pixel forms part of a tensor of 2D pixels.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] TECHNICAL FIELD This disclosure relates generally to data processing, and more particularly to integrating different data types into a coherent format. [Background technology]

[0002] Existing data formats often focus on a single dimension, such as visual data, temporal information, or thermal imagery. However, many real-world applications require a combination of such dimensions to understand a scenario. For example, autonomous vehicle navigation may require images, precise timestamps, thermal data, and tracking in six degrees of freedom to accurately interpret the surroundings, especially in low-light conditions or challenging environments. Summary of the Invention [Means for solving the problem]

[0003] An exemplary embodiment provides a computer-implemented method for generating data-enhanced voxels. The method includes receiving image data of a three-dimensional (3D) object. A number of key vertices are detected within the 3D object, and a bill of materials (BOM) is created for each key vertex. The BOM for each key vertex is then enriched with production data and sensor data, and the enriched BOM for each key vertex describes environmental conditions within a defined region around the 3D object. The enriched BOM for each key vertex is then fed to a respective neural network that generates two-dimensional (2D) pixels that include all data from the enriched BOMs, and the 2D pixels form part of a 2D pixel tensor.

[0004] Another exemplary embodiment provides a system for generating data-enhanced voxels, the system comprising: a storage device that stores program instructions; and one or more processors operatively connected to the storage device that execute the program instructions to cause the system to receive image data of a three-dimensional (3D) object, detect a number of key vertices within the 3D object, create a bill of materials (BOM) for each key vertex, enrich the BOM for each key vertex with production data and sensor data, the enriched BOM for each key vertex describing environmental conditions within a defined region around the 3D object, and feed the enriched BOM for each key vertex to a respective neural network that generates two-dimensional (2D) pixels including all data from the enriched BOM, the 2D pixels forming part of a 2D pixel tensor.

[0005] Another exemplary embodiment provides a computer program product for generating data-enhanced voxels, the computer program product comprising: a computer-readable storage medium having program instructions embodied thereon to perform the steps of receiving image data of a three-dimensional (3D) object, detecting a number of key vertices within the 3D object, creating a bill of materials (BOM) for each key vertex, augmenting the BOM for each key vertex with production data and sensor data, where the augmented BOM for each key vertex describes environmental conditions within a defined region around the 3D object, and feeding the augmented BOM for each key vertex to a respective neural network that generates two-dimensional (2D) pixels including all data from the augmented BOM, where the 2D pixels form a portion of a 2D pixel tensor.

[0006] The features and functions can be achieved alone in various embodiments of the present disclosure and may be combined in still other embodiments, further details of which can be seen with reference to the following description and drawings.

[0007] The novel features believed characteristic of the exemplary embodiments are set forth in the appended claims. However, the exemplary embodiments, as well as their preferred modes of use, further objects and features, will best be understood by reference to the following detailed description of exemplary embodiments of the present disclosure, when considered in conjunction with the accompanying drawings. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 illustrates a block diagram of a daxle system in accordance with an illustrative embodiment. [Figure 2] 10 is an illustration of a relationship between different dimensional data representations in accordance with an illustrative embodiment; [Figure 3] 1 illustrates the contrast between pixel data representation and daxle data representation according to an exemplary embodiment. [Figure 4] 1 illustrates a time representation of an N-dimensional data format in accordance with an example embodiment. [Figure 5] 1 illustrates an example of a 3D CAD object from which a daxle can be generated, in accordance with an illustrative embodiment; [Figure 6] 10 is an illustration of a table for creating a bill of materials for each key vertex of a 3D object in accordance with an illustrative embodiment; [Figure 7] 1 illustrates a time stack of N-dimensional daxle data in accordance with an example embodiment. [Figure 8] 1 illustrates the digestion of daxle data and its subsequent use in machine learning according to an exemplary embodiment. [Figure 9] 1 depicts a flowchart illustrating a process for generating data-enhanced voxels in accordance with an illustrative embodiment. [Figure 10] 1 is an illustration of a block diagram of a data processing system in accordance with an illustrative embodiment; DETAILED DESCRIPTION OF THE INVENTION

[0009] The illustrative embodiments recognize and take into account that existing data formats often focus on a single dimension, such as visual data, temporal information, or thermal imagery, however, many real-world applications require a combination of such dimensions to understand a scenario.

