JPH11339047A - Device for extracting selected area of image - Google Patents

Abstract

PROBLEM TO BE SOLVED: To selectively extract only a mask area including a marker area among plural mask area by geodesic reconstruction processing at a real time video rate. SOLUTION: This device is constituted of at least a mask signal labeling processing part 8 for labeling to each area included in a mask area, and applying each different label number to each area, marker signal labeling 10 for applying the same label number as the label number applied to the mask area including each area, to each area included in a marker area, and a label number-provided mask area selecting part 11 for outputting only are information indicating the mask area having the same label number as the label number applied to each area included in the marker area by the marker signal labeling processing part as selected area information. Thus, the extraction of the selected area of an image can be realized at a real time video rate.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image signal processing apparatus, and more particularly, to a method of removing a partial subset of a mask area based on a topographic distance of a two-dimensional image and removing the remaining subset. Geodesicrecons, an image composition processing method that restores a subset without changing its shape
The present invention relates to an apparatus for extracting a selected area of an image in which a truncation process is realized at a real time video rate.

[0002]

2. Description of the Related Art First, a well-known geodesic rec.
The onstruction processing will be described with reference to FIG. Here, there is a set group of Wi and Nj (each a subset), and the entire set is represented by W and N. The inclusive relationship between W and N is W⊃N, but for each of the subsets Wi and Nj, Nk is not necessarily included in the subset of Wk. In such a state, N is geodesic reconst under W
Performing the fraction processing means outputting only a subset of W including Nj which is a subset of N. In the case of FIG. 6, subsets W1 and W4 of W including subsets N1 and N2 of N are output as N1 'and N2', respectively. geodesic reconst
For example, L.R. Vincent
t, “Morphological Grayscal
e Reconstruction in Image
Analysis: Applications an
d Efficient Algorithms ", I
EEE Trans. on Image Procedures
sing, Vol. 2, No. 2, April 199
See, for example, No. 3.

[0003] Conventionally, geodesic rec
In the onstruction processing, the area W is called a mask area, the area N is called a marker area, and the two-dimensional position (x,
A binary signal consisting of “0” and “1” is made to correspond to the mask signal and the marker signal of y), and the area is set to “1” and the area outside the area is set to “0”. It is represented by a binary area signal represented by “0” and “1” on a plane.

[0004] geodesic reconstruct
As a conventional technique relating to the tion process, a sequential process is generally used in which a marker region (region N) is used as a starting point and a region is extended to a mask region (region W) including the marker region. Here, a typical processing procedure will be described below. 1) All the horizontal and vertical position information of the pixel at the boundary of the marker area is written into the FIFO address memory. 2) Only one piece of position information is read from the FIFO type address memory, and only when a pixel located in the vicinity of the position information is included in the mask area, the pixel located at that position is set as an effective mask area. 3) Only the position information of the pixel determined as the effective mask area is written to the FIFO type address memory. 4) Until the FIFO type address memory becomes empty, 2),
Step 3) is repeated.

If the above procedure is performed by hardware, the configuration is as shown in FIG. First, all the horizontal and vertical position information of the pixel at the boundary of the marker area is written into the FIFO address memory (process 1 in the above procedure). This writing process is performed as follows.

That is, a marker signal and a mask signal are supplied to an input frame memory 1 and an input frame memory 2 indicated by reference numerals 1 and 2, respectively, which are randomly accessible. The marker signal is also supplied to the output frame memory 3 and written in the output frame memory 3 at a corresponding position as area information. Further, the position information detecting section 4 detects the area boundary of the marker area (area N) from the marker signal supplied to the detecting section 4 and stores the horizontal and vertical position information in the FIFO type address memory 5. Supplied and written.

Next, the circuit operations of processes 2) to 4) in the above procedure will be described together. Only one horizontal and vertical position information is read out from the FIFO type address memory, and the next-stage neighboring address detection unit 6 compares the read horizontal and vertical position information with the horizontal and / or vertical address ±. 1 and calculate. Neighbor address detector 6
The position information in the horizontal and vertical directions calculated by the above becomes the address signals of the input frame memory 1 to which the marker signals indicated by 1 and 2 are supplied and the input frame memory 2 to which the mask signal is input, respectively. The states of the marker area and the mask area at the horizontal and vertical positions calculated by the neighboring address detection unit 6 from 1 and 2 are read, respectively. These pieces of information are supplied together with the address signal to the logical decision processing section 7 at the next stage.

