Image processing system, image processing method, and program

Patent metadata

Field	Value
Publication number	US-9984300-B2
Application number	US-201314428770-A
Country	US
Kind code	B2
Filing date	Aug 30, 2013
Priority date	Sep 19, 2012
Publication date	May 29, 2018
Grant date	May 29, 2018

Abstract

Provided are an image processing system, an image processing method, and a program capable of suitably performing the association of a person appearing in a picture in accordance with a highly reliable user input. This image processing system includes: an input unit for receiving an input of pictures captured by multiple video cameras; a person-to-be-tracked registration unit capable of registering one or more persons appearing in the pictures input from the input unit; a moving image display unit for displaying, on a display device, the pictures input by the input unit, and a UI generation unit capable of registering that the person appearing in the displayed pictures and the person registered by the person-to-be-tracked registration unit are the same person, or not the same person.

First claim

I claim:

1. An image processing system, comprising:
a memory storing instructions; and
a processor configured to execute the instructions to:
receive pictures captured by a plurality of video cameras;
register a first person appearing in the pictures;
calculate similarities between one or more persons who were previously registered and the first person by comparing characteristic feature values of the previously registered persons and a characteristic feature value of the first person;
display, on a display device, the pictures;
provide a user interface to receive a user input indicative of whether a second person appearing in the displayed pictures and the first person are the same person or different persons, the second person being one of the previously registered persons;
recalculating the similarities between the previously registered persons and the first person based on the user input; and
tracking the first person across the pictures captured by the plurality of video cameras based on the recalculated similarities,
wherein the pictures showing the first and second persons are captured at different points in time,
wherein the user interface is a pop-up window which displays the one or more previously registered persons in ascending order in accordance with the calculated similarities of the one or more previously registered persons to the first person, and
wherein the pop-up window is displayed on the pictures and adjacent to the first person.

2. The image processing system of claim 1 , wherein the processor is further configured to execute the instructions to:
estimate a correspondence relationship between the first and second persons based on the user input indicative of whether the first person and the second person are the same person or different persons.

3. The image processing system of claim 2 , wherein the processor is further configured to execute the instructions to:
display, on the display device, a movement history of the second person based on the correspondence relationship of the first and second persons.

4. The image processing system of claim 2 , wherein the processor is further configured to execute the instructions to:
estimate the correspondence relationship based on at least one of distances between the video cameras, time spent by the second person for movement, and a relation between characteristic feature values of the first and second persons.

5. An image processing method to be performed by an image processing system, the method comprising:
receiving pictures captured by a plurality of video cameras;
registering a first person appearing in the pictures;
calculating similarities between one or more persons who were previously registered and the first person by comparing characteristic feature values of the previously registered persons and a characteristic feature value of the first person;
displaying the pictures on a display device;
providing a user interface to receive a user input indicative of whether a second person appearing in the displayed pictures and the first person are the same person or different persons, the second person being one of the previously registered persons;
recalculating the similarities between the previously registered persons and the first person based on the user input; and
tracking the first person across the pictures captured by the plurality of video cameras based on the recalculated similarities,
wherein the pictures showing the first and second persons are captured at different points in time,
wherein the user interface is a pop-up window which displays the one or more previously registered persons in ascending order in accordance with the calculated similarities of the one or more previously registered persons to the first person, and
wherein the pop-up window is displayed on the pictures and adjacent to the first person.

6. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform a method comprising:
receiving pictures captured by a plurality of video cameras;
registering a first person appearing in the pictures;
calculating similarities between one or more persons who were previously registered and the first person by comparing characteristic feature values of the previously registered persons and a characteristic feature value of the first person;
displaying the pictures on a display device; and
providing a user interface to receive a user input indicative of whether a second person appearing in the displayed pictures and the first person are the same person or different persons, the second person being one of the previously registered persons;
recalculating the similarities between the previously registered persons and the first person based on the user input; and
tracking the first person across the pictures captured by the plurality of video cameras based on the recalculated similarities,
wherein the pictures showing the first and second persons are captured at different points in time,
wherein the user interface is a pop-up window which displays the one or more previously registered persons in ascending order in accordance with the calculated similarities of the one or more previously registered persons to the first person, and
wherein the pop-up window is displayed on the pictures and adjacent to the first person.

7. An image processing system, comprising:
input means configured to receive pictures captured by a plurality of video cameras;
registration means configured to register a first person appearing in the pictures;
calculation means configured to calculate similarities between one or more persons who were previously registered and the first person by comparing characteristic feature values of the previously registered persons and a characteristic feature value of the first person;
first display control means configured to display, on a display device, the pictures; and
second display control means configured to provide a user interface to receive a user input indicative of whether a second person appearing in the displayed pictures and the first person are the same person or different persons, the second person being one of the previously registered persons;
recalculation means configured to recalculate the similarities between the previously registered persons and the first person based on the user input; and
tracking means configured to track the first person across the pictures captured by the plurality of video cameras based on the recalculated similarities,
wherein the pictures showing the first and second persons are captured at different points in time,
wherein the user interface is a pop-up window which displays the one or more previously registered persons in ascending order in accordance with the calculated similarities of the one or more previously registered persons to the first person,
wherein the pop-up window is displayed on the pictures and adjacent to the first person.

8. The method of claim 5 , further comprising:
estimating a correspondence relationship between the first and second persons based on the user input indicative of whether the first person and the second person are the same person or different persons.

9. The method of claim 8 , further comprising:
displaying, on the display device, a movement history of the second person based on the correspondence relationship of the first and second persons.

10. The method of claim 8 , further comprising:
estimating the correspondence relationship based on at least one of distances between the video cameras, time spent by the second person for movement, and a relation between characteristic feature values of the first a

Assignees

• Nec Corp

Inventors

• Miyano Hiroyoshi

Classifications

• G06K9/00885 Primary

  Physics · mapped topic

• G06T7/20

  Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51) · CPC title

• G06K2009/3291

  Physics · mapped topic

• G06T2207/30232

  Surveillance · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title