KR102480973B1 - Method, apparauts and system for determining existence of object and computer program thereof - Google Patents

Abstract

The present invention relates to a method, apparatus, computer program and system for determining whether an object exists, and more particularly, in a method for determining whether an object exists in a predetermined first area, an object existence determining system comprising: an image collecting step of collecting a first image including a region; a frequency characteristic value calculation step for each pixel of the first image for each frequency characteristic value of a plurality of pixels included in the first area; a frequency characteristic comparison step of comparing each frequency characteristic value calculated for the plurality of pixels with each reference frequency characteristic value previously calculated for the plurality of pixels; and an object existence determination step of determining whether an object exists within the first area by using a result of comparing frequency characteristic values of the plurality of pixels.

Description

Object existence determination method, device, system and computer program

The present invention relates to a method, apparatus, system, and computer program for determining whether an object exists, and more particularly, to a method, apparatus, and method for determining whether an object exists or not, which can more effectively determine whether an object exists in a specific area using an image, It relates to systems and computer programs.

A technology for determining whether an object exists within a specific area is a basic element technology applied to various automation systems including factory automation.

For a more specific example, the technology for determining whether an object exists within a specific area is used in various fields, such as a technology for determining whether an object to be delivered is loaded inside the robot's loading box even in an autonomous delivery robot that has recently attracted attention. It is a technique that is widely used.

In this regard, conventionally, a method of determining whether or not an object exists within a specific area using a Time of Flight (ToF) sensor has been used. However, the ToF sensor may not be able to detect objects made of some materials depending on the reflection and absorption characteristics of the light used.

In contrast, recently, a technique for recognizing an object based on an image captured by a camera has been attempted. In the case of image-based object recognition technology, a feature of an object to be recognized is extracted from an image and used by learning a classifier such as SVM (Support Vector Machine). Recently, deep learning-based Classifiers using convolutional neural networks (CNNs) are also widely used.

However, in the case of such an image-based object recognition technology, there is a problem in that performance deviation may be large depending on which features are used, and furthermore, it is difficult to find an optimal method capable of optimizing recognition performance.

In addition, in the above method of recognizing an object by extracting features from an image, recognition performance may be deteriorated when illumination changes or light reflection occurs, and furthermore, training data for learning such as deep learning is generated. There was also the problem that it takes a lot of effort.

Republic of Korea Patent Publication No. 10-2019-0009121 (2019.01.28)

The present invention was invented to solve the problems of the prior art as described above. In the case of the conventional image-based object recognition technology, performance deviation may appear large depending on which feature is used, and recognition performance can be optimized. It is difficult to find an optimal method for learning, and furthermore, recognition performance may deteriorate when illumination changes or light reflection occurs, and it is improved that it takes a lot of effort to generate training data for learning. Accordingly, an object of the present invention is to provide an object existence determination method, apparatus, system, and computer program capable of more effectively determining whether an object exists within a specific area.

An object existence determination method according to an aspect of the present invention for solving the above problems is a method of determining the existence of an object in a first predetermined area, wherein the object existence determination system includes the first area. An image collection step of collecting a first image to be used; a pixel-specific frequency characteristic value calculation step of calculating frequency characteristic values for each of a plurality of pixels included in the first area in the first image; a frequency characteristic comparison step of comparing each frequency characteristic value calculated for the plurality of pixels with each reference frequency characteristic value previously calculated for the plurality of pixels; and an object existence determination step of determining whether an object exists within the first area by using a result of comparing frequency characteristic values of the plurality of pixels.

A computer program according to another aspect of the present invention is characterized in that it is a computer program stored in a computer readable medium for executing each step of the object existence determination method on a computer.

A system for determining whether an object exists according to another aspect of the present invention is a system for determining whether an object exists in a first predetermined area, comprising: an image collecting unit collecting a first image including the first area; a frequency characteristic value calculator for each pixel that calculates frequency characteristic values for each of the plurality of pixels included in the first area in the first image; a frequency characteristic comparator comparing each frequency characteristic value calculated for the plurality of pixels with each reference frequency characteristic value previously calculated for the plurality of pixels; and an object existence determination unit determining whether an object exists within the first area by using a result of comparing frequency characteristic values of the plurality of pixels.