The logical decision processing section 7 is a section for making a logical decision on the states of the marker area and the mask area at the supplied horizontal and vertical positions, and is usually constituted by a CPU. The logical decision processing unit 7 performs the following three processes.
When the horizontal and vertical positions calculated by the neighboring address detection unit 6 are included in the mask area and not included in the marker area, the position is determined as an effective area, and the output frame memory 3 Write the area information at the corresponding position. If the horizontal and vertical positions calculated by the neighboring address detector 6 are included in the mask area but not in the marker area, the position information is written to the FIFO type address memory 5. When the FIFO type address memory 5 receives empty information indicated by a broken line indicating that it has become empty, the output control (shown by a broken line) of the output frame memory 3 is enabled (switch SW).
Is turned on), the contents of the output frame memory 3 are read out and output as a selected area signal.

[0009]

SUMMARY OF THE INVENTION A geodesic r which removes a partial subset of a mask region while restoring the remaining subset without changing the shape of the original subset.
When the reconstruction processing is performed by the above-described conventional circuit configuration or apparatus, in order to realize the same at a real-time video rate of a television signal (generally, a video signal), signal processing for each frame is uniformly 1/30.
It may be done within seconds, but the CP that constitutes the logical decision processing unit
Due to the limitation of the processing speed of U, it is difficult to perform processing within 1/30 second depending on the image content of the video signal.

As a solution to this problem, it is conceivable to introduce parallel processing in the time direction, but it is still difficult to end the processing at a real time video rate. This is because the buffer time required for the parallel processing is not constant because the processing time varies depending on the shape and size of the mask area and the marker area.

An object of the present invention is to provide a geodesic re.
In performing the construction processing, in order to solve the above-described problem that the real-time video rate processing cannot be performed due to the shape and size of the mask area and the marker area as described above, the selection area of the image that is appropriately configured and arranged. An extraction device is provided.

[0012]

In order to achieve the above object, in the image selection area extracting apparatus according to the present invention, a different label number is assigned to each mask area for the mask area (the label number is assigned by itself. For example, CJN
icol, “A Systolic Approach
for Real Time Connected
Component Labeling ”, Compu
ter Vision And Image Unde
rstending, Vol. 61, no. 1, Jan
uary, pp. 17-31, 1995. ), And also assigns the same label number to the marker area included in the mask area, and then selects only the mask area having the same label number as the label number assigned to the marker area. Geodes which selects and outputs only the mask area including the marker area by outputting it as an area
The ic reconstruction process was realized at a real-time video rate.

That is, the apparatus for extracting a selected area of an image according to the present invention is capable of extracting an area included in the area group B only when each area included in the area group B is included in any of the areas included in the area group A. A region included in the included region group A is defined as an effective region, and geodesic reconstr.
A mask signal labeling processing unit that performs a labeling process on each region included in the region group A and assigns a different label number to each region in an apparatus for extracting a selected region of an image to be extracted at a real-time video rate by an union process. A marker signal labeling processing unit that assigns the same label number to each of the regions included in the region group B as the label numbers assigned to the regions of the region group A including the respective regions, and a marker signal labeling processing unit. At least a label number-added mask area selecting unit that outputs only area information indicating an area of the area group A having the same label number as a label number assigned to each area included in the area group B as selected area information. It is characterized by the following.

[0014]

DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below based on embodiments of the present invention with reference to the accompanying drawings. The present invention provides, as described above, geodesic recons.
When the truncation process is performed with a conventional circuit configuration,
In order to solve the problem that the real-time video rate cannot be used, the use of a labeling circuit and a random access memory RAM allows the effective mask area to be changed in real time without depending on the shape and size of the mask area and marker area. The detection is performed at the video rate.

Before describing the embodiments of the present invention with reference to the drawings, the operation of each of the three components which characterize the present invention in the claims of the present application will be described. Each is as follows.

