US 12,358,177 B2
System and method for tracking logs in a wood processing chain
Jan-Erik Rendahl, Virserum (SE); and Jonny Edvardsson, Virserum (SE)
Appl. No. 17/764,165
Filed by Tracy of Sweden AB, Virserum (SE)
PCT Filed Oct. 1, 2020, PCT No. PCT/IB2020/059190
§ 371(c)(1), (2) Date Mar. 25, 2022,
PCT Pub. No. WO2021/064622, PCT Pub. Date Apr. 8, 2021.
Claims priority of application No. 1930309-8 (SE), filed on Oct. 3, 2019.
Prior Publication US 2023/0024974 A1, Jan. 26, 2023
Int. Cl. G06V 20/52 (2022.01); B07C 5/14 (2006.01); B23D 59/00 (2006.01); B27B 1/00 (2006.01); G01N 21/898 (2006.01); G01N 33/46 (2006.01); G06V 10/147 (2022.01); G06V 10/764 (2022.01)
CPC B27B 1/007 (2013.01) [B07C 5/14 (2013.01); B23D 59/008 (2013.01); G01N 21/8986 (2013.01); G01N 33/46 (2013.01); G06V 10/147 (2022.01); G06V 10/764 (2022.01); G06V 20/52 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A system to track logs in a wood processing chain, the system comprises:
a database arrangement comprising at least one pre-recorded image of a first end or a second end of a given log at a harvesting site in the wood processing chain, wherein the given log is associated with log identification information;
a plurality of imaging devices implemented at a sorting station, wherein the plurality of imaging devices are configured to:
capture a first set of images that includes at least one image of the first end and at least one image of the second end of the given log from at least a first prespecified oblique angle with respect to a longitudinal axis in a direction of a length of the given log towards the log, wherein the first prespecified oblique angle is within a defined threshold range;
a data processing arrangement communicatively coupled to the database arrangement and the plurality of imaging devices, wherein the data processing arrangement is configured to:
identify the given log at the sorting station based on at least the captured first set of images;
compare the at least one pre-recorded image of the first end or the second end of the given log at the harvesting site with the captured first set of images at the sorting station in the database arrangement, in order to find an optimum image from the compared images for identification of the given log;
determine a plurality of physical characteristics of the given log at the sorting station based on at least one of the first set of images; and
append the log identification information associated with the given log with the determined plurality of physical characteristics of the given log in the database arrangement; and
a data memory device having a first machine learning model, wherein the data processing arrangement is configured to train the first machine learning model for identification of a new log when the new log enters the sorting station, wherein the identification is executed by the first machine learning model based on a similarity of features between a newly captured image of a first end or a second end of the new log at the sorting station and the corresponding pre-recorded images of the first end or the second end of the new log captured at the harvesting site.