JP6953184B2 - Image processing device and image processing method - Google Patents

Description

The present invention relates to an image processing technique for detecting a moving object region in a plurality of image data obtained by continuous shooting.

There is known a technique for detecting a moving subject (moving object) included in a shooting scene by using the difference in the brightness of pixels having the same coordinates in a plurality of image data acquired by continuous shooting. Specifically, the difference in brightness between the image data at the same coordinates is compared with the threshold value, and if the difference is larger than the threshold value, it is detected as a pixel containing a moving object. However, if the brightness fluctuates due to flicker of fluorescent lamps, blinking of the lighting device, movement of sunlight or clouds, etc., the brightness fluctuation due to lighting will be mistakenly detected as a moving object region just by using the difference value of the same coordinates. .. Therefore, in Patent Document 1, a method is used in which an image is divided into blocks composed of a plurality of pixels, orthogonal transformation is performed for each block, and a moving body region is detected based on the ratio of the total sum of the AC components in the horizontal direction and the total sum in the vertical direction. It is disclosed. In the brightness fluctuation due to illumination, the DC component mainly fluctuates, and the AC component does not fluctuate much. According to the method shown in Patent Document 1, erroneous detection of a moving body region due to fluctuations in lighting is reduced.

JP-A-2002-259985

However, when there is a lot of noise in the image data, the change in the brightness of the illumination also causes a large change in the AC component. As a result, in the method disclosed in Patent Document 1, erroneous detection of a moving body region may increase in image data having a lot of noise. Further, when the moving body region moves horizontally or vertically, the ratio of the total sum of the AC components in the horizontal direction and the total sum in the vertical direction does not change, so that the moving body cannot be detected as a moving body. Therefore, the present invention accurately discriminates whether it is a change in brightness due to illumination fluctuation or a moving object region.

In order to solve the above problem, the present invention uses N image data (natural numbers satisfying N> 3) to detect a moving object region in the reference image data, which is one of the N image data. In the image processing device, the acquisition means for acquiring the N image data and the average brightness in the local region composed of a plurality of pixels including the pixel of interest for each of the N image data are averaged by the pixels of interest. The first calculation means for calculating the brightness, the average brightness of the pixel of interest in the reference image data, and the average brightness of the pixel of interest in each of the image data other than the reference image data are the brightness equal to or higher than the first threshold value. A brightness difference determining means for determining whether or not there is a difference, a second calculating means for calculating the standard deviation of the average brightness corresponding to the pixel of interest in each of the N image data, and an average brightness of the pixel of interest. Based on the comparison means for comparing the standard deviation of the above and the second threshold value, the determination result by the brightness difference determination means, and the comparison result by the comparison means, whether or not the pixel of interest is a pixel included in the moving object region is determined. The moving body determining means has a moving body determining means for determining, and the moving body determining means determines that there is a brightness difference for the pixel of interest by the brightness difference determining means, and the standard deviation is equal to or greater than the second threshold value. The pixel of interest is determined to be a pixel included in the moving object region.

According to the present invention, it is possible to detect a moving object region in a plurality of image data while suppressing the influence of brightness fluctuation due to illumination.

It is a figure which shows the hardware configuration of the image processing apparatus in 1st Embodiment. It is a schematic diagram which shows the logical structure of the image processing apparatus in 1st Embodiment. It is a flowchart which shows the flow of image processing in 1st Embodiment. It is a figure for demonstrating the local region determination in 1st Embodiment. It is a flowchart which shows the flow of the determination process in 1st Embodiment. It is a flowchart which shows the flow of synthesis processing in 1st Embodiment. It is a schematic diagram which shows the logical structure of the image processing apparatus in 2nd Embodiment. It is a flowchart which shows the flow of image processing in 2nd Embodiment.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings, based on preferred embodiments. The configuration shown in the following embodiments is only an example, and the present invention is not limited to the illustrated configuration.

