Image analysis system and image analysis method

Abstract

Provided are an image analysis system and an image analysis method for making it possible to extract, at a high speed, groups of pixels each having a fluctuation according to the same probability distribution. An image analysis system 10 includes: a similarity calculation unit 11 for calculating similarities between the representative distributions indicating clusters and the distributions of pixels in the clusters; a representative calculation unit 12 for calculating the distribution of a plurality of pixels in each of the clusters as a representative distribution of the cluster; and a division unit 13 for, by referring to each of the similarities, assigning pixels in an input image to one of the plurality of clusters.

Description

[Technical Field]

[0001] The present invention relates to an image analysis system and an image analysis method that can be applied to image analysis based on radar images and the like. [Background technology]

[0002] Synthetic Aperture Radar (SAR) technology is a technology in which a radar mounted on a flying object such as a satellite or aircraft transmits and receives electromagnetic waves while the flying object is moving, and obtains images (hereinafter referred to as SAR images) equivalent to images obtained by an antenna with a large aperture. Synthetic aperture radar is used, for example, to analyze ground displacements by processing the signals of waves reflected from the ground surface. Note that the ground surface includes not only the ground but also the surface (top) on which low structures such as buildings exist.

[0003] An image taken by a flying object such as a satellite is called a radar image. An SAR image is an example of a radar image. Hereinafter, the flying object that transmits and receives electromagnetic waves will be referred to as a satellite, but the flying object is not limited to a satellite.

[0004] One example of image analysis is interferometry, which investigates displacement, elevation, etc. based on the phase difference between multiple SAR images. Another example of image analysis is change detection, which detects changes or abnormalities on the ground based on changes in intensity. Note that these are just examples of image analysis, and the field of image analysis is diverse.

[0005] SAR images capture natural and man-made objects with a variety of characteristics. Therefore, the pixel values ​​of each of the multiple pixels in a SAR image may have different characteristics depending on the object that the pixel captures. In particular, it is known that the stochastic variation in pixel values, or noise, has different characteristics depending on the type of object. Therefore, there is a problem that the results of image analysis will be inaccurate if characteristics dependent on the type of object are not taken into consideration.

[0006] Extracting statistically homogeneous pixels is useful for solving such problems. For example, Patent Document 1 describes a technique for extracting statistically homogeneous pixels. A pixel identification device to which this technique is applied sets a window of a predetermined size in an SAR image. The pixel identification device sets one pixel in the window as a pixel of interest. The pixel identification device determines whether pixels in the vicinity of the pixel of interest are statistically homogeneous pixels relative to the pixel of interest. The pixel identification device sequentially sets each of all pixels in the window as a pixel of interest and performs a determination process.

[0007] In the determination process, the pixel identification device calculates a vector containing N amplitude or intensity values ​​for a pixel of interest determined in N SAR images (N: a natural number equal to or greater than 2). The pixel identification device defines a window for the pixel of interest. For all pixels included in the window, the pixel identification device compares the vectors of each neighboring pixel (number of elements: N) with the vector of the pixel of interest using a statistical test. The pixel identification device uses the Kolmogorov-Smirnov test (KS test) as the statistical test.

[0008] That is, the pixel identification device uses a KS test to compare a cumulative density function created from N observations (corresponding to N SAR images) of a pixel of interest with a cumulative density function created for each neighboring pixel. Note that the cumulative density function is almost synonymous with the cumulative distribution function (CDF), but strictly speaking, it corresponds to the estimated CDF based on observed values. It is also possible to express the cumulative density function as a function obtained by interpolating cumulative relative frequency.

[0009] The pixel identification device extracts neighboring pixels that are directly or indirectly continuous with the pixel of interest from among neighboring pixels determined to be similar to the pixel of interest. The pixel identification device ultimately determines that the extracted neighboring pixels are statistically homogeneous with the pixel of interest. Specifically, if the maximum absolute value of the difference between the cumulative density function for the pixel of interest and the cumulative density function for the neighboring pixels is smaller than a predetermined threshold, the pixel identification device considers the pixel of interest and the neighboring pixels to follow the same probability distribution, i.e., to be generated by the same probability density function, and determines that the neighboring pixels are statistically homogeneous with the pixel of interest. [Prior art documents] [Patent documents]

[0010] [Patent Document 1] International Publication No. 2010 / 112426 Summary of the Invention [Problem to be solved by the invention]

[0011] According to the technology described in Patent Document 1, a statistically homogeneous pixel group can be extracted from an SAR image.

[0012] However, the pixel identification device described in Patent Document 1 requires a huge amount of calculation time because it compares each of a large number of target pixels with all pixels in the window, which means that it takes a long time to obtain a statistically homogeneous pixel group.

[0013] An object of the present invention is to provide an image analysis system and an image analysis method that can quickly extract multiple pixel groups from an image. [Means for solving the problem]

[0014] The image analysis system according to the present invention includes a similarity calculation means for calculating the similarity between a representative distribution representing a cluster and the distribution of pixel values ​​within the cluster, a representative calculation means for calculating the distribution for a plurality of pixels in each cluster as a representative distribution, and a division means for assigning pixels in an input image to one of a plurality of clusters by referring to the similarity.

[0015] The image analysis method according to the present invention calculates the similarity between a representative distribution representing a cluster and the distribution of pixel values ​​within the cluster, calculates the distribution for multiple pixels in each cluster as the representative distribution, and assigns pixels in the input image to one of the multiple clusters based on the similarity.

[0016] The image analysis program according to the present invention causes a computer to calculate the similarity between a representative distribution representing a cluster and the distribution of pixel values ​​within the cluster, calculate the distribution for multiple pixels in each cluster as a representative distribution, and assign pixels in an input image to one of multiple clusters based on the similarity. [Effects of the Invention]

[0017] According to the present invention, a plurality of pixel groups can be extracted from an image at high speed. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a block diagram showing an image analysis device according to a first embodiment; [Figure 2] 4 is a flowchart showing the operation of the image analysis device of the first embodiment. [Figure 3] 10 is an explanatory diagram for explaining a specific example of the processing of a division unit, a similarity calculation unit, and a representative calculation unit. FIG. [Figure 4] FIG. 10 is an explanatory diagram for explaining a specific example of processing by a representative calculation unit. [Figure 5] 10 is a flowchart illustrating an example of an operation of a representative calculation unit. [Figure 6] FIG. 10 is a block diagram showing an image analysis device according to a second embodiment. [Figure 7] 10 is a flowchart showing the operation of the image analysis device of the second embodiment. [Figure 8] FIG. 10 is an explanatory diagram showing an example of a search range. [Figure 9] FIG. 10 is an explanatory diagram showing another example of the search range. [Figure 10] FIG. 10 is a block diagram showing an image analysis device according to a third embodiment. [Figure 11] 10 is a flowchart showing the operation of the image analysis device of the third embodiment. [Figure 12] FIG. 10 is a block diagram showing an image analysis device according to a fourth embodiment. [Figure 13] 10 is a flowchart showing the operation of the image analysis device of the fourth embodiment. [Figure 14] FIG. 10 is a block diagram showing an image analysis device according to a fifth embodiment. [Figure 15] FIG. 1 is a block diagram showing an image analysis system according to a first embodiment. [Figure 16] FIG. 10 is a block diagram showing an image analysis system according to a modified example of the first embodiment. [Figure 17] FIG. 10 is a block diagram showing an image analysis system according to a second embodiment. [Figure 18] FIG. 10 is a block diagram showing an image analysis system according to a third embodiment. [Figure 19] 10 is a flowchart showing the operation of the image analysis system according to the third embodiment. [Figure 20] FIG. 1 is a block diagram illustrating an example of a computer having a CPU. [Figure 21] FIG. 1 is a block diagram showing the main parts of an image analysis system. DETAILED DESCRIPTION OF THE INVENTION

[0019] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In each embodiment described below, an SAR image is taken as an example of a radar image obtained using electromagnetic waves. However, the radar image is not limited to an SAR image. For example, the radar image may be an optical image.

