JPH0470294A - Background separating device for picture signal - Google Patents

Abstract

PURPOSE:To attain the correct separation of a background part from a picture signal to display a subject placed in the background by detecting difference from a background picture signal for every signal obtained by separating the picture signal of the subject in the background into a high color picture area and a low color picture area. CONSTITUTION:The picture signal S2 of only the background is stored in a background storage part 3. The picture signal S3 including an objective body is separated into the picture signals S4 and S5 of the high and the low color areas by a picture area separating part 4. The picture signals S4, S5 and the background picture signal S6 are received by a high color area difference signal detecting part 5 and a low color area difference signal detecting part 7 respectively, and difference signals S7, S8 are detected. A high color area background deciding part 6 and a low color area background deciding part 8 output mask signals S9, S10 for removing the background of each color area based on the decided result of whether each picture element displays the background part or not based on the difference signals S7, S8. A background removing part 9 receives the picture signal S3 and the mask signals S9, S10, and obtains the picture signal S11 obtained by removing the background part from the picture signal S3. Thus, the background part can be correctly separated.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention generally relates to a background separation device for an image signal, and more particularly, to a device for separating a background portion from an image signal for displaying a subject in a predetermined background. The present invention relates to a background separation device.

[Problems to be Solved by the Prior Art and the Invention 1] In the field of image processing, only the image of a target object is extracted from a video signal, and the object is measured or recognized, or combined with another video signal. There may be cases where 2. Description of the Related Art Conventionally, a chroma image system has been known as a method for removing the background portion of a color image and outputting only an image of a target object.

In the Chromaki one-way system, a screen of a specific color is prepared,
The target object is photographed with the screen as a background.

By removing the signal component corresponding to the specific color from the photographed video signal, the background video is erased, and a video signal that displays only the target object can be obtained. However, as mentioned above, this chroma system has the disadvantage that it is necessary to prepare a dedicated background screen coated with a specific color before photographing, and the equipment for this needs to be large-sized.

On the other hand, as a method that does not require a background screen, an image of only the background that does not include the target object is stored in advance as a background image, and by comparing the background image and the image that includes the target object, the parts that match in both There is a method to remove it as a background. In this method, there are the following two methods for comparing the above two images. In the first method, a color video signal is expressed using an RGB representation consisting of three components: R (red), G (green), and B (blue), and comparisons are made based on the values of each signal component. . In addition, in the second method, each R, G, and B signal component is changed to an HSV representation consisting of three components: H (hue), S (saturation), and V (lightness), and based on the value of each component. A comparison is made between the two.

However, in the first method, the three primary colors are used as they are, so if the brightness of the background changes due to changes in illumination or the shadow of the target object, the values of each color signal component will also change significantly. Therefore, there is a drawback that a portion where the brightness has changed is mistakenly recognized as a target object, and accurate background removal cannot be performed. In addition, in the second method, comparison is performed using hue components that represent the original color of the target object regardless of shading, so there is no error in background removal even if the background brightness changes, but RGB expression When converting from to H3V representation, errors are added in areas where the color intensity is low. As a result, the error becomes noise, which has the disadvantage that accurate comparison cannot be made.

The present invention was made in order to solve the above-mentioned problems, and it is an object of the present invention to provide a background separation device that can accurately separate a background portion from an image signal that displays a subject placed in the background. purpose.

[Means for Solving the Problems] A background separation device according to the present invention includes a background storage means for storing a background image signal for displaying only the background, and a first image signal for displaying a subject in the background. and separating the first image signal into a second image signal representing a high color image area and a third image signal representing a low color image area in response to the intensity of color represented by the first image signal. a first difference detection means for detecting a difference between the separated second image signal and the stored background image signal; and a first difference detection means for detecting the difference between the separated second image signal and the stored background image signal; the second to detect the difference between
a difference detection means for determining a background partial signal in the first image signal in response to the difference signal generated from the first and second difference detection means; and a determination means responsive to the determination result by the determination means. and background separation means for separating a background partial signal from the first image signal.

[Function] In the background separation device of the present invention, the first image signal representing a subject in the background is separated by the area separation means into a second image signal representing a high color image area and a third image signal representing a low color image area. The image signal is separated from the image signal. Since the difference from the background image signal is detected for each of the separated second and third image signals, the difference can be detected accurately. Therefore, the background partial signal can be accurately determined from the first image signal based on the obtained difference signal. As a result, background separation is performed accurately.