<First Embodiment>
In the present embodiment, a moving object region in the reference image data is detected using N image data (N is a natural number satisfying N> 3) acquired by continuous shooting, and noise in the reference image data is detected according to the detected result. An image processing apparatus that performs reduction processing will be described. Specifically, noise reduction processing by NonLocalMean is performed in the moving body region, and noise reduction is performed in the non-moving body region by using the summing average of the brightness of the corresponding pixels in the reference image data and the continuous image data (reference image data). Apply processing. Of the N image data taken continuously, the first image data is used as the reference image data, and the image data other than the reference image data is used as the reference image data. In the present embodiment, in order to simplify the explanation, it is assumed that the number of image data N is N = 4, all the image data to be handled are 8 bits, and the image data is photographed using a tripod. A sheet is used as a unit for expressing the number of image data. Further, the moving object means a subject that has moved at the moment when the four image data are acquired.

First, the hardware configuration of the image processing apparatus according to the first embodiment will be described with reference to FIG. FIG. 1 is a diagram showing a hardware configuration of an image processing device according to the present embodiment. The image processing device includes a CPU 101, a RAM 102, an HDD 103, a general-purpose interface (I / F) 104, and a monitor 108, and each component is connected to each other by a main bus 109.

The CPU 101 is a processor that comprehensively controls each part in the image processing apparatus. The RAM 102 is a memory that functions as a main memory, a work area, or the like of the CPU 101. Further, the HDD 103 is a memory that stores a group of programs executed by the CPU 101. The HDD 103 may be replaced with another storage medium such as a flash memory.

The general-purpose interface (I / F) 104 is an interface including a USB connector, and the image pickup device 105, the input device 106, and the external memory 107 are connected to the main bus 109 via the general-purpose I / F 104. The image pickup device 105 is a camera having an image shooting function, and outputs the shot image data to the image processing device. It has a continuous shooting mode in which one shot is taken four times in a row. The input device 106 is an input device such as a mouse and a keyboard, and the user can input an instruction to the image processing device via the input device 106. The external memory 107 is a recording medium such as an HDD or a memory card, and can store data output from the image processing device. The monitor 108 is a liquid crystal display provided in the image processing device, and can display image data, a user interface, and the like. The main bus 109 is a system bus that connects each component in the image processing apparatus to each other.

Hereinafter, the image processing in the present embodiment will be described with reference to FIG. FIG. 2 is a block diagram showing a logical configuration of the image processing apparatus of the present embodiment. In this embodiment, a logical configuration executed by software will be described as an example, but a part or all of each configuration can be realized by a dedicated circuit.

In FIG. 2, the image data input unit 201 inputs four continuously captured image data to the image processing device. The image data is input from the image pickup apparatus 105, the HDD 103, or the external memory 107 based on the instruction from the CPU 101. Of course, the image taken by the image pickup apparatus 105 may be temporarily stored in a storage device such as HDD 103 and then input. The parameter input unit 202 inputs a plurality of parameters used for image processing to the image processing device. The parameters are input from the HDD 103 or the external memory 107 based on the instructions from the CPU 101. Further, it may be directly specified by an input device 106 such as a keyboard or a mouse via a user interface (UI). The parameters include the size of the local region used by the average luminance calculation unit 203 and the threshold value used by the determination processing unit 204. A detailed description of the parameters will be described later.

The average brightness calculation unit 203 receives an instruction from the CPU 101, acquires a plurality of image data and parameters, and averages the brightness of each pixel included in the local area according to the size of the local area indicated by the parameter in the image data. The average luminance calculation unit 203 generates an average luminance map showing the average luminance in the image data. In this embodiment, since four image data are input, four average luminance maps are generated. The generated average luminance map is stored in the RAM 102. The details of the average luminance map will be described later.

