JPH05236340A - Method and device for image processing - Google Patents

Abstract

PURPOSE:To provide an image processing method to accurately detect the presence or absence and the position of a desired object included in a background image. CONSTITUTION:Hue calculators 5 and 6 calculate the hue Hv of the pixel (x, y) of a video memory 3 designated by a CPU 10 and the hue Hb of the pixel (x, y) of the corresponding background image memory 4 respectively, and inputs these hues Hv and Hb to a decider 9. At the same time, the threshold value TH which is read out of a threshold table memory 11 with the hue Hv defined as an address is inputted to the decider 9. The decider 9 outputs the object detection signal S (x, y) when the absolute value of difference between both hues Hv and Hb exceeds the threshold value TH.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to image processing technology,
In particular, the present invention relates to a technique effectively applied to a special effect process based on an operation in cooperation with a motion of a subject in a video signal.

[0002]

2. Description of the Related Art For example, the presence or absence of an object in a video signal obtained from a video camera or the like or the motion of the object is detected based on the difference in brightness between the object image and the background image, and another specific image on the video screen is detected. It is conceivable to realize various special effects such as controlling the movement of the object or controlling the external system in cooperation with the movement of the object.

[0003]

However, it is not possible to detect objects having similar brightness to the background and different colors, or to distinguish between objects having similar brightness and different colors, simply by determining the difference in brightness. There's a problem. For example, it is difficult to perform operations such as extracting the movement of a person on the screen by paying attention to the skin color of the person image in the background.

An object of the present invention is to provide an image processing technique capable of accurately detecting the position and presence / absence of a target object in a background image.

Another object of the present invention is to provide an image processing technique capable of arbitrarily controlling the detection sensitivity of the position of an object of a specific color in a background image.

Still another object of the present invention is to provide an image processing technique capable of performing various detection processes of an object image in a background image.

[0007]

Among the inventions disclosed in the present application, a brief description will be given to the outline of typical ones.
It is as follows.

That is, the image processing method of the present invention detects the difference between the background image data and the object image data mixed in the background image data, and detects the position and presence / absence of the object in the background. A first step of capturing and storing background image data in a state in which object image data is not mixed, a second step of capturing arbitrary target image data including a background image, and an arbitrary step in the target image data The third step of calculating the hue Hv at each pixel position and the hue Hb at the corresponding pixel position in the background image data, and comparing the absolute value of the difference between the hue Hv and the hue Hb with a predetermined threshold value TH. , The absolute value of the difference is the threshold value T
And a fourth step of outputting an object detection signal at the pixel position when H is exceeded.

Further, the image processing method of the present invention is described in claim 1.
In the image processing method described above, the value of the threshold value TH is changed according to the value of the hue Hv in the target image data, and the detection sensitivity of the object of the specific hue Hv is arbitrarily controlled.

Further, the image processing method of the present invention is described in claim 1.
Alternatively, in the third step of the image processing method described in 2, the luminance Yb and the luminance Yv at the corresponding pixel positions of the background image data and the target image data are examined at the same time as the hue Hv and the hue Hb, and in the fourth step, The magnitude relationship between the difference between the brightness Yv and the brightness Yb and a predetermined threshold value TY is determined, and the hue Hv and the hue H based on other threshold values TH are determined.
The presence or absence of the output of the object detection signal is determined together with the determination result of the difference b.

Further, the image processing apparatus of the present invention comprises an image pickup means for digitizing and fetching arbitrary image data, first and second image memories capable of holding the image data independently, and a second image memory. Second hue calculating means for calculating a hue Hb at an arbitrary pixel position in the background image data held in the image memory, and a hue Hv at an arbitrary pixel position in the target image data held in the first image memory. And a hue H at corresponding pixel positions in the first and second image memories.
The control unit compares the absolute value of the difference between v and the hue Hb with a predetermined threshold value TH, and outputs an object detection signal at the pixel position when the absolute value of the difference exceeds the threshold value TH, and each unit. And a control means.

Further, the image processing apparatus of the present invention comprises:
In the described image processing apparatus, the hue H of the target image data
A threshold value table memory in which the same or different threshold value TH is set at each address using the value of v as an address is provided, and the determining means determines the absolute value of the difference between the hue Hv and the hue Hb and the hue value Hv from the threshold value table memory. Is used as an address and an operation of comparing with a threshold value TH that is read out each time is performed.