[0020] Embodiment 1. 1 is a block diagram showing an image analysis device according to a first embodiment. The image analysis device 101 according to the first embodiment includes a division unit 110, a representative calculation unit 120, and a similarity calculation unit 130. The image analysis device 101 can input SAR images from an SAR image storage unit 200.

[0021] The image analysis device 101 of the first embodiment is an image analysis device (similar pixel extraction device) in an image analysis system that extracts similar pixels in an SAR image. Note that in other embodiments described later, the image analysis device also constitutes a similar pixel extraction device that extracts similar pixels in an SAR image.

[0022] The SAR image storage unit 200 stores N SAR images (for example, N=10 to 30) taken of the same area. In other words, the SAR image storage unit 200 stores N SAR images that capture a common analysis area. Hereinafter, the SAR images (SAR image group) stored in the SAR image storage unit 200 will also be referred to as input SAR images or input SAR image group. The SAR images are aligned so that pixels at the same position in each SAR image correspond to pixels of the same point or feature.

[0023] In Figure 1, the arrows simply indicate the flow of signals (data), but are not intended to exclude bidirectionality. This also applies to other block diagrams.

[0024] The N SAR images are radar images of the same area, but are radar images acquired at different times or on different trajectories. The SAR images stored in the SAR image storage unit 200 may be images acquired at different times but on the same trajectory. Alternatively, the multiple SAR images may be images acquired at the same time but on different trajectories. Furthermore, the multiple SAR images may be images acquired at different times and on different trajectories.

[0025] The imaging conditions (acquisition time, angle of incidence, band, etc.) are not limited to the conditions at the time of actual imaging, but may be artificially synthesized. For example, in an imaging method called polarized SAR, characteristics dependent on the electric field direction of the electromagnetic waves can be obtained by controlling conditions (polarized imaging conditions) such as the electric field direction of the irradiated electromagnetic waves and the sensitivity and phase delay of the electric field direction of the antenna when receiving the electromagnetic waves. With this imaging method, it is possible to reproduce an image taken under any polarization conditions by synthesizing two or three images taken under different polarization conditions.

[0026] Furthermore, even with a normal SAR that is not a polarized SAR, an image of only a portion of the band can be extracted by performing a conversion process to the frequency domain, such as a Fourier transform, on the captured SAR image and then performing a filter process to extract a portion of the band. The filter process to extract a portion of the band may be a process to randomly extract a portion, or a filter process to randomly exclude a portion.

[0027] By using the above-mentioned method, it is possible to construct a group of SAR images taken in multiple different bands. In other words, it is possible to construct a group of SAR images by generating images under imaging conditions that are not physically used.

[0028] In the following, we will take as an example a case where the dividing unit 110, the similarity calculation unit 130, and the representative calculation unit 120 use, as pixel values, absolute values ​​of the complex values ​​possessed by each pixel of the SAR, or values ​​obtained by converting those absolute values ​​using a method described below.

[0029] The dividing unit 110 allocates the pixels of the SAR image to one of the plurality of clusters by referring to the similarity calculated by the similarity calculation unit 130. Note that there may be pixels that are allocated across a plurality of clusters.

[0030] The representative calculation unit 120 calculates a distribution of a plurality of pixels in a cluster as a representative distribution (a representative distribution representing the cluster). As an example, the representative calculation unit 120 calculates a distribution that is similar to all pixels in each cluster as the representative distribution of the cluster.

[0031] The similarity calculation unit 130 calculates the similarity between the distribution (representative distribution) as a representative for each cluster calculated by the representative calculation unit 120 and the distribution of each pixel value in the SAR image. The distribution is, for example, a probability density function or its estimated value. However, other formats, such as probability distribution parameters or cumulative density functions, may be used as long as it can be determined that a pixel is statistically homogeneous with other pixels. The similarity calculation unit 130 determines that the two are similar when, for example, the difference (or the maximum absolute value of the difference) between the two distributions (such as cumulative density distributions) is equal to or less than a predetermined value.

[0032] Next, the operation of the image analysis device 101 will be described with reference to the flowchart of FIG. 2 and the explanatory diagram of FIG.

[0033] The dividing unit 110 divides the SAR image into a plurality of initial clusters (step S100). The division method is arbitrary. As an example, the dividing unit 110 creates a plurality of initial clusters so that each cluster has the same area.

[0034] In step S101, the dividing unit 110 assigns each pixel of the input SAR image to one of the clusters based on the similarity calculated in the previous processing loop (the processing of steps S102 and S103). That is, the dividing unit 110 creates multiple clusters.

[0035] The representative calculation unit 120 calculates a distribution that represents each cluster, i.e., a representative distribution of each cluster (step S102). The similarity calculation unit 130 calculates the similarity between the representative distribution and the distribution of each pixel value in each cluster for each cluster (step S103).

[0036] If the termination condition is not met, the process returns to step S101 (step S104). If the termination condition is met, the image analyzing device 101 terminates the process (step S104). The termination condition is met, for example, when the processes of steps S101 to S103 are executed a predetermined number of times. The termination condition may be met when the shape of each cluster created in the process of step S101 is no longer significantly different from the shape of each cluster created in the process executed last time (in the previous processing loop). The termination condition may also be met when the calculated similarity of each pixel is no longer significantly different from the similarity of corresponding pixels calculated in the previous processing loop. Note that each cluster determined when the termination condition is met corresponds to a cluster that satisfies the criterion for determining that it is homogeneous.

[0037] A specific example of the processing by the dividing unit 110, the representative calculation unit 120, and the similarity calculation unit 130 will be described with reference to the explanatory diagram of Fig. 3. Fig. 3 shows an example in which a SAR image includes a soil area s, a grass area l, and a road area r.

[0038] The top row of Figure 3 illustrates the generation of three rectangular clusters a, b, and c as initial clusters, with their respective representative distributions A, B, and C shown in bold. The other dashed lines show examples of the distribution of cluster members (i.e., pixels).

