SEARCH METHOD AND SYSTEM

• US 20160283590A1
• Filed: 02/22/2016
• Published: 09/29/2016
• Est. Priority Date: 03/24/2015
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: MATSUDA, Yuji, TSUJI, Kentaro, ZHENG, Mingxie, MIYAZAKI, Nobuhiro, MINAGAWA, Akihiro, UEHARA, Yusuke
• Granted Patent: US 10,127,310 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/784 the detected or recognised objects being people
• CPC Class Codes: G06V 10/247 by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

A search system includes circuitry configured to detect an first object to be a search target, from information of an image that is captured by an imaging device, determine a parameter in consideration of how the first object is viewed in the image, in accordance with a height at which the imaging device is installed, a depression angle of the imaging device, and a distance from the imaging device to the first object, divide an image region corresponding to the first object into at least two image regions based on a dividing ratio that is obtained by correcting a predetermined ratio in accordance with the parameter, and specify a second object in another image based on feature information of each of the at least two image regions, the second object corresponding to the first object in the image.

Claims

1. A search system comprising:

circuitry configured to;

detect an first object to be a search target, from information of an image that is captured by an imaging device,

determine a parameter in consideration of how the first object is viewed in the image, in accordance with a height at which the imaging device is installed, a depression angle of the imaging device, and a distance from the imaging device to the first object,

divide an image region corresponding to the first object into at least two image regions based on a dividing ratio that is obtained by correcting a predetermined ratio in accordance with the parameter, and

specify a second object in another image based on feature information of each of the at least two image regions, the second object corresponding to the first object in the image.

2. The search system according to claim 1, wherein the first object is designated based on information of the search target that is designated by a search request.

3. The search system according to claim 1, further comprising:

a memory configured to store each dividing ratio associated with information regarding how objects are viewed, and

wherein the dividing ratio is applied to the image region corresponding to the first object, in accordance with how the first object is viewed in the image.

4. The search system according to claim 3, wherein the circuitry is configured to:

detect an object region corresponding to the objects, from learning image information,

determine the dividing ratio for each detection position of the object region, and

store the dividing ratio in the memory in association with each detection position.

5. The search system according to claim 4, wherein the circuitry is configured to:

calculate a variation in luminance in the object region, and

determine the dividing ratio based on the variation in luminance.

6. The search system according to claim 1, wherein the first object and the second object are persons.

7. The search system according to claim 1, wherein the feature information is color information.

8. The search system according to claim 7, wherein the color information is a color histogram.

9. A search method comprising:

detecting an first object to be a search target, from information of an image that is captured by an imaging device;

determining, by circuitry, a parameter in consideration of how the first object is viewed in the image, in accordance with a height at which the imaging device is installed, a depression angle of the imaging device, and a distance from the imaging device to the first object;

dividing an image region corresponding to the first object into at least two image regions based on a dividing ratio that is obtained by correcting a predetermined ratio in accordance with the parameter; and

specifying a second object in another image based on feature information of each of the at least two image regions, the second object corresponding to the first object in the image.

10. The search method according to claim 9, wherein the first object is designated based on information of the search target that is designated by a search request.

11. The search method according to claim 9, further comprising:

generating each dividing ratio associated with information regarding how objects are viewed, and

wherein the dividing ratio is applied to the image region corresponding to the first object, in accordance with how the first object is viewed in the image.

12. The search method according to claim 11, further comprising:

detecting an object region corresponding to the objects, from learning image information;

determining the dividing ratio for each detection position of the object region; and

storing the dividing ratio into a memory in association with each detection position.

13. The search method according to claim 12, further comprising:

calculating a variation in luminance in the object region; and

determining the dividing ratio based on the variation in luminance.

14. The search method according to claim 9, wherein the first object and the second object are persons.

15. The search method according to claim 9, wherein the feature information is color information.

16. The search method according to claim 15, wherein the color information is a color histogram.

17. A non-transitory computer-readable storage medium storing a search program for causing a computer to execute a process, the process comprising:

detecting an first object to be a search target, from information of an image that is captured by an imaging device;

determining a parameter in consideration of how the first object is viewed in the image, in accordance with a height at which the imaging device is installed, a depression angle of the imaging device, and a distance from the imaging device to the first object;

dividing an image region corresponding to the first object into at least two image regions based on a dividing ratio that is obtained by correcting a predetermined ratio in accordance with the parameter; and

specifying a second object in another image based on feature information of each of the at least two image regions, the second object corresponding to the first object in the image.