KR101829231B1 - System and method for blob detecting - Google Patents

Abstract

A blob detection method and system capable of being implemented in a low-cost embedded board by detecting the blob included in the image at a high speed / low cost. According to an aspect of the present invention, there is provided a blob detection method for determining a blob included in a discrimination target image composed of N rows, the blob detection system including a step of initializing a blob, The system comprising a step of performing a row processing step for each of the first row to the Nth row of the discrimination target image, wherein the row for the i-th row (1 < = i < = N) The processing step includes the steps of: (a) generating information of a blob part constituted by each line included in the i-th row; And (b) for each of the blob parts, determining a connection blob connected to the blob part of the blob included in the blob list, and if there is no connection blob connected to the blob part, To the blob list, and if there is a connection blob connected to the blob part, generates information of a combination blob that combines the blob part and the connection blob, Adding to the blob list, and removing information of the connecting blob from the blob list.

Description

System and method for blob detecting &lt; RTI ID = 0.0 &gt;

The present invention relates to a system and method for detecting blobs included in an image. And more particularly, to a blob detection method and system that can be implemented in a low-cost embedded board by detecting blobs included in an image at a high speed / low cost.

In the field of computer vision, the blob detection method refers to a method of detecting an area having attributes (e.g., brightness, color, etc.) that can be distinguished from surrounding areas in a digital image , Object recognition, object tracking, and the like.

Conventional blob detection devices generally use a method of receiving a whole image photographed by a camera and detecting a blob therefrom. In this method, since a large amount of data must be processed, the processing cost (for example, Time, etc.) becomes very high. In addition, in order to transfer image data from a camera device that captures an image to a blob detection device, a high-speed interface having a high bandwidth must be used.

SUMMARY OF THE INVENTION The present invention provides a blob detection method and system that can be implemented in a low-cost embedded board by detecting blobs included in an image at high speed and low cost.

According to an aspect of the present invention, there is provided a blob detection method for determining a blob included in a discrimination target image composed of N rows, the blob detection system including a step of initializing a blob, The system comprising a step of performing a row processing step for each of the first row to the Nth row of the discrimination target image, wherein the row for the i-th row (1 < = i < = N) The processing step includes the steps of: (a) generating blob data of a blob part constituted by each line included in the i-th row; and (b) calculating, for each blob part, Determining a connection blob connected to the blob part and adding the blob data of the blob part to the blob list when the connection blob connected to the blob part does not exist, The method comprising: generating blob data of a combined blob that combines the blob part and the concatenated blob when the concatenated concatenated blob exists, adding blob data of the concatenated blob to the blob list, In the blob detection method.

In one embodiment, the step of initializing the bloblist includes initializing the blob list, the first line list and the second line list, and the step (b) includes the steps of: Adding the blob data of the blob part constituting the line to the blob list, and constructing the first line list so that the line information of each line included in the i-th row is included therein, Wherein the first line information includes a position and a length of a line, and blob information to which the line belongs, for each first line information included in the first line list and each second line information included in the second line list, And determines whether a first line corresponding to the first line information and a second line corresponding to the second line information are connected to each other. If the first line corresponds to the blob information included in the first line information Generates blob data of a combined blob in which a bloom to which the first line belongs and a bloom to which the second line belongs is generated based on the blob information included in the second line information, And removes blob data of the bloom to which the first line belongs and blob data of the blob to which the second line belongs from the blob list, and adds the blob information of the first line information and the second line information Replacing the blob information of the first line list with the blob information of the combining blob, and reconstructing the second line list so that the second line list includes items included in the first line list.

In one embodiment, an image processing system installed in a camera performs Run Length Encoding of raw data corresponding to an image to be discriminated which is photographed by the camera, And transmitting the length encoded data to the blob detection system through a predetermined interface.

In one embodiment, the step of the image processing system performing run length encoding of raw data corresponding to the discrimination target image photographed by the camera includes the steps of converting the discrimination target image photographed by the camera into grayscale, Lt; RTI ID = 0.0 &gt; RL &lt; / RTI &gt;

In one embodiment, the run-length-encoded data is composed of a run-length code corresponding to each horizontal line included in the discrimination target image, and the run-length code includes positional information and length information of the corresponding horizontal line can do.

