Guidance processing apparatus and guidance method

Patent metadata

Field	Value
Publication number	US-12283109-B2
Application number	US-202318238818-A
Country	US
Kind code	B2
Filing date	Aug 28, 2023
Priority date	Jun 30, 2014
Publication date	Apr 22, 2025
Grant date	Apr 22, 2025

Abstract

A guidance processing apparatus ( 100 ) includes an information acquisition unit ( 101 ) that acquires a plurality of different pieces of guidance information on the basis of states of a plurality of people within one or more images, and a control unit ( 102 ) that performs control of a plurality of target devices present in different spaces or time division control of a target device so as to set a plurality of different states corresponding to the plurality of pieces of guidance information.

First claim

The invention claimed is:

1. A guidance processing system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform:
acquiring surveillance images for each of getting-on positions for a vehicle at a platform;
analyzing the surveillance images to estimate left-behind conditions in the getting-on positions, the left-behind conditions including a degree of crowdedness for each of the getting-on positions;
determining, for each of the getting-on positions, a recommended getting-on position having a lower degree of crowdedness than other getting-on positions in a vicinity of and closest to the each of the getting-on positions, based on the left-behind conditions;
generating guidance information for each of the getting-on positions, the guidance information indicating the recommended getting-on position determined for the each of the getting-on positions; and
outputting the guidance information for each of the getting-on positions to display devices which have a display area including the getting-on positions.

2. The guidance processing system according to claim 1 ,
wherein an indicator of the left-behind conditions is a difference between the degrees of crowdedness at the getting-on positions before a train stops at the getting-on positions and after the train departs from the getting-on positions.

3. The guidance processing system according to claim 2 ,
wherein the at least one processor is configured to execute the instructions to perform determining the left-behind conditions by measuring movement of a queue and in consideration of how much the queue moves forward.

4. The guidance processing system according to claim 1 ,
wherein the at least one processor is configured to execute the instructions to perform generating the guidance information using environment condition information indicating conditions of an environment.

5. The guidance processing system according to claim 1 ,
wherein the guidance information includes a predicted crowdedness in a target area.

6. The guidance processing system according to claim 1 ,
wherein the at least one processor is configured to execute the instructions to perform:
acquiring the degree of crowdedness in a first target area and acquiring a flow rate in a second target area; and
calculating a predicted crowdedness in the first target area at a point in time in the future based on the flow rate.

7. The guidance processing system according to claim 1 ,
wherein the at least one processor is configured to execute the instructions to perform:
determining a degree of influence of a peripheral area on the degree of crowdedness in a target area; and
generating the guidance information for suppressing an increase in a number of people moving from the peripheral area with a high degree of influence on the target area to the target area.

8. A guidance processing method executed by a computer and comprising:
acquiring surveillance images for each of getting-on positions for a vehicle at a platform;
analyzing the surveillance images to estimate left-behind conditions in the getting-on positions, the left-behind conditions including a degree of crowdedness for each of the getting-on positions;
determining, for each of the getting-on positions, a recommended getting-on position having a lower degree of crowdedness than other getting-on positions in a vicinity of and closest to the each of the getting-on positions, based on the left-behind conditions;
generating guidance information for each of the getting-on positions, the guidance information indicating the recommended getting-on position determined for the each of the getting-on positions;
outputting the guidance information for each of the getting-on positions to display devices which have a display area including the getting-on positions.

9. The guidance processing method according to claim 8 ,
wherein an indicator of the left-behind conditions is a difference between the degrees of crowdedness at the getting-on positions before a train stops at the getting-on positions and after the train departs from the getting-on positions.

10. The guidance processing method according to claim 9 , further comprising
determining the left-behind conditions by measuring movement of a queue and in consideration of how much the queue moves forward.

11. The guidance processing method according to claim 8 , further comprising
generating the guidance information using environment condition information indicating conditions of an environment.

12. The guidance processing method according to claim 8 ,
wherein the guidance information includes a predicted crowdedness in a target area.

13. The guidance processing method according to claim 8 , further comprising:
acquiring the degree of crowdedness in a first target area and acquiring a flow rate in a second target area; and
calculating a predicted crowdedness in the first target area at a point in time in the future based on the flow rate.

14. The guidance processing method according to claim 8 , further comprising:
determining a degree of influence of a peripheral area on the degree of crowdedness in a target area; and
generating the guidance information for suppressing an increase in a number of people moving from the peripheral area with a high degree of influence on the target area to the target area.

15. A non-transitory computer-readable medium storing a program for causing a computer to perform operations comprising:
acquiring surveillance images for each of getting-on positions for a vehicle at a platform;
analyzing the surveillance images to estimate left-behind conditions in the getting-on positions, the left-behind conditions including a degree of crowdedness for each of the getting-on positions;
determining, for each of the getting-on positions, a recommended getting-on position having a lower degree of crowdedness than other getting-on positions in a vicinity of and closest to the each of the getting-on positions, based on the left-behind conditions;
generating guidance information for each of the getting-on positions, the guidance information indicating the recommended getting-on position determined for the each of the getting-on positions; and
outputting the guidance information for each of the getting-on positions to display devices which have a display area including the getting-on positions.

16. The non-transitory computer-readable medium according to claim 15 ,
wherein an indicator of the left-behind conditions is a difference between the degrees of crowdedness at the getting-on positions before a train stops at the getting-on positions and after the train departs from the getting-on positions.

17. The non-transitory computer-readable medium according to claim 15 ,
wherein the operations further comprise generating the guidance information using environment condition information indicating conditions of an environment.

18. The non-transitory computer-readable medium according to claim 15 ,
wherein the guidance information includes a predicted crowdedness in a target area.

19. The non-transitory computer-readable medium according to claim 15 ,
wherein the operations further comprise:
acquiring the degree of crowdedness in a first target area and acquiring a flow rate in a second target area; and
calculating a predicted crowdedness in the first target area at a point in time in the future based on the flow rate.

20. The non-transitory computer-readable medi

Assignees

• Nec Corp

Inventors

• Oami Ryoma
• Miyano Hiroyoshi
• Takahashi Yusuke
• Ikeda Hiroo
• Ebiyama Yukie
• Kawai Ryo
• Ogawa Takuya
• Koyama Kazuya
• Yamada Hiroshi

Classifications

• H04N7/181

  for receiving images from a plurality of remote sources · CPC title

• G06F3/147

  using display panels · CPC title

• H04N7/188 Primary

  Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position (signal generation from motion picture films H04N5/253) · CPC title

• G09G2380/06

  Remotely controlled electronic signs other than labels · CPC title

• G08G1/04

  using optical or ultrasonic detectors · CPC title