CN109949337A - Moving target detection method and device based on Gaussian mixture background model - Google Patents

Abstract

The embodiments of the present invention relate to a moving target detection method and device based on a Gaussian mixture background model, and relate to the technical field of image recognition technology. The main technical scheme adopted is: a moving target detection method based on a Gaussian mixture background model includes: establishing a Gaussian mixture background model based on video image pixels; updating parameters of the Gaussian mixture background model based on the pixels of the current frame image, and analyzing the pixels of the current frame image to obtain Foreground pixels; denoising the foreground pixels by using the wavelet threshold denoising method to generate a first filtered image; denoising the first filtered image by a mathematical form closing operation to generate a moving target of the current frame image. Compared with the prior art, the noise interference generated in the dynamic background can be eliminated, so that the detected moving target is more complete, thereby improving the detection accuracy of the moving target.

Description

Moving target detection method and device based on Gaussian mixture background model

technical field

Embodiments of the present invention relate to the technical field of image recognition, and in particular, to a moving target detection method and device based on a Gaussian mixture background model.

Background technique

With the development of digital video technology, people can detect, track, identify and analyze moving objects in surveillance video. Using these technologies, people can quickly obtain effective information such as the position, trajectory, and behavior of the moving target that needs to be detected. Moving object detection is the foundation of technologies such as moving object tracking, behavior recognition, and scene description. The detection results directly affect the accuracy of subsequent algorithms. Therefore, how to improve the accuracy and robustness of target detection has become one of the main research directions in the field of computer vision. At present, the main moving target detection methods are: inter-frame difference method, background subtraction method and optical flow method.

The optical flow method is a detection method based on the brightness information of the detected target image. This method has high computational complexity and weak anti-interference ability, so it is generally not used.

The inter-frame difference method uses continuous video frame images to perform differential operations to achieve the extraction of moving objects. It has a strong adaptability to background changes, but the detected objects have holes and missed detection of slow-moving objects.

The background subtraction method is the most widely used method. The background subtraction method is to first establish a background model, and then make a difference between the current frame image and the background model to extract the moving target. This method mainly relies on a stable background model to obtain a relatively complete foreground feature. Compare the current frame with the background model to get the moving object. Gaussian mixture background model method GMM is a kind of background subtraction and is the most popular background subtraction algorithm, but it also has the problem of low accuracy of moving target detection under dynamic background.

SUMMARY OF THE INVENTION

In view of this, the embodiments of the present invention provide a moving target detection method and device based on a Gaussian mixture background model, and the main technical problem to be solved is that the Gaussian mixture background model method does not have high accuracy for moving target detection.

To achieve the above purpose, the embodiments of the present invention mainly provide the following technical solutions:

On the one hand, an embodiment of the present invention provides a moving target detection method based on a Gaussian mixture background model, including:

Build a Gaussian mixture background model based on video image pixels;

Update the parameters of the Gaussian mixture background model based on the pixels of the current frame image, and analyze the pixels of the current frame image to obtain the foreground pixels;

Denoising the foreground pixels using a wavelet threshold denoising method to generate a first filtered image;

The first filtered image is denoised by the closing operation in mathematical form to generate the moving object of the current frame image.

The purpose of the embodiments of the present invention and the solution to the technical problems thereof can be further achieved by adopting the following technical measures.

Optionally, the aforementioned moving target detection method based on the Gaussian mixture background model, wherein the wavelet threshold denoising method is any one of the wavelet half-threshold denoising method, the wavelet soft threshold denoising method, and the wavelet hard threshold denoising method. kind.

Optionally, the aforementioned moving target detection method based on a Gaussian mixture background model, wherein a Gaussian mixture background model is established based on video image pixels, including:

The video image is divided into M sub-regions, where M is a positive integer greater than or equal to 2;

Calculate the mean of the pixels of each sub-region respectively;

A mixture Gaussian model of different pixels in each sub-region is constructed with multiple Gaussian distributions according to the mean of the pixels in each sub-region.

Optionally, the aforementioned moving target detection method based on the Gaussian mixture background model, wherein the parameters of the Gaussian mixture background model are updated based on the pixels of the current frame image, specifically:

Update the parameters of the Gaussian mixture background model for each pixel based on each pixel of the current frame image.

Optionally, the aforementioned method for detecting moving objects based on a Gaussian mixture background model, wherein the video image is divided into M sub-regions, including:

Obtain the hardware configuration information of the apparatus for executing the moving target detection method based on the Gaussian mixture background model, and determine the M value according to the hardware configuration information.

