Abnormality detection device, abnormality detection system, and method

• US 10,186,146 B2
• Filed: 12/18/2015
• Issued: 01/22/2019
• Est. Priority Date: 12/26/2014
• Status: Active Grant

• Current Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Corporation (Panasonic Holdings Corporation)
• Inventors: Hirotsu, Yuzo, Iwaoka, Koichiro
• Primary Examiner(s): Camby, Richard M
• Application Number:
  US15/538,880
• Publication Number:
  US 20170345294A1
• Time in Patent Office: 1,131 Days
• CPC Class Codes: G01C 21/3691 Retrieval, searching and output of information related to real-time traffic, weather, or environmental conditions arrangements for giving variable traffic instructions G08G1/09
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: G08G 1/0145 for active traffic flow control
• CPC Class Codes: G08G 1/0175 by photographing vehicles, e.g. when violating traffic rules
• CPC Class Codes: G08G 1/08 according to detected number or speed of vehicles
• CPC Class Codes: G08G 1/097 Supervising of traffic control systems, e.g. by giving an alarm if two crossing streets have green light simultaneously

Abstract

An abnormality detection device of an embodiment includes a traffic control center device to detect an abnormality of vehicle detectors installed in a road network, including: a first traffic management unit that collects detector information including measurement quantities from the vehicle detectors; a statistical processing unit that statistically processes the measurement quantities for each designated period to generate statistical information including statistical values of the measurement quantities; a map information generating unit that generates, based on the statistical values of the measurement quantities of the vehicle detectors that already have been determined to be abnormal by a user, map information representing a distribution situation of the statistical values of the measurement quantities in an abnormal state; and a detector state determination unit that determines, based on the measurement quantities of each vehicle detector to be assessed and the map information in the abnormal state, whether the vehicle detector is abnormal.

Claims

1. An abnormality detection device for detecting an abnormality of vehicle detectors installed in a road network, comprising:

a detector information collector that collects detector information including measurement quantities from the vehicle detectors;

a categorizer that classifies the vehicle detectors into a plurality of categories in accordance with a prescribed categorization condition regarding a factor having an influence on a traffic situation at installation points of the vehicle detectors, the categorization condition pertaining to a distance from each vehicle detector to a signal intersection having an incoming road consisting of a road where the vehicle detector is installed, a green time ratio associated with the incoming road of a traffic signal installed at the signal intersection, and whether the vehicle detector is installed above a right turn only lane;

a map information generator that generates, based on the measurement quantities of the vehicle detectors that already have been determined to be abnormal by a user, categorized map information representing a distribution situation of the measurement quantities in an abnormal state for each category; and

a detector state determiner that determines, based on the measurement quantity of each vehicle detector to be assessed and the categorized map information in the abnormal state, whether the vehicle detector is abnormal.

2. The abnormality detection device according to claim 1, further comprising:

a statistical processor that statistically processes the measurement quantities for each designated period to thereby generate statistical information including statistical values of the measurement quantities,

wherein the map information generator generates the categorized map information in the abnormal state based on the statistical values of the measurement quantities.

3. The abnormality detection device according to claim 1,

wherein the map information generator generates categorized map information representing the distribution situation of the measurement quantities in a normal state for each category based on the measurement quantities of the vehicle detectors that have not been determined to be abnormal by the user;

and

the detector state determiner determines, based on the categorized map information in the abnormal state and the categorized map information in the normal state, whether the vehicle detector is abnormal, normal, or in a state that requires attention.

4. The abnormality detection device according to claim 1,

wherein the map information generator excludes, from data to be processed, the measurement quantities during a period when at least one of a special event and a traffic restriction is occurring.

5. The abnormality detection device according to claim 2,

wherein the statistical processor excludes, from data to be processed, the measurement quantities during a period when at least one of a special event and a traffic restriction is occurring.

6. The abnormality detection device according to claim 1,

wherein the map information is based on a combination of a traffic volume and an occupancy.

7. The abnormality detection device according to claim 1, further comprising:

a traffic situation determiner that determines whether a traffic situation represented by the measurement quantities of the vehicle detectors that were not determined to be abnormal by the detector state determiner is abnormal; and

a traffic situation displayer that displays, on a display device, an abnormality of the traffic situation based on a determination result of the traffic situation determiner.

10. The abnormality detection device according to claim 7, further comprising:

a map information generator that generates, for each vehicle detector, individualized map information representing a distribution situation of the measurement quantities for each time slot in a given period of interest in the past,

wherein the traffic situation determiner determines, based on the measurement quantities of the vehicle detector to be assessed in a most recent period and the individualized map information regarding the vehicle detector, whether the traffic situation related to the vehicle detector is abnormal.

