Target analysis apparatus, method and computer-readable medium

• US 8,744,168 B2
• Filed: 08/24/2010
• Issued: 06/03/2014
• Est. Priority Date: 08/24/2009
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Chen, Maolin
• Primary Examiner(s): Akhavannik, Hadi
• Application Number:
  US12/862,330
• Publication Number:
  US 20110044506A1
• Time in Patent Office: 1,379 Days
• Field of Search: 382/154, 382/224
• US Class Current: 382/154
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

Provided is a target analysis apparatus, method and computer-readable medium based on a depth image and an intensity image of a target is provided. The target analysis apparatus may include a body detection unit to detect a body of the target from the intensity image of the target, a foreground segmentation unit to calculate an intensity threshold value in accordance with intensity values from the detected body, to transform the intensity image into a binary image using the intensity threshold value, and to mask the depth image of the target using the binary image as a mask to thereby obtain a masked depth image, and an active portion detection unit to detect an active portion of the body of the target from the masked depth image.

Claims

1. A target analysis apparatus having a depth image and an intensity image of a target as an input, the target analysis apparatus comprising:

a body detection unit to detect a body of the target from the intensity image of the target;

a foreground segmentation unit to calculate an intensity threshold value in accordance with intensity values from the detected body, to transform the intensity image into a binary image using the intensity threshold value, and to mask the depth image of the target using the binary image as a mask to thereby obtain a masked depth image; and

an active portion detection unit to detect an active portion of the body of the target from the masked depth image,

wherein the active portion of the body includes at least one part of the body having a relatively large motion,

wherein a non-active portion of the body of the target includes a human head and torso, and the active portion includes human arms and legs.

2. The target analysis apparatus of claim 1, further comprising:

a Time-Of-Flight (TOF) camera set to capture the depth image and the intensity image of the target to output the captured images.

3. The target analysis apparatus of claim 1, wherein the body detection unit is trained using a statistical learning method to detect from the intensity image, components constituting the body of the target, and to select, from a plurality of candidates for the components of the body, a candidate to meet a geometry constraint as the component of the body.

4. The target analysis apparatus of claim 1, wherein the foreground segmentation unit has as the intensity threshold value, a value obtained by averaging the intensity values from the detected body.

5. The target analysis apparatus of claim 1, wherein the active portion detection unit comprises:

a ridge detection unit to detect a plurality of ridges from the masked depth image; and

a ridge verification unit to verify the plurality of ridges and to select an optical ridge.

6. The target analysis apparatus of claim 5, wherein the ridge detection unit divides a depth image of the mask into the active portion of the body and the non-active portion of the body, and calculates a plurality of ridge candidates of each of the ridges, from a candidate of the active portion.

7. The target analysis apparatus of claim 6, wherein the ridge detection unit classifies the depth image of the mask into the active portion and the non-active portion, using an average depth value of the non-active portion as a threshold value.

8. The target analysis apparatus of claim 5, wherein the ridge verification unit determines a connection point between the active portion and the non-active portion in accordance with the body detected by the body detection unit, connects the determined connection point and an end of one of the plurality of ridges to generate an imaginary ridge, and verifies the plurality of ridges and the imaginary ridge.

9. A target analysis method based on a depth image and an intensity image of a target, the target analysis method comprising:

detecting, by a computer, a body of the target from the intensity image of the target;

calculating, by the computer, an intensity threshold value in accordance with intensity values from the detected body;

transforming, by the computer, the intensity image into a binary image using the intensity threshold value;

masking, by the computer, the depth image of the target using the binary image as a mask to thereby obtain a masked depth image; and

detecting, by the computer, an active portion of the body of the target from the masked depth image,

wherein the active portion of the body includes at least one part of the body having a relatively large motion,

wherein a non-active portion of the body of the target includes a human head and torso and the active portion includes human arms and legs.

10. The target analysis method of claim 9, further comprising:

capturing the depth image and the intensity image of the target using a TOF camera set.

11. The target analysis method of claim 9, wherein the detecting of the body comprises:

detecting, from a plurality of candidates for the components of the body, a candidate to meet a geometry constraint as the component of the body, using a portion detector trained through a statistical learning method.

12. The target analysis method of claim 9, wherein the calculating has as the intensity threshold value, a value obtained by averaging the intensity values from the detected body.

13. The target analysis method of claim 9, wherein the detecting of the active portion comprises:

detecting a plurality of ridges from the masked depth image; and

verifying the plurality of ridges and selecting an optical ridge.

14. The target analysis method of claim 13, wherein the detecting of the plurality of ridges classifies a depth image of the mask into the active portion of the body and the non-active portion of the body, and calculates a plurality of ridge candidates of each of the ridges from a candidate of the active portion.

15. The target analysis method of claim 14, wherein the detecting of the plurality of ridges divides the depth image of the mask into the active portion and the non-active portion, using an average depth value of the non-active portion as a threshold value.

16. The target analysis method of claim 15, wherein the verifying of the plurality of ridges comprises:

determining a connection point between the active portion and the non-active portion;

connecting the determined connection point and an end of one of the plurality of ridges to generate an imaginary ridge; and

verifying the plurality of ridges and the imaginary ridge.

17. At least one non-transitory computer-readable medium comprising computer readable instructions that control at least one processor to implement a target analysis method based on a depth image and an intensity image of a target, the target analysis method comprising:

detecting a body of the target from the intensity image of the target;

calculating an intensity threshold value in accordance with intensity values from the detected body;

transforming the intensity image into a binary image using the intensity threshold value;

masking the depth image of the target using the binary image as a mask to thereby obtain a masked depth image; and

detecting an active portion of the body of the target from the masked depth image,

wherein the active portion of the body includes at least one part of the body having a relatively large motion,

wherein a non-active portion of the body of the target includes a human head and torso and the active portion includes human arms and legs.