On the other hand, an embodiment of the present invention provides a moving target detection device based on a Gaussian mixture background model, including:

establishing a unit for establishing a Gaussian mixture background model based on video image pixels;

An analysis unit, used for updating the parameters of the Gaussian mixture background model based on the pixels of the current frame image, and analyzing the pixels of the current frame image to obtain the foreground pixels;

a first denoising unit, used for denoising the foreground pixels using a wavelet threshold denoising method to generate a first filtered image;

The second de-drying unit is configured to perform denoising on the first filtered image by using a closing operation in a mathematical form to generate a moving object of the current frame image.

The purpose of the embodiments of the present invention and the solution to the technical problems thereof can be further achieved by adopting the following technical measures.

Optionally, the aforementioned moving target detection device based on the Gaussian mixture background model, wherein the establishment unit includes:

A division module, for dividing the video image into M sub-regions, where M is a positive integer greater than or equal to 2;

The obtaining module is used to obtain the mean value of the pixels of each sub-region respectively;

The building block is used to construct a Gaussian mixture model of different pixels in each sub-region with multiple Gaussian distributions based on the mean of the pixels in each sub-region.

Optionally, the aforementioned moving target detection device based on the Gaussian mixture background model, wherein the establishment unit includes:

A determination module, configured to acquire hardware configuration information of an apparatus for executing the moving target detection method based on the Gaussian mixture background model, and determine the M value according to the hardware configuration information.

On the other hand, an embodiment of the present invention provides a storage medium, where the storage medium includes a stored program, wherein when the program runs, a device where the storage medium is located is controlled to execute the above-mentioned moving object detection method.

On the other hand, an embodiment of the present invention provides a moving target detection device based on a Gaussian mixture background model, the device includes a storage medium; and one or more processors, the storage medium is coupled to the processor, and the The processor is configured to execute the program instructions stored in the storage medium; when the program instructions are executed, the above-mentioned moving target detection method is executed.

With the above technical solutions, the method and device for detecting moving objects based on the Gaussian mixture background model provided by the technical solutions of the present invention have at least the following advantages:

In the technical solution provided by the embodiment of the present invention, after the foreground pixels are obtained by analyzing the pixels of the current frame image based on the Gaussian mixture background model established by the video image pixels, the wavelet threshold denoising method is used to denoise the foreground pixels to generate the first filter. image, and then use the closed operation in mathematical form to denoise the first filtered image to generate the moving target of the current frame image. Compared with the prior art, the noise interference generated in the dynamic background can be eliminated, so that the detected moving target is more complete, thereby improving the detection accuracy of the moving target.

The above description is only an overview of the technical solutions of the present invention. In order to understand the technical means of the embodiments of the present invention more clearly, and to implement them according to the contents of the description, the preferred embodiments of the present invention and the accompanying drawings are described in detail below. .

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for the purpose of illustrating preferred embodiments only and are not to be considered limiting of the invention. Also, the same components are denoted by the same reference numerals throughout the drawings. In the attached image:

1 is a schematic flowchart of a moving target detection method based on a Gaussian mixture background model provided by an embodiment of the present invention;

2 is a schematic flowchart of another moving target detection method based on a Gaussian mixture background model provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of a unit structure of a moving target detection device based on a Gaussian mixture background model provided by an embodiment of the present invention.

Detailed ways

In order to further illustrate the technical means and effects adopted by the present invention to achieve the purpose of the predetermined embodiment of the invention, the following describes the method for detecting moving objects based on the Gaussian mixture background model and the The specific implementation, structure, features and functions of the device are described in detail as follows. In the following description, different "an embodiment" or "embodiments" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

In the first aspect, FIG. 1 is an embodiment of a method for detecting moving objects based on a Gaussian mixture background model provided by the present invention. Please refer to FIG. 1 . The method for detecting moving objects based on a Gaussian mixture background model proposed by an embodiment of the present invention includes: :

101. Establish a Gaussian mixture background model based on video image pixels;

The Gaussian mixture background model is formed by constructing multiple Gaussian distributions for each pixel in the video image. For example, in some embodiments, multiple Gaussian distributions for each pixel point may be calculated and constructed in sequence, but not limited thereto.

102. Update the parameters of the Gaussian mixture background model based on the pixels of the current frame image, and analyze the pixels of the current frame image to obtain foreground pixels;

The analysis of foreground pixels can use the updated Gaussian mixture background model or the Gaussian mixture background model before the update, and match the pixel value with the Gaussian distribution of the Gaussian mixture background model. If there is a match, the pixel is a background pixel. , otherwise the pixel is detected as a foreground pixel, and the specific matching method can refer to the existing Gaussian mixture background model method, which is not particularly limited in this embodiment.

103. Denoising the foreground pixels using a wavelet threshold denoising method to generate a first filtered image;

The wavelet threshold denoising method may be any one of the wavelet half-threshold denoising method, the wavelet soft threshold denoising method, and the wavelet hard threshold denoising method. Among them, the wavelet half-threshold denoising method can produce better denoising effect on the high frequency components of the image. In the moving target detection stage, in order to effectively remove the interference of noise, the wavelet half-threshold function denoising method and the mathematical morphology denoising method are used to remove the influence of noise on the detection effect.

104. Denoise the first filtered image by using a closed operation in a mathematical form to generate a moving object of the current frame image.

There are still many holes in the first filtered image, and by filling the holes through the closed operation processing in the mathematical form, the noise interference caused by the dynamic background can be eliminated.

In the technical solution provided by the embodiment of the present invention, after the foreground pixels are obtained by analyzing the pixels of the current frame image based on the Gaussian mixture background model established by the video image pixels, the wavelet threshold denoising method is used to denoise the foreground pixels to generate the first filter. image, and then use the closed operation in mathematical form to denoise the first filtered image to generate the moving target of the current frame image. Compared with the prior art, the noise interference generated in the dynamic background can be eliminated, so that the detected moving target is more complete, thereby improving the detection accuracy of the moving target.

In the second aspect, the quality of the video picture is gradually improved, and the number of pixels also has the characteristics of big data. The problem caused by this is that the calculation amount of the Gaussian mixture background model construction increases exponentially, resulting in an exponential increase in the number of pixels. The Gaussian mixture background model method is difficult to complete the rapid modeling of new high-quality video images. For this reason, in order to apply the fast modeling of high-quality video images, FIG. 2 is an embodiment of a method for detecting moving objects based on a Gaussian mixture background model provided by the present invention. Please refer to FIG. 2 . The moving target detection method of Gaussian mixture background model, including:

Create a Gaussian mixture background model based on video image pixels, including:

201. Acquire hardware configuration information of an apparatus for executing a moving target detection method based on a Gaussian mixture background model, and determine an M value according to the hardware configuration information.

In some embodiments, the hardware configuration information includes information such as processor processing rate and memory capacity, and the processing capability of the integrated hardware configuration information determines the M value. In implementation, the M value is positively correlated with the processor processing rate and memory capacity. It should be noted that in the above step 201, the processor processing rate and memory capacity may also be other information to determine the M value. For example, in some embodiments, the hardware configuration information includes the size or resolution of the display. In practice, the M value is inversely related to the size or resolution of the display. Or, the method for determining the M value in step 201 can also be other methods, for example, the M value is determined according to the number of pixels in each frame of the video image. negative correlation. Of course, step 201 is an optional step, and the value of M can also be a preset value or a value changed by user input.

202. Divide the video image into M sub-regions, where M is a positive integer greater than or equal to 2;

Each sub-region contains at least 2 pixels. The number of pixels included in the M sub-regions may be the same, for example, each sub-region is a 3×3 9-pixel array or a 4×4 16-pixel array. In some embodiments, the number of pixels included in the M sub-regions may also be different, and the video image is pre-divided into a first region and a second region, and the first region and the second region are different regions. In the sub-area division, the number of pixels contained in the sub-areas of the first area is smaller than the number of pixels contained in the sub-areas of the second area, and the first area may be judged as a moving target with relatively high activity. The second area may be an area that is judged to be a more active area of the moving target.

203. Calculate the mean value of each sub-region pixel respectively;

Specifically, the process of calculating the mean value of pixels in one sub-region is: after calculating the sum of all pixels in one sub-region, divide the calculated result by the total number of pixels in the sub-region.

204. Construct a Gaussian mixture model of different pixels in each sub-region according to the mean value of the pixels in each sub-region.

In the calculation, each sub-region X _i,t in the image is modeled by a mixture Gaussian model composed of multiple Gaussian distributions, Among them, η _k (X _{i, t} , μ _{i, t, k} , ∑ _{i, t, k} ) is the Gaussian distribution function, μ _{i, t, k} is the mean value, ∑ _{i, t, k} is the covariance matrix, ω _{i, t, k} are weights, The larger the value of K, the more complex the background can be described, but it also increases the amount of calculation and affects the real-time effect, so K generally takes 3 to 5. X _i,t can represent a sub-region of the i-th row and the t-th column. The multiple Gaussian distributions corresponding to the mean value of the pixels in each sub-area are used as the multiple Gaussian distributions corresponding to all the pixels in the sub-area. Compared with calculating and constructing multiple Gaussian distributions for each pixel in turn, multiple Gaussian distributions corresponding to all pixels in a sub-area can be calculated by one operation, which greatly reduces the amount of calculation.

205. Update the parameters of the Gaussian mixture background model of each pixel based on each pixel of the current frame image, and analyze the pixels of the current frame image to obtain foreground pixels;

In the update step of the background Gaussian mixture background model, the parameters of the Gaussian mixture background model are updated by the method of adaptive background update.

206. Denoising the foreground pixels using a wavelet threshold denoising method to generate a first filtered image;

207 . Denoise the first filtered image by using a closing operation in a mathematical form to generate a moving object of the current frame image.

In step 204 of the background modeling stage, in order to facilitate the calculation and improve the speed of modeling, the video frame image is first divided into sub-regions, and then the average value of the pixels in the sub-region of the image block is used to replace the value of the pixels in the sub-region of the image block. Finally, the background model is reconstructed by the image block sub-region mean method.

In a third aspect, according to the method shown in FIG. 1 or FIG. 2 , another embodiment of the present disclosure further provides a moving target detection device. As shown in FIG. 3 , the device mainly includes:

establishing unit 10 for establishing a Gaussian mixture background model based on video image pixels;

The analysis unit 20 is used to update the parameters of the Gaussian mixture background model based on the current frame image pixels, and analyze the current frame image pixels to obtain foreground pixels;

a first denoising unit 30, configured to denoise the foreground pixels using a wavelet threshold denoising method to generate a first filtered image;

The second de-drying unit 40 is configured to perform denoising on the first filtered image by using the closing operation in mathematical form to generate a moving object of the current frame image.

In some embodiments, the establishment unit includes:

A division module, for dividing the video image into M sub-regions, where M is a positive integer greater than or equal to 2;

The obtaining module is used to obtain the mean value of the pixels of each sub-region respectively;

The building block is used to construct a Gaussian mixture model of different pixels in each sub-region with multiple Gaussian distributions based on the mean of the pixels in each sub-region.

In some embodiments, the establishment unit includes:

A determination module, configured to acquire hardware configuration information of an apparatus for executing the moving target detection method based on the Gaussian mixture background model, and determine the M value according to the hardware configuration information.

The device includes a processor and a storage medium, and the above-mentioned establishment unit, analysis unit, first de-drying unit, second de-drying unit, etc. are all stored in the storage medium as program units, and the processor executes the above-mentioned stored in the storage medium. program unit to achieve the corresponding function.

The above-mentioned processor includes a kernel, and the corresponding program unit is called from the storage medium by the kernel. The kernel can set one or more.

In the technical solution provided by the embodiment of the present invention, after the foreground pixels are obtained by analyzing the pixels of the current frame image based on the Gaussian mixture background model established by the video image pixels, the wavelet threshold denoising method is used to denoise the foreground pixels to generate the first filter. image, and then use the closed operation in mathematical form to denoise the first filtered image to generate the moving target of the current frame image. Compared with the prior art, the noise interference generated in the dynamic background can be eliminated, so that the detected moving target is more complete, thereby improving the detection accuracy of the moving target.

The apparatus for detecting moving objects based on the Gaussian mixture background model provided by the embodiments of the third aspect can be used to perform the method for detecting moving objects based on the Gaussian mixture background model provided by the embodiments of the first aspect or the second aspect. For the meaning and specific implementation, reference may be made to the relevant descriptions in the embodiments of the first aspect or the second aspect, which will not be described in detail here.

In a fourth aspect, an embodiment of the present disclosure provides a storage medium, where the storage medium includes a stored program, wherein when the program runs, a device where the storage medium is located is controlled to execute the first aspect or the second aspect A moving target detection method based on Gaussian mixture background model.

The storage medium may include non-persistent memory, random access memory (RAM) and/or non-volatile memory in the form of computer readable media, such as read only memory (ROM) or flash memory (flashRAM), the memory including at least one memory chip.

