Systems and methods for assisted plant pruning

Abstract

The invention relates to a method for assisting the pruning of plants (10) implemented by an electronic device (21), comprising the following steps: a. being equipped with an electronic device (12; 22; 32) comprising a display area (16; 26; 36) and a camera (18; 28; 38); b. taking at least one image of the plant (10) to be pruned using the camera (18; 28; 38) of the electronic device (12; 22; 32); c. using a machine learning engine (50) previously trained with training data to determine a pruning guide, and d. displaying the pruning guide as a superposition on a real image of the plant on the display area (16; 26; 36) of the electronic device. The invention also relates to a system (40) for assisting the pruning of plants intended to implement the above method.

Description

Technical Field

[0001] The present invention relates to a system and a method for assisting plant pruning, mainly in the fields of viticulture, arboriculture and rose cultivation. Said system and method are implemented by means of electronic devices, for example by means of augmented reality glasses, a tablet or a smartphone. Background Art

[0002] Particularly in the context of viticulture, there are techniques used to ensure good fruiting on the vine. Of the skills that need to be mastered, vine pruning is probably the one most relevant to the quality of the grapes produced. Winemakers seek grape yields while avoiding excessive vine length. Pruning serves to regularize and prolong the production of the vines. Pruning also allows an increase in yield by significantly reducing the number of bunches and ultimately increasing their size. Size is important for health, and therefore the preservation of the plant's assets. Improper pruning can cause the grape plants to wilt, in addition to inviting devastating diseases, especially Esca. Therefore, harvesting will become more and more regular year by year.

[0003] It is therefore very important that the vines are pruned by professionals in order to maintain the best quality of the plant for the longest possible time and in relation to the quality of the grapes produced.

[0004] However, in the field of viticulture, agricultural workers who carry out the pruning that must be quick and cost-effective are rarely trained in the rules of this field, which has a non-negligible impact on the quality of the grapes produced. Summary of the invention

[0005] The object of the present invention is therefore to provide a method for assisting plant pruning, which is particularly applicable in the fields of viticulture, arboriculture and rose cultivation, but is generally applicable to any plant that requires thoughtful pruning.

[0006] To this end, a method for assisting plant pruning implemented by an electronic device is proposed, which includes the following steps:

[0007] a. Equipping the subject with an electronic device including a display area and a camera;

[0008] b. Using a camera to capture at least one image of the plant to be pruned, hereinafter referred to as a reference image;

[0009] c. using a machine learning engine previously trained with the training data to determine cutting guidance, and

[0010] d. Displaying the cutting guide on the display area of ​​the electronic device as a superimposition on the actual image of the plant to be cut.

[0011] In one embodiment, the electronic device is in the form of augmented reality glasses that include a camera and lenses that include a display area.

[0012] Of course, the use of augmented reality in the agricultural field is known. For example, WO2015135786 discloses an assistance system for assisting an operator of agricultural machinery in his working environment. The assistance system comprises augmented reality glasses configured to display information as superimposed on the agricultural environment. The type of information displayed may be planning and / or management data, information about the operation of agricultural machinery, information for assisting the operator (help center) and / or training information.

[0013] However, the information displayed on the lenses of augmented reality glasses is not intended to assist agricultural producers in all the work they perform directly in the natural environment.

[0014] In one embodiment, the electronic device is in the form of a tablet or smartphone that includes a display area and a camera.

[0015] In one embodiment, the training data is in the form of recommended crop marks or crop points or coloring of unwanted branches in an image including reference features representing signatures unique to each plant image in a series of plant images having various appearances.

[0016] In one embodiment, in step b, a series of images of the plant to be pruned are taken from multiple angles using a camera of an electronic device. This step is followed by a step of generating a 3D digital model of the plant to be pruned based on the series of images of the plant. Reference features are extracted from the 3D digital model. These reference features represent signatures that are unique to the plant to be pruned.

[0017] In one embodiment, the reference feature corresponds in particular to a fork of a branch of the plant to be pruned, and preferably to the end of a branch.

[0018] In one embodiment, the machine learning engine is a neural network that has been trained using reference features obtained from training images to classify features extracted from the 3D digital model and then infer cropping guidelines therefrom, such as cropping guidelines selected from a cropping database.

[0019] These cutting instructions can then be displayed in augmented reality as an overlay on the camera-captured image of the plant to be pruned.