[0039] As illustrated in the second row from the top in FIG. 3, the dividing unit 110 collects pixels having a distribution similar to the representative distribution of the cluster (pixels that make the difference in distribution equal to or less than a predetermined value) and constructs a new cluster.

[0040] The representative calculation unit 120 recalculates the representative distribution for each new cluster, as illustrated in the third row from the top in Fig. 3. The similarity calculation unit 130 uses the recalculated representative distribution to calculate the similarity (new similarity) between the representative distribution and the distribution of pixel values ​​within the cluster. Then, the division unit 110 performs processing to create new clusters based on the new similarity.

[0041] The bottom row of Figure 3 shows examples of clusters a, b, and c when the termination condition is met, as well as examples of representative distributions A, B, and C and member distributions. As shown in the bottom row of Figure 3, when the termination condition is met, the representative distribution and the member distribution are similar.

[0042] Next, a specific example of the processing of the representative calculation unit 120 will be described with reference to the explanatory diagram of FIG.

[0043] In the example shown in Fig. 4, the representative calculation unit 120 calculates a representative distribution by averaging the distribution of pixel values ​​possessed by each member for all members. This is realized by creating an array by combining the sets of pixel values ​​possessed by each member for all members, and estimating (calculating) the distribution of pixel values ​​contained in the array, as shown in Fig. 4. Fig. 4 exemplarily shows that five pixels indicated by circles are combined.

[0044] As a method of estimating the distribution of the combined array, the representative calculation unit 120 can obtain the average of the histograms of each pixel by using, for example, a histogram for the array or a normalized version of the histogram (see (i) in FIG. 4). Alternatively, the representative calculation unit 120 may estimate (calculate) the representative distribution of the combined array using a kernel density function (see (ii) in FIG. 4). Furthermore, the representative calculation unit 120 can estimate (calculate) the representative distribution as the average of the cumulative density function, which is an estimate of the cumulative density distribution, by obtaining the cumulative frequency for the combined array and normalizing it (see (iii) in FIG. 4).

[0045] Furthermore, the representative calculation section 120 may estimate the median or the like as the representative distribution, instead of using the average for all members of the histogram, kernel density function, or cumulative density function.

[0046] 5 is a flowchart showing the process of obtaining an average cumulative density function when the representative calculation unit 120 uses the average cumulative density function. In the following description, the number of SAR images is set to N. The number of clusters is set to C. The number of members (number of pixels) of a cluster is set to K_c.

[0047] The representative calculation unit 120 stores the value of each pixel (pixel value) in a cluster in one array (step S121). In this example, the size of the array of cluster c (c=1 to C) is N×K_c. The representative calculation unit 120 rearranges the contents of the array in ascending order (step S122). Then, the representative calculation unit 120 calculates the cumulative density by dividing the element number (the number indicating the smallest number) by the size of the array (step S123).

[0048] The representative calculation unit 120 obtains a function that outputs a cumulative density for the values ​​of the array as a step function obtained by nearest neighbor interpolation (step S124). Note that the representative calculation unit 120 may derive another interpolation function instead of the step function as a function that outputs a cumulative density.

[0049] Note that nearest neighbor interpolation uses the value of the pixel at the closest position as the value of a given pixel, and as a result, nearest neighbor interpolation results in a step function that takes a constant value within a certain range.

[0050] Here, it should be noted that the cumulative density function obtained by the processing of steps S121 to S124 is roughly the same as the cumulative density function estimated from N pixel values ​​extracted as common pixels in N images for each of the K_c pixels and then averaged. Therefore, here, it is expressed as an average cumulative density function.

[0051] According to the process illustrated in Fig. 5, a cumulative density function can be obtained at high speed by using nearest neighbor interpolation, etc. In particular, when the function outputting the cumulative density is obtained as a step function, integral calculations can be replaced with summation calculations for the number of steps in the similarity calculation. In other words, the similarity calculation is also speeded up.

[0052] To simplify the cumulative density calculation, after pixel values ​​are stored in an array in step S121, the representative calculation unit 120 may randomly select several pixel values ​​to be processed in step S122. To simplify the cumulative density calculation, after the contents of the array are sorted in ascending order in step S122, the representative calculation unit 120 may select pixel values ​​to be processed in step S123 from the array at predetermined intervals. Adding such processing can eliminate increases and decreases in the amount of calculation that depend on the size of the cluster. As a result, when the image analysis device is implemented by a computer, excessive computer load and wasted computer capacity can be prevented. It is also possible to reduce the capacity required for memory that temporarily stores processing results.

[0053] Next, a description will be given of an example of processing by the similarity calculation unit 130. The similarity calculation unit 130 uses an index of distribution similarity to compare the distribution of each pixel value in the SAR image group with the representative distribution of each cluster.

[0054] Comparison methods using distribution similarity include, for example, comparing the distributions themselves, such as the distance between histograms or kernel density functions. The comparison method may also be a method comparing the distance obtained by defining the inner product of cumulative density functions, such as maximum mean discrepancy. Nonparametric tests that calculate the distance between cumulative density distributions, such as the Kolmogorov-Smirnov test, Cramer-von Mises test, Anderson-Darling test, or Wasserstein distance, may also be used. Furthermore, methods that calculate the distance between distribution parameters (e.g., mean, variance, etc.), the distance between moments, or the distance between moment-like distribution features may also be used.

[0055] When the function that outputs the cumulative density as described above is obtained as a step function, similarity calculation can be performed at high speed by using a method of calculating the cumulative density function as an unequal step function.

[0056] When the Kolmogorov-Smirnov test statistic is used, the maximum absolute value of the difference between the compared objects is used to determine whether the compared objects are similar. When the Wasserstein distance is used, the integral of the absolute value of the difference between the compared objects is used to determine whether the compared objects are similar. When the Cramer-von Mises test is used, the integral of the squared absolute value of the difference between the compared objects is used to determine whether the compared objects are similar. When the Anderson-Darling test is used, the weighted integral of the absolute value of the difference between the compared objects is used to determine whether the compared objects are similar.

[0057] The similarity calculation unit 130 may use other similarity indices in combination with the distribution similarity index. For example, the similarity calculation unit 130 can achieve this combination by adding or multiplying the distance between each pixel in the cluster and a pixel to be compared (in this example, a representative pixel corresponding to the representative distribution).

[0058] The representative calculation unit 120 and the similarity calculation unit 130 use absolute values ​​of pixel values ​​of the SAR image, but may also use data that has been modified. Examples of such modifications include gamma correction and monotonic logarithmic correction. By performing such modifications, the dynamic range of the absolute values ​​of the pixel values ​​of the SAR image can be reduced, making it easier to compare them as distributions and reducing the likelihood of a decrease in the accuracy of floating-point calculations. Furthermore, after reducing the dynamic range, the absolute values ​​of the pixel values ​​may be quantized into integers, and calculations related to distribution comparison may be performed using integer calculations, thereby speeding up processing. This also applies to other embodiments.