First, the first requirement, that is, a mask signal labeling processing unit that performs labeling processing on each area included in the area group A and assigns a different label number to each area, A labeling process is performed to assign a different label number to each included mask area and obtain a mask signal with a label number.
The labeling processing circuit can be easily realized according to the above-mentioned literature and the like. In brief, different numbers are assigned to the image signals divided into a plurality of regions, and the same number is assigned to all the pixels included in one region instead of the binary data “1” indicating the region. The area number is assigned.

Next, for each region included in the region group B,
The processing performed by the marker signal labeling processing unit that assigns the same label number to the area of the area group A including each area is realized by taking the product of the marker signal and the mask signal with the label number. . The marker signal is a binary signal having a region portion of “1” and a background portion of “0”, and a region to which “1” is added as a marker signal is included in a region to which “1” is added as a mask signal. Relationship. Since the marker signal is a binary signal of “1” and “0”, the product of the marker signal and the mask signal with the label number is “1” indicating the marker area.
Are replaced by the label numbers assigned to the mask signal area including the marker signals.

The last requirement, that is, only the area information indicated by the area of the area group A having the same label number as the label number given to each area included in the area group B by the marker signal labeling processing unit, is selected area information. The mask area selection unit with label number, which outputs the mask information with the label number, which has the same label number as the label number assigned to the marker signal with label number, is output as the selection area. This processing is realized by alternately using the two RAMs in the write mode and the read mode in frame units.
In the write mode, the label number given to the marker signal with the label number is used as the input address of the RAM,
As the data corresponding to the address, the fact that the address is an effective area is written. In the read mode, the contents written in the RAM are read using the label number assigned to the mask signal delayed by one frame as an address, and the mask area having the label number written as the effective area information in the data corresponding to the address By outputting only the position information, it becomes possible to select only the mask region including the marker region at the real time video rate.

Hereinafter, the present invention will be described in detail with reference to the embodiments shown in FIGS. FIG.
1A shows an example of a mask area, and FIG. 1B shows an example of a marker area. Here, when a labeling process is performed on the mask region shown in FIG.
As shown in FIG. In FIG. 2A, # 0 is assigned to the background area, and # 1 to # 4 of mutually different label numbers are assigned to each mask area.

From the area shown in FIG.
If only the area where the marker signal is present is cut out as shown in FIG. 2B, it becomes a marker area with a label number as shown in FIG. 2B. Next, by selecting only the mask area having the same label number as the label number-added marker signal of FIG. 2B from the respective mask areas of FIG. The selected mask area which is the object of the present invention shown in FIG.

The principle operation of the present invention is as described above. Next, an image selection region extracting apparatus according to the present invention for extracting an image selection region based on this operation principle will be described. FIG. 3 is a block diagram showing the basic configuration of the device of the present invention. In FIG. 3, reference numeral 8 denotes a mask signal labeling processing unit, 9 denotes a marker signal delay unit, 10 denotes a marker signal labeling processing unit, and 11 denotes a mask area selection unit with a label number.

The operation will be described. As shown in FIG.
The mask signal (1 bit) is supplied to the mask signal labeling processing unit 8, and a label number is assigned to each pixel in the mask area (see FIG. 2A). This label number is assigned, for example, according to C.I. J. This is performed according to the method described in Nicol's literature.

On the other hand, the marker signal (1 bit) is supplied to a marker signal delay section 9 for delaying the marker signal by a time required for the mask signal to be given a label number in the mask signal labeling processing section 8, and the output is supplied to the marker signal delay section. The signal is supplied to one input terminal of the signal labeling processing unit 10. The other input terminal of the marker signal labeling processing unit 10 is supplied with a mask signal to which a label number has been assigned by the mask signal labeling processing unit 8 as shown in the figure, and an output terminal of the marker signal labeling processing unit 10 Area where marker signal is "1" (indicating marker area)
2 is assigned the same label number as the label number assigned to the mask area including that area (FIG. 2).
(See (b)).

The marker signal labeling processing section 10 includes a marker signal (1 bit) delayed by a predetermined time by the marker signal delay section 9 and a mask signal (n bits) to which a label number is assigned by the mask signal labeling processing section 8. Is a signal processing unit that takes the product of the two, and is composed of, for example, a plurality of AND circuits as shown in FIG.

By passing both signals through the circuit shown in FIG. 4, # 0, which is the same as the label number of the background, is always written in the area other than the marker area. The same label number as the label number assigned to is output.