[0020] In one embodiment, the cutting guidance includes cutting points or cutting marks superimposed on branches in the real plant image or coloring and / or explanatory videos / images of branches that are not to be retained.

[0021] In one embodiment, instructions are displayed on a display area of ​​the electronic device for moving around the plant to be pruned to capture images of the plant from the best angles so that a 3D digital model can be generated.

[0022] In one embodiment, the reference image or 3D digital model may be transmitted to the remote operator in real time or near real time. The operator then transmits audio and / or visual cutting instructions to the object.

[0023] In one embodiment, the plant to be pruned is a grapevine plant. In another embodiment, the plant to be pruned may be a rose bush, a fruit tree such as an apple tree, or any other type of plant that requires careful consideration before pruning.

[0024] Another aspect of the invention relates to a system for assisting plant pruning, which is intended to implement the method according to its various embodiments as described above.

[0025] To this end, the system comprises:

[0026] - camera;

[0027] - an electronic device comprising a display area for displaying one or more cutting information as superimposed on the image of the plant captured by the camera in augmented reality, the one or more cutting information being selected from the group consisting of text, image, video, and / or cutting point / marker, and

[0028] - a machine learning engine, previously trained with training images, for identifying reference features of the plants photographed by the camera and for selecting cutting guidelines associated with these reference features.

[0029] In one embodiment, the electronic device is in the form of augmented reality glasses comprising a camera and lenses comprising a display area. The system further comprises a smartphone configured to transmit data related to the cutting instructions to the augmented reality glasses via a wireless interface, in particular via Wi-Fi or Bluetooth, so as to display the instructions on the display area of ​​the augmented reality glasses.

[0030] In one embodiment, the electronic device is in the form of a tablet or smartphone that includes a display area and a camera.

[0031] In one embodiment, the machine learning engine is a neural network.

[0032] In one embodiment, the system further comprises an electronic device or a remote processing unit. The electronic device or the remote processing unit comprises a computing unit for generating a 3D digital model.

[0033] In one embodiment, the electronic device is a smartphone or a tablet.

[0034] In one embodiment, the image database and / or instruction database is stored in a memory of the electronic device or in a memory of a remote processing unit.

[0035] In one embodiment, the machine learning engine is implemented by software executing in the memory of the electronic device or in the memory of a remote processing unit.

[0036] In one embodiment, processing of images captured by the camera is performed by software executing in the memory of the electronic device or in the memory of a remote processing unit.

[0037] In one embodiment, the 3D model is obtained based on a plurality of consecutive images captured by a camera by means of software executed in a memory of the electronic device or in a memory of a remote processing unit.

[0038] In one embodiment, reference features are extracted from one or more images of the plant or from a 3D model of the plant by means of software executed in a memory of the electronic device or in a memory of a remote processing unit.

[0039] In one embodiment, the remote processing unit is a server configured to transmit data related to cutting instructions to the electronic device via a communication network, such as a cellular telephone network.

[0040] Another aspect of the invention relates to a software application for a smartphone for assisting in the pruning of plants, in particular plants such as grapevines. The software application, when executed, allows the following operations to be performed:

[0041] - Generate a 3D digital model of the plant based on a series of images of various views of the plant;

[0042] - Extracting reference features from the 3D digital model, which represent the unique features of the plant to be pruned;

[0043] - Classifying reference features with the help of a machine learning engine previously trained using reference images; and

[0044] - Select a cutting guide based on that category.

[0045] Another aspect of the invention relates to a method for assisting the pruning of plants, in particular plants such as grapevines, comprising the following steps:

[0046] a. Equipping the subject with an electronic device including a display area and a camera;

[0047] b. photographing the plant to be pruned with the aid of a camera of the electronic device and transmitting the image of the plant to the remote operator in real time; and

[0048] c. The operator transmits instructions for pruning the plant, and the instructions are displayed on the display area in augmented reality as superimposed on the real image of the plant to be pruned.

[0049] In one embodiment, the electronic device is in the form of augmented reality glasses that include a camera and lenses that include a display area.

[0050] In one embodiment, the augmented reality glasses are equipped with a microphone and headphones to allow two-way communication between the subject and the operator.

[0051] In one embodiment, the electronic device is in the form of a tablet or smartphone that includes a display area and a camera.

[0052] In one embodiment, the instructions include an image selected by the operator from a series of plant images stored in a database. Each image includes cutting instructions including cutting points or cutting marks and / or explanatory videos / images superimposed on branches in the real plant image.

