公开(公告)号：US12263616B2

公开(公告)日：2025-04-01

申请号：US17876717

申请日：2022-07-29

Applicant: MICROTEC S.R.L.

Inventor： Jöst Frank ,  Federico Giudiceandrea

IPC: B27L5/02 ,  G01N23/046 ,  G01N33/46

Abstract: Apparatus for peeling a log (5) comprising a cutting station (3), a loading station (2) and a device (4) for transferring logs (5) from the loading station (2) to the cutting station (3), the cutting station (3), the loading station (2) and the transfer device (4), in use, interacting with each other to position the log (5) in the cutting station (3). The loading station (2) comprises a device (10) for axially rotating the log (5) about a second rotation axis (11) and a radiographic examination device (19) configured to generate, in use, radiographic scans of the log (5). An electronic unit is connected both to the radiographic examination device (19), to receive digital-format data from it relating to each radiographic scan generated by it, and to the axial rotation device (10), and which is programmed to use said digital-format data to control the operation of the transfer device (4) and/or the cutting station (3).

公开(公告)号：US11842272B2

公开(公告)日：2023-12-12

申请号：US17023579

申请日：2020-09-17

Applicant: MICROTEC S.R.L.

Inventor： Enrico Ursella ,  Davide Boschetto ,  Federico Giudiceandrea

IPC: G06N3/08 ,  G06T7/73 ,  B27B1/00 ,  G06T7/00 ,  G06V10/44

CPC classification number: G06N3/08 ,  B27B1/007 ,  G06T7/0004 ,  G06T7/73 ,  G06V10/454 ,  G06T2207/10116 ,  G06T2207/20081 ,  G06T2207/30161

Abstract: A computer-implemented method for training a software infrastructure based on machine-learning techniques to analyse data obtained from a instrumental examination of objects of a predetermined type, where each of the objects has been obtained by splitting a product into smaller pieces, wherein the software infrastructure receives, for each object in a training set, training input data comprising the data obtained from the instrumental examination and training output data comprising information on the characteristics of interest of the training object, wherein the information on the characteristics of interest is, at least in part, information that has been obtained from the results of a tomographic examination of the product from which the training object was obtained, and wherein the software infrastructure processes, through its own training unit, the training input data and the training output data for each training object in order to set internal processing parameters for the software infrastructure which correlate the training input data to the training output data.

公开(公告)号：US12290029B2

公开(公告)日：2025-05-06

申请号：US17502498

申请日：2021-10-15

Applicant: MICROTEC S.R.L.

Inventor： Federico Giudiceandrea ,  Martin Bacher ,  Enrico Ursella

IPC: A01G23/083 ,  A01G23/095 ,  G01L5/00 ,  G01N23/04 ,  G01N23/083

Abstract: A processing head (10) for a forestry machine (1) is intended to process a tree (9) having a trunk (92) with a longitudinal direction (90), branches (94) extending from the trunk (92) transversely to the longitudinal direction (90) and knots (96) extending into the trunk (92). The processing head (10) comprises: a frame (2) having a seat (20) for receiving the trunk (92) of the tree (9) to be processed; a motorised device for moving the trunk (92) relative to the seat (20), by advancing the trunk (92) through the seat (20) along the longitudinal direction (90) of the trunk (92); one or more blades (26) for cutting the branches (94) from the trunk (92) as the trunk (92) advances; a detection system for detecting positions of the branches (94) and/or of the knots (96) on the trunk (92) as the trunk (92) advances. Information on the positions of the branches (94) and/or of the knots (96) is processed to determine an identification code that is based on said positions and that refers to said trunk (92) or to a segment obtained from said trunk (92). The identification code is comparable against a code determined a posteriori for a specific trunk or for a specific segment of trunk, in order to establish whether the specific trunk or the specific segment of trunk corresponds to said trunk (92) or to said segment of trunk (92). The information on the positions of branches (94) and/or of knots (96) can also be used to determine, during a processing of the tree (9), one or more positions on the trunk (92) in which to cut the trunk (92) perpendicularly or transversely to the longitudinal direction (90), which is to say to optimise the truncation of the trunk (92).