[0059] Embodiment 2. 6 is a block diagram showing an image analysis device according to the second embodiment. The image analysis device 102 according to the second embodiment includes a division unit 110, a representative calculation unit 120, a similarity calculation unit 130, and a region limiting unit 140. The image analysis device 102 can input SAR images from an SAR image storage unit 200. The functions of the components in the image analysis device 102 other than the region limiting unit 140 are the same as the functions of the components in the image analysis device 101 according to the first embodiment shown in FIG. 1. However, in this embodiment, the representative calculation unit 120 also performs processing to determine the position of a representative pixel in a cluster (representative pixel position).

[0060] The region limiting unit 140 limits the range (region) of pixels whose distribution is compared with the representative distribution to a predetermined range.

[0061] Next, the operation of the image analysis device 102 will be described with reference to the flowchart of FIG.

[0062] The dividing unit 110 divides the SAR image into a plurality of initial clusters (step S100), as in the first embodiment. As in the first embodiment, in step S101, the dividing unit 110 assigns each pixel of the input SAR image to one of the clusters based on the similarity calculated in the previous processing loop (in this embodiment, the processing of steps S201 to S203). In other words, the dividing unit 110 creates a plurality of clusters.

[0063] The representative calculation unit 120 calculates the representative distribution of each cluster and also calculates the representative pixel position of each cluster (step S201).

[0064] The representative pixel position is a position that indicates where the pixels within a cluster are distributed. For example, the representative pixel position is the average position of the pixels within the cluster, such as the center of gravity. The representative pixel position may also be the position of a single point that represents the cluster, such as the center of a circle with a minimum radius or a square that encloses the pixels of the cluster. Alternatively, the representative pixel position may be the positions of multiple pixels included in the cluster.

[0065] The region limiting section 140 limits the search range, which is the processing range of the similarity calculation section 130, based on the representative pixel position output by the representative calculation section 120 (step S202).

[0066] The region limiting unit 140 may, for example, define the search range as a region within a certain distance from the representative pixel position of the cluster. The distance may be, for example, Euclidean distance, Chebyshev distance, or Manhattan distance, but other types of distances may also be used.

[0067] When expressing a pixel position, the row number and column number of the pixel can be used as the coordinates of the pixel position. Alternatively, the pixel size may be expanded or reduced in advance based on the geographical scale to convert it so that distance on the ground can be roughly calculated. Furthermore, the coordinates may be corrected for distortion based on the satellite position at the time of SAR image capture and the unevenness of the ground, allowing precise distance on the ground to be calculated.

[0068] Fig. 8 is an explanatory diagram showing an example of a search range. Fig. 8 shows an example in which the search range is an area within a predetermined Chebyshev distance from representative pixel position A. In Fig. 8, small circles indicate pixels. The large, shaded circle indicates representative pixel position A. The other large circles indicate representative pixel positions. The area indicated by dots is the search range.

[0069] When determining only one representative pixel position for each cluster, the region may be limited using a graph connecting the representative pixel positions. Fig. 9 is an explanatory diagram showing another example of the search range. In the example shown in Fig. 9, a graph connecting the representative pixel positions of adjacent clusters is generated. Then, the region for a certain cluster is limited to the inside of a polygon formed by the representative pixel positions connected by a predetermined number of sides or less.

[0070] Figure 9 shows an example of region division using a Delaunay diagram. In Figure 9, small circles represent pixels, and large circles represent representative pixel positions. If the large circle with diagonal lines is set to representative pixel position B, the polygonal region formed by other representative pixel positions connected to representative pixel position B by one side is determined as the search region.

[0071] By limiting the search area, when the image analysis device is implemented by a computer, the amount of calculation by the similarity calculation unit 130 can be reduced. For example, if the area is limited to the inside of a polygon formed by generating a graph using a Delaunay diagram and connecting the representative pixel positions with one edge, each pixel will be included in the search area of ​​approximately three clusters. In this case, the number of calculations of distribution similarity for the number of pixels K_c will be approximately 3K_c.

[0072] Furthermore, when the clusters are arranged at equal intervals, the amount of calculation required in this embodiment is often less than the number of times N×K_c that the distribution similarity is calculated when comparing the number of clusters C with all pixels K_c in the first embodiment.

[0073] The same is true when limiting the search area to within a certain distance from the representative pixel position. If the interval between the representative pixel positions of the clusters is L and the search area is 2L, the number of times the distribution similarity is calculated is almost less than 4K_c, and the amount of calculation is significantly reduced.

[0074] Embodiment 3. 10 is a block diagram showing an image analysis device according to the third embodiment. The image analysis device 103 according to the third embodiment includes a division unit 110, a representative calculation unit 120, a similarity calculation unit 130, and an outlier detection unit 150. The image analysis device 103 can input SAR images from an SAR image storage unit 200. The functions of the components in the image analysis device 103 other than the outlier detection unit 150 are the same as the functions of the components in the image analysis device 101 according to the first embodiment shown in FIG. 1.

[0075] As described above, the dividing unit 110 collects pixels having a distribution similar to the representative distribution of the cluster to construct a new cluster. The similarity calculation unit 130 calculates the similarity between the representative distribution and the distribution of pixel values ​​in the SAR image for each cluster. For each cluster, if the similarity calculated by the similarity calculation unit 130 is large (different) from any of the clusters compared to the representative distribution, the outlier detection unit 150 determines that the distribution of pixel values ​​is an outlier. For example, if the difference between the similarity calculated by the similarity calculation unit 130 and the representative distribution is equal to or greater than a predetermined value, the outlier detection unit 150 determines that the similarity differs from the representative distribution and determines that the distribution of pixel values ​​is an outlier. The dividing unit 110 excludes outliers from the targets for determining whether the distribution is similar to the representative distribution of the cluster.

[0076] As a result, the representative calculation unit 120 is not affected by outliers, and the cluster creation process by the division unit 110 becomes more accurate. In a SAR image, a few isolated pixels may have reflectance characteristics that differ from all other pixels, but the outlier detection unit 150 can eliminate the influence of such situations.

[0077] Next, the operation of the image analysis device 103 will be described with reference to the flowchart of FIG.

[0078] The dividing unit 110 divides the SAR image into a plurality of initial clusters (step S100), as in the first embodiment. In step S301, the dividing unit 110 assigns each pixel of the input SAR image to one of the clusters based on the similarity calculated in the previous processing loop (in this embodiment, the processing of steps S102 to S103). That is, the dividing unit 110 creates a plurality of clusters. Note that in this embodiment, the dividing unit 110 excludes outliers from the targets for determining whether or not they have a distribution similar to the representative distribution of the cluster.

[0079] The similarity calculation unit 130 calculates a distribution that represents each cluster, that is, a representative distribution of each cluster (step S102). The representative calculation unit 120 calculates the similarity between the representative distribution and the distribution of pixel values ​​within each cluster (step S103).

[0080] As described above, the outlier detection unit 150 determines that pixel as an outlier (step S301).

[0081] Embodiment 4. 12 is a block diagram showing an image analysis device according to the fourth embodiment. The image analysis device 104 according to the fourth embodiment includes a division unit 110, a representative calculation unit 120, a similarity calculation unit 130, and an isolated pixel determination unit 160. The image analysis device 104 can receive SAR images from an SAR image storage unit 200. The functions of the components in the image analysis device 104 other than the isolated pixel determination unit 160 are the same as the functions of the components in the image analysis device 101 according to the first embodiment shown in FIG.

[0082] The isolated pixel determination unit 160 determines that a pixel that has a particularly different distribution compared with neighboring pixels is an isolated pixel.

[0083] An isolated pixel may be, for example, a pixel with a large value obtained by dividing the average reflection intensity by the standard deviation of the reflection intensity. Pixels with such characteristics are known to occur in window frames, corners of staircases, and points where multiple steel beams intersect. In many cases, the distribution of pixel values ​​of an isolated pixel is characterized by being dissimilar to the distribution of pixel values ​​of surrounding pixels. Furthermore, in order to compare the distribution of pixel values ​​of surrounding pixels, the isolated pixel determination unit 160 may compare the distribution of pixel values ​​of a given pixel with the distributions of multiple neighboring pixels, and if the proportion of the distributions of pixel values ​​of the multiple neighboring pixels that are dissimilar to the distribution of pixel values ​​of the given pixel is small (for example, 1 / 4 or less), the given pixel may be determined to be an isolated pixel.

[0084] Next, the operation of the image analysis device 104 will be described with reference to the flowchart of FIG.

[0085] The dividing unit 110 divides the SAR image into a plurality of initial clusters in the same way as in the first embodiment (step S100). The isolated pixel determining unit 160 determines isolated pixels in the SAR image by the method described above (step S401).

[0086] In step S402, the dividing unit 110 assigns each pixel of the input SAR image to one of the clusters based on the similarity calculated in the previous processing loop (in this embodiment, the processing of steps S102 to S103). That is, the dividing unit 110 creates multiple clusters. Note that in this embodiment, the dividing unit 110 excludes isolated pixels from the targets for determining whether or not they have a distribution similar to the representative distribution of the cluster.

[0087] In this embodiment, the representative calculation unit 120 is not affected by isolated pixels, so the cluster creation process by the division unit 110 becomes more accurate.

[0088] Embodiment 5. 14 is a block diagram showing an image analysis device according to the fifth embodiment. The image analysis device 105 according to the fifth embodiment includes a division unit 110, a representative calculation unit 120, a similarity calculation unit 130, and a similarity synthesis unit 170. The image analysis device 105 can receive SAR images from an SAR image storage unit 200. The functions of the components in the image analysis device 105 other than the similarity synthesis unit 170 are the same as the functions of the components in the image analysis device 101 according to the first embodiment shown in FIG. 1. The similarity synthesis unit 170 calculates the similarity between pixels belonging to a certain cluster and pixels belonging to another cluster (specifically, the similarity in the distribution of pixel values), and stores the calculated similarity in, for example, a similarity storage unit 300.

[0089] As an example, the similarity combination unit 170 calculates the similarity between a pixel P belonging to a certain cluster and a pixel Q belonging to another cluster, both of which are similar to each other, in a cluster R. Specifically, the similarity combination unit 170 calculates the similarity by comparing the distribution of pixel P with a representative distribution of cluster R. The similarity combination unit 170 also calculates the similarity by comparing the distribution of pixel Q with a representative distribution of cluster R. The method of comparison by the similarity combination unit 170 may be the same as the method of comparison by the similarity calculation unit 130.

[0090] The similarity combining unit 170 further adds the two calculated similarities together to obtain the similarity between the distribution of pixel P and the distribution of pixel Q.

[0091] This embodiment is effectively utilized when the distribution similarity between two pixels within an arbitrary distance is required. That is, the distribution similarity between two pixels is obtained by combining (adding, for example) similarities with pre-calculated clusters, so that the distribution similarity between two pixels can be immediately provided.

[0092] In this embodiment, the similarity synthesis unit 170 is added to the first embodiment, but the similarity synthesis unit 170 may be added to the second to fourth embodiments. [Example]

[0093] A specific example of an image analysis system to which the image analysis device (similar pixel extraction device) realized in the above embodiment is applied will be described below.

[0094] Example 1 15 is a block diagram showing an image analysis system according to a first embodiment. The image analysis system 401 according to the first embodiment includes an image analysis device 101, an interference analysis unit 410, and a statistics calculation unit 411. Note that the image analysis devices 102 to 105 according to the second to fifth embodiments may be used instead of the image analysis device 101. The image analysis devices 102 to 105 according to the second to fifth embodiments may also be used in the following second and third embodiments.

[0095] The interference analysis unit 410 extracts two or more images from the SAR image group and calculates the phase difference between the two images by, for example, multiplying one of the two images by the complex conjugate of the other image. Furthermore, the interference analysis unit 410 receives information capable of identifying a cluster from the division unit 110. The statistics calculation unit 411 obtains the complex correlation between the two images for each cluster. The statistics calculation unit 411 then calculates a complex correlation matrix, which is a matrix representation of the complex correlations for all sets of input SAR images. The complex correlation matrix is ​​also referred to as a coherence matrix. The statistics calculation unit 411 only needs to calculate statistics (in this example, coherence rows) for at least one cluster.

[0096] The statistics calculation unit 411 stores, for example, statistics for each cluster in the correlation storage unit 500. The statistics (hereinafter also referred to as characteristics) may be, for example, a complex average of a simple complex correlation. The statistics calculation unit 411 may perform a process of normalizing the complex average by the intensity root mean square. The statistics calculation unit 411 may calculate a robust estimation value of the correlation matrix. That is, the statistics calculation unit 411 may use a robust estimation method for the correlation matrix. For the robust estimation method for the correlation matrix, a minimum covariance determinant or the like can be used.

[0097] The statistical calculation unit 411 may store the characteristics of each cluster together with associated information of the cluster in the correlation storage unit 500. The associated information is, for example, information indicating the position of the cluster in the SAR image or the position of the cluster on a map. The information indicating the position of the cluster represents, for example, the position of a representative pixel (e.g., a central position) in the cluster. The information indicating the position of the cluster may be information that can identify the area occupied by the cluster in the SAR image. The information that can identify the area occupied by the cluster is, for example, information including the position of a representative pixel in the cluster and the size of the cluster (e.g., a radius from the central position of the cluster).

[0098] The following is an example of application of the first embodiment.

[0099] Fig. 16 is a block diagram showing an image analysis system according to a modified example of the first embodiment. Image analysis system 401A shown in Fig. 16 is configured by adding a transmitter / receiver 412 and an area determination unit 413 to image analysis system 401 shown in Fig. 15. It is assumed that information capable of identifying an area is transmitted to image analysis system 401 from an information processing terminal (not shown) connected to image analysis system 401A via a wired transmission path or a wireless transmission path. Examples of the information processing terminal include a smartphone and a personal computer.