According to another aspect of the present invention, a computer program installed in a data processing apparatus and stored in a computer-readable recording medium for performing the above-described method is provided.

According to another aspect of the present invention there is provided a blob detection system comprising a processor and a memory for storing a computer program executed by the processor, wherein the computer program, when executed by the processor, A blob detection system is provided for causing the method described above to be performed.

According to another aspect of the present invention, there is provided a blob detection system for discriminating a blob included in a discrimination target image composed of N rows, comprising: a storage module for storing data corresponding to the discrimination object image; And performing a row processing step for each of the first row to the N-th row of the discrimination target image, wherein the i-th row (1 <= i <= N) of the discrimination target image The row processing step includes the steps of: (a) generating blob data of a blob part constituted by each line included in the i-th row; and (b) calculating, for each blob part, Determining a connecting blob connected to the blob part, adding blob data of the blob part to the blob list when there is no connecting blob connected to the blob part, Generating blob data of a combined blob in which the blob part and the connecting blob are combined, adding the blob data of the combining blob to the blob list when the connecting blob connected to the blob part exists, Removing from the blob list. &Lt; Desc / Clms Page number 10 &gt;

In one embodiment, the control module further initializes a first line list and a second line list, and the step (b) further comprises the steps of: (i) initializing the blob data of the blob part constituted by each line included in the i- Forming a first line list including line information of each line included in the i-th row, wherein the line information includes a position and a length of the corresponding line, Blob information, and for each of the first line information included in the first line list and each second line information included in the second line list, a first line corresponding to the first line information Based on the blob information included in the first line information and the blob information included in the second line information when the first line information and the second line corresponding to the second line information are connected, Generating blob data of a combined blob that combines the bloom to which the first line belongs and the bloom to which the second line belongs, adds the blob data of the combined blob to the blob list, And replacing the blob information of the first line information and the blob information of the second line information with the blob information of the combined blob, . &Lt; / RTI &gt;

In one embodiment, the data corresponding to the discrimination target image is run length encoded data received from an image processing system installed in the camera, and the image processing system includes: Run length encoding the data, and transmit the run length encoded data to the blob detection system over a predetermined interface.

In one embodiment, the image processing system may convert the discrimination target image photographed by the camera into grayscale, and run-length encode the raw data of the grayscale-converted image.

In one embodiment, the run-length-encoded data is composed of a run-length code corresponding to each horizontal line included in the discrimination target image, and the run-length code includes positional information and length information of the corresponding horizontal line can do.

According to one embodiment of the present invention, it is possible to detect blobs included in an image at high / low cost. Therefore, it is possible to provide a blob detection method and system that can be implemented in an embedded board having a low implementation cost.

Also, according to an embodiment of the present invention, it is possible to easily detect a blob using only run-length encoded data. Therefore, there is an advantage that a low-speed interface having a low bandwidth can be used instead of using a high-speed interface having a high cost in order to transmit image data from the camera to the blob detection system.

BRIEF DESCRIPTION OF THE DRAWINGS A brief description of each drawing is provided to more fully understand the drawings recited in the description of the invention.
FIG. 1 is a view for schematically explaining an operation environment of a blob discrimination method according to an embodiment of the present invention.
2 is a block diagram showing a schematic structure of a blob discrimination system according to an embodiment of the present invention.
3 is a flowchart illustrating a blob discrimination method performed by the blob discrimination system according to an embodiment of the present invention.
FIG. 4 illustrates an example of an image to be discriminated. FIG. 5 illustrates a process of performing a blob detection on the discrimination target image shown in FIG. 4 according to an exemplary embodiment of the present invention. FIG.
6 is a flowchart illustrating a method for determining a blob according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise.

In this specification, the terms "comprises" or "having" and the like refer to the presence of stated features, integers, steps, operations, elements, components, or combinations thereof, But do not preclude the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof.

Also, in this specification, when any one element 'transmits' data to another element, the element may transmit the data directly to the other element, or may be transmitted through at least one other element And may transmit the data to the other component. Conversely, when one element 'directly transmits' data to another element, it means that the data is transmitted to the other element without passing through another element in the element.

