Abnormality detection device and abnormality detection method

Patent metadata

Field	Value
Publication number	US-10423841-B2
Application number	US-201715794136-A
Country	US
Kind code	B2
Filing date	Oct 26, 2017
Priority date	Nov 14, 2016
Publication date	Sep 24, 2019
Grant date	Sep 24, 2019

Abstract

An abnormality detection device includes a space recognition success determination unit which determines whether an outside space recognition device is successful in space recognition from information which contains space recognition information and environment information, an environment dependence recognition failure classifying unit which determines and classifies whether a failure of the space recognition corresponds to any one of a failure type previously stored in an environment dependence recognition failure type storage unit with respect to the space recognition information determined as failing in the space recognition, and an abnormality detection unit which uses the space recognition information determined as not corresponding to any failure type by the environment dependence recognition failure classifying unit to detect an abnormality of the outside space recognition device in the space recognition information determined as failing in the space recognition.

First claim

What is claimed is:

1. An abnormality detection device that is connected to a vehicle through a communication network, the vehicle being equipped with an outside space recognition device comprising one or more sensors to acquire space recognition information by space recognition of the outside and an environment information acquisition device comprising one or more sensors to acquire environment information containing location information, and detects an abnormality of the outside space recognition device,
the abnormality detection device comprising a processor configured to:
receive information including the space recognition information which is transmitted from the vehicle and acquired by the outside space recognition device and the environment information which is acquired by the environment information acquisition device when the space recognition information is acquired;
determine whether a space recognition of the outside space recognition device when the space recognition information is acquired is successful on the basis of information which contains the space recognition information and the environment information received from the vehicle;
determine the space recognition information determined as failing in the space recognition by the processor regarding whether a failure of the space recognition corresponds to one of type conditions of a predetermined environment dependence space recognition failure, and classify a type of the environment dependence space recognition failure; and
use the space recognition information determined as not corresponding to any one of the type conditions of the environment dependence space recognition failure in the space recognition information determined as failing in the space recognition to detect an abnormality of the outside space recognition device,
wherein the abnormality detection device further comprises a recognition failure information storage unit that accumulates information, which is obtained by associating the space recognition information determined as failing in the space recognition by the processor and the environment information acquired by the environment information acquisition device when the space recognition information is acquired, as recognition failure information, and
wherein the processor is further configured to learn and update the type condition to determine a type of the environment dependence space recognition failure using the recognition failure information accumulated in the recognition failure information storage.

2. The abnormality detection device according to claim 1 , further comprising:
a space recognition failure location display that displays an occurrence location of a past space recognition failure on a map on the basis of the recognition failure information accumulated in the recognition failure information storage.

3. The abnormality detection device according to claim 1 , further comprising:
a highly accurate map storage that stores location information of an object to be recognized by the outside space recognition device,
wherein the processor is further configured to determine whether the space recognition of the outside space recognition device is successful on the basis of the space recognition information acquired by the space recognition, the location information contained in the environment information acquired by the environment information acquisition device when the space recognition information is acquired, and the location information of the object stored in the highly accurate map storage.

4. The abnormality detection device according to claim 1 ,
wherein the processor is further configured to determine whether the space recognition of the outside space recognition device is successful on the basis of the space recognition information acquired by the space recognition and another space recognition information obtained by the outside space recognition device which is mounted in each of a plurality of vehicles running on the front or rear side of a vehicle in which the outside space recognition device is mounted.

5. An abnormality detection device that is mounted in a vehicle equipped with an outside space recognition device comprising one or more sensors to acquire space recognition information by space recognition of the outside and an environment information acquisition device comprising one or more sensors to acquire environment information containing location information, and detects an abnormality of the outside space recognition device, the abnormality detection device comprising a processor configured to:
determine whether the space recognition of the outside space recognition device is successful on the basis of the space recognition information acquired by the outside space recognition device and the environment information containing the location information acquired by the environment information acquisition device when the space recognition information is acquired;
determine the space recognition information determined as failing in the space recognition by the processor regarding whether a failure of the space recognition corresponds to one of type conditions of a predetermined environment dependence space recognition failure, and classify a type of the environment dependence space recognition failure; and
use the space recognition information determined as not corresponding to any one of the type conditions of the environment dependence space recognition failure in the space recognition information determined as failing in the space recognition to detect an abnormality of the outside space recognition device,
wherein the abnormality detection device further comprises a recognition failure information storage that accumulates information, which is obtained by associating the space recognition information determined as failing in the space recognition by the processor and the environment information acquired by the environment information acquisition device when the space recognition information is acquired, as recognition failure information, and
wherein the processor is further configured to learn and update the type condition to determine a type of the environment dependence space recognition failure using the recognition failure information accumulated in the recognition failure information storage.

6. An abnormality detection method of detecting an abnormality of an outside space recognition device by a computer connected to a vehicle through a communication network, the vehicle being equipped with the outside space recognition device comprising one or more sensors to acquire space recognition information by space recognition of the outside and an environment information acquisition device comprising one or more sensors to acquire environment information containing location information, the method comprising:
receiving, by the computer, information which contains the space recognition information acquired by the outside space recognition device transmitted from the vehicle and the environment information acquired by the environment information acquisition device when the space recognition information is acquired,
determining, by the computer, whether the space recognition of the outside space recognition device when the space recognition information is acquired is successful on the basis of the information which contains the space recognition information and the environment information in the receiving,
classifying, by the computer, a type of an environment dependence space recognition failure by determining whether a failure of the space recognition corresponds to any one of type conditions of a predetermined environment dependence space recognition failure with respect to the space recognition information determined as failing in the space recognition in the determining

Assignees

• Hitachi Ltd

Inventors

• Nishida Takehisa
• Okude Mariko
• Ishikawa Masayoshi
• Muto Kazuo
• Katou Atsushi

Classifications

• G08G1/0112 Primary

  from the vehicle, e.g. floating car data [FCD] · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G06F18/2433

  Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection · CPC title

• G07C5/0808

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title