[0053] Another aspect of the invention relates to a method for assisting the pruning of plants, in particular plants such as grapevines, comprising the following steps:

[0054] a. Equipping the subject with a smartphone and augmented reality glasses, the augmented reality glasses comprising lenses having a display area;

[0055] b. the subject selects an image by means of a smartphone from a series of plant images in a database stored in the smartphone's memory, each image being associated with cutting instructions including cutting points or cutting marks and / or explanatory videos / images, and

[0056] c. Transmitting the cutting instructions to the augmented reality glasses so that the cutting instructions are displayed in augmented reality on the display area as superimposed on the real image of the plant to be pruned. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In the description exemplary embodiments of the invention are given, which are illustrated by the accompanying drawings, in which:

[0058] • Figure 1 illustrates a perspective view of augmented reality glasses for implementing a system and method for assisting plant pruning according to one embodiment of the present invention;

[0059] • Figure 2 A schematic diagram of a tablet computer for implementing a system and method for assisting plant pruning according to another embodiment of the present invention is illustrated;

[0060] • Figure 3A schematic diagram of a smartphone for implementing a system and method for assisting plant pruning according to another embodiment of the present invention is illustrated;

[0061] • Figure 4 The picture shows a grapevine plant to be pruned;

[0062] • Figure 5a , 5b and 5c illustrate various images of grapevine plants and instructions on how to prune the grapevine plants;

[0063] • Figure 6 A flowchart illustrating the main steps of an auxiliary pruning method according to an embodiment of a preferred version of the present invention; and

[0064] • Figure 7 A block diagram of a system for implementing a method according to another embodiment of the present invention is illustrated. DETAILED DESCRIPTION

[0065] According to one embodiment, the auxiliary method is suitable for trimming Figure 4 The grapevine plant 10 shown. To this end, the user (e.g., a person without pruning experience) is equipped with a pruning device according to Figure 1 Illustrative example of augmented reality glasses 12.

[0066] The augmented reality glasses 12 include a lens 14 provided with a display area 16, in particular for displaying instructions related to the pruning of the grapevine plant 10, and a camera 18, so as to be able to film the pruning of the grapevine plant 10. Figure 4 An image or series of images of a grapevine plant to be pruned is shown. Advantageously, the augmented reality glasses 12 may also include an accelerometer and preferably a compass (these are not shown).

[0067] In addition, according to a preferred embodiment not shown, the augmented reality glasses 12 include an RGB camera, an infrared camera and a 3D camera. The use of an infrared camera enables overcoming shadow or light problems. The use of a 3D camera (such as a time-of-flight measurement sensor) enables obtaining information about the position of each pixel along the three axes of X, Y and Z from each frame.

[0068] The method according to the invention may preferably comprise the following steps: Figure 6 The following steps are shown:

[0069] a. Using an RGB camera, or preferably using an RGB camera, an infrared camera and a 3D camera to limit shadow issues to capture one or more image sequences of the grapevine plant 10;

[0070] b. Transmitting the sequence of images and subjecting them to a preliminary digital processing in order to correct each image, in particular its brightness, whiteness, contrast, size, and to superimpose the RGB, infrared and 3D images and extract the foreground and background so that only the grapevine plant remains. It is also possible to segment the images of the grapevine plant in order to distinguish, for example, the woody parts (trunk and stalks), leaves, bunches of grapes, etc.; this allows, for example, the isolation of the woody parts and facilitates subsequent comparison with reference features obtained from plants at different stages of leaf and fruit development;

[0071] c. constructing a 3D digital model of the grapevine plant to be pruned based on said one or more image sequences, preferably taking into account data from an accelerometer and / or a compass of the augmented reality glasses. The 3D digital model may be obtained, for example, by aligning and superimposing various image frames obtained by various RGB, infrared and / or 3D sensors;

[0072] d. extracting "features", hereinafter referred to as reference features, from the 3D digital model, such as parts of the grapevine plant, in particular corresponding to the bifurcations of the vine stems and / or the ends of the vine stems, etc.;

[0073] e. transmitting these reference features to a neural network to determine cutting instructions for the grapevine plants to be pruned, the neural network previously trained with training images including only the training features and cutting instructions constructed from the reference features in the images; and

[0074] f. Displaying cutting guidance as a superimposition on the real-time video image, for example in the form of markers or points on the branches to be cut, or explanatory text, images or videos.

