Image processing method, non-transitory computer-readable recording medium, and image processing device

• US 10,115,020 B2
• Filed: 10/10/2016
• Issued: 10/30/2018
• Est. Priority Date: 11/06/2015
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Sasaki, Kazuo, Yabuki, Akihiko
• Primary Examiner(s): Sherali, Ishrat I
• Application Number:
  US15/289,428
• Publication Number:
  US 20170132470A1
• Time in Patent Office: 750 Days
• Field of Search: 382103
• CPC Class Codes: G06T 15/30 Clipping
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30224 Ball; Puck
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06V 20/42 of sport video content
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

An image processing device acquires multiple sets of continuous image data, captured by a capturing device, determines whether an object having a predetermined characteristic is present in a partial region of image data included in the sets of image data, using the processor repeatedly detects the object from image data that is captured prior to the image data where the object is present, when the object is determined to be present in the partial region, using the processor, calculates a movement trajectory of the object in accordance with positions of the object, detected from multiple sets of image data, and times of the sets of image data, using the processor and identifies a start position and a start time of the movement trajectory.

Claims

1. An image processing method comprising:

acquiring multiple sets of continuous image data, captured by a capturing device, using a processor;

determining whether an object having a predetermined characteristic is present in a partial region of image data included in the sets of image data, using the processor;

repeatedly detecting the object from image data that is captured prior to the image data where the object is present, when the object is determined to be present in the partial region, using the processor;

calculating a movement trajectory of the object in accordance with positions of the object, detected from multiple sets of image data, and times of the sets of image data, using the processor;

identifying a start position and a start time of the movement trajectory, using the processor; and

identifying a person related to the object by comparing the start position with positions of multiple persons included in image data, captured by the capturing device at a same time as the start time, using the processor.

2. The image processing method according to claim 1, further comprising clipping image data captured by the capturing device between the start time of the movement trajectory and a finish time that elapsed with a predetermined time, using the processor.

3. The image processing method according to claim 1, wherein the predetermined characteristic indicates a shape and a size of the object, and the partial region is set around a position of a goal that is present in image data and that is used for a sport.

4. The image processing method according to claim 1, wherein the detecting detects the object from a region other than the partial region with a low detection accuracy, as compared to an accuracy when detecting the object from the partial region.

5. The image processing method according to claim 1, wherein the calculating changes the movement trajectory in accordance with a type of sport.

6. A non-transitory computer-readable recording medium having stored therein a program that causes a computer to execute a process comprising:

acquiring multiple sets of continuous image data, captured by a capturing device;

determining whether an object having a predetermined characteristic is present in a partial region of image data included in the sets of image data;

repeatedly detecting the object from image data that is captured prior to the image data where the object is present, when the object is determined to be present in the partial region;

calculating a movement trajectory of the object in accordance with positions of the object, detected from multiple sets of image data, and times of the sets of image data;

identifying a start position and a start time of the movement trajectory; and

identifying a person related to the object by comparing the start position with positions of multiple persons included in image data, captured by the capturing device at a same time as the start time.

7. The non-transitory computer-readable recording medium according to claim 6, the process further comprising clipping image data captured by the capturing device between the start time of the movement trajectory and a finish time that elapsed with a predetermined time.

8. The non-transitory computer-readable recording medium according to claim 6, wherein the predetermined characteristic indicates a shape and a size of the object, and the partial region is set around a position of a goal that is present in image data and that is used for a sport.

9. The non-transitory computer-readable recording medium according to claim 6, wherein the detecting detects the object from a region other than the partial region with a low detection accuracy, as compared to an accuracy when detecting the object from the partial region.

10. The non-transitory computer-readable recording medium according to claim 6, wherein the calculating changes the movement trajectory in accordance with a type of sport.

11. An image processing device comprising:

a processor configured to execute a process comprising;

acquiring multiple sets of continuous image data, captured by a capturing device;

determining whether an object having a predetermined characteristic is present in a partial region of image data included in the sets of image data;

repeatedly detecting the object from image data that is captured prior to the image data where the object is present, when the object is determined to be present in the partial region;

calculating a movement trajectory of the object in accordance with positions of the object, detected from multiple sets of image data, and times of the sets of image data;

identifying a start position and a start time of the movement trajectory; and

identifying a person related to the object by comparing the start position with positions of multiple persons included in image data, captured by the capturing device at a same time as the start time.

12. The image processing device according to claim 11, the process further comprising clipping image data captured by the capturing device between the start time of the movement trajectory and a finish time that elapsed with a predetermined time.

13. The image processing device according to claim 11, wherein the predetermined characteristic indicates a shape and a size of the object, and the partial region is set around a position of a goal that is present in image data and that is used for a sport.

14. The image processing device according to claim 11, wherein the detecting detects the object from a region other than the partial region with a low detection accuracy, as compared to an accuracy when detecting the object from the partial region.

15. The image processing device according to claim 11, wherein the calculating changes the movement trajectory in accordance with a type of sport.