[0100] When the transmitting / receiving unit 412 receives information indicating a predetermined area in an SAR image or a predetermined area on a map from the information processing terminal, the transmitting / receiving unit 412 outputs the information to the area determination unit 413. The area determination unit 413 determines an area corresponding to the given area included in the information. Specifically, the area determination unit 413 compares each of the areas (specifically, positions and sizes) of one or more clusters stored in the correlation storage unit 500 with the given area. The area determination unit 413 selects a cluster whose position and size match those of the given area or a cluster whose position and size are most similar to those of the given area as the area corresponding to the given area. The transmitting / receiving unit 412 distributes the characteristics of the selected cluster to the information processing terminal.

[0101] The information processing terminal determines the predetermined area in response to, for example, a user's operation. That is, the user specifies the predetermined area on the information processing terminal. The image analysis system 401A can provide the information processing terminal with characteristics of the area (cluster) corresponding to the specified area, taking the specified area specified by the user as the given area.

[0102] If the information processing terminal has an SAR image, the information processing terminal can determine whether a change has occurred in the SAR image using the characteristics of the image analysis system 401A for the area corresponding to the area specified by the user. In this case, the image analysis system 401A supplies the characteristics for the specified area to the information processing terminal, so the amount of data received by the information processing terminal is smaller than when the characteristics for the entire SAR image are supplied to the information processing terminal. Therefore, the user of the information processing terminal can quickly grasp the change. As an example, if the characteristic is a histogram of pixel intensity, topographical changes can be quickly grasped, so the topographical situation when a disaster occurs can be quickly grasped.

[0103] Example 2. 17 is a block diagram showing an image analysis system according to Example 2. The image analysis system 402 according to Example 2 includes the image analysis device 101, a pixel feature extraction unit 420, an inter-cluster similarity calculation unit 421, and a segmentation unit 422.

[0104] One of the preprocessing steps in image analysis is region division (segmentation), which involves, for example, using the superpixel technique to group similar pixels together.

[0105] In this embodiment, the pixel feature extraction unit 420 extracts (calculates) feature amounts of pixels in an SAR image (pixel feature amounts). The inter-cluster similarity calculation unit 421 receives information capable of identifying clusters from the division unit 110. The inter-cluster similarity calculation unit 421 integrates the pixel feature amounts in each cluster to obtain the pixel feature amount of each cluster.

[0106] The segmentation unit 422 compares the feature amounts of the clusters and groups together clusters with similar feature amounts to form a superpixel.

[0107] When performing segmentation on a huge SAR image with a large number of pixels, if you compare the features of the pixels in the SAR image and try to group pixels with similar features together, the computational complexity of the segmentation process increases, and it takes a long time to complete the process.

[0108] In this embodiment, the dividing unit 110 has already grouped statistically homogeneous pixels into clusters, so segmentation can be performed by comparing the features of the clusters, thereby reducing the amount of calculation required for the segmentation process.

[0109] It is also possible to envision a system in which an image analysis system having the image analysis device 101 and the pixel feature extraction unit 420 is prepared, and information is received from an information processing terminal having the inter-cluster similarity calculation unit 421 and the segmentation unit 422. In this case, the information processing terminal performs the segmentation.

[0110] Example 3. 18 is a block diagram showing an image analysis system according to Example 3. The image analysis system 403 according to Example 3 includes the image analysis device 101, a cluster association unit 430, a probability calculation unit 431, and an anomaly detection unit 432.

[0111] In this embodiment, the cluster association unit 430 inputs SAR images from the detection target SAR image storage unit 210, which stores SAR images of targets for anomaly detection. The detection target SAR images are aligned with the SAR images stored in the SAR image storage unit 200 so that pixels at the same positions correspond to pixels of the same point or feature.

[0112] Next, the operation of the image analysis system 403 will be described with reference to the flowchart of Fig. 19. The processes in steps S100 to S104 are the same as those in the first embodiment.

[0113] The cluster associating unit 430 receives information capable of identifying a cluster from the dividing unit 110. The cluster associating unit 430 divides the detection target SAR image in accordance with the division (clustering) performed by the dividing unit 110 (step S431).

[0114] The probability calculation unit 431 calculates the probability that a pixel value within a cluster is obtained for the detection target SAR image based on the representative distribution calculated by the representative calculation unit 120 (step S432).

[0115] If the probability calculated by the probability calculation unit 431 is equal to or less than a predetermined threshold, the anomaly detection unit 432 determines that an anomaly (a state different from normal) has occurred in the detection target SAR image (step S433). If the image analysis system 403 is applied to change detection or displacement detection, the anomaly detection unit 432 determines that a change or displacement has occurred in the detection target SAR image.

[0116] Next, a modified example of the third embodiment will be described. In this modified example, the detection target SAR image storage unit 210 stores SAR images captured from a viewpoint different from the viewpoint when the SAR images stored in the SAR image storage unit 200 were captured. Note that a different viewpoint includes a different type of satellite used to generate the image and a different image resolution, but primarily means a different orbit of the satellite used to generate the image. Note that in this modified example, the SAR images stored in the detection target SAR image storage unit 210 and the SAR images stored in the SAR image storage unit 200 have not yet been aligned.

[0117] In addition, in the modified example, an image analysis device (hereinafter referred to as a second image analysis device) configured similarly to the image analysis device 101 is installed between the detection target SAR image storage unit 210 and the cluster association unit 430. Therefore, in the modified example, the cluster association unit 430 receives as input information capable of identifying clusters from the division unit 110 in the image analysis device 101, and also receives as input information capable of identifying clusters from the division unit in the second image analysis device.

[0118] In this modification, the cluster association unit 430 handles the characteristics of each cluster as well as the associated information of the cluster, similar to the statistical calculation unit 411 in the first embodiment. The associated information is information indicating the position and size of the cluster in the SAR image or the position and size of the cluster on a map, similar to the first embodiment. The cluster association unit 430 then uses the associated information of the cluster to detect an area (cluster) in the SAR image from a certain viewpoint (in this example, the SAR image stored in the SAR image storage unit 200) corresponding to an area (cluster) in the SAR image from another viewpoint (in this example, the SAR image stored in the detection target SAR image storage unit 210). Note that the corresponding clusters are, for example, clusters with the same position and size or clusters with the most similar position and size.

[0119] In a modified example, the cluster association unit 430 further combines (for example, adds) the characteristics of the area in the SAR image stored in the SAR image storage unit 200 with the characteristics of the area in the SAR image stored in the detection target SAR image storage unit 210 that is determined to correspond to the characteristics of the area in the SAR image stored in the detection target SAR image storage unit 210.

[0120] In this modification, the characteristics of the corresponding regions of SAR images taken from a plurality of different viewpoints are combined, and the following effects are obtained.

[0121] For example, when the characteristic is a coherence matrix, the present embodiment increases the possibility that displacements and three-dimensional shapes that are difficult to grasp from SAR images taken from only one viewpoint can be grasped.

[0122] Furthermore, when the characteristic is a pixel intensity histogram, combining multiple satellites increases the possibility of achieving more frequently updated anomaly detection, which in turn allows for anomaly detection to be performed at shorter time intervals.