[0075] It should be noted that the training features constitute signatures that are unique to each plant used for training. For example, these features may represent branch forks and vine ends of a grapevine plant, which were previously modeled so that only these data are retained to reduce the amount of data for each plant.

[0076] according to Figure 7 , a system 40 for assisting pruning of vine plants comprises the augmented reality glasses 12 and an electronic device 41 as described above. The electronic device 41 comprises: a receiver unit 42 for receiving data constituting an image sequence transmitted by the augmented reality glasses 12; a digital processing unit 43 for performing preliminary digital processing on the image sequence (see step b of the above method); a computing unit 44 (processor) for generating a 3D digital model of the grapevine plant to be pruned based on the image sequence; an instruction database 48; and a neural network 50, which has been previously trained with reference features obtained from training images corresponding to a large number of 3D digital models of grapevine plants in the database 26.

[0077] The neural system 50 is designed, on the one hand, to classify reference features extracted from the images captured using the camera or from the 3D model generated based on a plurality of image sequences and, on the other hand, to infer associated cutting instructions from this classification. The cutting instructions are then displayed on the display area 16 of the glasses 12 so as to be displayed in augmented reality as superimposed on the image of the grapevine plant captured by the camera. The cutting instructions are, for example, in the form of marks, colors or dots on the branches to be cut, in the form of Figures 5a to 5c In the form of an image shown in or in the form of an explanatory video. In this exemplary plant, an inexperienced person is therefore located in front of a grapevine plant 10 with guidance in their field of view to allow them to perform the correct actions to achieve optimal pruning of the grapevine plant 10.

[0078] The display area 16 of the augmented reality glasses 12 may display instructions other than instructions related to the pruning of grapevine plants. For example, instructions for moving around the grapevine plant 10 to be pruned may be displayed using data from an accelerometer and compass integrated into the glasses 12 to take images of the grapevine plant from optimal angles so that a 3D digital model of the grapevine plant to be pruned can be reconstructed. The accelerometer and compass may also be used to determine the position of the camera and the camera axis orientation so that the 3D digital model can be constructed using various optimal shots.

[0079] Advantageously, the machine learning engine is in the form of a neural network 50 that has been previously trained to learn to determine which cutting instructions to display for which plant. To this end, the neural network 50 has been trained with reference features from a large number of 2D or 3D models, each model corresponding to a specific grapevine plant and having cutting instructions entered by an expert for each plant.

[0080] In an advantageous embodiment, the electronic device 41 may be, for example, a smartphone communicating with the augmented reality glasses 12, for example via a communication protocol such as Bluetooth. The smartphone 41 may receive the image sequence comprising reference features of the grapevine plant 10 to be pruned, transmitted by the augmented reality glasses 12, and perform preliminary digital processing operations on the received image sequence, in particular of the type described above.

[0081] The computing power of the smartphone processor is sufficient on the one hand to generate a 3D digital model of the grapevine plant to be pruned based on the image sequence and to extract reference features from the 3D digital model, and on the other hand to classify these features using the neural network 50 .

[0082] According to this embodiment, the processor of the smartphone first performs image processing as described above on each consecutive frame of one or more image sequences and then uses the various images so processed to generate a 3D model of the photographed grapevine plant and subsequently extracts reference features from said 3D model. These reference features are input into a neural network, also embodied as software stored in a memory of the smartphone 41, which enables the model to be classified to determine the closest training model and / or to select cutting instructions associated with the identified plant model. These cutting instructions are then transmitted by the smartphone 41 to the augmented reality glasses 12 via a communication protocol such as Bluetooth or Wi-Fi, so that the cutting instructions are displayed in augmented reality on the display area 16 of the glasses 12 as superimposed on the real image of the grapevine plant to be pruned. This embodiment has the advantage of providing an autonomous system for assisting pruning, which system only includes augmented reality glasses 12 and a conventional smartphone 41.

[0083] In the context of this advantageous embodiment, a software application can be downloaded to smartphone 41 to implement the method for assisting in pruning grapevine plants. The software application, when executed, allows, inter alia, preliminary digital processing of the sequence of images received by the smartphone to correct each image, inter alia its brightness, contrast, size, and to extract the foreground and background so that only the grapevine plants remain.