[0010] The exemplary embodiment provides a data structure that encapsulates high resolution images, precise time stamps, thermal image layers, and six degrees of freedom tracking information in a single cohesive package.

[0011] Figure 1 is a block diagram of a daxle system depicted in accordance with an example embodiment. The daxle system 100 receives an input of a 3D object 102, such as a CAD (computer-aided design) model or an image of the 3D object. The daxle system 100 identifies several key vertices 104 that make up the 3D object 102. (See Figure 5.)

[0012] The daxle system 100 creates several bills of materials (BOMs) 108 for the key vertices 104. For each key vertex 104 in the key vertices 106, the daxle system 100 creates a respective BOM 110. Each BOM 110 is augmented with additional data about its corresponding key vertex to generate an augmented 3D BOM 112.

[0013] Additional data used to generate the enhanced 3D BOM 112 is provided by a data accumulator 126, which draws from multiple data sources. One data source includes production and manufacturing attributes 128, which can include, for example, materials used, suppliers, costs, processing times, and inspections. (See FIGS. 6 and 7.) The data accumulator 126 can also add design information 130, such as surface roughness, specific features at key vertices of interest, and geometrically based manufacturing instructions. The data accumulator can also add sensor data 132 to the enhanced 3D BOM 112. Examples of sensor data 132 include red, green, and blue (RGB) image data, timestamp information, thermal imaging data, humidity, and six-degree-of-freedom (6DOF) tracking data.

[0014] The enhanced 3D BOM 112 is fed to several data enrichment neural networks 114 (see FIG. 8). Each enhanced 3D BOM 112 is fed to a respective data enrichment neural network 116, which generates 2D pixels 118 containing the enhanced BOM data 120 contained in the enhanced 3D BOM 112 but in a form that is more amenable to machine learning.

[0015] The 2D pixels form part of a 2D tensor 122, which can be fed to a downstream neural network 124, such as a convolutional neural network (CNN).

[0016] The daxle system 100 may be implemented in software, hardware, firmware, or a combination thereof. When software is used, the operations performed by the daxle system 100 may be implemented in program code configured to run on hardware, such as a processor unit. When firmware is used, the operations performed by the daxle system 100 may be implemented in program code and data and stored in persistent memory running on a processor unit. When hardware is employed, the hardware may include circuitry that operates to perform the operations in the daxle system 100.

[0017] In illustrative examples, the hardware may take the form of at least one of a circuit system, an integrated circuit, an application-specific integrated circuit (ASIC), a programmable logic device, or other suitable type of hardware configured to perform a plurality of operations. Using a programmable logic device, the device may be configured to perform a plurality of operations. The device may be later reconfigured or may be permanently configured to perform a plurality of operations. Programmable logic devices include, for example, programmable logic arrays, programmable array logic, field programmable logic arrays, field programmable gate arrays, and other suitable hardware devices. Furthermore, processes may be implemented in organic components integrated with inorganic components, or may be comprised entirely of organic components, excluding humans. For example, processes may be implemented as organic semiconductor circuits.

[0018] Computer system 150 is a physical hardware system that includes one or more data processing systems. When multiple data processing systems are present in computer system 150, the data processing systems communicate with each other using a communication medium. The communication medium may be a network. The data processing systems may be selected from at least one of a computer, a server computer, a mobile device such as a tablet computer, or other suitable data processing system.

[0019] As shown, computer system 150 includes multiple processor units 152 capable of executing program code 154 that implements processes in the illustrative example. As used herein, a processor unit of number of processor units 152 is a hardware device, comprised of hardware circuitry, such as that on an integrated circuit, that processes in response to instructions and program code to operate a computer. When multiple processor units 152 execute program code 154 for a process, multiple processor units 152 are one or more processor units that may be on the same computer or different computers. In other words, a process may be distributed among processor units on the same or different computers within a computer system. Furthermore, multiple processor units 152 may be the same or different types of processor units. For example, multiple processor units may be selected from at least one of a single-core processor, a dual-core processor, a multi-processor core, a general-purpose central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), or some other type of processor unit.