Further, the image processing apparatus of the present invention comprises:
Alternatively, in the image processing device according to the fifth aspect, the first and second
The first and second brightness calculation means for calculating the brightness Yv and the brightness Yb at arbitrary pixel positions in the background image data and the target image data stored in the image memory are provided, and the determining means determines the brightness Yv and the brightness Yb. The presence or absence of the output of the object detection signal is determined by combining the determination result of the magnitude relationship between the difference of Yb and the predetermined threshold value TY and the determination result of the threshold value TH of the hue Hv and the hue Hb.

[0014]

According to the above-described image processing method and image processing apparatus of the present invention, the position of an object in the background is detected based on the difference in hue between the background and the object. Even if the backgrounds are similar, or if there are multiple types of objects of different colors with similar brightness in the background, the position and presence of the target object in the background, as well as the identification of multiple objects, etc. Can be accurately performed.

Further, since the value of the threshold value TH, which is the reference of the determination process, can be appropriately changed according to the hue Hv in the target image data, it is possible to arbitrarily control the detection sensitivity of an object of a specific color. ..

Further, by combining the measurement results of both the difference in hue and the difference in luminance between the background and the object, it is possible to perform various detection processing of the objects mixed in the background image.

[0017]

Embodiment 1 An image processing method and an image processing apparatus according to an embodiment of the present invention will be described in detail below with reference to the drawings.

FIG. 1 is a block diagram showing an example of the configuration of an image processing apparatus according to an embodiment of the present invention, and FIG. 2 is a flow chart showing an example of the operation of the image processing apparatus and the image processing method. ..

First, an outline of the configuration of the image processing apparatus of this embodiment will be described with reference to FIG.

For example, a video memory 3 is connected to a camera 1 such as a color video camera via an A / D converter 2. This video memory 3 is
Each plane of R, G, B is provided, and each plane is
The luminance of each of the primary colors of red, green, and blue in each pixel forming one screen is held as multivalued information having a predetermined bit width.

Although not particularly shown, the A / D converter 2 has three systems of A / D corresponding to the respective primary colors of R, G and B.
Equipped with a conversion circuit, each color data is stored in the video memory 3
It is designed to be written on the plane of the relevant color.

The video memory 3 includes the video memory 3
The background image memory 4 having the same capacity as the above is connected, and it is possible to copy and save the image data of each plane of R, G, and B which is once taken in the video memory 3.

A hue calculator 5 and a hue calculator 6 are connected to the succeeding stages of the video memory 3 and the background image memory 4, respectively. The hue calculator 5 and the hue calculator 6 are connected to the hue calculator 5 and the hue calculator 6.
The output of is the input to the determiner 9.

Each of the above-mentioned units is controlled by a central processing unit 10 (CPU) including a microprocessor, for example.

The hue calculator 5 belonging to the video memory 3 is
For the arbitrary pixel (x, y) in the video memory 3 designated by the central processing unit 10, the data of each plane of R, G, B is read out, the hue Hv (x, y) is calculated, and the determination unit 9 is executed. It is configured to perform an input operation.

Similarly, the hue calculator 6 belonging to the background image memory 4 performs R, G, and R for the arbitrary pixel (x, y) in the background image memory 4 designated by the central processing unit 10.
The data of each plane of B is read and the hue Hb (x,
It is configured to perform the operation of calculating y) and inputting it to the determiner 9.

In this case, the hue calculator 5 and the hue calculator 6 are arranged, for example, in the hue circle as shown in FIG. 4 for each color when red is 0 °, green is 120 ° and blue is 240 °. An operation of calculating the angle in the hue circle as the hue Hv and the hue Hb is performed.

A threshold table memory 11 is connected to the judging device 9. This threshold table memory 11 is used for the hue H calculated from the video memory 3 by the hue calculator 5.
This is a memory in which various thresholds TH are preset with v as an address, and when the hue Hv is input from the hue calculator 5 to the determiner 9, the threshold TH read with the hue Hv as an address is determined at the same time. It is input to the container 9.

The judging device 9 determines the hue Hv of an arbitrary pixel (x, y) on the video memory 3 side coming from the hue calculator 5 and the hue calculator 6 and the corresponding pixel (x, y) on the background image memory 4 side. y) the absolute value of the difference from the hue Hb is calculated, and when the absolute value exceeds the threshold TH at that time, which is input from the threshold table memory 11, the object detection signal at the pixel (x, y). It is configured to perform an operation of outputting S (x, y) to the outside.

An example of the operation of the image processing method and apparatus according to this embodiment will be described below.