Hereinafter, the present invention will be described in detail with reference to the embodiments of the present invention with reference to the accompanying drawings. Like reference symbols in the drawings denote like elements.

FIG. 1 is a view for schematically explaining an operation environment of a blob discrimination method according to an embodiment of the present invention. Referring to FIG. 1, a blob discrimination system 100 may be provided to implement the blob discrimination method according to an embodiment of the present invention.

In one embodiment, the blob discrimination system 100 is an embedded system that includes a field-programmable gate array (FPGA), which is a semiconductor device including a programmable logic element, a programmable internal line, and a memory element including a memory block, or an FPGA Can be implemented.

The blob discrimination system 100 may perform a blob detection for discriminating blobs contained in a digital image. Blob detection can refer to a method of detecting an area having attributes (e.g., brightness, color, etc.) that can be distinguished from surrounding areas in a digital image. Within an image, a blob may have the same or approximately the same property.

In one embodiment, the blob detection system 100 may perform blob detection on an image captured by a camera or a camera module 300, as shown in FIG.

In one embodiment, the camera 300 may be provided with an image processing system 300 that performs conversion, preprocessing, and / or encoding on images photographed by the camera 300. The image processing system 100 may also be implemented as an embedded system including an FPGA (Field-Programmable Gate Array) or an FPGA.

1, the blob discrimination system 100 is connected to the image processing system 200 through a predetermined communication interface to generate various kinds of information, data, and the like required to implement the technical idea of the present invention. And / or exchange signals. The communication interface connecting the blob recognition system 100 and the image processing system 200 may be a high-speed wired interface such as USB 3.0 or a low-speed wired interface such as a USB 2.0 or a UART. Or in some cases, the communication interface may be an air interface.

The image processing system 100 preprocesses (for example, converts or encodes) raw data corresponding to an image photographed by the camera, and then transmits the preprocessed data to the blob discrimination system 100 .

In one embodiment, the image processing system 200 may run length encode raw data corresponding to an image taken by the camera 300 to significantly reduce the capacity of the image data to be transmitted And transmits the run length encoded data to the blob discrimination system 100.

In another embodiment, the image processing system 200 converts the image taken by the camera into grayscale, performs run-length encoding of the raw data of the grayscale-converted image, and transmits it to the blob discrimination system 100 It is possible. If you go through the process of converting to grayscale, you can further reduce the image size, but there is no significant impact on blob discrimination.

In this case, the run length encoded data is composed of a run length code corresponding to each horizontal line included in the image, and the run length code may include positional information and length information of the corresponding horizontal line. For example, the run-length code may have a structure as shown in Table 1 below.

Structure of Run Length Code (RLC) field Explanation X The x coordinate of the starting pixel Y The y coordinate of the starting pixel Length Length

In this case, the run-length code <32, 42, 15> may mean a horizontal line of length 15 starting at (32, 42). Hereinafter, for convenience of description, an example will be described in which the image data transmitted to the blob discrimination system 100 is composed of a run length code having a structure of < x coordinate of the start pixel, y coordinate of the start pixel, and length & . However, it will be understood by those skilled in the art that the technical idea of the present invention is not limited thereto.

1 illustrates an example in which the image processing system 200 installed in the camera 300 and the blob recognition system 100 communicate with each other through a predetermined communication interface, The image processing system 200 and the blob discrimination system 100 may be integrated into one system. In this embodiment, the image processing system 200 may be in the form of a module (e.g., an image processing module) included in the blob detection system 100, and the blob detection system may be installed in the camera 300, May be in the form of being connected.

Meanwhile, the blob discrimination system 100 and the blob discrimination method according to the technical idea of the present invention can be used in a 3D scanner. In this case, the blob discrimination system 100 can receive blob by receiving image data photographed from two or more cameras, and can provide the detected blob information to a predetermined 3D scanning device. Or two or more blob discrimination systems may each receive image data photographed from different cameras to detect blobs and provide them to the 3D scanning device.

Also, unlike FIG. 1, it is needless to say that the blob detection system 100 can perform a blob detection on an image provided from an image providing apparatus other than the image taken by the camera 300.