[0020] 2 illustrates the relationship between different dimensional data representations according to an example embodiment. As shown, pixels (picture elements) 202 are typically used to represent two-dimensional (2D) visual data and are arranged in a 2D grid 204.

[0021] A voxel (volumetric pixel) 206 is the three-dimensional equivalent of a two-dimensional pixel 202. A voxel 206 represents a point in three-dimensional space. The voxels 206 are arranged in a three-dimensional grid 208 to form a volumetric representation of an object or space.

[0022] Exemplary embodiments incorporate additional data into voxels to form daxle210, an N-dimensional data-enriched voxel. daxle210 is a data format that integrates diverse data streams into a unified structure. It encapsulates high-resolution imagery, precise timestamps, thermal imaging layers, and six-degree-of-freedom tracking information in a single cohesive package. This combination allows users to not only observe the visual appearance of a scene, but also delve into its temporal aspects, thermal properties, and spatial dynamics. The fusion of these dimensions results in a holistic representation of the environment, facilitating deeper insights and more informed decision-making.

[0023] A daxle 210 consists of an encapsulated 3D BOM with temporal properties. Thus, each 3D BOM 112 is a subset of a daxle 210 at a point in time. Thus, each 3D BOM 112 is a member of a daxle 210 that represents an n-dimensional event and environment.

[0024] Conventional formats, such as conventional pixels 202 and voxels 206, inadequately encapsulate a complete understanding of complex scenarios. Such existing formats often focus on a single dimension, such as visual data, temporal information, or even thermal imagery. However, many real-world applications require the synthesis of these dimensions to comprehensively understand a scenario. For example, in autonomous vehicle navigation, a single format incorporating imagery, precise timestamps, thermal data, and six-degree-of-freedom tracking can enhance a vehicle's ability to accurately interpret its surroundings, especially in low-light conditions or challenging environments. The daxle format of the exemplary embodiment is applicable in a variety of fields, such as robotics, surveillance, and environmental monitoring.

[0025] 3 illustrates the contrast between pixel and daxle data representations in accordance with an example embodiment. This example shows an image 300 of a robot 302 on a factory floor.

[0026] A given point 304 in image 300 can be represented by a pixel 306 and a daxle 308. A pixel 306 contains RGB data, but by itself does not provide much context without metadata or additional information to describe the image.

[0027] In contrast, in this example, daxle 308 includes not only RGB layers of data, but also a depth layer (3D depth), an environment layer (where the image was captured), a six-degree-of-freedom layer related to the imaging device that captured the image, a timestamp layer, a state layer (e.g., acquired during stage 1 of the manufacturing process), a thermal layer (temperature in the environment at the time of image capture), a privacy layer (allowing or denying pixel-by-pixel access to image 300 or portions of the image per layer during specific time frames and / or for specified users), and an open (variable) data layer to allow users to define customized layers of specific types of data. Thus, for each RGB pixel, there is also an N-dimensional representation of the contextual data associated with that RGB pixel.

[0028] 4 illustrates a time representation of an N-dimensional data format according to an example embodiment. This example shows daxle values ​​between timestamp values ​​t=1 to t=n on a time axis 400.

[0029] In this example, the data point 402 at time t=1 is a 15-dimensional daxle that includes a time value (t1), an infrared value (IR1), an X-axis value (x1), a Y-axis value (y1), a Z-axis value (z1), a probability that event 1 occurs at time t1 (P1(e1)), a probability that event 2 occurs at time t1 (P1(e2)), a red value (R1), a green value (G1), a blue value (B1), a humidity value (Hu1), a pitch value (Pitch1), a roll value (Roll1), a yaw value (Yaw1), and a variable (open) layer value (Var1).

[0030] P1 (e1) and P2 (e2) can be generated, for example, from production data, environmental data (e.g., changing shadows or light indicating an approaching object), or historical data. Var1 allows the user to add values ​​to daxle 402, such as events, privacy settings, cost factors, etc., based on timestamp values. For example, Var1 can specify not to show a particular outline of an object throughout the supply chain timeframe. The system then encrypts the data accordingly.

