KR102315523B1 - Method of and system for eliminating background of image - Google Patents

Abstract

The present invention relates to a method and system for removing a background, and an embodiment of the present invention includes: a motion region detector for acquiring a motion region; a zone division unit dividing the movement area into zones; an edge value calculator for calculating a horizontal average edge value and a vertical average edge value for each zone; an edge component value determination unit that determines a larger value among a horizontal average edge value and a vertical average edge value for each region as an edge component value; a background removal unit for determining and removing a region having the edge component value equal to or less than a reference value as a background region; It provides a background removal system comprising a.

Description

{Method of and system for eliminating background of image}

The present invention relates to a method and system for removing a background, and to a method and system for removing a background component by dividing a motion detection area into regions and determining a region having an edge component value less than or equal to a reference value as a background region.

In recent years, the demand for monitoring systems for various purposes in various fields is increasing. A general surveillance system uses a method in which a camera is installed in a surveillance target area, and a monitor monitors an image of the camera. Since this method increases the labor cost and there is a problem that there is a limit in the range that a monitor can monitor, there have been attempts to detect a motion region in a surveillance image through image processing.

Such an image analysis technique includes a function of detecting a moving object from image information or analyzing the behavior of the object. The video analysis technique can replace or supplement the management personnel of the security system, such as intrusion/theft monitoring and the monitoring of moving objects, thereby helping to increase the effectiveness of the surveillance system.

However, since most surveillance systems receive a video stream for a long time, an image analysis technique with a small amount of computation is required to detect a motion region in a video stream received in real time within a limited resource.

An object of the present invention is to divide a motion detection region into a plurality of regions, and to remove a region having an edge component value equal to or less than a reference value as a background.

An embodiment of the present invention includes a motion region detector for acquiring a motion region; a zone division unit dividing the movement area into zones; an edge value calculator for calculating a horizontal average edge value and a vertical average edge value for each zone; an edge component value determination unit that determines a larger value among a horizontal average edge value and a vertical average edge value for each region as an edge component value; a background removal unit for determining and removing a region having the edge component value equal to or less than a reference value as a background region; It provides a background removal system comprising a.

In the present invention, the region divider may divide the movement region into one or more regions horizontally or vertically.

In the present invention, the background removing unit may determine the region of the inner region as the background region only when the region of the edge is removed.

In the present invention, the standard deviation calculator for calculating the standard deviation of the pixel value for each area; may be additionally included, and the background removing unit may determine the background as the corresponding area only when the standard deviation calculated by the standard deviation calculating unit is less than or equal to a specific value.

Another embodiment of the present invention includes a motion region detection step of acquiring a motion region; zone division step of dividing the movement area into zones; an edge value calculation step of calculating a horizontal average edge value and a vertical average edge value for each zone; an edge component value determination step of determining a larger value among a horizontal average edge value and a vertical average edge value for each region as an edge component value; a background removal step of determining and removing a region in which the edge component value is equal to or less than a reference value as a background region; It provides a background removal method comprising a.

In the present invention, the standard deviation calculating step of calculating the standard deviation of the pixel value for each area; may be additionally included, and the background removal step may determine the background as the corresponding area only when the standard deviation calculated by the standard deviation calculator is less than or equal to a specific value.

In addition to this, another method for implementing the present invention, another system, and a computer readable recording medium for recording a computer program for executing the method are further provided.

According to the present invention, it is possible to provide a method for removing a background area in an accurate motion detection area with a small amount of computation.

1 is a diagram illustrating a background removal system according to an embodiment of the present invention.
2 is a diagram illustrating an internal configuration of a background removal server according to an embodiment of the present invention.
3 illustrates a zoned motion detection area according to an embodiment of the present invention.
4 is a filter that can be used to calculate an edge value according to an embodiment of the present invention.
5 is a diagram illustrating an example of calculating an edge component value for each zone according to an embodiment of the present invention.
6 illustrates an example in which the standard deviation calculating unit 150 calculates the standard deviation for each zone according to an embodiment of the present invention.
7 is a diagram illustrating an execution sequence of a background removal method according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0023] Reference is made to the accompanying drawings, which show by way of illustration specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein may be implemented with changes from one embodiment to another without departing from the spirit and scope of the present invention. In addition, it should be understood that the location or arrangement of individual components within each embodiment may be changed without departing from the spirit and scope of the present invention. Accordingly, the following detailed description is not to be taken in a limiting sense, and the scope of the present invention should be taken to cover the scope of the claims and all equivalents thereto. In the drawings, like reference numerals refer to the same or similar elements throughout the various aspects.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings in order to enable those of ordinary skill in the art to easily practice the present invention.

