Driving assistant system

• US 10,317,235 B2
• Filed: 10/27/2017
• Issued: 06/11/2019
• Est. Priority Date: 11/14/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ishikawa, Nobuyuki, Okada, Masakuni, Shimura, Takeyuki, Yoshinaga, Hiroki
• Primary Examiner(s): Williams, Jeffery A
• Application Number:
  US15/795,989
• Publication Number:
  US 20180136002A1
• Time in Patent Office: 592 Days
• Field of Search: 348118
• CPC Class Codes: B60W 50/00 Details of control systems for road vehicle drive control not related to the control of a particular sub-unit , e.g. process diagnostic or vehicle driver interfaces
• CPC Class Codes: G01C 21/3644 Landmark guidance, e.g. using POIs or conspicuous other objects
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle

Abstract

Driving assistant systems and computer-implemented methods for improving landmark-based route guidance are provided. The computer-implemented method includes receiving, by a processor, image data including one or more landmarks. The computer-implemented method further includes identifying, by the processor, a candidate landmark within the image data. The computer-implemented method further includes presenting, by the processor, the candidate landmark to a user. The computer-implemented method further includes, in response to the user accepting the candidate landmark, storing, by the processor, the candidate landmark and a location of the candidate landmark.

Claims

1. A computer-implemented method comprising:

receiving, by a processor, image data comprising one or more landmarks;

identifying, by the processor, a candidate landmark within the image data;

presenting, by the processor, the candidate landmark to a user;

in response to the user accepting the candidate landmark, storing, by the processor, an image of the candidate landmark and a location of the candidate landmark;

comparing, by the processor, a position of the user to the location;

determining, by the processor, whether the position is within a threshold distance of the location;

in response to determining that the position is within a threshold distance of the location, comparing, by the processor, the stored image of the candidate landmark to a current image of the candidate landmark in the image data to identify a change in a visual appearance of the candidate landmark; and

presenting, by the processor, the change in the visual appearance of the candidate landmark to the user.

2. The computer-implemented method of claim 1, further comprising:

in response to the user rejecting the candidate landmark, presenting, by the processor, a new candidate landmark to the user.

3. The computer-implemented method of claim 1, further comprising:

in response to the user accepting the candidate landmark, tagging, by the processor, the candidate landmark with landmark metadata.

4. The computer-implemented method of claim 3, wherein the metadata comprises GPS coordinates, a landmark name, a landmark location, a shape, a color, a size, a type, a time, weather at the time, a season, a month, a year, a direction, a relative position, or a user recording.

5. The computer-implemented method of claim 1, wherein receiving the image data further comprises receiving, by the processor, the image data from a vehicle-mounted camera.

6. The computer-implemented method of claim 1, wherein identifying a candidate landmark within the image data is in response to receiving a trigger.

7. The computer-implemented method of claim 6, wherein the trigger comprises contextual user speech triggers, user command triggers, automatic route triggers, third party triggers, or user selection triggers.

8. The computer-implemented method of claim 1, wherein identifying a candidate landmark within the image data further comprises detecting a line of sight of the user.