FIG. 5 shows a circuit configuration of an example of the mask area selection unit with label number 11 shown in FIG.
This circuit basically uses two random access memories (shown as RAM (I) 16 and RAM (II) 17 in the figure, respectively), and uses RAM (I) 16, RA
The selection mode is extracted by switching the write mode and the read mode of the M (II) 17 on a frame basis by the selector (I) 13 and the selector (II) 14.

In FIG. 5, RAM (I) 16 and R
The AM (II) 17 is supplied with a read signal R and a write signal W of a two-frame cycle having the phase relationship shown in the figure as control signals. The write mode and the read mode are repeatedly repeated.

First, the operation in the write mode will be described. By the selector (I) 13 or (II) 14, a marker signal with a label number corresponding to a pixel position synchronized with a control signal (read signal, write signal) is input as an address input to the RAM (I) 16 or (II) 17, respectively. As the data input corresponding to the selected address, an output signal from the address valid data ROM 15 indicating that the address is a valid area (that is, a marker signal area) is supplied and written. The output signal of the address valid data ROM 15 is, for example, “0” when the marker signal is out of the area, that is, “0”. When the marker signal is in the area of the marker signal, all the output signals are “No. 1 ". At this time, the output of the address valid data ROM 15 is 1 bit (n 'bit in the figure).

Next, the operation in the read mode will be described. The mask signal with the label number delayed by one frame by the one-frame delay unit 12 placed before the selector (I) 13 or (II) 14 becomes an address input to the RAM (I) 16 or (II) 17. The data written in the write mode one frame before corresponding to the address is read as area information corresponding to a pixel position synchronized with a control signal (read signal, write signal). As a result, only the mask signal with the label number having the same label number as the marker signal with the label number is read from the RAM (I) 16 or (II) 17. The read signal is nothing but a signal representing selected area information intended to be extracted in the present invention.

[0030]

According to the image selection region extracting apparatus of the present invention, only the mask region including the marker region out of the plurality of mask regions is geodesic reconstr.
The action process allows selective extraction at the real-time video rate.

According to the device of the present invention, by applying the device of the present invention, Japanese Patent Application No. Hei 9-2
08414, “Label marker generation device for image region division processing and image region division processing device” (July 1, 1997)
The technology for detecting only a field portion of a field that does not include a player in a television field sports program disclosed in the application specification (filed on the 8th) is further improved to realize a more stable real-time video rate. Will be able to do it.

[Brief description of the drawings]

FIGS. 1A and 1B show an example of a mask area and an example of a marker area, respectively.

FIGS. 2 (a), (b) and (c) are the same as a labeled masking area, a marker area, and a labeling-processed marker area finally extracted by the present invention. Each of the mask areas has a label number.

FIG. 3 is a block diagram showing a basic configuration of the present invention.

FIG. 4 illustrates a circuit configuration of an example of a marker signal labeling processing unit in FIG. 3;

FIG. 5 shows a circuit configuration of an example of a mask area selection unit with a label number in FIG. 3;

FIG. 6: geodesic reconstructi
It is a figure explaining an ON process.

FIG. 7: geodesic reconstructi
1 shows a conventional circuit configuration in which on processing is performed by hardware.

[Explanation of symbols]

 Reference Signs List 8 mask signal labeling processing section 9 marker signal delay section 10 marker signal labeling processing section 11 mask area selecting section with label number 12 1 frame delay 13 selector (I) 14 selector (II) 15 address valid data ROM 16 RAM (I) 17 RAM (II)

Claims (1)

[Claims] 1. An area included in an area group A including an area included in the area group B only when each area included in the area group B is included in any area included in the area group A. Geodesic rec
A mask signal labeling processing unit for performing a labeling process on each region included in a region group A and assigning a different label number to each region in an apparatus for extracting a selected region of an image to be extracted at a real time video rate by an onstruction process. A marker signal labeling processing section for assigning the same label number to each of the areas included in the area group B as the label numbers assigned to the areas of the area group A including the respective areas, and a marker signal labeling processing section. At least a label number-added mask area selecting unit that outputs only area information indicating an area of the area group A having the same label number as a label number assigned to each area included in the area group B as selected area information. An apparatus for extracting a selected area of an image, comprising: