IP Library Granted Patent US 12,300,015
Granted Patent B2
US 12,300,015 · App. 17/769,793 · Granted May 13, 2025

Image processing apparatus, image processing method, and non-transitory computer readable medium storing image processing program

Inventors: Noboru Yoshida (Tokyo, JP); Shoji Nishimura (Tokyo, JP)
Assignee: NEC CORPORATION
G06V40/103G06F16/538G06V10/761G06V10/764G06V40/23
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 12,300,015
App. No.
17/769,793
Granted
May 13, 2025
Kind
B2
Abstract

An image processing apparatus ( 10 ) according to the present disclosure includes: a skeleton detection unit ( 11 ) configured to detect two-dimensional skeleton structures of a plurality of persons based on an acquired two-dimensional image; a feature calculation unit ( 12 ) configured to calculate features of the plurality of two-dimensional skeleton structures that have been detected by the skeleton detection unit ( 11 ); and a recognition unit ( 13 ) configured to perform processing of recognizing states of the plurality of persons based on a degree of similarity among the plurality of features that have been calculated by the feature calculation unit ( 12 ).

Claims (40)

1. An image processing apparatus comprising:

at least one memory storing instructions, and

at least one processor configured to execute the instructions stored in the at least one memory to:

detect two-dimensional skeleton structures of a plurality of persons based on an acquired two-dimensional image;

calculate features of the plurality of two-dimensional skeleton structures that have been detected;

perform processing of recognizing states of the plurality of persons based on a degree of similarity among the plurality of features that have been calculated;

classify the states of the plurality of persons as the recognition processing; and

classify two-dimensional skeleton structures in which the right side and the left side of a person are opposite from each other as one state.

2. The image processing apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to classify the states of the plurality of persons based on all or some of the features of the two-dimensional skeleton structures.

3. The image processing apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to classify the states of the plurality of persons based on a feature of a first part of the two-dimensional skeleton structure and a feature of a second part of the two-dimensional skeleton structure.

4. The image processing apparatus according to claim 1 , wherein

the at least one processor is further configured to execute the instructions stored in the at least one memory to:

detect two-dimensional skeleton structures of the plurality of persons from a plurality of two-dimensional images that are continuous in time series, and

classify the states of the plurality of persons based on the features of the two-dimensional skeleton structures detected from the plurality of two-dimensional images.

5. The image processing apparatus according to claim 4 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to classify the states of the plurality of persons based on changes in the features of the two-dimensional skeleton structures in the plurality of two-dimensional images.

6. The image processing apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to display results of classification of the states of the plurality of persons in accordance with the degree of similarity.

7. The image processing apparatus according to claim 6 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to retrieve a state of a person selected from the displayed results of classification from the states of the plurality of persons.

8. The image processing apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to retrieve, as the recognition processing, a query state from the states of the plurality of persons.

9. The image processing apparatus according to claim 8 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to retrieve the query state based on all or some of the features of the two-dimensional skeleton structures.

10. The image processing apparatus according to claim 8 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to retrieve the query state based on a feature of a first part of the two-dimensional skeleton structure and a feature of a second part of the two-dimensional skeleton structure.

11. The image processing apparatus according to claim 10 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to retrieve the query state based on a weight of the feature of the first part and a weight of the feature of the second part.

12. The image processing apparatus according to claim 8 , wherein

the at least one processor is further configured to execute the instructions stored in the at least one memory to detect two-dimensional skeleton structures of the plurality of persons from a plurality of two-dimensional images that are continuous in time series, and

retrieve the query state based on the features of the two-dimensional skeleton structures detected from the plurality of two-dimensional images.

13. The image processing apparatus according to claim 12 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to retrieve the query state based on changes in the features of the two-dimensional skeleton structures in the plurality of two-dimensional images.

14. The image processing apparatus according to claim 8 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to retrieve two-dimensional skeleton structures in which the right side and the left side of a person are opposite from each other as one state.

15. The image processing apparatus according to claim 8 , wherein the at least one processor is further configured to execute the instructions stored in the at least one memory to display results of retrieval of the states of the plurality of persons in accordance with the degree of similarity.

16. The image processing apparatus according to claim 1 , wherein the feature is a feature of only a height direction of the person.

17. An image processing method performed by a computer and comprising:

detecting two-dimensional skeleton structures of a plurality of persons based on an acquired two-dimensional image;

calculating features of the plurality of two-dimensional skeleton structures that have been detected;

performing processing of recognizing states of the plurality of persons based on a degree of similarity among the plurality of features that have been calculated;

classifying the states of the plurality of persons as the recognition processing; and

classifying two-dimensional skeleton structures in which the right side and the left side of a person are opposite from each other as one state.

18. A non-transitory computer readable medium storing an image processing program executable by a computer to perform processing comprising:

detecting two-dimensional skeleton structures of a plurality of persons based on an acquired two-dimensional image;

calculating features of the plurality of two-dimensional skeleton structures that have been detected;

performing processing of recognizing states of the plurality of persons based on a degree of similarity among the plurality of features that have been calculated;

classifying the states of the plurality of persons as the recognition processing; and

classifying two-dimensional skeleton structures in which the right side and the left side of a person are opposite from each other as one state.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 18, 2022
From: YOSHIDA, NOBORU; NISHIMURA, SHOJI
To: NEC CORPORATION
Reel/Frame 059620/0473 →
Continuity (1)
Related Publication 20220383653A1 · Dec 1, 2022
References Cited (25)
US 20110148875A1 · Kim · 2011 [cited by examiner]
US 20130028517A1 · Yoo · 2013 [cited by examiner]
US 20130181988A1 · Yoo et al. · 2013 [cited by applicant]
US 20130230211A1 · Tanabiki · 2013 [cited by examiner]
US 20140301605A1 · Kawaguchi · 2014 [cited by examiner]
US 20190147292A1 · Watanabe et al. · 2019 [cited by applicant]
US 20200394393A1 · Kraft · 2020 [cited by examiner]
US 20220108468A1 · Nakamura · 2022 [cited by examiner]
US 20240087353A1 · Yoshida et al. · 2024 [cited by applicant]
CN 114641794A · 2022 [cited by applicant]
JP 2006260405A · 2006 [cited by applicant]
JP 2012120647A · 2012 [cited by applicant]
JP 2014522035A · 2014 [cited by applicant]
JP 2018073091A · 2018 [cited by applicant]
JP 2019028509A · 2019 [cited by applicant]
JP 2019091138A · 2019 [cited by applicant]
TW 201738827A · 2017 [cited by applicant]
WO 2019048011A1 · 2019 [cited by applicant]
Zhe Cao et al “Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields”, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017. p. 7291-7299 (Year: 2017). [cited by examiner]
JP Office Communication for JP Application No. 2021-553977, mailed on Mar. 5, 2024 with English Translation. [cited by applicant]
International Search Report for PCT Application No. PCT/JP2019/042746, mailed on Dec. 3, 2019. [cited by applicant]
Zhe Cao et al., “Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields”. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, p. 7291-7299. [cited by applicant]
Extended European Search Report for EP Application No. 19951063.7, dated on Sep. 12, 2022. [cited by applicant]
India Office Action for IN Application No. 202217025223, mailed on Sep. 8, 2022 with English Translation. [cited by applicant]
CN Office Action for CN Application No. 201980101757.0, mailed on Mar. 3, 2025 with English Translation. [cited by applicant]