US 12,736,339 B2Granted

Road surface abnormality detection apparatus, road surface abnormality detection method, and non-transitory computer readable medium

AssigneeNEC Corporation

InventorsMasahiro Yamaguchi, Kyota Higa, Yusuke Nonaka, Hideo Saito, Hideaki Uchiyama

Life of this patent

Estimating the term…

Loading patent…

Abstract

A road surface abnormality detection apparatus includes a data acquisition unit, a prediction unit, and an abnormality detection unit. The data acquisition unit acquires road surface observation data obtained by observing a road surface in a chronological order. The prediction unit predicts road surface data at a first timing from a plurality of road surface observation data at a plurality of respective timings earlier than the first timing by using a trained model generated in advance through machine learning. The abnormality detection unit detects, when a difference between road surface observation data at the first timing and the predicted road surface data at the first timing is equal to or larger than a predetermined threshold, an abnormality of the road surface.

Claims16

Dependent claims

A road surface abnormality detection apparatus comprising;

a memory configured to store instructions;
and
a processor configured to execute the instructions to:
acquire road surface observation data obtained by observing a road surface in a chronological order;
convert the road surface observation data into road surface observation data composed of low-dimensional vector data having a smaller number of dimensions than that of a vector representing the road surface observation data;
predict low-dimensional road surface data at a first timing from a plurality of the converted road surface observation data, corresponding to the road surface observation data, at a plurality of respective timings earlier than the first timing by using a trained model generated in advance through machine learning, the low-dimensional road surface data having dimensions corresponding to those of the low-dimensional vector data;
detect, when a difference between the converted road surface observation data at the first timing and the predicted low-dimensional road surface data at the first timing is equal to or larger than a predetermined threshold, an abnormality of the road surface;
generate, based on the detection, road surface abnormality information indicating where the road surface abnormality information was observed;
and
output, based on the road surface abnormality information, image data indicating where the abnormality of the road surface has been detected.

7 more elements

A road surface abnormality detection method comprising:

acquiring road surface observation data obtained by observing a road surface in a chronological order;
converting the road surface observation data into road surface observation data composed of low-dimensional vector data having a smaller number of dimensions than that of a vector representing the road surface observation data;
predicting low-dimensional road surface data at a first timing from a plurality of the converted road surface observation data, corresponding to the road surface observation data, at a plurality of respective timings earlier than the first timing by using a trained model generated in advance through machine learning, the low-dimensional road surface data having dimensions corresponding to those of the low-dimensional vector data;
detecting, when a difference between the converted road surface observation data at the first timing and the predicted low-dimensional road surface data at the first timing is equal to or larger than a predetermined threshold, an abnormality of the road surface;
generating, based on the detection, road surface abnormality information indicating where the road surface abnormality information was observed;
and
outputting, based on the road surface abnormality information, image data indicating where the abnormality of the road surface has been detected.

4 more elements

Dependencies are inferred from the claim text.