2 is a block diagram showing a schematic structure of a blob discrimination system 100 according to an embodiment of the present invention. Referring to FIG. 2, the blob discrimination system 100 may include a storage module 110 and a control module 120. According to an embodiment of the present invention, the blob detection system 100 may include more components. For example, the blob detection system 100 may further include a communication module (not shown) for communicating with the image processing system 200.

The blob discrimination system 100 may include hardware resources and / or software necessary to implement the technical idea of the present invention, and it is understood that the blob discrimination system 100 means one physical component or one device no. That is, the blob detection system 100 may mean a logical combination of hardware and / or software provided to implement the technical idea of the present invention. If necessary, The present invention may be embodied as a set of logical structures for realizing the technical idea of the present invention. In addition, the blob detection system 100 may mean a set of configurations separately implemented for each function or role for implementing the technical idea of the present invention. For example, storage module 110 and control module 120 may be located in different physical devices, or may be located in the same physical device.

In this specification, a module may mean a functional and structural combination of hardware for carrying out the technical idea of the present invention and software for driving the hardware. For example, the module may mean a logical unit of a predetermined code and a hardware resource for executing the predetermined code, and it does not necessarily mean a physically connected code or a kind of hardware. Can be easily deduced to the average expert in the field of &lt; / RTI &gt;

The control module 130 may control the functions and / or resources of other configurations (e.g., the storage module 110) included in the blob detection system 100 according to an embodiment of the present invention, And may control the functions and / or resources of the image processing system 200 as needed.

The storage module 110 may store data corresponding to the discrimination target image to be subjected to the blob detection. For example, the storage module 110 may store image data received from the image processing system 200. The determination target image may be composed of N rows (N is an integer), and the data stored in the storage module 110 may be run length encoded data as described above.

The control module 120 may determine a blob included in the determination target image based on image data stored by the storage module 110 and may generate a blob list including the determined blob data have.

Hereinafter, the process performed by the control module 120 will be described in more detail with reference to FIG. 3 is a flowchart illustrating a blob determination method performed by the control module 130 according to an embodiment of the present invention.

Referring to FIG. 3, the control module 120 may initialize the blob list blob_list (S100).

A bloblist may store at least one blob data, and may be a data structure that can store and retrieve at least one data item such as an array, a set, a linked list, and so on. The blob data stored in the bloblist may include information about the location, size, and / or type of the blob. For example, the blob data may have a structure as shown in Table 2 below.

Structure of blob data field Explanation X The x coordinate of the center pixel of the Blob Y The y coordinate of the center pixel of the blob Size Size of the Blob in pixels

Hereinafter, for convenience of description, an example will be described in which the blob data stored in the blob list has a structure of <x coordinate of the center pixel, y coordinate of the center pixel, and size>. However, it will be understood by those skilled in the art that the technical idea of the present invention is not limited thereto.

Referring again to FIG. 3, the control module 120 may perform a row processing step for each of the first row to the Nth row of the determination target image (S110).

At this time, the process of performing the row processing step for the i-th (1 <= i <= N) row Row (i) of the determination target image may include S120 to S130 of FIG.

In step S120, the control module 120 may generate blob data of a blob part constituted by each line included in the i-th row Row (i).

One line may consist of consecutive pixels having the same attributes. Thus, each line may constitute a corresponding blob part, and the shape of the blob part may be the same as the shape of the corresponding line.

If the discrimination target image is run length encoded as described above, the control module 120 can generate the blob data of the blob part through a very simple calculation. When the runlength code representing a specific line is referred to as RLC and the blob data of the blob part constituting the specific line is referred to as blob, the blob data of the blob part constituted by the corresponding line can be generated in the following manner.

Blob.X = (RLC.X + RLC.Length-1) / 2

Blob.Y = RLC.Y

Blob.Size = RLC.Length

The control module may generate blob data of the blob part corresponding to the corresponding line for all the lines included in Row (i).

The blob part corresponding to each line may be an independent blob, or a part of another blob, as viewed from the overall image.

On the other hand, in step S130, the control module 120 determines whether or not the blob list blob_list is included in the blob list blob_list (1 <= j <= the number of blob parts of Row (i) It may be determined whether there is a connection blob connected to the blob part BP (j) among the blobs (S140).