In the method, apparatus, system, and computer program for determining whether an object exists according to an embodiment of the present invention, it is possible to effectively determine whether an object exists even if a local or global illumination change or light reflection occurs in an image.

In addition, in the method, apparatus, system, and computer program for determining the presence of an object according to an embodiment of the present invention, the existence of an object is determined through comparison with data calculated in advance from a reference image, so training data for learning (training data ) is unnecessary, and it is possible to more effectively determine whether an object exists by using the pattern of the first area.

The accompanying drawings, which are included as part of the detailed description to aid understanding of the present invention, provide examples of the present invention and explain the technical idea of the present invention together with the detailed description.
1 is a diagram illustrating an operating environment of a method for determining whether an object exists or not, an apparatus, a system, and a computer program according to an embodiment of the present invention.
2 is a flowchart of a method for determining whether an object exists according to an embodiment of the present invention.
3 is an exemplary view of a first image including a first region in a method for determining whether an object exists according to an embodiment of the present invention.
4 is a diagram illustrating mask generation in a method for determining whether an object exists according to an embodiment of the present invention.
5 and 6 are diagrams illustrating automatic mask generation in a method for determining whether an object exists according to an embodiment of the present invention.
7 to 9 are diagrams illustrating calculation of a reference frequency characteristic value and a frequency characteristic value by an object in a method for determining whether an object exists according to an embodiment of the present invention.
10 is a diagram illustrating a case in which a plurality of patterns are provided by dividing a first region in a method for determining whether an object exists according to an embodiment of the present invention.
11 is a diagram illustrating frequency characteristic value verification according to illuminance in a method for determining whether an object exists according to an embodiment of the present invention.
12 is another flowchart of a method for determining whether an object exists according to an embodiment of the present invention.
13 is a block diagram of an object existence determination system according to an embodiment of the present invention.

The present invention can apply various transformations and can have various embodiments. Hereinafter, specific embodiments will be described in detail based on the accompanying drawings.

The following examples are provided to facilitate a comprehensive understanding of the methods, apparatus and/or systems described herein. However, this is only an example and the present invention is not limited thereto.

In describing the embodiments of the present invention, if it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted. In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a user or operator. Therefore, the definition should be made based on the contents throughout this specification. Terms used in the detailed description are only for describing the embodiments of the present invention, and should not be limiting. Unless expressly used otherwise, singular forms of expression include plural forms. In this description, expressions such as "comprising" or "comprising" are intended to indicate any characteristic, number, step, operation, element, portion or combination thereof, one or more other than those described. It should not be construed to exclude the existence or possibility of any other feature, number, step, operation, element, part or combination thereof.

In addition, terms such as first and second may be used to describe various components, but the components are not limited by the terms, and the terms are used for the purpose of distinguishing one component from another. used only as

Hereinafter, exemplary embodiments of an object existence determination method, apparatus, system, and computer program according to the present invention will be described in detail with reference to the accompanying drawings.

First, FIG. 1 shows a diagram for explaining an operating environment of an object existence determination method, apparatus, and system 100 according to an embodiment of the present invention. As can be seen in FIG. 1 , in the object existence determination system 100 according to an embodiment of the present invention, a first image captured by an image capture device that captures a first area 20 such as a camera 10 It is determined whether an object 30 exists in the first area 20 by using .

At this time, in FIG. 1, the image capture device such as the camera 10 is shown as a device separated from the object existence determination system 100, but the present invention is not limited thereto, and the camera 10 or the like captures an image. It is also possible that the device is integrally configured with the object existence determination system 100 .

In addition, the object presence determination system 100 may be configured using a separate device such as dedicated hardware, but may also be configured using a server connected through a communication network, etc., or a camera 10, etc. It can be configured using a computer program that runs on the terminal device of a smartphone equipped with an image capture device, and implemented in various ways, such as being configured in conjunction with or integrated with other devices or systems such as self-driving delivery robots or courier storage boxes. It could be.

2 illustrates a flowchart of a method for determining whether an object exists according to an embodiment of the present invention.

As can be seen in FIG. 2 , a method for determining whether an object exists according to an embodiment of the present invention is a method for determining whether an object 30 exists with respect to a predetermined first area 20, and whether an object exists An image collection step (S110) of collecting a first image including the first region 20 by the determination system 100, each of a plurality of pixels included in the first region 20 in the first image. Frequency characteristic value calculation step for each pixel (S120) of calculating a frequency characteristic value, frequency characteristic comparison of comparing each frequency characteristic value calculated for the plurality of pixels with each reference frequency characteristic value previously calculated for the plurality of pixels It may include step S130 and an object existence determination step S140 of determining whether an object 30 exists within the first area 20 by using a result of comparing frequency characteristic values of the plurality of pixels. there is.

Accordingly, in the method, apparatus, and system 100 for determining whether an object exists according to an embodiment of the present invention, a first area 20 determined in advance using a first image captured by an image capturing device such as the camera 10 ), it is possible to determine whether the object 30 exists.

Below, with reference to FIGS. 1 and 2 , the method, apparatus, and system 100 for determining whether an object exists according to an embodiment of the present invention are reviewed in more detail by dividing them into respective components.

First, in the image collection step ( S110 ), the object presence/absence determination system 100 collects a first image including the first region 20 .

More specifically, as shown in FIG. 3 , the object existence determination system 100 may receive and store a first image including the first region 20 photographed by an image photographing device such as a camera 10. there is.

Here, the image capture device such as the camera 10 may capture the first image by sensitizing light in the visible ray region, but the present invention is not necessarily limited thereto, and sensitizes light of other wavelengths such as infrared rays or ultraviolet rays to capture the first image. It is also possible to create a second image.

At this time, the object 30 may not exist in the first area 20 in the first image as shown in (a) of FIG. 3, or as shown in (b) of FIG. 3 An object 30 may exist in the first region 20 .

In contrast, in the present invention, the object presence determination system 100 determines whether an object 30 exists in the first area 20 using the first image, and at this time, FIG. 3(c) As shown in , it is possible to effectively determine whether an object 30 exists in the first area 20 even if a change in illuminance appears in the first image or reflection of light occurs.

Subsequently, in the step of calculating frequency characteristic values for each pixel ( S120 ), each frequency characteristic value for a plurality of pixels included in the first region 20 in the first image is calculated.

In this case, in the step of calculating frequency characteristic values for each pixel (S120), each frequency characteristic value may be calculated for all pixels included in the first region 20, but the present invention is not necessarily limited thereto. It is also possible to calculate frequency characteristic values only for some pixels among all pixels included in the first region 20 .

More specifically, in the step of calculating the frequency characteristic value for each pixel ( S120 ), a frequency characteristic value for the pixel may be calculated by performing a Fourier transform on the first sub-region including the pixel.

Accordingly, in the step of calculating the frequency characteristic value for each pixel (S120), a Fourier transform is performed on the first sub-region including the pixel, and a frequency having the largest magnitude is calculated as a frequency characteristic value for the pixel. there is.

For a more specific example, the object existence determination system 100 determines a first sub-region having a predetermined size, such as a 4x4 pixel or an 8x8 pixel including the pixel, with respect to the pixels included in the first region 20 . It can be extracted and transformed into a frequency domain through a Fourier transform on the first sub-domain.

In this case, both direction and period may be considered by using Short Time Fourier Transform (STFT) as the Fourier transform, but the present invention is not necessarily limited thereto.

In addition, as an embodiment of the present invention, it is also possible to apply Fast Fourier Transform (FFT) to increase the calculation speed.

Furthermore, in the step of calculating the frequency characteristic value for each pixel (S120) in the present invention, a step of removing image distortion from the first image may be performed prior to the Fourier transform.

More specifically, as can be seen in FIG. 4, since the shape of the first region 20 of the first image may be distorted by the lens of the camera 10 (Fig. 4(a)) , it is preferable to go through a preprocessing process to remove this distortion (Fig. 4(b)).

In addition, the step of calculating frequency characteristic values for each pixel (S120) may include a first region masking step (not shown) of separating the first region 20 by applying a mask 40 to the first image. (FIG. 4 (c)).

Accordingly, in the present invention, by separating and processing only the first region 20 from the first image, it is possible to reduce the amount of computation required and more accurately determine whether or not the object 30 exists in the first region 20. there will be

Furthermore, in the step of masking the first region (not shown) in the present invention, the mask 40 for the first region 20 is formed using the pattern 50 having a predetermined shape formed on the first region 20 It is also possible to calculate and apply automatically.

More specifically, as can be seen in FIG. 5, the first area 20 of the first image may be provided with a pattern 50 having a certain shape, such as a pattern 50 having an inclination of 45 degrees. When the pattern 50 undergoes Fourier transform, it has a dominant value at a specific frequency.

Therefore, in the present invention, the object presence determination system 100 extracts pixels having a specific frequency value through frequency analysis of the first image (FIG. 6(a)), and is formed by the extracted pixels. After calculating the area (for example, the largest area is calculated using a Flood Fill algorithm, etc.) (FIG. 6(b)), noise is removed through morphology calculation, etc. to remove the first area. The mask 40 for (20) can be automatically calculated.

However, the present invention is not necessarily limited thereto, and it is also possible to separate the first region 20 from the first image using the predetermined mask 40 .

In addition, as can be seen in FIG. 7 , the first sub-region may be a 2-dimensional region having a predetermined size (Fig. 7(b)). Accordingly, in the step of calculating the frequency characteristic value for each pixel (S130) , it is possible to calculate a two-dimensional frequency conversion value by performing a Fourier transform on the first sub-region (FIG. 7(c)).

In this case, a frequency having the largest magnitude among the two-dimensional frequency conversion values may be calculated as a frequency characteristic value for the pixel.

As a more specific example, in (c) of FIG. 7, the magnitude of the frequency signal is indicated by contrast, and therefore, as can be seen in (c) of FIG. 7, the largest magnitude at the frequency of (0.125, -0.125) Therefore, the frequency characteristic value for the pixel may be (0.125, -0.125).

While FIG. 7 illustrates the case where the object 30 does not exist in the first area 20 , FIG. 8 illustrates the case where the object 30 exists in the first area 20 .

As can be seen in FIG. 8 , when the object 30 exists in the first area 20, the first sub-area (FIG. 8(b)) for the pixel may be different. The 2D frequency transform value calculated by performing the Fourier transform on the sub-region may also be different (Fig. 8(c)).

Accordingly, when the object 30 exists in the first area 20, it has the largest size at the frequency of (0.125, 0.125), as can be seen in (c) of FIG. 8, so that the pixel The frequency characteristic value for may be (0.125, 0.125).

Next, in the frequency characteristic comparison step (S130), each frequency characteristic value calculated for the plurality of pixels is compared with each reference frequency characteristic value previously calculated for the plurality of pixels.

In this case, the reference frequency characteristic value may be a frequency characteristic value calculated when the object 30 does not exist in the first region 20 .

For a more specific example, as can be seen in (a) of FIG. 9 , the first area 20 may be provided with a pattern 50 having a predetermined shape, and at this time, the first area 20 When the object 30 does not exist, the reference frequency characteristic value 70 may have a constant value according to the pattern 50 .

On the other hand, as can be seen in (b) and (c) of FIG. 9, when the object 30 exists in the first area 20, the frequency characteristic value of the area where the object 30 is located (60) will be different.

Accordingly, in the frequency characteristic comparison step (S130), each frequency characteristic value 60 calculated for the plurality of pixels is compared with each reference frequency characteristic value 70 previously calculated for the plurality of pixels.

More specifically, in the frequency characteristic comparison step (S130) in the present invention, each frequency characteristic value calculated for the plurality of pixels is compared with each reference frequency characteristic value previously calculated for the plurality of pixels, and the difference value can be calculated.

Accordingly, as can be seen in FIG. 9 , the difference value converges to 0 in the area where the object 30 does not exist in the first area 20, but the object in the first area 20 ( 30), it is possible to determine whether or not the object 30 exists in the first area 20 by using this difference value.

Therefore, in the object presence determination step ( S140 ), it is determined whether an object 30 exists within the first region 20 by using a result of comparing the frequency characteristic values of the plurality of pixels.

More specifically, in the object presence determination step (S140), when a value obtained by summing each difference value calculated with respect to the plurality of pixels exceeds a predetermined first reference value, the object is located in the first area 20. (30) can be judged to exist.

However, the present invention is not necessarily limited thereto, and it is possible to determine whether the object 30 exists in the first area 20 by various methods other than this.

For a more specific example, in the object existence determination step (S140), the number or distribution position of pixels for which the difference value calculated with respect to the plurality of pixels exceeds a predetermined second reference value is considered, and the first area It is also possible to determine whether the object 30 exists in (20).

Furthermore, as shown in FIG. 10 , in the present invention, the first region 20 may be divided into a plurality of regions 20a, 20b, and 20c, and patterns having different shapes may be formed in each region.

Accordingly, the plurality of areas 20a, 20b, and 20c may have different reference frequency characteristic values 70a, 70b, and 70c according to each pattern, and thus, even when recognition performance in a specific pattern is slightly lowered, another pattern As a result, it is possible to easily determine the existence of the object 30 .

In addition, as can be seen in FIG. 11 , in the object presence determination system method, apparatus, and system 100 according to an embodiment of the present invention, even when there is a change in illuminance in the first region 20, the frequency characteristics of each pixel It can be seen that the change in the value 60 does not vary greatly, and accordingly, even when there is a change in illuminance, it is possible to effectively determine whether the object 30 exists.

Furthermore, in the object presence determination system method, apparatus, and system 100 according to an embodiment of the present invention, when the object 30 is placed in the same direction as the pattern 50 of the first area 20 It is also possible to effectively determine whether the object 30 exists.

More specifically, in the case of identifying the object 30 based on conventional features, the direction or size of the pattern was determined mainly by using differentiation for each pixel in the image, so the frequency characteristics were not considered. In the present invention, more accurate determination is possible by determining whether or not the object 30 exists in consideration of the direction of the pattern 50 and the corresponding frequency characteristics.

In addition, in the object presence determination system method, apparatus, and system 100 according to an embodiment of the present invention, one reference image (ie, when the object 30 does not exist in the first region 20) Since the presence or absence of the object 30 is determined through comparison with the reference frequency characteristic value 70 calculated in advance for the object 30, generation of training data for learning such as deep learning is not required.

In addition, in the object existence determination system method, apparatus, and system 100 according to an embodiment of the present invention, since the existence of the object 30 is determined through comparison with the reference image, a specific pattern 50 It is possible to determine whether the object 30 exists by applying various patterns 50 without being limited thereto.

12 illustrates another flowchart of a method for determining whether an object exists according to an embodiment of the present invention.

Referring to FIG. 12 , in the object existence determination method according to an embodiment of the present invention, in step S210, the object existence determination system 100 captures a first image including the first region using a camera ( 10) is received from the video recording device.

Subsequently, in step S220, a preprocessing process is performed to remove distortion that may appear in the input first image by the lens of the camera 10 or the like.

Also, in step S230, the first region 20 is separated from the first image using the mask 40.

In this case, the mask 40 may be automatically calculated and applied using the pattern 50 having a predetermined shape formed in the first region 20 .

Next, in step S240, the object existence determination system 100 performs a Fourier transform such as a 2-dimensional STFT (Short Time Fourier Transform) on a plurality of pixels included in the first area 20 to obtain a 2-dimensional frequency A conversion value is calculated and a frequency having the largest magnitude is detected as a frequency characteristic value for each pixel.

Subsequently, in step S250, the sum of the difference between the reference frequency characteristic value of the reference image (ie, the case where the object 30 does not exist in the first region 20) and the frequency characteristic value for each pixel is calculated. will do

Accordingly, when the sum value is greater than the first predetermined reference value, it is determined that the object 30 exists in the first area 20 (S260), and when the sum value is less than the first predetermined reference value It is determined that the object 30 does not exist in the first area 20 (S270).

In addition, the computer program according to another aspect of the present invention is characterized in that it is a computer program stored in a computer readable medium in order to execute each step of the method for determining whether an object exists or not in the above search on a computer. The computer program may be a computer program including machine code generated by a compiler, as well as a computer program including high-level language code that can be executed on a computer using an interpreter or the like. At this time, the computer is not limited to a personal computer (PC) or a notebook computer, etc., and has a central processing unit (CPU) such as a server, smart phone, tablet PC, PDA, mobile phone, etc. to execute a computer program. All information processing include the device

In addition, the computer-readable medium may continuously store a computer-executable program or temporarily store it for execution or download. In addition, the medium may be various recording means or storage means in the form of a single or combined hardware, but is not limited to a medium directly connected to a certain computer system, and may be distributed on a network. Examples of the medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROM and DVD, magneto-optical media such as floptical disks, and ROM, RAM, flash memory, etc. configured to store program instructions. In addition, examples of other media include recording media or storage media managed by an app store that distributes applications, a site that supplies or distributes various other software, and a server.