The determination processing unit 204 receives an instruction from the CPU 101, acquires image data, an average luminance map, and parameters, and detects a region (moving object region) including a moving object in the reference image data. The detected moving body area is stored in the RAM 102 as a moving body area map. The synthesis processing unit 205 receives an instruction from the CPU 101, acquires image data, a moving body area map, and parameters, and generates composite image data. For each pixel in the reference image data, the brightness that has been noise-reduced by different processing depending on whether or not it is a moving object is calculated. The generated composite image data is stored in the RAM 102.

The image data output unit 206 outputs the composite image data generated by the composite processing unit 205 to the monitor 108, the HDD 103, or the like. The output destination is not limited to these, and may be output to, for example, an external memory connected to the general-purpose I / F 104.

Hereinafter, details of each process in the logical configuration of the image processing apparatus described with reference to FIG. 2 will be described with reference to the flowchart shown in FIG. The process shown in FIG. 3 is realized by the CPU 101 executing the program stored in the RAM 102. Further, a part or all of each component shown in FIG. 2 may be realized as a dedicated processing circuit or the like having the function.

In step S301, the image data input unit 201 inputs a plurality of image data acquired by the image pickup device 105 continuously shooting in the continuous shooting mode to the image processing device. In the present embodiment, the image data taken first among the four image data is used as the reference image data, and the subsequent three image data are used as the reference image data.

In step S302, the parameter input unit 202 inputs the parameters required for the subsequent processing to the image processing device. The parameters to be input in the present embodiment include the size of the local region required for generating the average luminance map, the parameter threshold value th for determining the luminance difference, and the parameter threshold value th2 for determining variation.

In step S303, the average luminance calculation unit 203 generates an average luminance map for each of the reference image data and each reference image data. The average brightness calculation unit 203 sets a local region of the size indicated by the parameter for the pixel of interest in the image data to be processed so as to include the pixel of interest, and sets the average value of the brightness of each pixel included in the local region as the pixel of interest. Calculated as average brightness. Therefore, the average luminance map is a map having an average value in a local region of image data for each pixel. This is generated for all four image data. Specifically, in each image data, the average value in the local region composed of the pixel of interest and the peripheral pixels is calculated for each RGB. The size S1 of the local region is determined based on the parameters, and here, S1 = 5, and the case of 5 pixels × 5 pixels will be described with reference to FIG. In FIG. 4A, the pixel 401 indicated by the black block is the pixel of interest, the pixel group 402 indicated by the gray block is the peripheral pixel, and the area 403 surrounded by the thick line is the local area set for the pixel 401 of interest. Represents. The shape of the local region is not limited to the rectangular region, and may be any shape, for example, the shape shown in FIG. 4B. If the size of the local region is too large, different subjects are likely to be included in the local region, and the accuracy of moving object determination is lowered. Therefore, a size of at most 15 pixels × 15 pixels is desirable.

In step S304, the determination processing unit 204 determines whether or not each pixel in the reference image data is a pixel representing a moving object, based on the average luminance map generated in step S303. The determination processing unit 204 detects a moving object region according to the determination result and generates a moving object region map. The details of the determination process will be described later.

In step S305, the synthesis processing unit 205 synthesizes the reference image data and each reference image data based on the moving body region map generated in step S304, and generates the composite image data. The details of the synthesis process will be described later. In step S306, the image data output unit 206 outputs the composite image data generated in step S305 to the monitor 108 or the like. The above is the processing flow performed by the image processing apparatus of the present embodiment.

Hereinafter, the details of the determination process performed in step S304 and the synthesis process performed in step S305 will be described. The determination process executed by the determination processing unit 204 in step S304 in the present embodiment will be described with reference to FIG. FIG. 5 is a flowchart showing the flow of the determination process.

