Method for smartphone-based accident detection

• US 9,818,239 B2
• Filed: 08/22/2016
• Issued: 11/14/2017
• Est. Priority Date: 08/20/2015
• Status: Active Grant

• Current Assignee: Zendrive, Inc.
• Original Assignee: Zendrive, Inc.
• Inventors: Pal, Jayanta, Islam, Bipul, Choudhury, Romit Roy, Risbood, Pankaj, Matus, Jonathan, Verma, Vishal
• Primary Examiner(s): Swarthout, Brent
• Application Number:
  US15/243,565
• Publication Number:
  US 20170053461A1
• Time in Patent Office: 449 Days
• Field of Search: None
• CPC Class Codes: B60R 2325/205 Mobile phones
• CPC Class Codes: B60R 25/24 using electronic identifiers containing a code not memorised by the user
• CPC Class Codes: B60W 40/10 related to vehicle motion
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/597 Recognising the driver's state or behaviour, e.g. attention or drowsiness
• CPC Class Codes: G06V 40/15 Biometric patterns based on physiological signals, e.g. heartbeat, blood flow
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/02 Registering or indicating driving, working, idle, or waiting time only apparatus forming part of taximeters G07B13/00
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G07C 5/0866 the electronic data carrier being a digital video recorder in combination with video camera
• CPC Class Codes: G08B 25/00 Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
• CPC Class Codes: G08B 25/001 Alarm cancelling procedures or alarm forwarding decisions, e.g. based on absence of alarm confirmation
• CPC Class Codes: G08B 25/006 Alarm destination chosen according to type of event, e.g. in case of fire phone the fire service, in case of medical emergency phone the ambulance
• CPC Class Codes: G08B 25/016 Personal emergency signalling and security systems emergency non-personal manually actuated alarm activators G08B25/12
• CPC Class Codes: G08G 1/012 from other sources than vehicle or roadside beacons, e.g. mobile networks
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: H04M 1/72421 with automatic activation of emergency service functions, e.g. upon sensing an alarm
• CPC Class Codes: H04M 1/72454 : according to context-related or environment-related conditions
• CPC Class Codes: H04M 2250/12 : including a sensor for measuring a physical value, e.g. temperature or motion telephones including GPS signal receivers H04M2250/10
• CPC Class Codes: H04W 4/027 : using movement velocity, acceleration information
• CPC Class Codes: H04W 4/029 : Location-based management or tracking services
• CPC Class Codes: H04W 4/40 : for vehicles, e.g. vehicle-to-pedestrians [V2P]
• CPC Class Codes: H04W 88/00 : Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices

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.

Claims

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.