If the horizontal range of the line constituting the last row of the specific blob overlaps the horizontal range of the blob part, the control module 120 may determine that the blob and the blob part are connected.

Also, the control module 120 may add the blob data of the blob part to the blob list when there is no connection blob connected to the blob part included in the blob list (S150, S160) .

If there is a connection blob connected to the blob part BP (j), the control module 120 adds the blob part BP (j) to the connected blob BP (j) Lt; / RTI &gt; That is, the control module 120 generates the blob data of the combined blob that combines the blob part BP (j) and the concatenated blob (S170), adds the blob data of the combined blob to the blob list blob_list (S180) , The blob data of the connection blob may be removed from the blob list (S190).

Hereinafter, an example of the above-described process will be described with reference to FIGS. 4 and 5. FIG. FIG. 4 illustrates an example of an image to be discriminated. FIG. 5 illustrates a case where the control module 150 performs a blob detection on the discrimination target image shown in FIG. 4 to detect two blobs 10 and 20 And FIG.

4, two blob parts 31 and 32 are included in the third row Row (3) of the discrimination target image, and three blob parts 41 and 42 (4) are included in the fourth row Row And 43. The fifth row Row 5 includes two blob parts 51 and 52. The sixth row Row 6 includes one blob part 61, The seventh row Row (7) contains two blob parts (71, 72).

If the control module 120 performs the blob detection on the determination target image shown in Fig. 4, since there is no line (i.e., blob part) in the first and second rows of the determination target image, the blob_list There will be no change.

Fig. 5 (a) shows the blob determined in the state in which the control module 120 processes up to the third row of the determination target image in Fig. In the case of the third row, there are two blob parts 31 and 32, and since the blob_list is empty due to initialization, there will be no connection blob associated with the two blob parts 31 and 32. Accordingly, the control module 120 may add blob data corresponding to each of the two blob parts 31 and 32 included in the third row to the blob_list (S150 and S160).

When the control module 120 processes up to the third row of the discrimination target image in Fig. 4, the blob list blob_list stores the blob data of each of the blobs b1 and b2 shown in Fig. 5 (a) (I.e., blob_list = {b1 blo data, b2 blob data}).

FIG. 5B shows the blob determined in a state where the control module 120 processes up to the fourth row of the determination target image in FIG. In the case of the fourth row, there are three blob parts (41, 42, 43). Since the first blob part 41 is connected to the blob b1 of Fig. 5 (a), the control module 120 generates blob data for the combined blob b3 combining the blob b1 and blob part 41, which are connected blobs (S170), the blob data of b3 is added to the blob list blob_list (S180), and the blob data of blob1 is deleted to the blob list blob_list (S190). In the case of the second blob part 42, since the connecting blob does not exist, the control module 120 recognizes the blob part 42 as a new blob b4 and adds the blob data of the blob part 42 to the blob list blob_list (S160). Since the third blob part 43 is connected to the blob b2 of Fig. 5 (a), the control module 120 generates the blob data for the combined blob b5 that combines the blob b2 and the blob part 43, which are the connecting blobs (S170), the blob data of b5 is added to the blob list blob_list (S180), and the blob data of blob2 is deleted to the blob list blob_list (S190).

The blob list blob_list stores the blob data of each of the blobs b3, b4, and b5 shown in FIG. 5B in the case where the control module 120 processes up to the fourth row of the determination target image in FIG. (I.e., blob_list = {b3 blob data, b4 blob data, b5 blob data}).

Fig. 5 (c) shows the blob determined in the state where the control module 120 processes up to the fifth row of the determination target image in Fig. In the case of the fifth row, there are two blob parts 51 and 52. Since the first blob part 51 is connected to the blob b3 and b4 of Fig. 5 (b), the control module 120 controls the combining blob b6 combining the blobs b3, b4 and blob parts 41, Blob data for blob b3 and blo4 may be deleted in the blob list blob_list (S190). The blob data for blob b3 and blob_list may be added to the blob list blob_list (S180). Since the second blob part 52 is connected to the blob b5 of Fig. 5 (b), the control module 120 generates blob data for the combined blob b7 that combines the connecting blobs b5 and blob parts 52 (S170), the blob data of b7 is added to the blob list blob_list (S180), and the blob data of blob5 is deleted to the blob list blob_list (S190).