In step S501, the determination processing unit 204 selects the pixel of interest to be processed in the reference image data input in step S301. In step S502, the determination processing unit 204 refers to the average luminance map, and whether or not there is a difference between the average luminance of the pixel of interest and the average luminance of the pixel (reference pixel) at the same coordinates as the pixel of interest in each reference image data. Is determined. Specifically, first, the average luminance for each RGB corresponding to the pixel positions of the pixel of interest and the reference pixel is acquired from the average luminance map. Then, the average brightness of each reference pixel is subtracted from the average brightness of the pixel of interest, and the difference value for each RGB is calculated. Next, when the three difference values are compared with the parameter threshold value th for luminance difference determination input in step S302 and even one of the difference values is equal to or greater than the threshold value, the determination processing unit 204 considers the candidate to have a luminance difference. do. The threshold value th is preferably larger than the standard deviation σ calculated from the noise dispersion value σ2 according to the ISO sensitivity at the time of shooting, and is set as, for example, th = ασ (α = 1.5). Then, in the pixel of interest, when the number of candidates having a brightness difference from the corresponding pixel in the reference image data is more than half of the number of reference image data, the pixel of interest is finally determined as a pixel having a brightness difference. If the pixel of interest has a difference in brightness, the process proceeds to step S503, and if not, the process proceeds to step S504. Although the number of reference image data is set to half or more, the threshold value may be arbitrarily determined, for example, if it is x% or more of the number of reference image data (however, x ≧ 50), it is determined that there is a brightness difference. ..

In step S503, the determination processing unit 205 determines whether the luminance variation is due to a moving object or the luminance variation for the pixels determined to have the luminance difference in step S502, based on the variation in the average luminance. FIG. 5B is a detailed flowchart of the variation determination process. In step S601, the determination processing unit 204 acquires the variation determination parameter threshold value th2 input in step S302. The threshold value th2 is preferably calculated based on the noise dispersion value σ2 according to the ISO sensitivity at the time of shooting and the total number of pixels for each RGB in the local region. For example, in the case of R, β√ σ ² / Nr (β). = 3.0) is set. In step S602, the determination processing unit 204 selects a pixel at the same coordinates as the pixel of interest of the reference image data selected in step S501 from the reference image data as a reference pixel. In this embodiment, three reference pixels are selected. In step S603, the determination processing unit 204 acquires the average luminance corresponding to the pixel positions of the pixel of interest and all the reference pixels from the average luminance map, and calculates the standard deviations σR, σG, and σB for each RGB from the equation (1). do.

はＮフレーム分のｒ、ｇ、ｂの平均値を示している。

Indicates the average value of r, g, and b for N frames.

In step S604, the determination processing unit 204 compares the three standard deviations σR, σG, and σB calculated in step S603 with the threshold value th2. If any one of the three standard deviations σR, σG, and σB is equal to or greater than the threshold value, the process proceeds to step S605, and if not, the process proceeds to step S606. In step S605, the determination processing unit 204 determines that the pixel of interest is a moving object region, and outputs 1 to a pixel having the same coordinates as the pixel of interest in the moving object region map. In step S606, the odor determination processing unit 204 determines that the pixel of interest is a stationary region, and outputs 0 to a pixel having the same coordinates as the pixel of interest in the moving object region map. This completes the variation determination process in step S503.

In step S504, the determination processing unit 204 determines whether the processes of S502 and S503 have been completed for all the pixels of the reference image data, and if so, ends the determination process, and if not, proceeds to step S501. The above is the details of the determination process in step S304.

Hereinafter, the synthesis process executed by the synthesis processing unit 205 in step S305 in the present embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing a detailed flow of the synthesis process. In step S701, the synthesis processing unit 205 selects a pixel to be processed in the reference image data as a pixel of interest.

In step S702, the moving body area map is referred to, and it is determined whether or not the pixel of interest is the moving body area. If the pixel of interest is a moving object region, the process proceeds to step S704, and if not, the process proceeds to step S703.

