US 12,258,055 B2
System and method for railway weeding
Aurelien Benoit-Levy, Gentilly (FR); Loic Steunou, Gentilly (FR); and Hugo Serrat, Gentilly (FR)
Assigned to Bilberry SAS, Gentilly (FR)
Appl. No. 17/413,240
Filed by BILBERRY SAS, Gentilly (FR)
PCT Filed Dec. 16, 2019, PCT No. PCT/EP2019/085431
§ 371(c)(1), (2) Date Jun. 11, 2021,
PCT Pub. No. WO2020/120802, PCT Pub. Date Jun. 18, 2020.
Claims priority of application No. 18020639 (EP), filed on Dec. 14, 2018.
Prior Publication US 2022/0076065 A1, Mar. 10, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. B61L 23/04 (2006.01); E01H 11/00 (2006.01); G06F 18/214 (2023.01); G06F 18/28 (2023.01); G06N 20/00 (2019.01); G06V 20/56 (2022.01)
CPC B61L 23/041 (2013.01) [B61L 23/04 (2013.01); E01H 11/00 (2013.01); G06F 18/214 (2023.01); G06F 18/28 (2023.01); G06N 20/00 (2019.01); G06V 20/56 (2022.01)] 11 Claims
OG exemplary drawing
 
1. A weeding system for a railway weeding vehicle, comprising:
at least one camera adapted to be mounted on a railway vehicle to acquire an image of a portion of a railway track while said railway vehicle is travelling on a train track, said image comprising a matrix of pixel values,
a spraying unit adapted to be mounted on said railway vehicle,
a control unit adapted to receive images from said camera, generate a weed species detection signal and selectively cause the spraying of a chemical agent by the spraying unit on the basis of said weed species detection signal,
the control unit being adapted to execute in a running mode a training-based algorithm, the training being based on a set of reference images labeled so as to indicate the effective presence or not of at least one weed species in said images,
wherein each of said reference images comprises a pair of a nighttime image and a daytime image of the same scene, said labeling is performed on the daytime images and applied to the corresponding nighttime images, the training is based on the labeled nighttime images, a species contouring is performed on the daytime images and applied to the corresponding nighttime image for training the algorithm, and in the running mode, the algorithm receives nighttime real images.