[0031] 5 shows an example of a 3D CAD object from which a daxle can be generated, according to an exemplary embodiment. Model-based instructions may describe manufacturing instructions in a specification, such as applying a particular sealant to any sharp 90-degree edges or applying sealant around drilled holes (e.g., circle 504). While such instructions can be extracted from the specification, applying them requires geometric references for the object 500, which can be provided by a daxle.

[0032] For a 3D object 500, the daxle system can detect a number of key vertices 502. The number of key vertices can be more or less depending on the complexity of the object 500 and the manufacturing instructions that need to reference the object's geometry.

[0033] 6 shows a table for creating a bill of materials for each key vertex of a 3D object 500 according to an example embodiment. Table 600 specifies several parameters for each identified key vertex of the object in question.

[0034] In this example, for each key vertex V1-V2, table 600 specifies the X, Y, Z values, material used, aircraft coordinate system (station (STA), water line (WL), butt line (BL)), and supplier. Depending on the production stage, other metadata may be included in table 600, such as cost, features that should be found at that location (e.g., sealant, primer, decal), etc. Using the information in table 600, a 3D bill of materials (BOM) is populated for each key vertex based on production and manufacturing attributes to generate a daxle for each key vertex.

[0035] 7 illustrates a temporal stacking of N-dimensional daxle data in accordance with an exemplary embodiment. Because daxles are multidimensional, they can be used to support temporal product lifecycle management (PLM).

[0036] In this example, daxle data is presented according to different stages of the product cycle, including original, manufacturing, assembly, and service by the supplier. BOM data, including daxle, may change over time from one lifecycle stage to the next. For example, material or inspection requirements may change from one stage to another. Similarly, processing time or costs may change from one stage to another.

[0037] 8 illustrates the digestion of daxle data and its subsequent use in machine learning according to an exemplary embodiment. To digest the multi-layer data per daxle, each daxle 802 is passed through a fully connected input layer 804 of a data-reinforced neural network 806.

[0038] The data-enhanced neural network 806 converts the multi-layered N-dimensional data in daxles 802 into 2D pixels 808 that contain all of the information in daxles 802. The data-enhanced neural network 806 is trainable to not lose any information during this conversion process and can use the information present in daxles 802 to predict the probability of missing values. For example, given six degrees of freedom and a heat data value, the data-enhanced neural network 806 can likely predict the humidity value if that value is missing from daxles 802. Thus, the data-enhanced neural network 806 represents a transition from data that is deterministic in nature to data that is probabilistic in nature.

[0039] The 2D pixels can form part of a 2D tensor 810 that can be used to train a downstream neural network 812 for AI and machine learning applications such as classification, feature generation, etc. The downstream neural network 812 can include, for example, a CNN.

[0040] 9 shows a flowchart illustrating a process for generating data-enhanced voxels according to an example embodiment. The process 900 can be implemented in the daxle system 100 of FIG.

[0041] Process 900 begins by receiving image data for a three-dimensional (3D) object (act 902). Process 900 detects a number of key vertices within the 3D object (act 904).

[0042] Process 900 creates a bill of materials (BOM) for each key vertex (operation 906), then enriches the BOM for each key vertex with production data and sensor data, where the enriched BOM for each key vertex describes environmental conditions within a defined region around the 3D object (operation 908). The production data can include materials used to manufacture the 3D object, suppliers, surface roughness, cost, processing time, inspection, specified features at each location, airframe coordinate data, and manufacturing instructions with geometric references.

[0043] The sensor data can include RGB image data, timestamp, thermal image layer, humidity, and six-degree-of-freedom tracking data (i.e., X, Y, Z coordinates and roll, pitch, and yaw). The enhanced BOM can further include privacy data to restrict access to specified sensor data.

[0044] Process 900 feeds the augmented BOM for each key vertex to a respective neural network that generates a two-dimensional (2D) pixel containing all data from the augmented BOM, where the 2D pixel forms part of a 2D pixel tensor (operation 910). If one or more data values ​​are missing from a given augmented BOM, its respective neural network can predict the missing data values ​​based on other data values ​​in the augmented BOM.

[0045] Process 900 may further include training a downstream neural network using the 2D pixels as input (operation 912).

[0046] Process 900 performs a computer-aided manufacturing process according to the data in the 2D pixels (operation 914).