1 is a diagram illustrating a background removal system according to an embodiment of the present invention.

Referring to FIG. 1 , the background removal system of the present invention includes a background removal server 100 , a plurality of surveillance cameras 200 , and a network 300 .

Referring to FIG. 1 , a plurality of surveillance cameras 200 exchange data with the background removal server 100 through a network 300 . Specifically, the plurality of cameras 200 communicate with the background removal server 100 through the communication channel (DCOM), and transmit live view video data to the background removal server 100 through the image data channel (DIMA). . Of course, not a plurality of monitoring cameras, only one monitoring camera may communicate with the background removal server 100 , and one monitoring camera or a plurality of monitoring cameras may communicate with a plurality of background removal servers 100 , etc. Of course, variations are possible.

Here, the network 300 forming the communication channel (DCOM) and the image data channel (DIMA) may be any means capable of transmitting and receiving data or commands by wire or wirelessly. For example, the network 300 may connect the plurality of cameras 200 and the background removal server 100 by wire through a cable, and wirelessly connect the plurality of cameras 200 and the background using a wireless LAN, etc. It is also possible to connect the removal server 100 .

Background removal server 100 may be used without limitation, such as general computing devices and server devices. For example, a control system for a surveillance camera, etc. may be used as the background removal server 100 . The background removal server 100 may store a real-time video from the plurality of cameras 200 as necessary.

The background removal server 100 serves to remove the background area through edge component analysis after a motion detection area is marked in the images obtained from the plurality of surveillance cameras 200 . In particular, the background removal server 100 can reduce the amount of computation in image processing for motion detection by removing the region determined as the background from the images obtained from the plurality of surveillance cameras 200 by region.

2 is a diagram illustrating an internal configuration of a background removal server according to an embodiment of the present invention.

Referring to FIG. 2 , the background removal server 100 according to an embodiment of the present invention includes a motion region detection unit 110 , a zone division unit 120 , an edge value calculation unit 130 , and an edge component value determination unit ( 140 ), a standard deviation calculating unit 150 , and a background removing unit 160 .

The existing motion area detection method has a problem of detecting even the surrounding area where there is no direct object movement as a moving area, such as detecting a shadow as a moving object, detecting a lighting change section as a moving object, or including an afterimage of movement as an object. there was. In one embodiment of the present invention, in order to solve the above-described problem, a background removal method capable of accurately removing a background region among detected motion regions with a small amount of computation is provided. To this end, the background removal server 100 according to an embodiment of the present invention divides the obtained motion image by region, calculates an average edge value, and determines and removes a region having an edge component value equal to or less than a reference value as a background. Hereinafter, a background removal method according to an embodiment of the present invention will be described in detail with a focus on the roles performed by each internal component of the background removal server 100 .

First, the motion region detector 110 serves to acquire a motion detection region from an image acquired by the surveillance camera 200 according to an embodiment of the present invention. For the role of acquiring the motion detection region from the surveillance image, the existing motion region detection method such as using changes in pixel values of the previous frame and the current frame can be borrowed without limitation.

In the embodiment of FIG. 2 , although the motion region detection unit 110 is shown to exist in the background removal server 100 , in another embodiment of the present invention, the motion region detection unit 110 is installed in another server or device, or It may be included in the surveillance camera 200 .

The zone divider 120 divides the motion detection area obtained according to an embodiment of the present invention into a plurality of zones. The zone divider 120 may divide the motion detection area horizontally or vertically.

3 illustrates a zoned motion detection area according to an embodiment of the present invention.

Referring to FIG. 3A , the region divider 120 divides the motion detection area MD into four regions h_1, h_2, h_3, and h_4 in the horizontal direction. Also, referring to (b) of FIG. 3 , the zone divider 120 divides the motion detection area MD into four zones v_1, v_2, v_3, and v_4 in the vertical direction. As can be seen from (a) and (b) of FIG. 3 , the horizontal or vertical area may include a motion detection area MD but not including an actual object. In more detail, the first horizontal section h_1 and the fourth vertical section v_4 are included in the motion detection area MD, but do not include an actual moving object.

The edge value calculator 130 calculates an edge value according to an embodiment of the present invention and calculates a horizontal average edge value and a vertical average edge value for each zone. In an embodiment of the present invention, the edge value calculator 130 may use an edge filter to calculate an edge value. The edge value includes a horizontal edge value and a vertical edge value. A horizontal edge value is a value obtained by obtaining a vertical gradient, and a vertical edge value is a value obtained by obtaining a horizontal gradient.