First, the central processing unit 10 sets a desired threshold value TH at each address of the threshold value table memory 11 (step 20).

After that, first, the background image data of only the background in which no object exists is taken into the video memory 3 (step 21), and the background image data is further taken into the background image memory 4.
And copy (step 22).

Thereafter, first, the target image data to be judged is loaded into the video memory 3 (step 23), and the central processing unit 10 further designates the pixel (x, y) to specify the hue calculator 5 and the hue calculator. 6 is started, and the hue Hv and the hue Hb of the corresponding pixel (x, y) in the video memory 3 and the background image memory 4 are calculated at the same time, and are input to the determiner 9 (step 24).

At this time, the hue Hv on the video memory 3 side is
At the same time, the threshold value TH is input to the threshold value table memory 11 as an address, and the threshold value TH read from the address is input to the determiner 9 (step 25).

Further, the central processing unit 10 activates the judging device 9, and the judging device 9 compares the absolute value of the difference between the hue Hv and the hue Hb with the threshold value TH input from the threshold value table memory 11. Check the relationship (step 26).

If the absolute value exceeds the threshold TH, the object detection signal S (x, y) is output (step 27).

Then, after the determination processing for one pixel (x, y) as described above is completed, the central processing unit 10 determines whether or not the determination is completed for all the pixels of the target image data taken into the video memory 3. It is checked (step 28), and if not completed, the next pixel (x, y) is designated and the operations after step 24 are repeated (step 29).

On the other hand, if it is determined in step 28 that the determination process for all pixels for one screen in the current video memory 3 is completed, the above step 23 is performed.
Then, the next target image data is read into the video memory 3, and the processing of each subsequent step is repeated.

As described above, in the case of the image processing method and apparatus of the present embodiment, the desired pixel image data and the corresponding pixel (x, y) of the background image data in which no object exists.
Since the presence or absence and the position of an object in the target image data are detected according to the magnitude of the absolute value of the difference between the hue Hb and the hue Hv in each of the above, for example, when the difference in brightness between the background and the object is small, Even if a plurality of similar objects are mixed in the background, the target object can be accurately discriminated from the background and other objects by the color difference and detected.

When setting the threshold TH for each address of the threshold table memory 11, for example, the threshold TH set for the address of the hue Hv corresponding to the skin color is
By selectively setting the value smaller than the value set in the address of the hue Hv of another color, the detection sensitivity of the flesh-colored object becomes higher than the detection sensitivity of the other-colored object, and the background The position and presence of a person can be detected with high sensitivity.

[0041]

Second Embodiment Next, an image processing method and apparatus according to another embodiment of the present invention will be described with reference to FIG.

In the case of this embodiment, between the video memory 3 and the background image memory 4 and the determiner 9a, the hue calculator 5 and the hue calculator 6 as well as the luminance calculator 7 are provided.
The difference from the first embodiment is that the brightness calculator 8 and the brightness calculator 8 are respectively arranged.

The brightness calculator 7 and the brightness calculator 8 are
The brightness Yv and the brightness Yb at the corresponding pixel (x, y) of the video memory 3 and the background image memory 4 designated by the central processing unit 10 are calculated, and the brightness Yv and the brightness Yb are input to the determiner 9a. ..

Further, the determining device 9a in this embodiment determines the magnitude relationship between the absolute value of the difference between the hue Hv and the hue Hb and the threshold value TH, and sets the difference between the luminance Yv and the luminance Yb from the outside. It is configured to perform the operation of determining the magnitude relationship with the desired threshold value TY.

Then, for example, when the absolute value of the hue difference is larger than the threshold value TH, the judging device 9a concerned (condition A).
And the difference in luminance is larger than the threshold value TY (condition B),
If the conditions A and B are satisfied at the same time, or if at least one of the conditions A and B is satisfied, the object detection signal S (x,
The determination operation such as outputting y) is performed.

As described above, in the case of the second embodiment, since the presence / absence of an object in the background and the position detection operation are performed based on both the difference in hue and brightness, it is possible to detect a wider variety of objects. It can be carried out.

[0047]

The effects obtained by the typical ones of the inventions disclosed in the present application will be briefly described as follows.
It is as follows.

That is, according to the image processing method of the present invention, it is possible to accurately detect the position and presence / absence of a target object in the background image.

Further, according to the image processing method of the present invention, there is an effect that the detection sensitivity of the position of the object of the specific color in the background image can be arbitrarily controlled.