[0084] In another embodiment, the neural network 50 is embodied as software stored in a memory of a server, which includes one or more processors whose computing power is particularly suitable for executing the model classification algorithm and the algorithm for generating a 3D digital model based on a series of images transmitted by the augmented reality glasses 12. The server may also store the guidance database 48 in the memory.

[0085] According to this configuration, the server is configured to communicate with the smartphone 41 or the augmented reality glasses 12 via a communication network (e.g., a cellular phone network). Therefore, the server can receive a sequence of images of the grapevine plant 10 to be pruned transmitted by the augmented reality glasses 12 or the smartphone 41 via the cellular phone network to generate a 3D digital model in order to extract reference features required for selecting a cutting guide, which is based on one or more images recognized by the neural network 30 according to the reference features of the 3D digital model.

[0086] The server then transmits the cutting instructions to the augmented reality glasses 12 via the cellular telephone network for display in augmented reality on the display area 16 of the glasses 12 as superimposed on the real image of the grapevine plant to be pruned.

[0087] Data compression / decompression software may be used to improve data transmission speeds between the augmented reality glasses 12 and the smartphone 41 , between the augmented reality glasses 12 and a server, or between the smartphone 21 and a server.

[0088] According to another embodiment, a method of assisting in pruning grapevine plants includes equipping a person without pruning experience with augmented reality glasses 12, which include lenses 14 with a display area 16. The augmented reality glasses 12 also include a camera 18, which is used to capture and transmit in real time an image of the grapevine plant to be pruned to a remotely located operator who has the knowledge required to instruct the inexperienced person.

[0089] The operator is provided with a computer unit to be able to select, from a series of images of grapevine plants stored in a database, one or more images that are similar to the images received in real time and that include instructions regarding the pruning of the plant shown in the or each image. The one or more images from the database are then transmitted to the augmented reality glasses 12 via the communication network and displayed on the display area 16 of the lens 14 of the glasses 12. The glasses 12 may advantageously be equipped with a microphone and headphones to allow two-way communication between an inexperienced person and the operator.

[0090] According to another embodiment, a method of assisting in pruning grapevine plants comprises equipping a person without pruning experience with a smartphone 41 and augmented reality glasses 12, the augmented reality glasses 12 comprising lenses 14 with a display area 16. The inexperienced person can select an image with the help of the smartphone 41 from a series of images of grapevine plants in a database stored in the memory of the smartphone 41. The selection is made manually and is based on the inexperienced person's estimation of the similarity with the appearance of the grapevine plant to be pruned. Each image has cutting instructions, which preferably include cutting points or cutting marks. These images are transmitted from the smartphone 41 to the augmented reality glasses 12, for example via a communication protocol such as Bluetooth or Wi-Fi, so as to be able to display the cutting instructions in augmented reality as superimposed on the real image of the grapevine plant on the display area 16 of the glasses 12.

[0091] According to another embodiment of the present invention, a person without pruning experience is equipped with a Figure 2 and Figure 3 A tablet computer 22 or smartphone 32 comprising a display area 26, 36 on one face and a camera 28, 38 on the back to be able to take an image or a series of images of the vine plant to be pruned. Advantageously, the tablet computer 22 or smartphone 32 may also comprise an accelerometer and preferably a compass (these are not shown).

[0092] This embodiment has the advantage of reducing the number of devices, since the tablet computer 22 or smartphone 32 includes the necessary hardware to perform the Figure 6 , so that the cutting instructions are displayed in augmented reality as superimposed on the real image of the plant.

[0093] More specifically, the tablet computer or smartphone comprises: a digital processing unit for performing preliminary digital processing of a sequence of images of grapevine plants; a computing unit (processor) for generating a 3D digital model of the grapevine plant to be pruned based on the sequence of images; an instruction database; and a neural network previously trained with reference features obtained from training images corresponding to a large number of 3D digital models of grapevine plants in the database.

[0094] Thus, the tablet computer 22 or smartphone 32 performs the same functions as the electronic device 41 described above in connection with the augmented reality glasses 12. Thus, the cutting guidance selected via a neural network based on features extracted from the 3D model can be displayed directly in augmented reality on the display area of ​​the tablet computer or smartphone, superimposed on the real image of the plant.

[0095] According to another embodiment, a machine learning engine is trained based on reference features obtained from 2D training images, which are annotated by an operator using a labeling code, in order to classify features extracted from these images taken by an electronic device (e.g., augmented reality glasses 12, tablet computer 22, smartphone 32) rather than from a 3D digital model, and then infer cutting guidelines therefrom, such as cutting guidelines selected from a cutting database.