公开(公告)号：US12061153B2

公开(公告)日：2024-08-13

申请号：US17327180

申请日：2021-05-21

Applicant: MICROTEC S.R.L.

Inventor： Federico Giudiceandrea ,  Mauro Cossi ,  Marco Boschetti

IPC: G01N21/898 ,  G06T5/00 ,  G06T5/50

CPC classification number: G01N21/8986 ,  G06T5/00 ,  G06T5/50 ,  G06T2207/10024

Abstract: Method and apparatus for capturing an image of a lateral face of a wooden board, where the lateral face (2) is parallel to a main axis of development of the wooden board (3), with the method comprising a step for feeding the wooden board (3) with the lateral face (2) transverse to a feeding direction (4), a step for illuminating the lateral face (2), a step for capturing, using a plurality of area scan cameras (9), a plurality of first digital images at different times, where each first digital image comprises a portion (10) of the lateral face (2) extending for an entire height of the lateral face (2) transverse to the main axis of development and for part of a length of the lateral face (2) along the main axis of development, where the set of all such portions (10) corresponds to the entire lateral face (2), and a merging step for merging the first digital images using an electronic processing unit to obtain a second digital image showing the entire lateral face (2).

公开(公告)号：US11620742B2

公开(公告)日：2023-04-04

申请号：US16928385

申请日：2020-07-14

Applicant: MICROTEC S.R.L.

Inventor： Enrico Ursella ,  Enrico Vicario ,  Federico Giudiceandrea

IPC: G06T7/00 ,  G06N20/00 ,  G01N23/046

Abstract: Computer implemented method for training a software infrastructure based on machine learning techniques and intended for analysis of data obtained from a three-dimensional tomographic inspection of objects of a predetermined type, such as logs, with the aim of determining information about internal characteristics of interest of the self-same objects, wherein, once a training set comprising a plurality of objects of the same predetermined type has been selected, for each object the software infrastructure is supplied with training input data and corresponding training output data, which are processed by the software infrastructure for setting internal processing parameters of the software infrastructure which correlate the training input data with the training output data; where the training input data comprise data obtained from a three-dimensional tomographic inspection of the object, and the training output data comprise information about internal characteristics of interest assessed at internal points of the object, and where the information about the internal characteristics of interest is at least partly assessed at real internal points of the object, previously made accessible by cutting or breaking the object.

公开(公告)号：US11428648B2

公开(公告)日：2022-08-30

申请号：US17072982

申请日：2020-10-16

Applicant: MICROTEC S.R.L.

Inventor： Enrico Ursella ,  Federico Giudiceandrea

IPC: G01N23/046 ,  G06T7/73 ,  G06T7/246 ,  G01N23/083 ,  G01N33/02 ,  G06T7/00 ,  G06T11/00

Abstract: A method and a related apparatus for performing a tomographic examination of an object (2) which advances through an examination area (6), wherein the examination area (6) is irradiated with x-rays transversally to a motion trajectory of the object (2) and the residual intensity of the x-rays which have crossed the object (2) is repeatedly detected to obtain, for each detection, an electronic two-dimensional pixel map, the two-dimensional maps thus obtained being processed by a computer to obtain a three-dimensional tomographic reconstruction of the object (2); wherein, during the advancement, the object (2) is made or let rotate, at least partly uncontrolled, in such a way that the object (2) rotates around one or more rotation axes which are transversal both to the motion trajectory and to the propagation directions of the x-rays crossing it; and wherein a computer also determines the spatial position in which the object (2) is located relative to the one or more emitters (4) and/or the one or more detectors (5) at the instant when each two-dimensional map is detected, and factors this in the tomographic reconstruction.