[Embodiment of the Invention] FIG. 1 is a block diagram of a background removing apparatus showing an embodiment of the present invention. Referring to FIG. 1, this background separation device includes an input section 1 that receives a color video signal S1 and performs signal processing necessary for subsequent calculation processing, and a digital image signal S2 and S3 generated from the input section 1. and an arithmetic processing section 10 that receives data and performs arithmetic processing. The arithmetic processing section 10 includes a switching section 2 that selects image signals S2 and S3 generated from the input section 1. The background storage unit 3 receives an image signal S2 that displays only a background that does not include the target object via the switching unit 2, and stores this. The image region separation section 4 and the background removal section 9 convert the image signal S3 containing the target object via the switching section 2 into
receive. The image area separation unit 4 separates the image signal S3 containing the target object into an image signal S4 of a high color area and an image signal S5 of a low color area. The high color area difference signal detection unit 5 receives the image signal S4 and the background image signal S6, and detects a difference signal S7 for each pixel. The low color area difference signal detection unit 7 receives the image signal S5 and the background image signal S6, and outputs a difference signal S8. The high color area background determination unit 6
Based on the difference signal S7, it is determined whether each pixel displays a background portion. As a result of this determination, a mask signal S9 is output that defines a mask for removing the background of the high color area.

Similarly, the low color area background determination unit 8 determines whether each pixel displays a background portion based on the difference signal S8.

Based on the determination result, a mask signal SIO that defines a mask for background removal in a low color area is output. The background removal unit 9 receives the image signal S3 including the target object and the mask signals S9 and 510, and outputs an image signal Sll obtained by removing the background portion from the image signal S3.

FIG. 2 is a block diagram of the high color area difference signal detection section 5 shown in FIG. Referring to FIG. 2, this difference signal detection unit 5 includes a conversion unit 51 that converts an image signal S4 in a high color area expressed in RGB to an HSV expression, and a conversion unit 51 that similarly converts a background image signal S6 to an H5V expression. Conversion unit 52 and conversion unit 5
1 and 52, respectively.

Next, the processing in the background removal apparatus shown in FIG. 1 will be specifically explained. First, the input section 1 receives a color video signal S1. Normally, the video signal that makes up one screen is divided into frames, and by updating the frames, a temporally continuous image can be obtained. Processing of image signals of two screens, that is, one frame will be explained. The input unit 1 receives a video signal S for one screen.
1 into R, G, and B color signal components. Each separated color signal component is A/D converted and three image matrices Rhv, Ghv and Bhv are generated for each of R, G and B. Each image matrix is horizontally
The pixel is composed of color signal pixel elements each representing V pixels (H and V are positive integers) in the vertical direction. The input unit 1 is alternately supplied with a video signal of only the background that does not include the target object and a video signal that includes the target object. Therefore, the input section 1 is
Image matrix BRhv+ B that displays only the background
G h v and BBhv (in Fig. 1, these are the signal S
2) and image matrices Rhv, Ghv and Bhv (indicated by signal S3 in FIG. 1) of images containing the target object.

First, the switching section 2 is connected to the terminal B side, and the background image matrix signal S2 is stored in the background storage section 3. next,
The switching section 2 is connected to the terminal A side, and an image matrix signal S3 containing the target object is given to the image region separating section 4 and the background removing section 9.

In the image region separation unit 4, the given image matrix Rh
The following processing is performed for each pixel for v, Ghv, and Bhv.

However, Dhv-max (Rhv, Ghv, Bhv
) mt n (Rhv, Ghv, Bhv) - (7
) max (Rhv, Ghv, Bhv) Maximum value of each color component for each element (h, v) of the two-image matrix min (Rhv, Ghv, Bhv) Each color for each element (h, v) of the two-image matrix The minimum value of the component Here, Dhv defined by equation (7) indicates the color strength of each pixel. Further, T indicates a predetermined threshold value, which is set to T-10 in this embodiment. Therefore, for each image matrix Rhv, Ghv and Bhv, equations (1), (2) and (3)
High color image matrices HRhv, HGhv and HBhv are generated by applying respectively. In a high-color image matrix, each element of the image matrix that does not fall within the high-color area has a value of "-1" indicating that it is outside the area.
has been replaced with Similarly, formula (4), (5
) and (6), the low color image matrices LRhv, LGhv and HBhv are generated. That is, the image region separation unit 4 separates the applied image matrix signal S3 into a high color image matrix signal S4 and a low color image matrix signal S5, and generates them.

FIG. 3 is a matrix diagram showing an example of a high-color image matrix generated by the image region separation section 4. As shown in FIG. Third
A matrix as shown in the figure is generated for each of R, G, and B.

As shown in Figure 3, the high color image matrix allows
A high color area D1 and a region outside the area D2 are shown.

FIG. 4 is a matrix diagram showing an example of a low color image matrix. This matrix is also generated for each R1G and B. As shown in FIG. 4, a low color area D3,
The area outside the area D4 is shown.

