公开(公告)号：US20240201007A1

公开(公告)日：2024-06-20

申请号：US18066237

申请日：2022-12-14

Applicant: NEC CORPORATION

Inventor： Hemant Shivsagar PRASAD ,  Takashi MATSUSHITA ,  Daisuke IKEFUJI ,  Tomoyuki HINO

IPC: G01H9/00

CPC classification number: G01H9/004

Abstract: A distributed optical fiber sensing (DFOS) system includes a non-transitory computer readable medium configured to store instructions thereon. The DFOS system includes a processor connected to the non-transitory computer readable medium. The processor is configured to receive DFOS data from a sensor connected to an optical fiber, wherein the optical fiber is adjacent a roadway having a bridge. The processor is further configured to filter the DFOS data based on a frequency range. The processor is further configured to generate a plurality of spread features, wherein each spread feature of the plurality of spread features corresponds to a channel of a plurality of channels of the filtered DFOS data. The processor is further configured to perform binarization of the plurality of spread features. The processor is further configured to identify a location of the bridge along the roadway based on results of the binarization of the plurality of spread features.

公开(公告)号：US20250037575A1

公开(公告)日：2025-01-30

申请号：US18358945

申请日：2023-07-26

Applicant: NEC Corporation

Inventor： Hemant Shivsagar PRASAD ,  Daisuke IKEFUJI ,  Tomoyuki HINO

IPC: G08G1/04 ,  G01H9/00

Abstract: A vehicle tracking method includes receiving distributed optical fiber sensing (DFOS) data. The vehicle tracking method includes identifying hit points within the DFOS data, wherein each of the hit points corresponds to a location of a corresponding vehicle at a detection time. The vehicle tracking method includes clustering the identified hit points to define one or more clusters. The vehicle tracking method includes classifying each of the one or more clusters into a first or second classification based on a quantity of the hit points in each of the one or more clusters and a quantity of the detection times. The vehicle tracking method includes estimating a vehicle parameter of a first vehicle corresponding to the hit points of a first cluster of the one or more clusters, wherein the first cluster has the first classification, and the estimating is based on the hit points of the first cluster.