In step S703, the brightness of the pixel of interest and the brightness of the three reference pixels are added and averaged, and the calculation result is output to the output image data as the brightness of the pixel of interest after the noise reduction processing. In step S704, NonLocalMeans is applied to the reference image data, and the calculation result is output to the output image data as the brightness after the noise reduction processing of the pixel of interest. In step S705, it is determined whether or not all the pixels have completed the processing of steps S702 to S704, and if it is completed, the composition processing is ended, and if not, the process proceeds to step S701. The above is the details of the synthesis process in step S306.

As described above, according to the present embodiment, only when there is an average luminance difference in the local region including the pixel of interest between a plurality of image data acquired by continuous shooting and the average luminance in each image data varies, the moving object region It is determined as a pixel of. If there is no difference in the average brightness of the local region including the pixel of interest between multiple image data acquired by continuous shooting, or if there is no variation in the average brightness for each RGB even if there is a difference in average brightness, it is judged as a moving object region. Not done. In the present embodiment, it is determined whether or not the pixel of interest is a moving object by using the average brightness of the local region including the pixel of interest. As a result, even if the image data contains a lot of noise, the influence of the noise can be reduced and the accuracy of the moving object determination can be improved. Furthermore, moving objects tend to have a larger average luminance difference than lighting fluctuations such as flicker of fluorescent lamps and blinking of lighting devices. Therefore, the moving object can be determined with high accuracy by determining whether or not there is a variation in the average luminance difference in the corresponding local region between the reference image data and the reference image data.

In the present embodiment, the region to which the NonLocalMeans method is applied has been described for the region detected as a moving body, but the region is not limited to NonLocalMeans. Since there is a high possibility that an edge is included in the region detected as a moving object, it is desirable to apply an edge-preserving noise reduction process such as NonLocalMeans. In addition to NonLocalMeans, the edge-preserving noise reduction process includes a process using a bilateral filter.

<Second Embodiment>
In the first embodiment, it has been explained that the influence of noise is reduced by determining the moving object using the average brightness in the local region including the pixel of interest. Generally, in image data, the influence of noise can be reduced by averaging the pixels included in a larger local region in a flat portion. On the other hand, if the local region is made too large, the brightness of the pixels of different subjects will be mixed and averaged when the edge portion is included, so that the accuracy of the moving object determination will be lowered. Therefore, in the present embodiment, when calculating the average brightness, a method of increasing the size S1 of the local region in the flat portion as compared with the edge portion will be described. The second embodiment has the same configuration and processing as the first embodiment, and the description thereof will be omitted.

FIG. 7 is a block diagram showing a logical configuration of the image processing apparatus according to the present embodiment. The image data input unit 801 and the parameter input unit 802, the determination processing unit 805, the composition processing unit 806, and the image data output unit 807 of FIG. 7 are the image data input unit 201, the parameter input unit 202, the determination processing unit 204, and the composition processing unit. 205, the same as the image data output unit 206.

The edge strength calculation unit 803 receives an instruction from the CPU 101, acquires image data and parameters, and generates an edge strength map showing the edge strength of each pixel for each image data based on the parameters. The generated edge strength map is stored in the RAM 102. The details of the edge strength map will be described later. The average brightness calculation unit 804 receives an instruction from the CPU 101, acquires image data, parameters, and edge strength maps, and generates an average brightness map showing the average brightness of each pixel for each image data based on the parameters and edge strength. do. The generated average luminance map is stored in the RAM 102. The details of the average luminance map will be described later. Hereinafter, details of each process in the logical configuration of the image processing apparatus described with reference to FIG. 7 will be described with reference to the flowchart shown in FIG. The process shown in FIG. 8 is realized by the CPU 101 executing the program stored in the RAM 102. A dedicated processing circuit or the like that plays a part or all of each component shown in FIG. 8 may be provided.

In the flowchart shown in FIG. 8A, steps S901, S902, and S905 to S907 are the same as steps S301, S302, and S304 to S306, respectively. In step S903, the edge strength calculation unit 803 generates an edge strength map from the reference image data. The edge intensity map is a map having a ratio of the dispersion value in the local region of the reference image data to the noise dispersion value for each sensitivity calculated in advance for each pixel. Hereinafter, the method of generating the edge strength map will be specifically described. First, in the reference image data, a local region composed of a pixel of interest and a pixel in the vicinity is set. The size S1 of the local region is determined according to the parameters as described in step S303 of the first embodiment. Next, the dispersion values VR, VG, and VB for each RGB in the local region are calculated using the equation (2).

ここで、Ｍは局所領域に含まれる画素数、ｒ、ｇ、ｂは局所領域内の画素ｉのＲＧＢ値であり、

Here, M is the number of pixels included in the local region, and r, g, and b are the RGB values of the pixels i in the local region.

は局所領域に含まれる画素のＲＧＢ毎の平均値を示している。そして、これら分散値Ｖを、撮影時のＩＳＯ感度に応じたノイズ分散値σ２で割ることで分散値の比率を算出し、これを着目画素のエッジ強度Ｅとする。具体的には、式（３）により算出する。エッジ強度は値が大きいほど、鮮鋭度が高く、逆に小さいほど鮮鋭度が低いことを示す指標である。

Indicates the average value of the pixels included in the local region for each RGB. Then, the ratio of the dispersion values is calculated by dividing these dispersion values V by the noise dispersion value σ2 according to the ISO sensitivity at the time of shooting, and this is used as the edge strength E of the pixel of interest. Specifically, it is calculated by the formula (3). The larger the value of the edge strength, the higher the sharpness, and conversely, the smaller the value, the lower the sharpness.

この処理を基準画像データの全画素について行うことでエッジ強度マップを生成する。なお、エッジ強度の算出方法はこれに限らず、ソーベルフィルタやラプラシアンフィルタなどを使用して算出するなど、エッジ強度に相当する値が算出できれば何でもよい。また、本実施形態では画素毎にＲＧＢそれぞれのエッジ強度を持つが、３つのエッジ強度のうち、最大値や最小値のみを代表のエッジ強度として１つだけエッジ強度を持たせてもよい。

An edge strength map is generated by performing this process for all pixels of the reference image data. The method for calculating the edge strength is not limited to this, and any value can be used as long as a value corresponding to the edge strength can be calculated, such as using a Sobel filter or a Laplacian filter. Further, in the present embodiment, each pixel has an edge strength of each of RGB, but of the three edge strengths, only one edge strength may be provided with only the maximum value or the minimum value as a representative edge strength.

In step S904, the average luminance calculation unit 804 generates an average luminance map for each of the reference image data and each reference image data. FIG. 8B is a flowchart showing a detailed flow of the average luminance map generation process. In step S1001, the average luminance calculation unit 804 acquires the parameter th3 for generating the average luminance map input in step S302. In step S1002, the average luminance calculation unit 804 selects the pixel of interest to be processed from the reference image data input in step S901.

In step S1003, the average brightness calculation unit 804 determines the size of the local region for which the average brightness is calculated based on the edge intensity map. When the edge strength is small, the average brightness is calculated with a size S2 larger than the size S1 when the edge strength map is generated. Specifically, first, the number of pixels whose edge strength is the parameter th3 or less is counted for each pixel of the edge strength map and a local region (here, a block of 9 × 9 pixels) including the peripheral region thereof. Next, when the total number of pixels in the local region is y% (y = 80 in this case) or more, it is determined that the pixel of interest is a flat portion, and the size S2 is determined so that size S2> size S1. ..

In step S1004, the average luminance calculation unit 804 calculates the average luminance based on the size S of the local region determined in step S1002. Step S1005 determines whether or not all the pixels have completed the processes of steps S1002 to S1004, and if so, ends the synthesis process, and if not, proceeds to step S1001. In the present embodiment, the average brightness of the local region is calculated using two sizes, sizes S1 and S2, but the average brightness is calculated according to each size by setting a threshold value more finely and using a plurality of sizes. May be calculated to generate an average luminance map.