[0047] The process 900 then ends.

[0048] Referring now to Figure 10, a block diagram of a data processing system is shown in accordance with an illustrative embodiment. Data processing system 1000 may be used to implement computer system 150 in Figure 1. In this illustrative example, data processing system 1000 includes a communications framework 1002 that provides communications between a processor unit 1004, a memory 1006, persistent storage 1008, a communications unit 1010, an input / output (I / O) unit 1012, and a display 1014. In this example, communications framework 1002 takes the form of a bus system.

[0049] Processor unit 1004 is responsible for executing instructions for software that may be loaded into memory 1006. Processor unit 1004 may be multiple processors, a multi-processor core, or some other type of processor, depending on the particular implementation. In one embodiment, processor unit 1004 comprises one or more conventional general-purpose central processing units (CPUs). In an alternative embodiment, processor unit 1004 comprises one or more graphical processing units (GPUs).

[0050] Memory 1006 and persistent storage 1008 are examples of storage device(s) 1016. A storage device is any hardware capable of storing information, such as, but not limited to, data, program code in functional form, or other suitable information, on a temporary, persistent, or both temporary and persistent basis. Storage device 1016, in these illustrative examples, may also be referred to as a computer-readable storage device. Memory 1006, in these examples, may be, for example, a random access memory or any other suitable volatile or non-volatile storage device. Persistent storage 1008 may take various forms depending on the particular implementation.

[0051] For example, persistent storage 1008 may include one or more components or devices. For example, persistent storage 1008 may be a hard drive, a flash memory, a rewritable optical disk, a rewritable magnetic tape, or some combination thereof. The medium used by persistent storage 1008 may be removable. For example, a removable hard drive may be used for persistent storage 1008. Communications unit 1010, in these illustrative examples, provides for communication with other data processing systems or devices. In these examples, communications unit 1010 is a network interface card.

[0052] Input / output unit 1012 allows for the input and output of data with other devices that may be connected to data processing system 1000. For example, input / output unit 1012 may provide a connection for user input through at least one of a keyboard, a mouse, or some other suitable input device. Additionally, input / output unit 1012 may send output to a printer. Display 1014 provides a mechanism for displaying information to a user.

[0053] Instructions for at least one of the operating system, applications, or programs may be located in storage devices 1016, which are in communication with processor unit 1004 through communications framework 1002. The processes of the different embodiments may be performed by processor unit 1004 using computer-implemented instructions, which may be located in a memory, such as memory 1006.

[0054] These instructions are referred to as program code, computer usable program code, or computer readable program code, which may be read and executed by a processor in processor unit 1004. The program code in different embodiments may be embodied on different physical or computer readable storage media, such as memory 1006 or persistent storage 1008.

[0055] Program code 1018 is located in a functional form on computer readable media 1020 that is selectively removable and may be loaded onto or transferred to data processing system 1000 for execution by processor unit 1004. Program code 1018 and computer readable media 1020 form computer program product 1022 in these illustrative examples. In one example, computer readable media 1020 may be computer readable storage media 1024 or computer readable signal media 1026.

[0056] In these illustrative examples, computer readable storage medium 1024 is not a medium that propagates or transmits program code 1018, but rather a physical or tangible storage device used to store program code 1018. Computer readable storage medium 1024 as used herein should not be interpreted as being a transitory signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through fiber optic cable), or electrical signals transmitted through wires. Computer readable medium as used herein should not be interpreted as being a transitory signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through fiber optic cable), or electrical signals transmitted through wires.

[0057] Alternatively, program code 1018 may be transferred to data processing system 1000 using computer readable signal medium 1026. Computer readable signal medium 1026 may be, for example, a propagated data signal containing program code 1018. For example, computer readable signal medium 1026 may be at least one of an electromagnetic signal, an optical signal, or any other suitable type of signal. These signals may be transmitted over at least one of a communications link, such as a wireless communications link, an optical fiber cable, a coaxial cable, a wire, or any other suitable type of communications link.

