Predicting Vehicle Movements Based on Driver Body Language

Patent metadata

Field	Value
Publication number	US-2019362168-A1
Application number	US-201916538571-A
Country	US
Kind code	A1
Filing date	Aug 12, 2019
Priority date	Nov 4, 2015
Publication date	Nov 28, 2019
Grant date	—

Abstract

Systems, methods, and devices for predicting driver intent and future movements of a human driven vehicles are disclosed herein. A computer implemented method includes receiving an image of a proximal vehicle in a region near a vehicle. The method includes determining a region of the image that contains a driver of the proximal vehicle, wherein determining the region comprises determining based on a location of one or more windows of the proximal vehicle. The method includes processing image data only in the region of the image that contains the driver of the proximal vehicle to detect a driver's body language.

First claim

1 . A method comprising:
identifying a region of an image that comprises a driver of a proximal vehicle; processing the region of the image to detect a driver's body language for the driver of the proximal vehicle; and predicting a vehicle maneuver for the proximal vehicle based at least in part on the driver's body language.

2 . The method of claim 1 , wherein identifying the region of the image further comprises identifying a location of one or more windows of the proximal vehicle and identifying a location of the driver of the proximal vehicle based on the location of the one or more windows of the proximal vehicle.

3 . The method of claim 1 , wherein detecting the driver's body language comprises detecting one or more of a head orientation, a gaze direction, a body gesture, or a hand gesture of the driver of the proximal vehicle.

4 . The method of claim 3 , further comprising accessing a database or model that correlates one or more of the head orientation, the gaze direction, the body gesture, or the hand gesture with one or more potential future vehicle maneuvers for the proximal vehicle.

5 . The method of claim 4 , wherein predicting the vehicle maneuver based on the driver's body language comprises predicting based on the one or more potential future vehicle maneuvers for the proximal vehicle that correlate with the driver's body language.

6 . The method of claim 4 , wherein the database or model correlates one or more of the following with the one or more potential future vehicle maneuvers for the proximal vehicle:
a waving motion of a hand; a hand gesture comprising a palm facing toward the vehicle with fingers upward; a gaze direction of the driver for a threshold period of time; a series of head movements; or a series of changes in gaze direction.

7 . The method of claim 1 , wherein identifying the region of the image that comprises the driver of the proximal vehicle comprises identifying based on a predicted location of a driver's seat in the proximal vehicle.

8 . The method of claim 1 , further comprising:
receiving the image from a camera of a parent vehicle; and processing the image with a neural network to identify the proximal vehicle as being a vehicle.

9 . The method of claim 1 , further comprising receiving a wireless communication from the proximal vehicle indicating a future driving maneuver of the proximal vehicle.

10 . The method of claim 1 , further comprising detecting traffic signals and/or traffic signs to determine the presence of one or more of an intersection, a road type, a speed limit, or a location.

11 . A system comprising:
one or more processors; computer readable media storing instructions that, when executed by the one or more processors, cause the system to:
identify a region of an image that comprises a driver of a proximal vehicle;
process the region of the image to detect a driver's body language for the driver of the proximal vehicle; and
predict a vehicle maneuver for the proximal vehicle based at least in part on the driver's body language.

12 . The system of claim 11 , wherein the instructions cause the system to identify the region of the image by identifying a location of one or more windows of the proximal vehicle and identifying a location of the driver of the proximal vehicle based on the location of the one or more windows of the proximal vehicle.

13 . The system of claim 11 , wherein the instructions cause the system to detect the driver's body language by detecting one or more of a head orientation, a gaze direction, a body gesture, or a hand gesture of the driver of the proximal vehicle.

14 . The system of claim 13 , wherein the instructions further cause the system to access a database or model that correlates one or more of the head orientation, the gaze direction, the body gesture, or the hand gesture with one or more potential future vehicle maneuvers for the proximal vehicle.

15 . The system of claim 14 , wherein the instructions cause the system to predict the vehicle maneuver based on the driver's body language by predicting based on the one or more potential future vehicle maneuvers for the proximal vehicle that correlate with the driver's body language.

16 . One or more processors configurable to execute instructions stored in non-transitory computer readable storage media, the instructions comprising:
identifying a region of an image that comprises a driver of a proximal vehicle; processing the region of the image to detect a driver's body language for the driver of the proximal vehicle; and predicting a vehicle maneuver for the proximal vehicle based at least in part on the driver's body language.

17 . The one or more processors of claim 16 , wherein the instructions are such that identifying the region of the image further comprises identifying a location of one or more windows of the proximal vehicle and identifying a location of the driver of the proximal vehicle based on the location of the one or more windows of the proximal vehicle.

18 . The one or more processors of claim 16 , wherein the instructions are such that detecting the driver's body language comprises detecting one or more of a head orientation, a gaze direction, a body gesture, or a hand gesture of the driver of the proximal vehicle.

19 . The one or more processors of claim 18 , wherein the instructions further comprise accessing a database or model that correlates one or more of the head orientation, the gaze direction, the body gesture, or the hand gesture with one or more potential future vehicle maneuvers for the proximal vehicle.

20 . The one or more processors of claim 19 , wherein the instructions are such that predicting the vehicle maneuver based on the driver's body language comprises predicting based on the one or more potential future vehicle maneuvers for the proximal vehicle that correlate with the driver's body language.

Assignees

• Ford Global Tech Llc

Inventors

• Micks Ashley Elizabeth
• Banvait Harpreetsingh
• Jain Jinesh J
• Reiff Brielle

Classifications

• G06V20/597

  Recognising the driver's state or behaviour, e.g. attention or drowsiness · CPC title

• G06V40/20 Primary

  Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) · CPC title

• G06T7/00

  Image analysis · CPC title

• B60W40/08 Primary

  related to drivers or passengers · CPC title

• G08G1/163 Primary

  involving continuous checking · CPC title