The high color area difference signal detection unit 5 receives the high color image matrix signal S4 and the background image matrix signal S6. The high color image matrix signal S4 is a matrix HRhv, H
Including Ghv and HBhv. On the other hand, the background image signal S6
contains the matrices BRhv, BGhv and BBhv.

The converter 51 shown in FIG. 2 converts the high color image matrix signal S4 into H3V representation. Similarly, the conversion unit 52 converts the background image matrix signal S6 into HSV representation. That is, in each converter 51 and 52, RGB
The image matrix being represented is converted into a matrix indicating H (hue), S (saturation) and V (lightness) components. The conversion formula for this will be explained next.

For example, if the values of the R, G, and B components of one pixel are r, g, and b, respectively, the values s and v of the H8V expression for that pixel can be obtained by the following equations.

v-max (r, g, b) ・= (
8) 5=max (r, g, b)-min (r, g,
b) ■ ... (9) ... (10) However, r' - (v-r) / (v-min (r, g,
b) )... (11) g' = (v-g) / (v-min (r,
g, b) )... (12) b' = (v-b) / (v-min (r,
g+ b) )... (13) The above conversion formula is, for example, “C0LORGAMUT
TRANSFORM PAIR5” (Computer Graphics 12, 3
August 1978, pages 12-19).

By applying the above equations (8) to 13) to the high color image matrix and the background image matrix, the following hue values, saturation values, and brightness values are obtained as elements of each matrix.

Hlhv Elements of the H high color image matrix (h.

(2)) Hue value H2hv; Hue value 5lhv of element (h, v) of background image matrix: Element (h.

52 hv: Saturation value of element (h, v) of background image matrix Vlhv: Saturation value of element (h, v) of high color image matrix.

Brightness value of V2hv of By performing the calculation, a high chromatic image difference signal matrix HEhv is generated.

-V2hv) -(15) That is, in the distance calculation unit 53 shown in FIG.
A distance is calculated for each pixel represented by 6V, and a matrix indicating the distance, that is, a high color image difference signal matrix HEhv is generated. This matrix HEhv is
The high color area background determination unit 6 shown in FIG. 1 as the signal S7
given to. An example of a high chromatic image difference signal matrix is shown in FIG.

On the other hand, the low color difference signal detection section 7 performs the following processing in parallel with the processing in the high color difference signal detection section 5. The low color area difference signal detection unit 7 receives the low color image matrix signal S5 expressed in RGB and the background image matrix signal S6, and compares the distance of each corresponding pixel based on the signal components expressed in RGB. That is, R.G.
When a low color image signal represented by B is converted to HSV representation, the error during the conversion is large, so it is impossible to accurately detect a difference signal as in the above-described high color area difference signal detecting section 5. Therefore, the low color area difference signal detection unit 7 detects the difference signal in RGB representation without converting it to HSV representation. Specifically, the low color image difference signal matrix Ehv is generated by calculating according to the following equation.

BBhv) 2 - (16)...
(17) The low color image difference signal matrix LEhv generated by equation (16) is given to the low color area background determination section 8 shown in FIG. 1 as a difference signal S8.

An example of the low color image difference signal matrix LEhv is shown in FIG.

The high color area background determination unit 6 uses a high color difference signal matrix H
Ehv is received, and a high color background area mask matrix HMhv is generated by determining whether each element of the matrix should belong to the background using the following calculation formula.

In the matrix HMhv, the value "1" of an element indicates that the pixel corresponding to that element belongs to the background, and the value "0" indicates that the pixel corresponding to that element belongs to the background.
indicates that it does not belong to the background. Here, TH is a predetermined threshold value, and in this embodiment, TH-10 is set.

Similarly, the low color background determination unit 8 determines whether each element in the matrix belongs to the background by calculating the low color difference signal matrix LEhv using the following formula, and determines whether each element in the matrix belongs to the background. A background region mask matrix L M h v is generated.

In the matrix L M h v, the element value "1" indicates that the pixel belongs to the background, and the value rOJ indicates that it does not belong to the background. Note that TL is a predetermined threshold, and in this embodiment, it is set to TL-10.

Examples of matrices HMhv and L M hv generated in the background determination units 6 and 8, respectively, are shown in FIGS. 7 and 8. Each matrix HMhv and LM
Signals S9 and S10 indicating hv are given to the background removal section 9.

The background removal unit 9 shown in FIG.
), high color background area mask matrix HMhv (signal S9), and low color background area mask matrix LMhv
(signal 510). In the background removal unit 9, when the value of an element of each element of the mask matrices HMhv and LMhv is "0", it is assumed that the corresponding pixel displays the target object, and each matrix Rhv of the corresponding pixel is Leave the values of each element of Ghv and Bhv as they are. On the other hand, when the value of each element is "1", the value of the corresponding element of the image matrices Rhv, Ghv, and BhV is replaced with a value representing no signal, for example, the value "0".