[0123] In the above-described embodiment and example, multiple pixels having variations according to the same probability distribution can be extracted at high speed. Furthermore, in the above-described example, multiple pixels having variations according to the same probability distribution are grouped into a small number of clusters, so that analyses such as displacement analysis, coverage classification, and anomaly detection can be performed at high speed by replacing pixel-by-pixel analysis with cluster-by-cluster analysis.

[0124] In the above embodiments and examples, SAR images are used as examples of images, but the above embodiments and examples can be applied to images or point clouds that have different distribution characteristics for each pixel.

[0125] Each component in the above embodiments and examples can be configured as a single piece of hardware, or as a single piece of software. Each component can also be configured as multiple pieces of hardware, or as multiple pieces of software. Furthermore, some of the components can be configured as hardware, and the other parts can be configured as software.

[0126] Each function (each process) in the above-described embodiments can be realized by a computer having a processor such as a CPU (Central Processing Unit), a memory, etc. For example, a program for implementing the method (process) in the above-described embodiments may be stored in a storage device (storage medium), and each function may be realized by executing the program stored in the storage device by a CPU.

[0127] FIG. 20 is a block diagram showing an example of a computer having a CPU. The computer is implemented in an image analysis system. The CPU 1000 executes processing in accordance with a program stored in a storage device 1001, thereby realizing the functions of the above-described embodiments and examples. That is, the CPU 1000 realizes the functions of the division unit 110, the representative calculation unit 120, the similarity calculation unit 130, the region limiting unit 140, the outlier detection unit 150, the isolated pixel determination unit 160, the similarity synthesis unit 170, the interference analysis unit 410, the statistics calculation unit 411, the pixel feature extraction unit 420, the inter-cluster similarity calculation unit 421, the segmentation unit 422, the cluster association unit 430, the probability calculation unit 431, and the anomaly detection unit 432 in the image analysis device and image analysis system shown in FIGS. 1, 6, 10, 12, and 14 to 18.

[0128] The storage device 1001 is, for example, a non-transitory computer-readable medium. The non-transitory computer-readable medium includes various types of tangible storage media. Specific examples of non-transitory computer-readable media include magnetic recording media (e.g., hard disks), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Compact Disc-Read Only Memory), CD-Rs (Compact Disc-Recordable), CD-R / Ws (Compact Disc-ReWritable), and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), and flash ROMs).

[0129] The program may also be stored in various types of transitory computer-readable media, to which the program is supplied, for example, via a wired or wireless communication path, i.e., via an electrical signal, an optical signal, or an electromagnetic wave.

[0130] The memory 1002 is realized by, for example, a random access memory (RAM), and is a storage means for temporarily storing data when the CPU 1000 executes processing. A configuration is also conceivable in which a program held in the storage device 1001 or a temporary computer-readable medium is transferred to the memory 1002, and the CPU 1000 executes processing based on the program in the memory 1002.

[0131] Fig. 21 is a block diagram showing the main components of an image analysis system. The image analysis system 10 shown in Fig. 21 includes a similarity calculation unit (similarity calculation means) 11 (implemented by similarity calculation unit 130 in the embodiment and examples) that calculates the similarity between a representative distribution of a cluster (a representative distribution representing a cluster) and the distribution of pixel values ​​within the cluster, a representative calculation unit (representative calculation means) 12 (implemented by representative calculation unit 120 in the embodiment and examples) that calculates the distribution of multiple pixels in each cluster as a representative distribution, and a division unit (division means) 13 (implemented by division unit 110 in the embodiment and examples) that assigns pixels in an input image to one of multiple clusters by referring to the similarity.

[0132] Some or all of the above-described embodiments and examples may be described as, but are not limited to, the following supplementary notes.

[0133] (Supplementary Note 1) A similarity calculation means for calculating a similarity between a representative distribution of a cluster and a distribution of pixel values ​​within the cluster; a representative calculation means for calculating a distribution similar to any of the distributions of the pixels in each of the clusters as a representative distribution of the cluster; a dividing means for allocating pixels in the input image to any one of the plurality of clusters by referring to the similarity; An image analysis system comprising:

[0134] (Note 2) A region limiting means (implemented by the region limiting unit 140 in the embodiment and examples) is provided for limiting a search range, which is a processing range of the similarity calculation means, based on the position of a pixel representing the cluster, The representative calculation means determines the position of a pixel that represents the cluster. Appendix 1 Image analysis system.

[0135] (Supplementary Note 3) An outlier detection means (implemented by the outlier detection unit 150 in the embodiments and examples) is provided that determines the distribution of pixel values ​​as an outlier when the similarity calculated by the similarity calculation means is different from any of the clusters compared with the representative distribution, The dividing means excludes the outliers from the targets for determining whether or not they have a distribution similar to the representative distribution of the cluster. Appendix 1 Image analysis system.

[0136] (Note 4) An isolated pixel determination means (implemented by the isolated pixel determination unit 160 in the embodiment and example) is provided for determining that a pixel having a different distribution compared with neighboring pixels in the input image is an isolated pixel, The dividing means excludes isolated pixels from the target of determining whether or not the isolated pixels have a distribution similar to the representative distribution of the cluster. Appendix 1 Image analysis system.

[0137] (Supplementary Note 5) A similarity synthesis means (implemented by the similarity synthesis unit 170 in the embodiment and example) is provided to synthesize the similarity of the distribution of pixel values ​​belonging to a certain cluster with the similarity of the distribution of pixel values ​​belonging to another cluster. 1. An image analysis system according to any of Annexes 1 to 4.

[0138] (Note 6) For each cluster, a complex correlation calculation unit (implemented by the interference analysis unit 410 and the statistics calculation unit 411 in the embodiment and examples) is provided to calculate the complex correlation between two images. 1. An image analysis system according to any of Annexes 1 to 5.

[0139] (Supplementary Note 7) An inter-cluster similarity calculation means for calculating the similarity between clusters (which is realized by the inter-cluster similarity calculation unit 421 in the embodiment and examples), a segmentation means (implemented by the segmentation unit 422 in the embodiment and example) for dividing the image based on the similarity between the clusters; 6. The image analysis system of any one of appendix 1 to appendix 5, comprising:

[0140] (Supplementary Note 8) A cluster association means (implemented by the cluster association unit 430 in the embodiment and examples) that divides the detection target image according to the clusters created by the division means; a probability calculation means (realized by a probability calculation unit 431 in the embodiment and examples) for calculating the probability of obtaining a pixel value in a cluster for the detection target image based on pixels in the cluster for the detection target image and a representative distribution of the cluster; 6. The image analysis system of any one of appendix 1 to appendix 5, comprising:

[0141] (Supplementary Note 9) A dividing means (implemented by the dividing unit 110 in the embodiment) for dividing a plurality of SAR images in which a common analysis region is captured into a plurality of regions each satisfying a criterion for determining that the regions are homogeneous; A characteristic acquisition means (implemented by the statistics calculation unit 411 in the embodiment) for obtaining characteristics for at least one of the plurality of regions; a distribution means (implemented by the transmitting / receiving unit 412 in the embodiment) for distributing information about the at least one region, the information including the location of the region and the characteristics determined for the region; An image analysis system comprising:

[0142] (Note 10) A region determination means (implemented by the region determination unit 413 in the embodiment) is provided to determine a region corresponding to a given region among the plurality of regions, The distribution means distributes the determined characteristics of the region. Appendix 9 Image analysis system.