[0096] Of course, the method for assisted pruning according to the invention is not limited to the field of grape cultivation and can be applied in particular to the field of arboriculture of any type of tree (in particular fruit trees), to the field of landscaping for pruning ornamental shrubs, or to the field of floriculture for pruning flowering plants (in particular roses), etc.

Claims

1. A method for assisting plant (10) pruning implemented by an electronic device (21), comprising the following steps: a. Equipping the subject with an electronic device (12; 22; 32) comprising a display area (16; 26; 36) and a camera (18; 28; 38), the electronic device being a smartphone (32), a tablet computer (22) or in the form of augmented reality glasses (12) comprising a camera (18) and lenses (14) comprising a display area (16); b. using a camera (18; 28; 38) of an electronic device (12; 22; 32) to capture at least one image of the plant to be pruned (10), hereinafter referred to as a reference image; c. using a machine learning engine (50) previously trained with training images to determine cropping guidance based on the construction of reference features on the reference image, and d. displaying the cutting instructions in augmented reality on the display area (16; 26; 36) as superimposed on the real image of the plant to be cut, and wherein said training of the machine learning engine (50) comprises classifying cutting instructions according to the construction of reference features of said training images, and wherein the cutting instructions are in the form of marks, colors or dots on the branches to be cut, Wherein at least some of the reference features correspond to bifurcations of branches of the plant to be pruned.

2. The method according to claim 1, wherein: The training data includes recommended cutting marks or cutting points associated with reference features representing landmarks unique to each of a plurality of plants having various appearances.

3. The method according to claim 1, wherein: In step b, a series of images of the plant to be pruned are taken from multiple angles using a camera (18; 28; 38) of an electronic device (12; 22; 32), followed by a step of generating a 3D digital model of the plant to be pruned based on the series of images of the plant, and wherein reference features are extracted from the 3D digital model, the reference features representing markers unique to the plant to be pruned.

4. The method according to claim 3, wherein: The machine learning engine (40) is a neural network designed, on the one hand, to classify reference features extracted from the 3D model and then, on the other hand, to determine cutting instructions associated with these reference features so as to display said cutting instructions in augmented reality as superimposed on the captured image of the plant to be pruned.

5. The method according to claim 4, wherein: Cutting guidance takes the form of cutting marks superimposed on branches in the plant image.

6. The method according to claim 3, wherein: Instructions for moving around the plant to be pruned are displayed on the display area (16; 26; 36) of the electronic device to take images of the plant from the best angle so that a 3D digital model can be generated.

7. The method of claim 1, comprising transmitting the reference image or 3D digital model to a remote operator in real time or near real time, and the subject receiving audio and / or visual cutting guidance from the remote operator.

8. The method according to claim 1, wherein: The plant is a vine plant.

9. A system (40) for assisting plant pruning, intended to implement the method according to claim 1, comprising: - an electronic device (12; 22; 32) comprising a display area (16; 26; 36) for displaying one or more cutting instructions as an augmented reality superimposed on a real image of the plant, the one or more cutting instructions being from the group consisting of text, images, videos, and cutting points / markers, the electronic device (12; 22; 32) also comprising a camera (18; 28; 38); one or more processors, a memory storing a neural network previously trained with training images, the neural network being used to determine the cutting instructions based on a 2D image taken by the electronic device (12; 22; 32) or based on a 3D digital model, The electronic device is in the form of a smartphone (32), a tablet computer (22), or augmented reality glasses (12) including a camera (18) and lenses (14) including a display area (16).

10. The system according to claim 9, wherein: The machine learning engine is a neural network.

11. The system according to claim 9, further comprising an electronic device (41) or a remote processing unit, the electronic device (41) or the remote processing unit comprising a computing unit (44) for generating a 3D digital model.

12. The system according to claim 11, wherein: The electronic device (41) is integrated into a tablet computer (22) or a smart phone (32).

13. The system according to claim 11, wherein: The machine learning engine (50) is implemented in the form of software stored in a memory of the electronic device (41) or in a memory of a remote processing unit.

14. The system according to claim 11, wherein: The remote processing unit is a server configured to transmit data related to cutting instructions to the electronic device (12; 22; 32) via a communication network.

Images