In a fifth aspect, an embodiment of the present disclosure provides a moving target detection device based on a Gaussian mixture background model, the device includes a storage medium; and one or more processors, the storage medium is coupled to the processor, the The processor is configured to execute the program instructions stored in the storage medium; when the program instructions are executed, the moving target detection method based on the Gaussian mixture background model described in the first aspect or the second aspect is executed.

The embodiments of the present disclosure reduce the root mean square error of the image while improving the peak signal-to-noise ratio of the detected image, and obtain better visual effects.

As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media having computer-usable program code embodied therein, including but not limited to disk storage, CD-ROM, optical storage, etc. .

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products of embodiments of the present disclosure. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory in the form of, for example, read only memory (ROM) or flash memory (flashRAM). Memory is an example of a computer-readable medium.

Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

It should also be noted that the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements, but also Other elements not expressly listed, or which are inherent to such a process, method, article of manufacture, or apparatus are also included. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article of manufacture or apparatus that includes the element.

As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system or computer program product. Accordingly, embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media having computer-usable program code embodied therein, including but not limited to disk storage, CD-ROM, optical storage, etc. .

The above are merely examples of the present application, and are not intended to limit the present application. Various modifications and variations of this application are possible for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims (10)

1. a moving target detection method based on Gaussian mixture background model, is characterized in that, comprises: Build a Gaussian mixture background model based on video image pixels; Update the parameters of the Gaussian mixture background model based on the pixels of the current frame image, and analyze the pixels of the current frame image to obtain the foreground pixels; Denoising the foreground pixels using a wavelet threshold denoising method to generate a first filtered image; The first filtered image is denoised by the closing operation in mathematical form to generate the moving object of the current frame image. 2. moving target detection method according to claim 1, is characterized in that, The wavelet threshold denoising method is any one of the wavelet half-threshold denoising method, the wavelet soft threshold denoising method and the wavelet hard threshold denoising method. 3. The moving target detection method according to claim 1 or 2, wherein a Gaussian mixture background model is established based on video image pixels, comprising: The video image is divided into M sub-regions, where M is a positive integer greater than or equal to 2; Calculate the mean of the pixels of each sub-region respectively; A mixture Gaussian model of different pixels in each sub-region is constructed with multiple Gaussian distributions according to the mean of the pixels in each sub-region. 4. moving target detection method according to claim 3, is characterized in that, the parameter of Gaussian mixture background model is updated based on current frame image pixel, is specifically: Update the parameters of the Gaussian mixture background model for each pixel based on each pixel of the current frame image. 5. The moving target detection method according to claim 3, wherein the video image is divided into M sub-regions, comprising: Obtain the hardware configuration information of the apparatus for executing the moving target detection method based on the Gaussian mixture background model, and determine the M value according to the hardware configuration information. 6. A moving target detection device based on a Gaussian mixture background model, characterized in that, comprising: establishing a unit for establishing a Gaussian mixture background model based on video image pixels; An analysis unit, used for updating the parameters of the Gaussian mixture background model based on the pixels of the current frame image, and analyzing the pixels of the current frame image to obtain the foreground pixels; a first denoising unit, used for denoising the foreground pixels using a wavelet threshold denoising method to generate a first filtered image; The second de-drying unit is configured to perform denoising on the first filtered image by using a closing operation in a mathematical form to generate a moving object of the current frame image. 7. The moving target detection device according to claim 6, wherein the establishment unit comprises: A division module, for dividing the video image into M sub-regions, where M is a positive integer greater than or equal to 2; The obtaining module is used to obtain the mean value of the pixels of each sub-region respectively; The building block is used to construct a Gaussian mixture model of different pixels in each sub-region with multiple Gaussian distributions based on the mean of the pixels in each sub-region. 8. The moving target detection device according to claim 7, wherein the establishment unit comprises: A determination module, configured to acquire hardware configuration information of an apparatus for executing the moving target detection method based on the Gaussian mixture background model, and determine the M value according to the hardware configuration information. 9. A storage medium, characterized in that the storage medium comprises a stored program, wherein when the program is run, a device where the storage medium is located is controlled to execute the moving target according to any one of claims 1 to 5 Detection method. 10. A moving target detection device based on a Gaussian mixture background model, wherein the device comprises a storage medium; and one or more processors, the storage medium is coupled to the processor, and the processor is It is configured to execute the program instructions stored in the storage medium; when the program instructions are executed, the moving target detection method according to any one of claims 1 to 5 is executed.