When the control module 120 processes up to the fifth row of the determination target image in Fig. 4, the blob list blob_list stores the blob data of each of the blobs b6 and b7 shown in Fig. 5C (I.e., blob_list = {b6 blob data, b7 blob data}).

The control module 120 can sequentially process the respective lines in the above manner. When the control module 120 processes up to the sixth row of the discrimination target image of FIG. 4, (I.e., blob_list = {blob data of b6, blob data of b7}) of the respective blobs b8 and b9 shown in FIG. 4 The blob list blob_list may store the blob data of each of the blobs b10 and b11 shown in FIG. 5E (i.e., blob_list = {b10 of b10 , b11 blob data}).

There will be no change in the blob_list since there is no line (i.e., blob part) in the 8th, 9th, and 10th rows of the image to be discriminated.

Therefore, the blob list in the state where the control module 120 has completed the blob detection for the determination target image is the blob data of the blob b10 (the same as the blob 10 of Fig. 4) in Fig. 5 (e) May include blob data of blob b11 (the same as blob 20 of Fig. 4) in Fig. 5 (e).

On the other hand, the control module 120 maintains and manages the line list (first line list) of the current line to be processed and the line list (second line list) of the line processed immediately before, FIG. 6 is a block diagram illustrating a method for determining whether a blob is present or not according to an embodiment of the present invention. Referring to FIG.

Referring to FIG. 6, the control module 120 initializes a blob list blob_list and initializes a first line list new_line_list and a second line list old_line_list.

The first line list, new_line_list, may include line information of each line included in the current line, and the second line list old_line_list may include line information of each line included in the immediately preceding line. have.

The line list may store at least one line information, and may be a data structure capable of storing and searching at least one data such as an array, a set, a linked list, and the like. The line information stored in the line list may include the position and length of the line, and the blob information to which the line belongs. The blob information included in the line information may be identification information (or unique information) for identifying a specific blob stored in the blob list or reference information for referring to a specific blob stored in the blob list.

For example, the line information may have a structure as shown in Table 3 below.

Structure of line information field Explanation X The x coordinate of the starting pixel of the line Y The y coordinate of the start pixel of the line Length Length (in pixels) Blob Information on the blobs to which the line belongs

Hereinafter, for convenience of explanation, an example in which the line information stored in the line list has the structure of < x coordinate of the starting pixel, y coordinate of the starting pixel, length, and blob information > However, it will be understood by those skilled in the art that the technical idea of the present invention is not limited thereto.

Referring again to FIG. 6, the control module 120 may perform a row processing step for each of the first row to the Nth row of the determination target image (S210).

At this time, the process of performing the row process for the i-th row (1 <= i <= N) row Row (i) of the discrimination target image may include S220 to S290 of FIG.

In step S220, the control module 120 may generate the blob data of the blob part constituted by each line included in the i-th row Row (i).

When the runlength code representing a specific line L is called RLC (L) and the blob data of the blob part constituting the line is Blob (L), the blob data of the blob part constituted by the line is converted in the following manner It can be generated as described above.

(L) .X = (RLC (L) .X + RLC (L) .Length-1) / 2

Blob (L) .Y = RLC (L) .Y

Blob (L) .Size = RLC (L) .Length

Meanwhile, the control module 120 may add the blob data of the blob part constituted by each line included in the i-th row Row (i) to the blob list blob_list.

Also, the control module 120 may configure the first line list new_line_list so that the line information of each line included in the i-th row is included. As described above, the line information may include the position and length of the line, and the blob information to which the line belongs.

If the determination target image is run-length-encoded as described above, the control module 120 can generate line information of each line through very simple assignment. If the runlength code representing a specific line L is referred to as RLC (L) and the line information included in the line is referred to as Line (L), the line information of the corresponding line can be generated in the following manner.