11. The abnormality detection device according to claim 10,

wherein the traffic situation displayer displays, on a map image visualizing the individualized map information regarding the vehicle detector to be assessed, a screen in which the measurement quantities of the vehicle detector in the most recent period are plotted.

8. An abnormality detection device for detecting an abnormality of vehicle detectors installed in a road network, comprising:

a detector information collector that collects detector information including measurement quantities from the vehicle detectors;

a map information generator that generates, based on the measurement quantities of the vehicle detectors that already have been determined to be abnormal by a user, map information representing a distribution situation of the measurement quantities in an abnormal state;

a detector state determiner that determines, based on the measurement quantity of each vehicle detector to be assessed and the map information in the abnormal state, whether the vehicle detector is abnormal;

a traffic situation determiner that determines whether a traffic situation represented by the measurement quantities of the vehicle detectors that were not determined to be abnormal by the detector state determiner is abnormal; and

a traffic situation displayer that based on the determination result of the traffic situation determiner, distinguishably displays, in a screen showing the traffic situation at each link of the road network, links corresponding to the vehicle detectors with regard to which the traffic situation has been determined to be abnormal.

9. An abnormality detection device for detecting an abnormality of vehicle detectors installed in a road network, comprising:

a detector information collector that collects detector information including measurement quantities from the vehicle detectors;

a map information generator that generates, based on the measurement quantities of the vehicle detectors that already have been determined to be abnormal by a user, map information representing a distribution situation of the measurement quantities in an abnormal state;

a detector state determiner that determines, based on the measurement quantity of each vehicle detector to be assessed and the map information in the abnormal state, whether the vehicle detector is abnormal;

a traffic situation determiner that determines whether a traffic situation represented by the measurement quantities of the vehicle detectors that were not determined to be abnormal by the detector state determiner is abnormal; and

a traffic situation displayer based on the determination result of the traffic situation determiner, distinguishably displays, in a screen showing the traffic situation at each link of the road network, a degree of abnormality of the traffic volume at each of the links corresponding to the vehicle detectors.

12. An abnormality detection system for detecting an abnormality of vehicle detectors installed in a road network, comprising:

a first device that, based on information obtained by the vehicle detectors, generates traffic information and controls traffic signals; and

a second device provided additionally to the first device,

wherein the first device comprises a detector information collector that collects detector information including measurement quantities from the vehicle detectors,

and wherein the second device includes

a categorizer that classifies the vehicle detectors into a plurality of categories in accordance with a prescribed categorization condition regarding a factor having an influence on a traffic situation at installation points of the vehicle detectors, the categorization condition pertains to a distance from each vehicle detector to a signal intersection having an incoming road consisting of a road where the vehicle detector is installed, a green time ratio associated with the incoming road of a traffic signal installed at the signal intersection, and whether the vehicle detector is installed above a right turn only lane;

a map information generator that obtains the detector information from the first device, and generates, based on the measurement quantities of the vehicle detectors that already have been determined to be abnormal by a user, categorized map information representing a distribution situation of the measurement quantities in an abnormal state for each category; and

a detector state determiner that determines, based on the measurement quantities of each vehicle detector to be assessed and the categorized map information in the abnormal state, whether the vehicle detector is abnormal.

13. The abnormality detection system according to claim 12,

wherein the second device further includes

a traffic situation determiner that determines whether a traffic situation represented by the measurement quantities of the vehicle detectors that were not determined to be abnormal by the detector state determiner;

and

a traffic situation displayer that displays, on the display device, an abnormality of the traffic situation based on a determination result of the traffic situation determiner.

14. An abnormality detection method, performed by a computer, for detecting an abnormality of vehicle detectors installed in a road network, the method comprising:

collecting detector information including measurement quantities from the vehicle detectors;

classifying the vehicle detectors into a plurality of categories in accordance with a prescribed categorization condition regarding a factor having an influence on a traffic situation at installation points of the vehicle detectors, the categorization condition pertaining to a distance from each vehicle detector to a signal intersection having an incoming road consisting of a road where the vehicle detector is installed, a green time ratio associated with the incoming road of a traffic signal installed at the signal intersection, and whether the vehicle detector is installed above a right turn only lane;

generating, based on the measurement quantities of the vehicle detectors that already have been determined to be abnormal by a user, categorized map information representing a distribution situation of the measurement quantities in an abnormal state for each category; and

determining, based on the measurement quantities of each vehicle detector to be assessed and the categorized map information in the abnormal state, whether the vehicle detector is abnormal.

15. The abnormality detection method according to claim 14, further comprising:

determining whether a traffic situation represented by the measurement quantities of the vehicle detectors that were not determined to be abnormal by the determining of whether the vehicle detector is abnormal is abnormal; and

displaying, on a display device, an abnormality of the traffic situation based on a determination result of the determining of whether the traffic situation is abnormal.