Further, according to the image processing method of the present invention, there is an effect that various detection processing of the object image in the background image can be performed.

Further, according to the image processing apparatus of the present invention, there is an effect that the position and presence / absence of the target object in the background image can be accurately detected.

Further, according to the image processing apparatus of the present invention, it is possible to arbitrarily control the detection sensitivity of the position of the object of the specific color in the background image.

Further, according to the image processing apparatus of the present invention, there is an effect that various detection processing of the object image in the background image can be performed.

[Brief description of drawings]

FIG. 1 is a block diagram showing an example of the configuration of an image processing apparatus that is an embodiment of the present invention.

FIG. 2 is a flowchart showing an example of the operation of the image processing apparatus and the image processing method according to the embodiment of the present invention.

FIG. 3 is a block diagram showing an example of the configuration of an image processing apparatus that is another embodiment of the present invention.

FIG. 4 is an explanatory diagram showing an example of a hue circle showing the magnitude relationship of hues in the image processing method and apparatus of the present invention.

[Explanation of symbols]

 1 camera (imaging means) 2 A / D converter (imaging means) 3 video memory (first image memory) 4 background image memory (second image memory) 5 hue calculator (first hue calculation means) 6 hue Calculator (second hue calculation means) 7 Luminance calculator (first luminance calculation means) 8 Luminance calculator (second luminance calculation means) 9 Judgment device (judgment means) 9a Judgment device (judgment means) 10 Central Processing device (control means) 11 Threshold table memory Hb Hue of background image data Hv Hue of target image data Yb Luminance of background image data Yv Luminance of target image data TH Threshold for hue difference determination TY Threshold for luminance difference determination S Object detection signal

Claims (6)

[Claims] 1. An image processing method for detecting the difference between background image data and object image data mixed in the background image data to detect the presence or absence and the position of an object in the background. A first step of capturing and storing the background image data in a state in which no data is mixed, a second step of capturing any target image data including the background image, and a second step of capturing any target image data in the target image data. The third step of calculating the hue Hv and the hue Hb at the corresponding pixel position in the background image data, and comparing the absolute value of the difference between the hue Hv and the hue Hb with a predetermined threshold value TH, The absolute value of the difference is the threshold value T
And a fourth step of outputting an object detection signal at the pixel position when H is exceeded. 2. The value of the threshold value TH is changed according to the value of the hue Hv in the target image data, and the detection sensitivity of an object of a specific hue Hv is arbitrarily controlled. The described image processing method. 3. In the third step, the luminance Yb and the luminance Yv at corresponding pixel positions of the background image data and the target image data are checked at the same time as the hue Hv and the hue Hb, and in the fourth step. Is the presence or absence of the output of the object detection signal together with the determination result of the difference between the luminance Yv and the luminance Yb and a predetermined threshold value TY, and the determination result of the difference between the hue Hv and the hue Hb by the threshold value TH. 3. The method according to claim 1 or 2, wherein
The described image processing method. 4. An image pickup unit for digitizing and capturing arbitrary image data, first and second image memories capable of independently retaining the image data, and the second image memory. Second hue calculating means for calculating a hue Hb at an arbitrary pixel position in the background image data, and first for calculating a hue Hv at an arbitrary pixel position in the target image data held in the first image memory. Comparing the absolute value of the difference between the hue Hv and the hue Hb at a corresponding pixel position in the first and second image memories with a predetermined threshold value TH, and the absolute value of the difference is calculated as follows. An image processing apparatus comprising: a determination unit that outputs an object detection signal at the pixel position when the threshold value TH is exceeded; and a control unit that controls each unit. 5. A threshold value table memory in which the same or different threshold value TH is set at each address using the value of the hue Hv of the target image data as an address, and the determining means includes the hue Hv and the hue Hb. 5. The image processing apparatus according to claim 4, further comprising an operation of comparing an absolute value of a difference between the threshold value TH and the threshold value TH read from the threshold value table memory with the hue Hv as an address. 6. A luminance Yv and a luminance Yb at arbitrary pixel positions in the background image data and the target image data stored in the first and second image memories.
The first and second luminance calculating means for calculating the above are provided, and the determining means determines the magnitude relationship between the difference between the luminance Yv and the luminance Yb and a predetermined threshold value TY, and the hue Hv and the hue Hb. The image processing apparatus according to claim 4, wherein the presence or absence of the output of the object detection signal is determined together with the determination result based on the threshold value TH.