Method and appartus for informing pedetrian and occupant of vehicle of each other's approach

Patent metadata

Field	Value
Publication number	US-2018126902-A1
Application number	US-201715646862-A
Country	US
Kind code	A1
Filing date	Jul 11, 2017
Priority date	Nov 9, 2016
Publication date	May 10, 2018
Grant date	—

Abstract

Disclosed is a method and apparatus of detecting an object approaching a vehicle, the method includes a user from the image, extracting feature points associated with the device or a portion of the user's body from the image of the user, detecting the object using a device based on the feature point, and issuing an alert of the approaching object.

First claim

What is claimed is:

1 . A method of informing of an approaching vehicle, the method comprising:
detecting an object using a device from an image; and informing the object that the vehicle is approaching.

2 . The method of claim 1 , wherein the detecting of the object comprises:
detecting a user from the image; extracting a feature point associated with the device from the image of the user; determining whether the user is using the device based on the extracted feature point; and detecting the user as the object, in response to determining that the user is using the device.

3 . The method of claim 2 , wherein the extracting of the feature point comprises any one or any combination of:
extracting a static feature point comprising an exterior feature of the user; and extracting dynamic feature points comprising any one or any combination of features of consecutive motions of the user and a feature of a distinctive movement in an ambient environment around the user.

4 . The method of claim 3 , wherein the extracting of the static feature point comprises:
extracting the static feature point comprising the exterior feature of the user using a first classifier trained in advance.

5 . The method of claim 3 , wherein the extracting of the dynamic feature points comprises:
extracting the dynamic feature points using at least one of an optical flow-based object tracking method or a second classifier trained in advance.

6 . The method of claim 3 , wherein the determining of whether the user is using the device comprises:
determining whether the user is using the device based on at least one of the static feature point or the dynamic feature points.

7 . The method of claim 1 , further comprising:
detecting a position of a portion of a body of the object.

8 . The method of claim 7 , wherein the detecting of the object comprises:
detecting a user from the image; and extracting at least one of a feature point associated with the device or a feature point associated with the portion of the body of the object from the image of the user.

9 . The method of claim 7 , wherein the portion of the body of the object comprises at least one of a head, an ear, or a hand of the object.

10 . The method of claim 1 , wherein the informing of the object that the vehicle is approaching comprises any one or any combination of:
informing the object that the vehicle is approaching by providing auditory information using a directional speaker; informing the object that the vehicle is approaching by providing visual information using a headlight of the vehicle; and informing the device of the object that the vehicle is approaching through wireless communication between the device and the vehicle.

11 . The method of claim 1 , further comprising:
Informing an occupant of the vehicle that the object is approaching, in response to a determination that the object is using the device.

12 . The method of claim 11 , wherein the informing of the occupant of the vehicle that the object is approaching comprises:
informing the passenger in the vehicle that the object is approaching based on any one or any combination of auditory information using an audio apparatus in the vehicle, visual information on a display in the vehicle, tactile information delivered by a steering of the vehicle, and a vibration of a seat.

13 . The method of claim 1 , wherein the detecting of the object comprises:
detecting the object currently using the device from the image using a classifier trained based on images of users using the device.

14 . The method of claim 1 , wherein the device comprises at least one of a headset, an earphone, cell phone, smart phone, mobile device, music player, or a portable terminal.

15 . The method of claim 2 , wherein the user comprises any one of a pedestrian, a wheelchair rider, or a bicycle rider.

16 . The method of claim 3 , wherein the static feature point comprises any one or any combination of points indicating an angle of a head or a neck pointing downward, a gaze of the user pointing downwards, an angle of a hand pointing upward, a shape of a hand manipulating the device, and points on an ear of the user wearing a headphone.

17 . The method of claim 3 , wherein the dynamic feature points comprises any one or any combination of the user shaking a body, dancing motions of the user, the user walking at a different pace when compared to other in the ambient environment, and the user moving with a different gesture when compared to the others in the ambient environment.

18 . The method of claim 3 , wherein the static feature point and the dynamic feature points are extracted simultaneously.

19 . The method of claim 3 , wherein the static feature point and the dynamic feature points are extracted separately.

20 . A non-transitory computer-readable medium storing instructions that, when executed by a processor, causes the processor to perform the method of claim 1 .

21 . An apparatus for informing an occupant of a vehicle of an approaching object, the apparatus comprising:
a processor configured to
detect an object using a device from an image, and
inform the occupant that the object is approaching.

22 . The apparatus of claim 21 , wherein the processor is further configured to detect a user from the image, to determine whether the user is using the user based on a feature point associated with the device extracted from the image of the user, and to detect the user as the object, in response to determining that the user is using the device.

23 . The apparatus of claim 22 ,
wherein the processor is further configured to: extract a static feature point comprising an exterior feature of the user using a first classifier trained in advance; and extract dynamic feature points comprising any one or any combination of features of consecutive motions of the user and a feature of a distinctive movement in an ambient environment around the user using at least one of an optical flow-based object tracking method or a second classifier trained in advance.

24 . The apparatus of claim 21 , further comprising:
a vision sensor configured to capture the image.

25 . The apparatus of claim 21 , wherein the processor is further configured to detect a user from the image, to detect a position of a body portion of the user, and to extract at least one of a feature point associated with the device or a feature point associated with the body portion of the user from the image.

26 . The apparatus of claim 21 , wherein the processor is further configured to inform the occupant in the vehicle that the object is approaching based on any one or any combination of auditory information using an audio apparatus in the vehicle, visual information on a display in the vehicle, tactile information delivered by a steering of the vehicle, or a vibration of a seat.

27 . The apparatus of claim 22 , wherein the processor is further configured to inform the object that the vehicle is approaching, in response to the determination that the object is using the device.

28 . The apparatus of claim 27 , further comprising:
a directional speaker configured to face a direction of the object, wherein the processor is further configured to inform the object that the vehicle is approaching by providing auditory information using the directional

Assignees

• Samsung Electronics Co Ltd

Inventors

• Seo Youngwan
• Cho Baek Hwan
• Jeon Paul Barom

Classifications

• B60Q5/006

  indicating risk of collision between vehicles or with pedestrians · CPC title

• B60Q9/008 Primary

  for anti-collision purposes · CPC title

• B60R2300/307

  virtually distinguishing relevant parts of a scene from the background of the scene · CPC title

• B60Q1/525

  automatically indicating risk of collision between vehicles in traffic or with pedestrians, e.g. after risk assessment using the vehicle sensor data · CPC title

• B60R1/00

  Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles · CPC title