IP Library Granted Patent US 10,607,356
Granted Patent B2
US 10,607,356 · App. 15/760,704 · Granted Mar 31, 2020

Congestion analysis device, congestion analysis method, and congestion analysis program

Inventors: Daisuke Matsubara (Tokyo, JP); Miyako Iida (Tokyo, JP)
Assignee: Hitachi, Ltd.
G06T7/60G06T7/20G06T7/246G06T7/277H04N5/272G06T2207/30196G06T2207/30241G06T2207/30242
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,607,356
App. No.
15/760,704
Granted
Mar 31, 2020
Kind
B2
Abstract

The present invention suitably determines how is congestion in an area. A congestion analysis device includes: a person classifying unit that is configured to determine, based on a moving image in which persons are photographed, the number of the persons; a motion trajectory determination unit that is configured to determine a motion trajectory of each of the persons; and a congestion information analysis unit that is configured to determine a state of each of the persons based on the motion trajectory thereof photographed in the moving image and also determine a congestion degree in accordance with the number of the persons and the state of each of the persons.

Claims (55)

1. A congestion state visualization device, comprising a processor that is configured to:

photograph a moving image of a prescribed area, and detect a moving direction of a person therein from the moving image;

create a human-shaped icon indicating a moving direction of the person, in accordance with the detected moving direction of the person; and

create a congestion image which is obtained by superimposing the human-shaped icon on a previously-prepared background image in which the prescribed area is photographed, but the person is not photographed;

wherein the background image is a previously-prepared image of an unmanned ticket gate; and

wherein, if the human-shaped icon is overlapped with an image of a ticket gate in the unmanned ticket gate image, the processor creates a congestion image by superimposing the human-shaped icon on the unmanned ticket gate image with an overlapping portion removed therefrom.

2. The congestion state visualization device according to claim 1 ,

wherein the processor creates a human-shaped icon indicating a prescribed direction, in accordance with the moving direction of the person.

3. The congestion state visualization device according to claim 2 ,

wherein the processor creates a human-shaped icon indicating any one of at least four directions, in accordance with the moving direction of the person.

4. The congestion state visualization device according to claim 3 , wherein the processor creates the human-shaped icon, at least an upper part of which indicates the moving direction of the person.

5. The congestion state visualization device according to claim 4 ,

wherein the processor: extracts a motion trajectory of the person from a plurality of the moving images; and detects a moving direction of the person based on the motion trajectory.

6. The congestion state visualization device according to claim 5 ,

wherein the processor:

detects whether the person is in a standing-still state or in a moving state; and creates respective different human-shaped icons, in accordance with whether the person is in the standing-still state or in the moving state.

7. The congestion state visualization device according to claim 6 ,

wherein the processor creates respective human-shaped icons in different colors, in accordance with whether the person is in the standing-still state or in the moving state.

8. The congestion state visualization device according to claim 7 ,

wherein a combination of the different colors is a combination of colors which even those who have color vision deficiency can readily recognize.

9. The congestion state visualization device according to claim 8 ,

wherein the processor:

extracts, from the moving image, the number of persons present in the moving image; and

outputs a congestion degree based on the number of the persons therein, the number of persons in standing-still state therein, and the number of persons in the moving state therein.

10. The congestion state visualization device according to claim 9 ,

wherein the processor change a determination condition used when the congestion degree is determined, based on an external factor.

11. The congestion state visualization device according to claim 10 ,

wherein the processor outputs time information which is displayed together with the congestion image.

12. A congestion state visualization system, comprising:

a camera to photograph a moving image of a prescribed area; and

a processor to:

detect a moving direction of a person from the moving image taken by the camera; create a human-shaped icon indicating a moving direction of a person, in accordance with the detected moving direction of the person; and

create a congestion image which is obtained by superimposing the human-shaped icon on a previously-prepared background image in which the prescribed area is photographed, but the person is not photographed;

wherein the background image is a previously-prepared image of an unmanned ticket gate; and

wherein, if the human-shaped icon is overlapped with an image of a ticket gate in the unmanned ticket gate image, the processor creates a congestion image by superimposing the human-shaped icon on the unmanned ticket gate image with an overlapping portion removed therefrom.

13. The congestion state visualization system according to claim 12 ,

wherein the processor creates a human-shaped icon indicating a prescribed direction, in accordance with the moving direction of the person.

14. The congestion state visualization system according to claim 13 ,

wherein the processor creates a human-shaped icon indicating at least any one of four directions, in accordance with the moving direction of the person.

15. The congestion state visualization system according to claim 14 ,

wherein the processor creates the human-shaped icon, at least an upper part of which indicates the moving direction of the person.

16. A congestion state visualization method performed by a processor, comprising:

photographing a moving image of a prescribed area, and detecting a moving direction of a person therein from the moving image;

creating a human-shaped icon indicating a moving direction of the person, in accordance with the detected moving direction of a person;

creating a congestion image which is obtained by superimposing the human-shaped icon on a previously-prepared background image in which the prescribed area is photographed, but the person is not photographed, wherein the background image is a previously-prepared image of an unmanned ticket gate; and

if the human-shaped icon is overlapped with an image of a ticket gate in the unmanned ticket gate image, creating a congestion image by superimposing the human-shaped icon on the unmanned ticket gate image with an overlapping portion removed therefrom.

17. The congestion state visualization method according to claim 16 , further comprising:

creating the human-shaped icon indicating a prescribed direction, in accordance with the moving direction of the person.

18. The congestion state visualization method according to claim 17 , further comprising:

creating the human-shaped icon indicating at least any one of four directions, in accordance with the moving direction of the person.

19. The congestion state visualization method according to claim 16 , further comprising:

creating the human-shaped icon, at least an upper part of which indicates the moving direction of the person.

20. The congestion state visualization method according to claim 16 , further comprising:

extracting a motion trajectory of the person from a plurality of the moving images; and

detecting the moving direction of the person based on the motion trajectory.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 16, 2018
From: MATSUBARA, DAISUKE; IIDA, MIYAKO
To: HITACHI, LTD.
Reel/Frame 045252/0001 →
Continuity (1)
Related Publication 20180286068A1 · Oct 4, 2018