[0058] The different components illustrated for data processing system 1000 are not meant to provide architectural limitations to the manner in which different embodiments may be implemented. The different illustrative embodiments may be implemented in a data processing system including components in addition to or instead of those illustrated for data processing system 1000. Other components illustrated in FIG. 10 may vary from the illustrative example shown. The different embodiments may be implemented using any hardware device or system capable of running program code 1018.

[0059] As used herein, the phrase "at least one of," when used in conjunction with a list of items, means that different combinations of one or more of the listed items may be used, and that only one of each item in the list may be required. In other words, "at least one of" means that any combination and number of items may be used from the list, but not all of the items in the list may be required. An item may be a specific object, thing, or category.

[0060] For example, without limitation, "at least one of item A, item B, or item C" may include item A, item A and item B, or item B. This example may also include item A, item B, and item C, or item B and item C. Of course, any combination of these items may be present. In some illustrative examples, "at least one of" may be, for example, without limitation, two items A, one item B, and ten items C, four items B and seven items C, or other suitable combinations.

[0061] As used herein, "plurality," when used with reference to an item, means one or more items. For example, "plurality of different types of networks" is one or more different types of networks. In illustrative examples, a "set" used with a reference item means one or more items. For example, a set of metrics is one or more of the metrics.

[0062] The descriptions of different exemplary embodiments are presented for purposes of illustration and description and are not intended to be exhaustive or limited to the disclosed forms of embodiments. Various exemplary examples describe components that perform actions or operations. In the exemplary examples, a component may be configured to perform the described actions or operations. For example, a component may have a structural configuration or design that provides the component with the ability to perform the actions or operations described as being performed by the component in the exemplary examples. Furthermore, to the extent that the terms "includes," "including," "has," "contains," and variations thereof are used herein, such terms are intended to be inclusive, similar to the open transitional term "comprises," without excluding any additional or other elements.

[0063] Numerous modifications and variations will be apparent to those skilled in the art. Furthermore, various exemplary embodiments may provide different configurations than other preferred embodiments. The selected embodiment or embodiments have been chosen and described in order to best explain the principles, practical applications of the embodiments, and to enable others skilled in the art to understand the disclosure of the various embodiments with various modifications suited to the particular use contemplated. [Explanation of symbols]

[0064] 1st stage, event 2. Events 100 daxle system 102 3D objects 104 key vertices 106 key vertices 108 Bill of Materials (BOM) 110 Bill of Materials (BOM) 112 Enhanced 3D BOM 114 Data-enhanced Neural Networks 116 Data-enhanced Neural Networks 118 2D pixels 120 Enhanced BOM Data 122 2D Tensors 124 Downstream Neural Network 126 Data Accumulator 128 Production and Manufacturing Attributes 130 Design information 132 Sensor Data 150 Computer Systems 152 processor units 154 Program Code 202 2D pixels 204 2D Grid 206 voxels 208 3D Grid 300 images 302 Robot 306 pixels 400 time axes 402 data points 500 3D objects 502 key vertices 504 yen 804 fully connected input layer 806 Data-enhanced Neural Networks 808 2D pixels 810 2D Tensors 812 Downstream Neural Network 900 processes 1000 Data Processing Systems 1002 Communication Framework 1004 processor unit 1006 memory 1008 Persistent Storage 1010 Communication Unit 1012 Input / Output Unit 1014 Display 1016 Storage Devices 1018 Program Code 1020 Computer-readable medium 1022 Computer program products 1024 computer-readable storage medium 1026 Computer-readable signal medium

Claims

1. 1. A computer-implemented method for generating data-enhanced voxels, comprising: Using some processors, receiving (902) image data of a three-dimensional (3D) object (102); Detecting (904) a number of key vertices (104) within the 3D object; creating (906) a bill of materials (BOM) (110) for each key vertex; augmenting (908) the BOM for each key vertex with production data (128, 130) and sensor data (132), wherein the augmented BOM for each key vertex describes environmental conditions within a defined region around the 3D object; and feeding (910) the augmented BOM (112) for each key vertex to a respective neural network (116) that generates a two-dimensional (2D) pixel (118) containing all data from the augmented BOM, the 2D pixel forming part of a 2D pixel tensor (122).

2. The method of claim 1 , further comprising training (912) a downstream neural network (124) using the 2D pixels as input.

