IP Library › Granted Patent US 12682599
Granted Patent B2
US 12682599 · App. 18/026,530 · Granted Jul 14, 2026

Image processing method

Inventor: Azusa Sawada (Tokyo, JP)
Assignee: NEC CORPORATION
G06V10/751G06T7/50G06T7/70G06V10/25G06V2201/07
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 12682599
App. No.
18/026,530
Granted
Jul 14, 2026
Kind
B2
Abstract

An image processing device 100 of the present invention includes a region extraction unit 121 that extracts, from a captured image, a mobile body region that is a region having a possibility that a mobile body exists, a matching unit 122 that performs template matching on the mobile body region by using a template corresponding to a mobile body that is a detection object, and a detection unit 123 that detects each mobile body from the mobile body region separately, on the basis of the template matching.

Claims (33)

1 . An image processing method comprising:

specifying, in a captured image, a candidate region for detecting an object;

performing template matching on the candidate region by using a plurality of templates corresponding to a plurality of objects to be detected, each of the plurality of templates being matched within the same candidate region; and

based on the template matching, separately detecting each of the plurality of objects in the same candidate region;

wherein the candidate region is specified when an outer appearance of the candidate region does not match an outer appearance of a template according to a preset criterion.

2 . An image processing device comprising:

at least one memory configured to store instructions; and

at least one processor configured to execute instructions to:

specify, in a captured image, a candidate region for detecting an object;

perform template matching on the candidate region by using a plurality of templates corresponding to a plurality of objects to be detected, each of the plurality of templates being matched within the same candidate region; and

based on the template matching, separately detect each of the plurality of objects in the same candidate region,

wherein the candidate region is specified when an outer appearance of the candidate region does not match an outer appearance of a template according to a preset criterion.

3 . The image processing device according to claim 2 , wherein the at least one processor is configured to execute the instructions to:

perform the template matching on the candidate region that is specified as a region having a possibility that a plurality of objects exist, based on an extraction result of the candidate region.

4 . The image processing device according to claim 3 , wherein the at least one processor is configured to execute the instructions to:

perform the template matching on the candidate region that is specified as the region having a possibility that a plurality of objects exist, based on a shape of the candidate region.

5 . The image processing device according to claim 2 , wherein the at least one processor is configured to execute the instructions to:

perform the template matching on the candidate region that is specified as a region having a possibility that a plurality of objects exist, based on a past detection result of an object.

6 . The image processing device according to claim 5 , wherein the at least one processor is configured to execute the instructions to:

perform the template matching on the candidate region that is specified based on at least one of: (i) a position or (ii) a time, in the captured image, at which a plurality of objects were detected in the past.

7 . The image processing device according to claim 2 , wherein the at least one processor is configured to execute the instructions to:

perform the template matching by using a template selected, from among templates stored in advance, based on an extraction result of the candidate region.

8 . The image processing device according to claim 7 , wherein the at least one processor is configured to execute the instructions to:

perform the template matching by using a template selected based on at least one of: (i) a position or (ii) a time, in the captured image, of the candidate region.

9 . The image processing device according to claim 2 , wherein the at least one processor is configured to execute the instructions to:

generate a template based on a past detection result of an object.

10 . The image processing device according to claim 9 , wherein the at least one processor is configured to execute the instructions to:

generate the template based on at least one of (i) a position or (ii) a time, in the captured image, of the object detected in the past.

11 . An image processing method comprising:

specifying, in a captured image, a candidate region for detecting an object;

performing template matching on the candidate region by using a plurality of templates corresponding to a plurality of objects to be detected, each of the plurality of templates being matched within the same candidate region; and

based on the template matching, separately detecting each of the plurality of objects in the same candidate region;

wherein the specified candidate region has an aspect ratio that differs from an outer appearance of a template.