Line (L) .X = RLC (L) .X

Line (L) .Y = RLC (L) .Y

Line (L) .Length = RLC (L) .Length

Line (L) .Blob = Blob (L) information

Then, the control module 120 determines whether or not the first line information new_line included in the first line list new_line_list and the second line information old_line included in the second line list old_line_list are S250 Step S280 may be performed (S240).

First, the control module 120 may determine whether a first line corresponding to the first line information (new_line) and a second line corresponding to the second line information (old_line) are connected to each other S250). Since the line corresponding to new_line and the line corresponding to old_line exist in adjacent rows, when the horizontal range of new_line overlaps with the horizontal range of old_line, the control module 120 determines that the line corresponding to new_line and the line corresponding to old_line It can be determined that the lines are connected to each other.

If so, the control module 120 controls the blob information included in the first line information (new_line) and the blob information included in the second line information (old_line) The blob data of the combined blob in which the bloom to which the second line belongs can be generated (S260).

If the combining blob is comb_blob, the control module 120 can generate the combining data of the combining blob through the following equation.

<Formula>

(1) comb_blob.X = (new_line.Blob.X * new_line.Blob.Size + old_line.Blob.X * old_line.Blob.Size) / (new_line.Blob.Size + old_line.Blob.Size)

(2) comb_blob.Y = (new_line.Blob.Y * new_line.Blob.Size + old_line.Blob.Y * old_line.Blob.Size) / (new_line.Blob.Size + old_line.Blob.Size)

(3) comb_blob.Size = new_blob.Size + old_blob.Size

Then, the control module 120 adds the blob data Comb_blob of the combined blob to the blob list blob_list (S270), and the blob data new_line.Blob of the bloom to which the first line belongs and the blob data new_line.Blob to which the second line belongs The blob data old_line.Blob of the blob list may be removed from the blob list (S275).

Also, the control module 120 may replace the blob information of the first line information and the blob information of the second line information with the blob information of the combined blob (S280)

On the other hand, after the above-described processes are completed for each first line information (new_line) included in the first line list new_line_list and each second line information (old_line) included in the second line list old_line_list, The control module 120 may reconfigure the second line list so that the second line list includes items included in the first line list (S290).

Meanwhile, according to an embodiment, the blob discrimination system 100 may include a processor and a memory for storing a program executed by the processor. The processor may include a single-core CPU or a multi-core CPU. The memory may include high speed random access memory and may include non-volatile memory such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid state memory devices. Access to the memory by the processor and other components can be controlled by the memory controller. Here, when the program is executed by a processor, the program may cause the blob discrimination system 100 according to the present embodiment to perform the above-described blob discrimination method.

Meanwhile, the method for determining a blob according to an embodiment of the present invention may be implemented in the form of a computer-readable program command and stored in a computer-readable recording medium. Also, the control program and the target program And can be stored in a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored.

Program instructions to be recorded on a recording medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of software.

Examples of the computer-readable recording medium include magnetic media such as a hard disk, a floppy disk and a magnetic tape, optical media such as CD-ROM and DVD, a floptical disk, And hardware devices that are specially configured to store and execute program instructions such as magneto-optical media and ROM, RAM, flash memory, and the like. The computer readable recording medium may also be distributed over a networked computer system so that computer readable code can be stored and executed in a distributed manner.

Examples of program instructions include machine language code such as those produced by a compiler, as well as devices for processing information electronically using an interpreter or the like, for example, a high-level language code that can be executed by a computer.

The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

It is intended that the present invention covers the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents. .

Claims (12)

