Method for smartphone-based accident detection

Patent metadata

Field	Value
Publication number	US-9994218-B2
Application number	US-201715584375-A
Country	US
Kind code	B2
Filing date	May 2, 2017
Priority date	Aug 20, 2015
Publication date	Jun 12, 2018
Grant date	Jun 12, 2018

Abstract

A method and system for detecting an accident of a vehicle, the method including: receiving a movement dataset collected at least at one of a location sensor and a motion sensor arranged within the vehicle, during a time period of movement of the vehicle, extracting a set of movement features associated with at least one of a position, a velocity, and an acceleration characterizing the movement of the vehicle during the time period, detecting a vehicular accident event from processing the set of movement features with an accident detection model, and in response to detecting the vehicular accident event, automatically initiating an accident response action.

First claim

We claim:

1. A method for detecting a vehicular accident with a mobile computing device, the method comprising:
extracting a vehicle motion characteristic from at least one of a first location dataset and a first motion dataset collected at the mobile computing device during a first time period, wherein the vehicle motion characteristic describes movement of a vehicle;
detecting satisfaction of a motion characteristic condition based on the vehicle motion characteristic;
after detecting satisfaction of the motion characteristic condition:
retrieving an accident detection model,
receiving at least one of a second location dataset and a second motion dataset collected at the mobile computing device, and
receiving a first traffic dataset describing traffic conditions proximal a vehicle location extracted from the at least one of the second location dataset and the second motion dataset, wherein the traffic conditions comprise at least one of: a traffic level, a traffic law, and accident data, and wherein the first traffic dataset and the at least one of the second location dataset and the second motion dataset are collected during a second time period after the first time period;

detecting a vehicular accident event with the accident detection model, the first traffic dataset, and the at least one of the second location dataset and the second motion dataset; and
in response to detecting the vehicular accident event, facilitating an accident response action associated with the mobile computing device.

2. The method of claim 1 , wherein detecting satisfaction of the motion characteristic condition comprises detecting satisfaction of the motion characteristic condition based on the vehicle motion characteristic and a second traffic dataset describing the traffic conditions proximal the vehicle location at a time period prior to detecting satisfaction of the motion characteristic condition.

3. The method of claim 2 , wherein detecting satisfaction of the motion characteristic condition based on the second traffic dataset comprises dynamically modifying the motion characteristic condition based on the second traffic dataset.

4. The method of claim 1 , wherein detecting the vehicular accident event comprises:
determining a monitoring frequency, for monitoring for the vehicular accident event, based on the first traffic dataset; and
applying the accident detection model according to the monitoring frequency.

5. The method of claim 1 , further comprising determining a vehicular accident type describing the vehicular accident event, based on the first traffic dataset, wherein the accident response action is based on the vehicular accident type.

6. The method of claim 5 , wherein determining the vehicular accident type comprises determining a multi-vehicle collision based on a high traffic level indicated by the first traffic dataset.

7. The method of claim 1 , wherein facilitating the accident response action comprises facilitating transmission of communications for automatically deploying emergency services to a location proximal the vehicle location, based on the at least one of the second location dataset and the second motion dataset.

8. The method of claim 5 , wherein the communications comprise traffic information derived from the first traffic dataset and associated with the vehicular accident event.

9. The method of claim 1 , wherein the traffic data comprises the traffic law, wherein the traffic law is associated with the vehicle location, and wherein the method further comprises determining a vehicular accident cause for the vehicular accident event based on the traffic law.

10. A method for detecting an accident of a vehicle, the method comprising:
receiving at least one of a first location dataset and a first motion dataset collected at a mobile computing device;
receiving a first traffic dataset describing traffic conditions proximal a vehicle location extracted from the at least one of the first location dataset and the first motion dataset;
extracting a vehicle motion characteristic from the at least one of the first location dataset and the first motion dataset, wherein the vehicle motion characteristic describes movement of the vehicle;
determining a vehicular accident event based on an accident detection model, the first traffic dataset, and the vehicle motion characteristic;
in response to determining the vehicular accident event, facilitating an accident response action associated with the mobile computing device; and
after determining the vehicular accident event:
receiving a second traffic dataset associated with the vehicular accident event, and
updating the accident detection model based on the second traffic dataset.

11. The method of claim 10 , wherein determining the vehicular accident event comprises:
detecting satisfaction of a motion characteristic condition based on the first traffic dataset; and
monitoring for the vehicular accident event in response to detecting satisfaction of the motion characteristic condition.

12. The method of claim 11 ,
wherein monitoring for the vehicular accident event comprises:
retrieving the accident detection model;
receiving at least one of a second location dataset and a second motion dataset collected at the mobile computing device; and

wherein determining the vehicular accident event comprises determining the vehicular accident event based on the accident detection model, the first traffic dataset, the vehicle motion characteristic, and the at least one of the second location dataset and the second motion dataset.

13. The method of claim 11 , wherein detecting satisfaction of the motion characteristic condition comprises detecting satisfaction of the motion characteristic condition based on the vehicle motion characteristic and the first traffic dataset.

14. The method of claim 10 , wherein the traffic conditions comprise at least one of: a traffic level, a traffic law, accident data, and a type of vehicular path.

15. The method of claim 10 , wherein receiving the first traffic dataset comprises:
extracting GPS coordinates from the first location dataset; and
querying a traffic information database for the first traffic dataset based on the GPS coordinates.

16. The method of claim 10 , further comprising extracting a set of supplemental features based on the first traffic dataset and a weather dataset describing weather conditions proximal the vehicle location, wherein determining the vehicular accident event comprises determining the vehicular accident event based on the accident detection model, the set of supplemental features, and the vehicle motion characteristic.

17. The method of claim 10 , wherein determining the vehicular accident event comprises determining an accident confidence metric for the vehicular accident event based on the first traffic dataset, and wherein the accident response action is based on the accident confidence metric.

18. The method of claim 10 , wherein the vehicle motion characteristic comprises a vertical vehicular motion feature describing motion of the vehicle perpendicular a road surface, and wherein determining the vehicular accident event comprises determining the vehicular accident event based on the accident detection model, the first traffic dataset, and the vertical vehicular motion feature.

Assignees

• Zendrive Inc

Inventors

• Pal Jayanta
• Islam Bipul
• Choudhury Romit Roy
• Risbood Pankaj
• Matus Jonathan
• Verma Vishal

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• B60W30/08 Primary

  Active safety systems} predicting or avoiding probable or impending collision {or attempting to minimise its consequences · CPC title

• G08G1/012

  from other sources than vehicle or roadside beacons, e.g. mobile networks · CPC title

• G08B25/00

  Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems · CPC title

• G07C5/02

  Registering or indicating driving, working, idle, or waiting time only (apparatus forming part of taximeters G07B13/00) · CPC title