In addition, FIG. 13 illustrates a configuration diagram of an object presence/absence determination system 100 according to an embodiment of the present invention.

As can be seen in FIG. 13, the object existence determination system 100 according to an embodiment of the present invention includes an image collection unit 110, a frequency characteristic value calculation unit 120 for each pixel, and a frequency characteristic comparison unit 130. and an object existence determination unit 140.

Below, the object presence/absence determination system 100 according to an embodiment of the present invention will be divided for each component. More detailed information about the object existence determination system 100 according to an embodiment of the present invention can be inferred from the description of the object existence determination method according to an embodiment of the present invention described above. A detailed explanation is omitted.

First, the image collecting unit 110 collects a first image including the first region 20 of the imager.

Next, the frequency characteristic value calculation unit 120 for each pixel calculates each frequency characteristic value for a plurality of pixels included in the first region 20 in the first image.

In this case, the frequency characteristic value calculation unit 120 for each pixel may calculate a frequency characteristic value for the pixel by performing a Fourier transform on the first sub-region including the pixel.

In addition, the frequency characteristic value calculation unit 120 for each pixel may perform Fourier transform on the first sub-region including the pixel and calculate a frequency having the largest magnitude as the frequency characteristic value for the pixel. .

In addition, a pattern 50 having a predetermined shape may be formed in the first region 20 .

Furthermore, the first region 20 may be divided into a plurality of regions to form patterns having different shapes.

At this time, the pattern 50 formed in the first region 20 may be a pattern 50 having a dominant size at a specific frequency when subjected to Fourier transform.

In addition, the frequency characteristic value calculation unit 120 for each pixel may include a first region masking unit (not shown) that separates the first region 20 by applying a mask 40 to the first image. can

At this time, the first region masking unit (not shown) automatically calculates the mask 40 for the first region 20 using the pattern 50 having a predetermined shape formed on the first region 20 and can be applied.

In addition, the first sub-region may be a 2-dimensional region having a predetermined size, and in this case, the frequency characteristic value calculation unit 120 for each pixel performs a Fourier transform on the first sub-region to calculate a 2-dimensional frequency. A frequency having the largest magnitude in the converted value may be calculated as a frequency characteristic value for the pixel.

Next, the frequency characteristic comparator 130 may compare each frequency characteristic value calculated for the plurality of pixels with each reference frequency characteristic value previously calculated for the plurality of pixels.

Here, the reference frequency characteristic value may be a frequency characteristic value calculated when the object 30 does not exist in the first region 20 .

At this time, the frequency characteristic comparator 130 may compare each frequency characteristic value calculated for the plurality of pixels with each reference frequency characteristic value previously calculated for the plurality of pixels to calculate a difference value. .

Subsequently, the object existence determination unit 140 determines whether an object 30 exists within the first region 20 by using a result of comparing frequency characteristic values of the plurality of pixels.

At this time, in the object existence determination unit 140, when a value obtained by summing each difference value calculated for the plurality of pixels exceeds a first predetermined reference value, the object 30 is placed in the first area 20. ) can be judged to exist.

In addition, the object existence determination unit 140 considers the number or distribution position of pixels for which the difference value calculated with respect to the plurality of pixels exceeds a predetermined second reference value, and It is also possible to determine whether the object 30 exists.

Accordingly, in the method, apparatus, system 100, and computer program for determining whether an object exists according to an embodiment of the present invention, even if a local or global illumination change or light reflection occurs in an image, it is possible to effectively determine whether an object exists or not. be able to judge

In addition, in the method, apparatus, system, and computer program for determining the presence of an object according to an embodiment of the present invention, the existence of an object is determined through comparison with data calculated in advance from a reference image, so training data for learning (training data ) is unnecessary, and it is possible to more effectively determine whether an object exists by using the pattern of the first area.