A blob detection method for determining a blob included in a discrimination target image composed of N (N is an integer) rows,
The blob detection system comprising: initializing a blob list; And
Wherein the blob detection system performs a row processing step for each of the first row to the Nth row of the determination target image,
The row processing step for the i-th row (1 < = i < = N)
(a) generating blob data of a blob part constituted by each line included in the i-th row; And
(b) for each of the blob parts,
Determining a connection blob connected to the blob part among the blobs included in the blob list,
Adding blob data of the blob part to the blob list if there is no connected blob associated with the blob part,
Generating blob data of a combined blob in which the blob part and the connecting blob are combined, adding the blob data of the combining blob to the blob list when the connecting blob connected to the blob part exists, From the blob list. &Lt; Desc / Clms Page number 16 &gt;
The method according to claim 1,
Wherein the initializing the bloblist comprises:
And initializing the blob list, the first line list and the second line list,
The step (b)
Adding blob data of a blob part constituted by each line included in the i-th row to the blob list;
Configuring the first line list to include line information of each line included in the i-th row, wherein the line information includes a position, a length of the corresponding line, and blob information to which the corresponding line belongs;
For each of the first line information included in the first line list and each second line information included in the second line list,
Determining whether a first line corresponding to the first line information and a second line corresponding to the second line information are connected,
The first blob information and the second blob information included in the first line information and the blob information included in the first line information and the blob information included in the second line information, Adds the blob data of the combined blob to the blob list, removes from the blob list the blob data of the bloom to which the first line belongs and the blob of the bloom to which the second line belongs, Replacing blob information of the first line information and blob information of the second line information with blob information of the combining blob; And
And reconstructing the second line list such that the second line list includes an item included in the first line list.
The method according to claim 1,
An image processing system installed in a camera, the method comprising the steps of: performing run length encoding of raw data corresponding to an image to be discriminated by the camera; And
Wherein the image processing system further comprises transmitting run length encoded data to the blob detection system via a predetermined interface.
The method of claim 3,
Wherein the image processing system performs run length encoding of raw data corresponding to an image to be discriminated by the camera,
Converting the discrimination target image photographed by the camera into grayscale; And
And performing run length encoding of raw data of an image converted to grayscale.
5. The method of claim 4,
Wherein the run length encoded data comprises a run length code corresponding to each horizontal line included in the discrimination target image,
Wherein the run length code includes positional information and length information of the corresponding horizontal line.
A computer program installed in a data processing apparatus and stored in a computer-readable medium for performing the method of any one of claims 1 to 2.
A blob detection system,
A processor; And
A memory for storing a computer program executed by the processor,
The computer program, when executed by the processor, causes the blob detection system to perform the method recited in any one of claims 1 to 2.
A blob detection system for discriminating a blob included in a discrimination target image composed of N (N is an integer) rows,
A storage module for storing data corresponding to the discrimination target image;
Initialize the blob list,
And a control module for performing a row processing step for each of the first row to the Nth row of the determination target image,
The row processing step for the i-th row (1 < = i < = N)
(a) generating blob data of a blob part constituted by each line included in the i-th row; And
(b) for each of the blob parts,
Adding blob data of the blob part to the blob list when there is no connected blob connected to the blob part among the blobs included in the blob list,
Generating blob data of a combined blob in which the blob part and the connecting blob are combined, adding the blob data of the combining blob to the blob list when the connecting blob connected to the blob part exists, From the blob list.
9. The method of claim 8,
The control module includes:
The first line list and the second line list are further initialized,
The step (b)
Adding blob data of a blob part constituted by each line included in the i-th row to the blob list;
Configuring the first line list to include line information of each line included in the i-th row, wherein the line information includes a position, a length of the corresponding line, and blob information to which the corresponding line belongs; And
For each of the first line information included in the first line list and each second line information included in the second line list,
Determining whether a first line corresponding to the first line information and a second line corresponding to the second line information are connected,
The first blob information and the second blob information included in the first line information and the blob information included in the first line information and the blob information included in the second line information, Adds the blob data of the combined blob to the blob list, removes from the blob list the blob data of the bloom to which the first line belongs and the blob of the bloom to which the second line belongs, And replacing the blob information of the first line information and the blob information of the second line information with the blob information of the combining blob.
9. The method of claim 8,
The data corresponding to the discrimination target image is run length encoded data received from the image processing system installed in the camera,
The image processing system comprising:
Length encoding the raw data corresponding to the discrimination target image taken by the camera and transmitting the run length encoded data to the blob detection system through a predetermined interface.
11. The method of claim 10,
Wherein the image processing system converts the discrimination target image photographed by the camera into grayscale and performs run length encoding of the raw data of the image converted into grayscale.
12. The method of claim 11,
Wherein the run length encoded data comprises a run length code corresponding to each horizontal line included in the discrimination target image,
Wherein the run length code includes positional information and length information of a corresponding horizontal line.

Images