4 is a filter that can be used to calculate an edge value according to an embodiment of the present invention.

Referring to FIG. 4 , a Sobel filter and a Prewitt filter are exemplified as edge filters for calculating an edge value. The edge value calculating unit 130 may use the Sobel filter or the Pre-Witt filter shown in FIG. 4 to calculate the edge value according to an embodiment of the present invention. In more detail, the edge value calculating unit 130 may use a Gx filter of a Sobel filter or a PreWitt filter to calculate a vertical edge value, and use a Gy filter of a Sobel filter or a PreWitt filter to calculate a horizontal edge value. have.

After calculating the edge value, the edge value calculator 130 may calculate an average of the edge values for each zone. With respect to the average edge value for each region calculated by the edge value calculator 130 , the horizontal average edge value may be expressed as Mean(hor) and the vertical average edge value may be expressed as Mean(ver).

The edge component value determining unit 140 serves to determine a larger value among a horizontal average edge value and a vertical average edge value for each zone as an edge component value. The edge component value determined by the edge component value determining unit 140 may be expressed as Max(Mean(hor), Mean(ver)).

5 is a diagram illustrating an example of calculating an edge component value for each zone according to an embodiment of the present invention.

Referring to (a) of FIG. 5 , the edge component value determining unit 140 determines the edge component value Max( It can be seen that Mean(hor), Mean(ver)) is calculated. Similarly to FIG. 5B , the edge component value determination unit 140 sets the edge component value Max(Mean) for each of the zones v_1, v_2, v_3, and v_4 generated in the vertical direction of the motion detection area MD. It can be seen that (hor), Mean(ver)) are calculated.

The background removing unit 160 determines and removes a region having an edge component value equal to or less than a reference value as a background region. Since the edge component value determined by the edge component value determination unit 140 is a value obtained by taking a larger value among a horizontal average edge value and a vertical average edge value for each zone, the fact that the edge component value is less than or equal to the reference value means that the edge value of the corresponding zone is an object. It means that it is not large enough to indicate Accordingly, when the edge component value is less than or equal to the reference value, the background removing unit 160 may determine the corresponding area as the background and remove it. In this case, the reference value is a value determined by the user and can be freely changed according to the characteristics of the corresponding image.

That is, the background removing unit 160 determines, as a background, a region having an edge component value less than or equal to the reference value among the regions h_1, h_2, h_3, and h_4 generated in the horizontal direction in the example shown in FIG. It can be removed from the motion detection area (MD). Similarly, the background removing unit 160 determines a region having an edge component value less than or equal to the reference value among the regions v_1, v_2, v_3, and v_4 generated in the vertical direction in the example shown in FIG. 5(b) as the background, It can be removed from the motion detection area (MD). For example, when the reference value is 50 and the edge component value of the first horizontal region h_1 is 45, the background removing unit 160 determines the first horizontal region h_1 as the background and determines the motion detection area MD. can be removed from

According to an embodiment of the present invention, the background removing unit 160 removes the background area by determining from the edge of the motion detection area MD, and when the edge area is not the background area, the inner area is removed as the background area. may not More specifically, in the example of FIG. 5A , the background removing unit 160 determines whether the first horizontal region h_1 is a background region, and then, only in the case of the background region, the edge of the second horizontal region h_2 . When the component value is below the reference value, it is judged as a background area. Alternatively, after determining whether the fourth horizontal region h_4 is a background region, it is determined as a background region when the edge component value of the third horizontal region h_3 is equal to or less than a reference value only in the case of the background region. This is because when only the edge component value of the middle section suddenly decreases in the motion detection area (MD), it is highly likely to be an error in the imaging environment or an error in the image itself. Only to check whether the background area of the middle section.

The standard deviation calculator 150 serves to calculate the standard deviation of pixel values for each region according to an embodiment of the present invention.

6 illustrates an example in which the standard deviation calculating unit 150 calculates the standard deviation for each zone according to an embodiment of the present invention.

Referring to FIG. 6A , it can be seen that the motion detection area MD is divided into four regions in the horizontal direction, and the standard deviation of pixel values of each region is calculated as Std(im). Also, referring to FIG. 6B , it can be seen that the motion detection area MD is divided into four zones in the vertical direction, and the standard deviation of each zone is calculated as Std(im). The standard deviation of each area calculated by the standard deviation calculator 150 may be a measure of how much the pixel value is changed in the corresponding area. For example, if the standard deviation of the first horizontal region h_1 is smaller than the standard deviation of the fourth horizontal region h_4, the first horizontal region h_1 has a small change in pixel value, and thus the probability of being a background region is second. 4 is larger than the case of the horizontal region (h_4).