[0143] (Supplementary Note 11) A division means for dividing each SAR image in a SAR image group including SAR images from a plurality of different viewpoints into a plurality of regions that satisfy a criterion for determining that each SAR image is homogeneous; a characteristic acquisition means for acquiring characteristics for each of the plurality of regions; a synthesis means for synthesizing the characteristics found for a region in an SAR image from a certain viewpoint among the plurality of viewpoints with a corresponding region in an SAR image from another viewpoint; An image analysis system comprising:

[0144] (Appendix 12) Calculating the similarity between a representative distribution representing a cluster and a distribution of pixel values ​​within the cluster; calculating a distribution similar to the distribution for the plurality of pixels in each of the clusters as the representative distribution; By referring to the similarity, pixels in the input image are assigned to any one of the plurality of clusters. Image analysis methods.

[0145] (Supplementary Note 13) determining the position of a pixel representing the cluster; A search range is limited based on the position of a pixel representative of the cluster, which is a range for calculating the similarity between the representative distribution of the cluster and the distribution of pixel values ​​within the cluster. Appendix 12 Image analysis methods.

[0146] (Appendix 14) For each cluster, calculate the complex correlation between the two images. Image analysis methods of Appendix 12 or Appendix 13.

[0147] (Appendix 15) A computer-readable recording medium storing an image analysis program, The image analysis program is installed on a computer. calculating a similarity between a representative distribution representing a cluster and a distribution of pixel values ​​within the cluster; calculating a distribution similar to the distribution for the plurality of pixels in each of the clusters as the representative distribution; By referring to the similarity, pixels in the input image are assigned to any of the plurality of clusters. A computer-readable recording medium.

[0148] (Appendix 16) The image analysis program is installed on the computer. determining the location of a pixel representative of said cluster; A search range is limited based on the position of a pixel representative of the cluster, which is a range for calculating the similarity between the representative distribution of the cluster and the distribution of pixel values ​​within the cluster. 16. The computer-readable storage medium of claim 15.

[0149] (Appendix 17) The image analysis program is installed on the computer. For each cluster, calculate the complex correlation between the two images. 17. The computer-readable storage medium of claim 15 or claim 16.

[0150] (Appendix 18) To the computer, calculating a similarity between a representative distribution of a cluster and a distribution of pixel values ​​within the cluster; calculating a distribution similar to any distribution of pixels in each of the clusters as a representative distribution of the cluster; By referring to the similarity, pixels in the input image are assigned to any of the plurality of clusters. Image analysis program for.

[0151] (Supplementary Note 19) causing a computer to determine the position of a pixel representing the cluster; A search range is limited based on the position of a pixel representative of the cluster, which is a range for calculating the similarity between the representative distribution of the cluster and the distribution of pixel values ​​within the cluster. Appendix 18 Image analysis program.

[0152] (Appendix 20) Have the computer calculate the complex correlation between the two images for each cluster. Image analysis programs in Appendix 18 or Appendix 19.

[0153] Although the present invention has been described above with reference to the embodiments and examples, the present invention is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. [Explanation of symbols]

[0154] 10,401,401A,402,403 Image analysis system 11 Similarity calculation unit 12 Representative calculation section 13 Division 101,102,103,104,105 Image analysis device 110 Split section 120 Representative calculation section 130 Similarity calculation unit 140 Area limited section 150 Outlier detection unit 160 Isolated pixel determination unit 170 Similarity synthesis section 200 SAR image storage unit 410 Interference Analysis Department 411 Statistics Calculation Department 412 Transmitter / Receiver 413 Area determination section 420 Pixel feature extraction unit 421 Inter-cluster similarity calculation part 422 Segmentation Department 430 Cluster Matching Unit 431 Probability Calculation Department 432 Anomaly detection unit 500 Correlation memory unit 1000 CPU 1001 Storage device 1002 memory

Claims

1. a similarity calculation means for calculating a similarity between a representative distribution representing a cluster and a distribution of pixel values ​​within the cluster; a representative calculation means for calculating a distribution of a plurality of pixels in each of the clusters as the representative distribution; a dividing means for allocating pixels in the input image to any one of the plurality of clusters by referring to the similarity; An image analysis system comprising:

2. a region limiting means for limiting a search range, which is a processing range of the similarity calculation means, based on the position of a pixel representing the cluster; The representative calculation means determines the position of a pixel that represents the cluster. The image analysis system according to claim 1 .

3. an outlier detection means for detecting a pixel value distribution as an outlier when the similarity calculated by the similarity calculation means is different from any of the clusters compared with the representative distribution; The dividing means excludes the outliers from the targets for determining whether or not they have a distribution similar to the representative distribution representing the cluster. The image analysis system according to claim 1 .

4. an isolated pixel determining means for determining, as an isolated pixel, a pixel having a different distribution compared with neighboring pixels in an input image; The dividing means excludes isolated pixels from the target of determining whether or not the isolated pixels have a distribution similar to the representative distribution representing the cluster. The image analysis system according to claim 1 .

5. The system includes a similarity synthesis means for synthesizing the similarity of the distribution of pixel values ​​belonging to a certain cluster with the similarity of the distribution of pixel values ​​belonging to another cluster. The image analysis system according to any one of claims 1 to 4.

6. For each cluster, a complex correlation calculation means is provided for calculating the complex correlation between two images. The image analysis system according to any one of claims 1 to 5.

7. an inter-cluster similarity calculation means for calculating a similarity between clusters; a segmentation means for dividing the image based on the similarity between the clusters; The image analysis system according to any one of claims 1 to 5, comprising:

8. a cluster association means for dividing the detection target image in accordance with the clusters created by the division means; a probability calculation means for calculating a probability that a pixel value in the cluster for the detection target image is obtained based on pixels in the cluster for the detection target image and a representative distribution representing the cluster; The image analysis system according to any one of claims 1 to 5, comprising:

9. The dividing means divides a plurality of SAR images that share a common analysis region into a plurality of regions that satisfy a criterion for determining that the regions are homogeneous, a characteristic acquisition means for acquiring a characteristic of at least one of the plurality of regions; and a distribution means for distributing information about the at least one region, the information including the location of the region and the characteristics determined for the region. The image analysis system according to claim 1 .

10. The dividing means divides each SAR image in a SAR image group including SAR images from a plurality of different viewpoints into a plurality of regions each satisfying a criterion for determining that the SAR images are homogeneous; a characteristic acquisition means for acquiring characteristics for each of the plurality of regions; a synthesis means for synthesizing the characteristics found for an area in an SAR image from a certain viewpoint among the plurality of viewpoints and an area in an SAR image from another viewpoint corresponding to the area in the SAR image from the other viewpoint. The image analysis system according to claim 1 .

Images