Detecting apparatus of human component and method thereof

• US 9,400,935 B2
• Filed: 04/22/2013
• Issued: 07/26/2016
• Est. Priority Date: 10/10/2007
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Chen, Maolin, Jeon, Moon-Sik
• Primary Examiner(s): Park, Edward
• Application Number:
  US13/867,464
• Publication Number:
  US 20130236057A1
• Time in Patent Office: 1,191 Days
• Field of Search: 382/155, 382/159
• US Class Current: 1/1
• CPC Class Codes: G06V 10/40 Extraction of image or video features
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G06V 40/107 Static hand or arm
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

Disclosed are an apparatus and a method of detecting a human component from an input image. The apparatus includes a training database (DB) to store positive and negative samples of a human component, an image processor to calculate a difference image for the input image, a sub-window processor to extract a feature population from a difference image that is calculated by the image processor for the positive and negative samples of a predetermined human component stored in the training DB, and a human classifier to detect a human component corresponding to a human component model using the human component model that is learned from the feature population.

Claims

1. An image forming system comprising:

a photographing sensor configured to capture an image of a physical object;

a detector configured to use an object model to detect a region of the image that includes the physical object, wherein the object model is trained by an image of the physical object, wherein the image of the physical object is extracted from a difference image by use of at least one sub-window, wherein each difference image is either a positive or a negative image of the physical object, and wherein each difference image corresponds to a difference between a first image of the physical object and a second image of the physical object;

a status parameter computing processor configured to compute status parameters, based on the region where the detected physical object exists in the image of the physical object, so as to enable the physical object to be in the central region of the image;

a controller configured to receive the status parameters, and adjust the status of the image;

a memory device configured to store the image of the physical object;

a display configured to display the image of the physical object; and

a sub-window processor configured to use at least one sub-window to extract the image of the physical object from the difference image,

wherein the sub-window processor is configured to;

create double windows by simultaneously varying width and height of two windows, in an adjustable scale according to the image scale;

vary the width and height of the double windows, by using consistent zoom parameters, and

slide the double windows on the image, so as to capture a wide-range hidden pattern according to the scale, wherein the double windows are slid relative to each other in a horizontal direction or in a vertical direction, in order to capture a wide-range hidden pattern.

2. The system of claim 1 further comprising:

a user interface, including a touch screen, configured to enable a user to indicate a region including the physical object, and to provide the indication to the detector.

3. The system of claim 1, wherein the controller is configured to control at least one of the following operations:

rotation, tilting, zooming, and selecting a focus region according to the status parameters.

4. The system of claim 1, wherein the controller is configured to select, as a focus region, a new region where the physical object exists.

5. The system of claim 1, wherein the controller is configured to make the central region of the image as a default focus region, dynamically select a new region where the physical object exists as a focus region, and control status parameters of zoom, focal distance, rotation, or tilt, based on image information of the focus region.

6. The system of claim 1, wherein the sub-window processor is configured to:

create a single window by sliding the single window on a training image, while varying its width and height in an adjustable scale according to an image scale.

7. An image forming system comprising:

a photographing sensor configured to capture an image of a physical object;

a detector configured to use an object model to detect a region of the image that includes the physical object, wherein the object model is trained by an image of the physical object, wherein the image of the physical object is extracted from a difference image by use of at least one sub-window, wherein each difference image is either a positive or a negative image of the physical object, and wherein each difference image corresponds to a difference between a first image of the physical object and a second image of the physical object;

a status parameter computing processor configured to compute status parameters, based on the region where the detected physical object exists in the image of the physical object, so as to enable the physical object to be in the central region of the image;

a controller configured to receive the status parameters, and adjust the status of the image;

a memory device configured to store the image of the physical object;

a display configured to display the image of the physical object; and

a sub-window processor configured to use at least one sub-window to extract the image of the physical object from the difference image,

wherein the sub-window processor is configured to;

create triple windows by sliding three connected windows on a sample;

wherein the triple windows have identical width and height, while varying their scales in order to capture a wide-range pattern according to the scale; and

wherein a second window of the triple windows captures convex and concave contours from a movement of a first window and a third window.

8. The system of claim 7, wherein there are a plurality of kinds of triple windows, including:

a first kind of triple windows, comprising a horizontal layout of the three windows, wherein the second window is configured to slide horizontally and relatively between the first and third windows, and

a second kind of triple windows, comprising a vertical layout of the three windows, wherein the second window is configured to slide vertically and relatively vertically between the first and the third windows.

9. The system of claim 7 further comprising:

a user interface, including a touch screen, configured to enable a user to indicate a region including the physical object, and to provide the indication to the detector.

10. The system of claim 7, wherein the controller is configured to control at least one of the following operations:

rotation, tilting, zooming, and selecting a focus region according to the status parameters.

11. The system of claim 7, wherein the controller is configured to select, as a focus region, a new region where the physical object exists.

12. The system of claim 7, wherein the controller is configured to make the central region of the image as a default focus region, dynamically select a new region where the physical object exists as a focus region, and control status parameters of zoom, focal distance, rotation, or tilt, based on image information of the focus region.