IP Library › Granted Patent US 11,487,001
Granted Patent B2
US 11,487,001 · App. 16/470,301 · Granted Nov 1, 2022

Image analysis device, image analysis method, and computer-readable recording medium

Inventors: Taichi Tanaka (Tokyo, JP); Osamu Hoshuyama (Tokyo, JP)
Assignee: NEC CORPORATION
G01S13/9023G06T7/60G06T2207/10044
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 11,487,001
App. No.
16/470,301
Granted
Nov 1, 2022
Kind
B2
Abstract

An image analysis device that ease association between an SAR image and an object is provided. The image analysis device includes: a stable reflection point identification unit that identifies, based on a plurality of synthetic aperture radar (SAR) images, stable reflection points at which reflection is stable in the plurality of SAR images; a phase identification unit that identifies a phase at each of the stable reflection points, based on the plurality of SAR images and a location of the stable reflection point in the plurality of SAR images; and a clustering means that clusters the stable reflection points, based on a Euclidian distance between each of the stable reflection points and a correlation of the phases at each of the stable reflection points.

Claims (54)

1. An image analysis device comprising:

at least one memory; and

at least one processor coupled to the at least one memory,

the at least one processor is configured to perform operations to:

identify, based on a plurality of synthetic aperture radar (SAR) images, stable reflection points at which reflection is stable in the plurality of SAR images; and

cluster each of the stable reflection points, based on each distance determined by using a Euclidian distance between two of the stable reflection points and correlations of phases of two of the stable reflection points,

wherein the distance indicates a degree of a relation between two of the stable reflection points.

2. The image analysis device according to claim 1 , wherein

the at least one processor is configured to perform operations to:

cluster each of the stable reflection points by separating, based on the distance, each of the stable reflection points connected to one another.

3. The image analysis device according to claim 2 , wherein

the at least one processor is configured to perform operations to:

identify the distance, using the Euclidian distance and the correlation of the phases;

generate a minimum spanning tree where the stable reflection points are connected in such a way that a sum of the distances is minimum; and

separate the minimum spanning tree, based on a magnitude of the distance.

4. The image analysis device according to claim 3 , wherein

the at least one processor is configured to perform operations to:

identify, using a correlation of the phases relating to each of two stable reflection points and a Euclidian distance between the two stable reflection points in the plurality of SAR images, the distance between the two stable reflection points.

5. The image analysis device according to claim 2 , wherein

the at least one processor is configured to perform operations to:

identify, using a correlation of the phases relating to each of two stable reflection points and a Euclidian distance between the two stable reflection points in the plurality of SAR images, the distance between the two stable reflection points.

6. The image analysis device according to claim 1 , wherein

the at least one processor is configured to perform operations to:

cluster each of the stable reflection points by classifying each of the stable reflection points into a cluster of the stable reflection points.

7. The image analysis device according to claim 6 , wherein

the at least one processor is configured to perform operations to:

generate the cluster of the stable reflection points;

identify the distance, using the Euclidian distance and the correlation of the phases; and

classify the stable reflection points into the cluster, based on the distance between a centroid relating to the distance of the cluster and each of the stable reflection points.

8. The image analysis device according to claim 7 , wherein

the at least one processor is configured to perform operations to:

identify, using a correlation of the phases relating to each of two stable reflection points and a Euclidian distance between the two stable reflection points in the plurality of SAR images, the distance between the two stable reflection points.

9. The image analysis device according to claim 6 , wherein

the at least one processor is configured to perform operations to:

identify, using a correlation of the phases relating to each of two stable reflection points and a Euclidian distance between the two stable reflection points in the plurality of SAR images, the distance between the two stable reflection points.

10. The image analysis device according to claim 1 , wherein

the at least one processor is configured to perform operations to:

identify, using a correlation of the phases relating to each of two stable reflection points and a Euclidian distance between the two stable reflection points in the plurality of SAR images, the distance between the two stable reflection points.

11. The image analysis device according to claim 1 , wherein

the at least one processor is configured to perform operations to:

identify the phase at each of the stable reflection points, based on the plurality of SAR images.

12. The image analysis device according to claim 1 , wherein

the at least one processor is configured to perform operations to:

output information relating to the stable reflection points being clustered.

13. The image analysis device according to claim 12 , wherein

output information relating to the clustered stable reflection points by overlapping the information with geographical information.

14. An image analysis method comprising:

identifying, based on a plurality of synthetic aperture radar (SAR) images, stable reflection points at which reflection is stable in the plurality of SAR images; and

clustering each of the stable reflection points, based on each distance determined by using a Euclidian distance between two of the stable reflection points and correlations of phases of two of the stable reflection points,

wherein the distance indicates a degree of a relation between two of the stable reflection points.

15. A non-transitory computer readable storage medium storing a program which causes a computer to execute processing of:

identifying, based on a plurality of synthetic aperture radar (SAR) images, stable reflection points at which reflection is stable in the plurality of SAR images; and

clustering each of the stable reflection points, based on each distance determined by using a Euclidian distance between two of the stable reflection points and correlations of phases of two of the stable reflection points,

wherein the distance indicates a degree of a relation between two of the stable reflection points.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 17, 2019
From: TANAKA, TAICHI; HOSHUYAMA, OSAMU
To: NEC CORPORATION
Reel/Frame 049482/0281 →
Priority Claims (1)
JP JP2016-252479 · Dec 27, 2016 · national
Continuity (1)
Related Publication 20200096628A1 · Mar 26, 2020