Through the above processing, the background removal unit 9 generates an image matrix Rhv.

Among the elements of Ghv and Bhv, the value of the element determined to indicate the background part is replaced with "0", and therefore the background part has been removed.

The signal S11 output from the background removal section 9 is converted into an analog video signal by a D/A converter (not shown), and an image of the target object from which the background portion has been removed can be obtained.

In this way, the background removal device shown in Fig. 1 detects the background by dividing the image into two areas, high color and low color, and applies a background detection method suitable for the characteristics of each area. This makes it possible to remove background images with high precision. Moreover, there is no need to use dedicated background equipment, and processing can be performed in any background. In addition, since image processing for high color areas and image processing for low color areas are performed in parallel, background removal can be performed at high speed.

[Effects of the Invention] As described above, the present invention provides an area separation means for separating an image signal representing a subject in the background into an image signal of a high color image area and an image signal of a low color image area. Because of this provision, errors are less likely to occur in detecting the difference with the background image signal, and a background separation device that can accurately separate the background portion has been obtained.

[Brief explanation of drawings]

FIG. 1 is a block diagram of a background removal device showing one embodiment of the present invention. FIG. 2 is a block diagram of the high color area difference signal detection section shown in FIG. 1. FIG. 3 is a matrix diagram showing an example of a high color image matrix. FIG. 4 is a matrix diagram showing an example of a low color image matrix. FIG. 5 is a matrix diagram showing an example of a high color image difference signal matrix. FIG. 6 is a matrix diagram showing an example of a low color image difference signal matrix. FIG. 7 is a matrix diagram showing an example of a high color background area mask matrix. FIG. 8 is a matrix diagram showing an example of a low color background area mask matrix. In the figure, 1 is an input unit, 2 is a switching unit, 3 is a background storage unit, 4 is an image area separation unit, 5 is a high color area difference signal detection unit,
6 is a high color area background determination unit, 7 is a low color area difference signal detection unit, 8 is a low color area background determination unit, 9 is a background removal unit, 10
is an arithmetic processing unit. Second diagram taste ψ 11 + 1 1 Il
+ l I's ~ ~ O
−, −, −−, −, −, −+ , −φ COl
l l l l 1't''
till Jo 877 〒 〒 777 〒1'NL
l'l gu 已 tfl Fl , -----
-774u'l gu o-z gu bar's q ~
N-7tfl -J tn %F
OOOU'+ In Ln F)77 Autopsy
S $ ψ n bar q dimension 7 out 8
Hatake G g G ” ”
? 7: i17 <o,: Q
8 ” ” ” 7 7 7 7 7
7 7 7-s yen j%17 7 7 7 7 〒
7770 ° ---1 ---P 1 ---
. --He Figure 3 Figure 4 Figure 7-+ -1-1-1-4-1-1-1-1-1-1-
1-+-4-1-+-+-1-1-100+-1-1-
+ -1-1-7-10001-1-1-+ -+
-1-10000+-1-1-1-1-+ OOO
OI -+-+-1000000+ -1-11000001M l 11 TOO (M +1 Figure 8) 1 +1111444111 + 0 0 0 0 0-+-1-++ OOO0
-4-1-+-1-1

Claims (3)

[Claims] (1) A background separation device that separates a background portion signal for displaying the background portion from a first image signal for displaying a subject in a predetermined background, the background from which the subject has been removed. background storage means for storing a background image signal for displaying a high color image area; region separation means for separating a second image signal and a third image signal indicating a low color image region; and a background image stored in the second image signal separated by the region separation means and the background storage means. a first difference detection means for detecting a difference between the third image signal separated by the region separation means and a background image signal stored by the background storage means; a detection means; a determination means for determining the background partial signal in the first image signal in response to a difference signal generated from the first and second difference detection means; and a determination result by the determination means. background separation means for separating the background partial signal from the first image signal in response to. (2) Each of the second image signal and the background image signal includes red, green, and blue color signals, and the first difference detection means receives the second image signal and detects the second image signal. a first conversion means for converting the red, green and blue color signals contained in the background image signal into hue, saturation and lightness signals; a second conversion means for converting the color signal into signals of hue, saturation, and lightness; and a first distance for calculating the distance for each pixel between the signals converted by the first and second conversion means, respectively. The background separation device according to claim 1, further comprising a calculation means. (3) Each of the third image signal and the background image signal includes red, green, and blue color signals, and the second difference detection means receives the third image signal and the background image signal, and the second difference detection means receives the third image signal and the background image signal; 2. The background separation apparatus according to claim 1, further comprising second distance calculation means for calculating a distance for each pixel between the three image signals and the background image signal.