<Other Embodiments>
In the present embodiment, the head image data of the image data obtained by continuous shooting is used as the reference image data, but the present invention is not limited to this. For example, the image data having the largest total edge strength of each image data may be used as the reference image data.

Further, in the present embodiment, an example of acquiring a plurality of image data in a continuous shooting mode in which one shot is taken four times in a row has been described. However, for example, a moving image may be taken and a plurality of frames may be acquired as image data. In this case, it is desirable that they are continuous in chronological order. Alternatively, the configuration may be such that a plurality of images are acquired for image processing in one shooting instead of the continuous shooting mode.

The present invention supplies a program that realizes one or more functions of the above-described embodiment to a system or device via a network or storage medium, and one or more processors in the computer of the system or device reads and executes the program. It can also be realized by the processing to be performed. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

Claims (7)

An image processing device that detects a moving object region in reference image data, which is one of the N image data, using N image data (natural numbers satisfying N> 3).
An acquisition means for acquiring the N image data and
For each of the N image data, a first calculation means for calculating the average luminance in a local region composed of a plurality of pixels including the pixel of interest as the average luminance of the pixel of interest.
Luminance difference for determining whether or not there is a luminance difference between the average luminance of the pixel of interest in the reference image data and the average luminance of the pixel of interest in each of the image data other than the reference image data, which is equal to or greater than the first threshold value. Judgment means and
A second calculation means for calculating the standard deviation of the average luminance corresponding to the pixel of interest in each of the N image data, and
A comparison means for comparing the standard deviation of the average brightness of the pixel of interest with the second threshold value, and
It has a moving object determining means for determining whether or not the pixel of interest is a pixel included in the moving object region based on the determination result by the luminance difference determining means and the comparison result by the comparing means.
When the moving object determination means determines that the pixel of interest has a luminance difference by the luminance difference determining means and the standard deviation is equal to or greater than the second threshold value, the pixel of interest is a pixel included in the moving object region. An image processing device characterized in that it is determined to exist. The comparison means is characterized in that the standard deviation of the average brightness of the pixel of interest is compared with the second threshold value only for the pixels determined by the luminance difference determination means to have a luminance difference. The image processing apparatus according to. Further, the reference image data has a third calculation means for calculating the edge strength for each pixel.
The first calculation means according to claim 1 or 2, wherein the size of the local region of the pixel of interest is set according to the edge strength of the pixel of interest calculated by the third calculation means. The image processing apparatus described. The third calculation means calculates the edge intensity by the ratio of the noise dispersion for each sensitivity set when the reference image data is captured and the noise dispersion calculated for each local region of the reference image data. The image processing apparatus according to claim 3, wherein the image processing apparatus is characterized by the above. The image processing apparatus according to any one of claims 1 to 4, wherein the N image data are images acquired by continuous shooting. An image processing method for detecting a moving object region in reference image data, which is one of the N image data, using N image data (natural numbers satisfying N> 3).
The N image data are acquired, and the image data is acquired.
For each of the N image data, the average brightness in the local region composed of a plurality of pixels including the pixel of interest is calculated as the average brightness of the pixel of interest.
It is determined whether or not there is a luminance difference of the first threshold value or more between the average luminance of the pixel of interest in the reference image data and the average luminance of the pixel of interest in each of the image data other than the reference image data.
The standard deviation of the average brightness corresponding to the pixel of interest in each of the N image data was calculated.
Comparing the standard deviation of the average brightness of the pixel of interest with the second threshold value,
When the luminance difference determining means determines that the pixel of interest has a luminance difference and the standard deviation is equal to or greater than the second threshold value, it is determined that the pixel of interest is a pixel included in the moving body region. Characteristic image processing method. A program for operating a computer as an image processing device according to any one of claims 1 to 5.

Images