3. The method of claim 1 , further comprising: performing (914) a computer-aided manufacturing process according to the data in the 2D pixels.

4. 10. The method of claim 1, further comprising predicting, by each neural network, missing data values ​​of the augmented BOM based on other data values ​​in the augmented BOM.

5. The production data is material, Suppliers, Surface roughness, cost, Processing time, inspection, specified characteristics at each location, Aircraft coordinate system data, or The method of claim 1 , further comprising at least one of geometrically based manufacturing instructions.

6. The sensor data is Red, Green, Blue (RGB), timestamp, Thermal imaging layer, Humidity, or The method of claim 1 , including at least one of six degrees of freedom (DOF) tracking data.

7. The method of claim 1 , wherein the enriched BOM further includes privacy data for restricting access to specified sensor data.

8. 1. A system for generating data-enhanced voxels, comprising: a storage device for storing program instructions; a device operatively connected to said storage device and executing said program instructions to said system; receiving (902) image data of a three-dimensional (3D) object (102); Detecting (904) some key vertices (104) within the 3D object; Generate a bill of materials (BOM) (110) for each key vertex (906); augmenting (908) the BOM for each key vertex with production data (128, 130) and sensor data (132), the augmented BOM for each key vertex describing environmental conditions within a defined region around the 3D object; and one or more processors for feeding (910) the augmented BOM (112) for each key vertex to a respective neural network (116) that generates a two-dimensional (2D) pixel (118) containing all data from the augmented BOM, the 2D pixel forming part of a 2D pixel tensor (122).

9. 9. The system of claim 8, wherein the one or more processors further execute program instructions for training (912) a downstream neural network (124) using the 2D pixels as input.

10. 9. The system of claim 8, wherein the one or more processors further execute program instructions to cause the system to perform (914) a computer-aided manufacturing process according to the data in the 2D pixels.

11. 10. The system of claim 8, wherein the one or more processors further execute program instructions to cause the system to predict, with a respective neural network, missing data values ​​of the augmented BOM based on other data values ​​in the augmented BOM.

12. The production data is material, Suppliers, Surface roughness, cost, Processing time, inspection, specified characteristics at each location, Aircraft coordinate system data, or The system of claim 8 , further comprising at least one of geometrically based manufacturing instructions.

13. The sensor data is Red, Green, Blue (RGB), timestamp, Thermal imaging layer, Humidity, or The system of claim 8 , including at least one of six degrees of freedom (DOF) tracking data.

14. The system of claim 8 , wherein the enriched BOM further includes privacy data for restricting access to specified sensor data.

15. 1. A computer program for generating data-enhanced voxels, comprising: receiving (902) image data of a three-dimensional (3D) object (102); Detecting (904) a number of key vertices (104) within the 3D object; creating (906) a bill of materials (BOM) (110) for each key vertex; augmenting (908) the BOM for each key vertex with production data (128, 130) and sensor data (132), wherein the augmented BOM for each key vertex describes environmental conditions within a defined region around the 3D object; and feeding (910) the augmented BOM (112) for each key vertex to a respective neural network (116) that generates a two-dimensional (2D) pixel (118) containing all data from the augmented BOM, the 2D pixel forming part of a 2D pixel tensor (122).

16. 16. The computer program of claim 15, further comprising instructions for training (912) a downstream neural network (124) using the 2D pixels as input.

17. 16. The computer program product of claim 15, further comprising instructions for performing (914) a computer-aided manufacturing process according to the data in the 2D pixels.

18. 16. The computer program of claim 15, further comprising instructions for predicting, by each neural network, missing data values ​​of the augmented BOM based on other data values ​​in the augmented BOM.

19. The production data is material, Suppliers, Surface roughness, cost, Processing time, inspection, specified characteristics at each location, Aircraft coordinate system data, or 16. The computer program of claim 15, further comprising at least one of geometrically based manufacturing instructions.

20. The sensor data is Red, Green, Blue (RGB), timestamp, Thermal imaging layer, Humidity, or 16. The computer program of claim 15, comprising at least one of six degrees of freedom (DOF) tracking data.

21. The computer program product of claim 15 , wherein the enhanced BOM further includes privacy data for restricting access to specified sensor data.

Images