The above description is merely an example of the technical idea of the present invention, and various modifications and variations can be made to those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments described in the present invention are not intended to limit the technical spirit of the present invention, but to explain, and are not limited to these embodiments. The protection scope of the present invention should be construed by the following claims, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

10 : Camera
20: first area
30: object
40: mask
50: pattern
60: frequency characteristic value
70: reference frequency characteristic value
100: object presence determination system
110: image collection unit
120: frequency characteristic value calculation unit for each pixel
130: frequency characteristic comparison unit
140: object existence determination unit

Claims (15)

A method for determining whether an object exists in a first region in which a pattern having a predetermined shape is formed,
an image collection step of collecting a first image including the first region by an object existence determination system;
a frequency characteristic value calculation step for each pixel of the first image for each frequency characteristic value of a plurality of pixels included in the first area;
a frequency characteristic comparison step of comparing each frequency characteristic value calculated for the plurality of pixels with a pre-calculated reference frequency characteristic value according to the pattern of the predetermined shape; and
An object existence determination step of determining whether an object exists within the first area by using a result of comparing frequency characteristic values of the plurality of pixels;
The pattern formed in the first region is a pattern having a dominant size at a specific frequency when subjected to Fourier transform,
In the frequency characteristic comparison step,
Each frequency characteristic value calculated for a plurality of pixels in the first image is compared with each reference frequency characteristic value calculated in advance for a plurality of pixels in the reference image in which no object exists in the first area, and the difference value is obtained. A method for determining whether an object exists, characterized in that for calculating. According to claim 1,
In the step of calculating frequency characteristic values for each pixel,
A method for determining whether an object exists or not, characterized in that a frequency characteristic value for the pixel is calculated by performing a Fourier transform on the first sub-region including the pixel. According to claim 2,
In the step of calculating frequency characteristic values for each pixel,
A method for determining whether an object exists, characterized in that performing a Fourier transform on a first sub-region including the pixel and calculating a frequency having the largest magnitude as a frequency characteristic value for the pixel. delete delete According to claim 1,
In the step of calculating the frequency characteristic value for each pixel,
and a first region masking step of separating the first region by applying a mask to the first image. According to claim 6,
In the first region masking step,
The method of determining whether an object exists, characterized in that the mask for the first area is automatically calculated and applied using a pattern having a predetermined shape formed in the first area. According to claim 2,
The first sub-region is a 2-dimensional region having a predetermined size,
In the step of calculating frequency characteristic values for each pixel,
The method of determining whether an object exists, characterized in that by performing a Fourier transform on the first sub-region and calculating a frequency having the largest magnitude as a frequency characteristic value for the pixel in the two-dimensional frequency conversion value. According to claim 1,
The reference frequency characteristic value is,
An object presence/absence determination method, characterized in that the frequency characteristic value calculated when an object does not exist in the first area. delete According to claim 1,
In the step of determining whether the object exists,
When a value obtained by summing each difference value calculated for the plurality of pixels exceeds a predetermined first reference value,
The method of determining whether an object exists or not, characterized in that it is determined that an object exists in the first area. According to claim 1,
In the step of determining whether the object exists,
Considering the number or distribution position of pixels for which the difference value calculated for the plurality of pixels exceeds a predetermined second reference value,
An object presence/absence determination method characterized in that determining whether an object exists in the first area. According to claim 3,
The first region,
A method for determining whether an object exists, characterized in that patterns having different shapes are formed by dividing into a plurality of areas. A computer program stored in a computer readable medium for executing each step according to any one of claims 1 to 3, 6 to 9, and 11 to 13 on a computer. In the system for determining the presence or absence of an object in a first region in which a pattern having a predetermined shape is formed,
an image collecting unit collecting a first image including the first region;
a frequency characteristic value calculator for each pixel that calculates frequency characteristic values for each of the plurality of pixels included in the first area in the first image;
a frequency characteristic comparator comparing each frequency characteristic value calculated for the plurality of pixels with a pre-calculated reference frequency characteristic value according to the pattern of the predetermined shape; and
An object existence determination unit determining whether an object exists within the first area by using a result of comparing frequency characteristic values of the plurality of pixels;
The pattern formed in the first region is a pattern having a dominant size at a specific frequency when subjected to Fourier transform,
In the frequency characteristic comparison unit,
Each frequency characteristic value calculated for a plurality of pixels in the first image is compared with each reference frequency characteristic value calculated in advance for a plurality of pixels in the reference image in which no object exists in the first area, and the difference value is obtained. An object existence determination system, characterized in that for calculating.

Images