Method for smartphone-based accident detection

Patent metadata

Field	Value
Publication number	US-9818239-B2
Application number	US-201615243565-A
Country	US
Kind code	B2
Filing date	Aug 22, 2016
Priority date	Aug 20, 2015
Publication date	Nov 14, 2017
Grant date	Nov 14, 2017

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 event with a mobile computing device located within a vehicle, the method comprising:
receiving a first location dataset collected at a location sensor of the mobile computing device during a first time period of movement of the vehicle;
receiving a first motion dataset collected at a motion sensor of the mobile computing device during the first time period;
extracting a vehicle motion characteristic from at least one of the location dataset and the motion dataset, wherein the vehicle motion characteristic describes the movement of the vehicle within a time window of the first time period;
comparing the vehicle motion characteristic to a motion characteristic threshold;
in response to the vehicle motion characteristic exceeding the motion characteristic threshold:
retrieving an accident detection model,
receiving a second location dataset collected at the location sensor of the mobile computing device during a second time period of the movement of the vehicle, wherein the second time period is after the first time period, and
receiving a second motion dataset collected at the motion sensor of the mobile computing device during the second time period;
receiving a traffic dataset describing traffic conditions proximal a vehicle location extracted from the second location dataset, wherein the traffic conditions comprise at least one of: a traffic level, a traffic law, and accident data;
detecting the vehicular accident event with the accident detection model, the traffic dataset, and at least one of the second location dataset and the second motion dataset;
in response to detecting the vehicular accident event, automatically initiating an accident response action at the mobile computing device.

2. The method of claim 1 , further comprising:
calculating an accident confidence metric indicating a degree of confidence in occurrence of the vehicular accident event, based on at least one of the second location dataset and the second motion dataset;
selecting a personalized accident response action from a set of accident response actions, based on the accident confidence metric, and wherein the personalized accident response action is the accident response action.

3. The method of claim 1 , wherein automatically initiating an accident response action comprises:
generating an audio sample comprising GPS coordinates associated with the vehicular accident event, wherein the GPS coordinates are derived from the second location dataset; and
transmitting the audio sample to an emergency service.

4. The method of claim 3 , further comprising:
receiving a camera dataset captured at a camera mounted to the vehicle;
determining a number of passengers in the vehicle from the camera dataset, wherein the audio sample further comprises the number of passengers in the vehicle.

5. The method of claim 1 , further comprising, prior to comparing the vehicle motion characteristic to the motion characteristic threshold, dynamically adjusting the motion characteristic threshold based on the traffic dataset.

6. The method of claim 1 , further comprising determining a vehicular accident type describing the vehicular accident event, based on at least one of the second location dataset and the second motion dataset, wherein the vehicular accident type comprises at least one of: a single-vehicle collision, a multi-vehicle collision, and a pedestrian collision.

7. The method of claim 6 :
wherein determining the vehicular accident type is substantially concurrent with detecting the vehicular accident event, and
the method further comprising selecting a personalized accident response action from a set of accident response actions, based on the vehicular accident type, and wherein the personalized accident response action is the accident response action.

8. The method of claim 6 , further comprising, in response to determining the vehicular accident type, automatically pre-filling, at the mobile computing device, an insurance claim with the vehicular accident type.

9. The method of claim 1 , further comprising, before the first time period:
generating a first accident detection trained model from first training data characterized by a first training data motion characteristic below the motion characteristic threshold, and
generating a second accident detection trained model from second training data characterized by a second training data motion characteristic exceeding the motion characteristic threshold, wherein the second accident detection trained model is the accident detection model.

10. The method of claim 1 , wherein the vehicle motion characteristic is a vehicular speed value, and wherein the threshold motion characteristic is a vehicular speed threshold.

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

• G07C5/02 Primary

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

• G08B25/001

  Alarm cancelling procedures or alarm forwarding decisions, e.g. based on absence of alarm confirmation · CPC title

• B60W40/10

  related to vehicle motion · CPC title

• G08G1/0129

  for creating historical data or processing based on historical data · CPC title