Image processing apparatus and image processing method

Patent metadata

Field	Value
Publication number	US-9953225-B2
Application number	US-201113287382-A
Country	US
Kind code	B2
Filing date	Nov 2, 2011
Priority date	Nov 5, 2010
Publication date	Apr 24, 2018
Grant date	Apr 24, 2018

Abstract

An image processing apparatus includes an object detection unit configured to detect an object from an image, a tracking unit configured to track the detected object, a trajectory management unit configured to manage a trajectory of the object being tracked, and a specific object detection unit configured to detect a specific object from the image. In a case where the specific object determination unit detects the object being tracked by the object tracking unit to be the specific object, the trajectory management unit manages a trajectory of the object being tracked at a time point before the time point the object being tracked is detected to be the specific object as the trajectory of the specific object.

First claim

What is claimed is:

1. An image processing apparatus comprising a processor executing a program recorded on a memory device, the executed program performing functions of:
an object detection unit configured to detect an object area corresponding to an object from an image by using a first method;
a tracking unit configured to track the detected object;
a trajectory management unit configured to manage a trajectory of the object being tracked;
a specific object detection unit configured to detect a specific object area corresponding to a specific object having a specific character or a specific pattern from the image by using a second method capable of detecting the specific object area without using a result of detection by the first method; and
an object association unit configured to determine, based on a size of a crossover between the object area detected by the object detection unit by using the first method on the image and the specific object area detected by the specific object detection unit by using the second method on the image, whether to associate the object detected by the object detection unit and the specific object detected by the specific object detection unit,
wherein the trajectory management unit stores data indicating that the object detected by the object detection unit and the specific object detected by the specific object detection unit are associated with each other by the object association unit.

2. The image processing apparatus according to claim 1 , wherein, the trajectory management unit is configured to determine, after a first time when the object being tracked by the tracking unit is detected as the specific object having the specific character or the specific pattern, a trajectory of the object being tracked by the tracking unit before the first time as the trajectory of the specific object, wherein the object being tracked by the tracking unit has not been detected as the specific object before the first time, and to determine, in a case where the object being tracked by the tracking unit is detected as a plurality of specific objects by the specific object detection unit, that the object being tracked by the tracking unit before the first time includes the plurality of the specific objects.

3. The image processing apparatus according to claim 1 , wherein, the trajectory management unit is configured to determine, after a first time when the object being tracked by the tracking unit is detected as the specific object having the specific character or the specific pattern, a trajectory of the object being tracked by the tracking unit before the first time as the trajectory of the specific object, wherein the object being tracked by the tracking unit has not been detected as the specific object before the first time, and to determine, in a case where the object being tracked by the tracking unit is determined as a plurality of types of specific objects by the specific object detection unit, that the object being tracked by the tracking unit before the first time includes the plurality of types of specific objects.

4. The image processing apparatus according to claim 1 , wherein, the trajectory management unit is configured to store a position included in the trajectory in association with attribute information for identifying whether the position is a position of the specific object and determine, after a first time when the object being tracked by the tracking unit is detected as the specific object having the specific character or the specific pattern, a position where the object existed before the first time as a position of the specific object.

5. The image processing apparatus according to claim 1 , wherein the trajectory management unit is configured to determine, after a first time when the object being tracked by the tracking unit is detected as the specific object having the specific character or the specific pattern, a trajectory of the object being tracked by the tracking unit before the first time as the trajectory of the specific object, wherein the object being tracked by the tracking unit has not been detected as the specific object before the first time, and to determine whether the object detected as the specific object passes through a specific place before the first time.

6. The image processing apparatus according to claim 1 , wherein the trajectory management unit is configured to determine, in a case where an object being tracked by the tracking unit and not being associated with the specific object passes through a specific place and in a case where the object being tracked by the tracking unit is associated with the specific object after the object has passed through the specific place, that the specific object has passed through the specific place.

7. The image processing apparatus according to claim 1 , wherein the first method is a background subtraction method.

8. The image processing apparatus according to claim 1 , wherein the second method is a pattern matching method.

9. The image processing apparatus according to claim 1 , wherein the specific object detection unit detects a human, an automobile or an animal.

10. The image processing apparatus according to claim 1 ,
wherein the object detection unit is configured to detect a position of the object area; and wherein the specific object detection unit is configured to detect a position of the specific object area.

11. An image processing method comprising:
detecting an object area corresponding to an object from an image by using a first method;
tracking the detected object;
managing a trajectory of the object being tracked;
detecting a specific object area corresponding to a specific object having a specific character or a specific pattern from the image by using a second method capable of detecting the specific object area without using a result of detection by the first method;
determining, based on a size of a crossover between the object area detected on the image by using the first method and the specific object area detected on the image by using the second method, whether to associate the object detected and the specific object detected; and
storing data indicating that the object detected and the specific object detected are associated with each other.

12. The image processing method according to claim 11 , further comprising:
determining, after a first time when the object being tracked is detected as the specific object having the specific character or the specific pattern, a trajectory of the object being tracked before the first time as the trajectory of the specific object, wherein the object being tracked has not been detected as the specific object before the first time; and
determining, in a case where the object being tracked is detected as the specific object detected, a position where the object existed before the first time, when the object is detected as the specific object existed before the first time.

13. The image processing method according to claim 11 , further comprising:
determining, after a first time when the object being tracked is detected as the specific object having the specific character or the specific pattern, a trajectory of the object being tracked before the first time as the trajectory of the specific object, wherein the object being tracked has not been detected as the specific object before the first time; and
determining whether the object detected as the specific object passes through a specific place before the first time.

14. The image processing method according to claim 11 , wherein the first method is a background subtraction method.

15. The i

Assignees

• Kawano Atsushi
• Canon Kk

Inventors

• Kawano Atsushi

Classifications

• G06T2207/30241

  Trajectory · CPC title

• G06T2207/30196

  Human being; Person · CPC title

• G06K2009/3291

  Physics · mapped topic

• G06K9/00771 Primary

  Physics · mapped topic

• G06K9/00362

  Physics · mapped topic