Accordingly, the standard deviation value calculated by the standard deviation calculating unit 150 may be used as an auxiliary criterion when the background removing unit 160 removes the background.

Even in a region having an edge component value equal to or less than the reference value, the background removing unit 160 may determine the region as a background and remove it from the motion detection region MD only when the standard deviation value of the region is equal to or less than a specific value. For example, even when the edge component value of the first horizontal region h_1 of the motion detection area MD is less than or equal to the reference value, if the standard deviation value is greater than or equal to a specific value, the first horizontal region h_1 may not be determined as the background. .

Even when the background is removed in consideration of the standard deviation calculated by the standard deviation calculator 150 , the inner region may be determined as the background only when the edge region is the background by judging from the edge region.

7 is a diagram illustrating an execution sequence of a method for removing a background according to an embodiment of the present invention.

First, the motion region detector 110 acquires a motion region (S1).

Next, the zone dividing unit 120 divides the movement region into n zones in the horizontal or vertical direction ( S2 ).

Next, the edge value calculating unit 130 calculates a horizontal average edge value and a vertical average edge value for each n areas ( S3 ).

Next, the edge component value determining unit 140 determines the greater of the calculated horizontal average edge value and the vertical average edge value as the edge component value of the corresponding region ( S4 ).

Next, the background removing unit 160 assigns 1 to the i value (S5), determines whether the calculated edge component value of the i-th region is less than or equal to the reference value (S6), and then determines whether the value of the i-th region is less than or equal to the reference value (S6). Assign +1 and go back to step S6.

When the edge component value is less than or equal to the reference value, the background removing unit 160 determines whether the standard deviation of the i-th area calculated by the standard deviation calculating unit 150 is equal to or less than a specific value (S7), Allocate i+1 and return to step S6.

When the standard deviation is less than or equal to a specific value, the i-th zone is removed from the motion detection area (S8).

Finally, if the value assigned to i is n, the procedure ends (S9). If the value of i is not n, i+1 is assigned to i and the process returns to step S6 (S9).

The embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include hard disks, magnetic media such as floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floppy disks. medium), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. A hardware device may be converted into one or more software modules to perform processing in accordance with the present invention, and vice versa.

The specific implementations described in the present invention are only examples, and do not limit the scope of the present invention in any way. For brevity of the specification, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connection or connection members of the lines between the components shown in the drawings exemplarily represent functional connections and/or physical or circuit connections, and in an actual device, various functional connections, physical connections that are replaceable or additional may be referred to as connections, or circuit connections. In addition, unless there is a specific reference such as “essential” or “importantly”, it may not be a necessary component for the application of the present invention.

In the specification of the present invention (especially in the claims), the use of the term “above” and similar referential terms may be used in both the singular and the plural. In addition, when a range is described in the present invention, each individual value constituting the range is described in the detailed description of the invention as including the invention to which individual values belonging to the range are applied (unless there is a description to the contrary). same as Finally, the steps constituting the method according to the present invention may be performed in an appropriate order unless the order is explicitly stated or there is no description to the contrary. The present invention is not necessarily limited to the order in which the steps are described. The use of all examples or exemplary terms (eg, etc.) in the present invention is merely for the purpose of describing the present invention in detail, and unless defined by the claims, the scope of the present invention is limited by the examples or exemplary terminology. it's not going to be In addition, those skilled in the art will recognize that various modifications, combinations, and changes may be made in accordance with design conditions and factors within the scope of the appended claims or their equivalents.

100: background removal server 110: motion area detection unit
120: zone division unit 130: edge value calculation unit
140: edge component value determination unit 150: standard deviation calculation unit
160: background removal unit 200: surveillance camera
300: network

Claims (6)

a motion region detector for acquiring a motion region from an image;
a region dividing unit dividing the moving region into a plurality of regions;
an edge value calculator for calculating a horizontal average edge value and a vertical average edge value in each of the plurality of regions;
an edge component value determination unit that determines, in each of the plurality of zones, a larger value among a horizontal average edge value and a vertical average edge value as an edge component value of each zone; and
a background removing unit for determining and removing a region having an edge component value less than or equal to a reference value among the plurality of regions as a background region;
including,
and the background removing unit determines whether inner regions are background regions only when an edge region among the plurality of regions is removed. delete delete According to claim 1,
It additionally includes; a standard deviation calculator for calculating the standard deviation of the pixel values of each of the plurality of regions;
wherein the background removing unit determines a region in which the standard deviation calculated by the standard deviation calculating unit is equal to or less than a specific value as the background region. delete delete

Images