JP2007256254A - Water flow area detection system, water flow area detection method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To detect a water flow area by only an image signal that has a river or the like as subject, without having to install any object in water. <P>SOLUTION: This water flow area detection system/method is provided with a frame addition part 2 for adding images, including the water flow area and a non-water-flow area photographed by using a fixed camera CM over a plurality of frames; a space filter processing part 3 for intensifying an edge component in an added image; a binarization processing part 4 for classifying respective pixels in an image generated by the space filer processing part 3, based on whether the each pixel is an edge pixel; and an area division part 5A for determining the water flow area and a non-water-flow area, based on the binarized image obtained, and the water flow area is thereby detected by only the image signal with the river or the like as the subject, without having to install any object in the water. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a flowing water region detection system, a flowing water region detection method, and a program, and more particularly, to a flowing water region detection technique such as a river based on a video signal obtained by photographing.

  The Ministry of Land, Infrastructure, Transport and Tourism has established a system that installs water level meters and monitoring cameras at various locations on the riverbed and collects the data obtained from them in one place in order to detect flood damage caused by river floods in advance and use it for flood control activities. Many telemeters have been implemented. In addition, a water level plate with an inclined pattern is installed in the river, and the water level of the river is detected from the river image without installing a water level meter by capturing the image including the level water plate and performing image processing. A method has been proposed (for example, see Patent Document 1).

Japanese Patent Laid-Open No. 9-161076

  However, the installation of objects that obstruct running water in rivers can cause floods and other disasters, so they are strictly controlled by the River Law, and there are only a limited number of places where water can be installed in rivers. . On the other hand, collecting water level data from as many locations as possible is indispensable for generating more accurate and reliable disaster prevention information.

  An object of the present invention is to make it possible to detect a flowing water region of a river or the like from only a video signal having the river or the like as a subject without installing any object in the water.

The flowing water region detection system of the present invention is supplied with an image including a flowing water region and a non-flowing water region photographed using a fixed camera, and integrates the supplied image in a time direction. Spatial filter processing means for enhancing the edge component of the received video, and for each pixel in the video processed by the spatial filter processing means is determined for each pixel, and based on the determination result And a region discriminating unit for discriminating between the flowing water region and the non-flowing water region.
Further, the flowing water region detection system of the present invention is supplied with an image including a flowing water region and a non-flowing region imaged using a fixed camera, and integrates the supplied image in the time direction, and the integrating device The spatial filter processing means for enhancing the edge component of the image obtained by the above, and the flowing water region and the non-flowing water region are discriminated based on the feature value obtained for each line in the video processed by the spatial filter processing device. It comprises an area discriminating means.
The flowing water region detection method of the present invention emphasizes the integration step of integrating an image including a flowing water region and a non-flowing region photographed using a fixed camera in the time direction, and the edge component of the image obtained in the integration step. A spatial filter processing step, a determination step for determining whether each pixel in the video processed in the spatial filter processing step is an edge pixel, and a determination result in the determination step And an area discriminating step for discriminating between the flowing water area and the non-flowing water area.
Further, the flowing water region detection method of the present invention includes an integration step of integrating in a time direction an image including a flowing water region and a non-flowing region photographed using a fixed camera, and an edge component of the image obtained in the integration step. Based on the feature amount calculated in the feature amount calculation step, the feature amount calculation step for calculating the feature amount for each line of the video processed in the spatial filter processing step, and the feature amount calculated in the feature amount calculation step, An area discriminating step for discriminating between the flowing water area and the non-flowing water area.
The program of the present invention includes an integration step for integrating in a time direction an image including a flowing water region and a non-flowing region photographed using a fixed camera, and a spatial filter for enhancing an edge component of the image obtained in the integration step. A step of determining for each pixel whether or not each pixel in the image processed in the spatial filter processing step is an edge pixel, and the flow of water based on the determination result in the determination step An area determination step for determining an area and the non-flowing water area is caused to be executed by a computer.
In addition, the program of the present invention emphasizes an integration step for integrating in a time direction an image including a flowing water region and a non-flowing region photographed using a fixed camera, and an edge component of the image obtained in the integration step. A spatial filter processing step; a feature amount calculation step for calculating a feature amount for each line of the video processed in the spatial filter processing step; and the flowing water region based on the feature amount calculated in the feature amount calculation step. And a region determining step for determining the non-flowing water region.

  According to the present invention, an image including a flowing region and a non-flowing region captured by a fixed camera with a river or the like as a subject is integrated in the time direction to suppress edge components in the flowing region, and in the non-flowing region in the image A spatial filter that enhances the edge component is applied to the entire image. And it determines whether it is an edge component with respect to each pixel of the image | video with which the spatial filter was given, and discriminate | determines a flowing water area | region and a non-flowing water area | region based on the result. Alternatively, the flowing water region and the non-flowing water region are discriminated based on the feature amount obtained for each line in the image subjected to the spatial filter. Thereby, the flowing water region can be detected only from the video signal having the river or the like as a subject without installing any object in the water.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

<First Embodiment>
FIG. 1 is a block diagram showing a configuration example of a flowing water region detection system according to the first embodiment of the present invention. The flowing water region detection system according to the first embodiment performs integration in the time direction (for example, frame addition in this embodiment) and spatial filter processing from a video signal having a subject such as a river obtained by photographing using a fixed camera CM. Based on this, a flowing water area in the river or the like is detected.

  As shown in FIG. 1, the flowing water region detection system according to the first embodiment includes a region extraction unit 1, a frame addition unit 2, a spatial filter processing unit 3, a binarization processing unit 4, and a region division unit 5A. Hereinafter, each function part of the flowing water area detection system shown in FIG. 1 will be described in detail. In the following, a case where the water level of a river is detected by detecting and discriminating a flowing water region and a non-flowing water region in an actual river image as shown in FIG.

(Region extraction unit 1)
The region extraction unit 1 extracts a region in which a land portion is captured in half and a flowing water portion in half, from a captured image captured using the fixed camera CM over several frames. Here, the flowing water part is an area where water such as a water surface in the captured image is reflected, and the land part is an area other than the flowing water part (for example, an area such as a background image).

  For example, the region extraction unit 1 extracts a region image in which the upper half is a land portion and the lower half is a flowing portion as shown in FIG. When extracting the area image, the land part may be below and the flowing part may be above, or the land part and flowing part may be shown on the left and right, or on the right and left, respectively, and the flowing area can be detected. . Further, it is also possible to perform shooting by adjusting the angle of the fixed camera CM so that half of the entire shot video is a land portion and the other half is a flowing water portion, and the obtained shot video itself may be used as a region image.

  Here, it is desirable that a stationary object with a pattern appears in the land portion in the region image, and that the water surface always moves in the flowing water portion. Further, it is desirable that the water surface is horizontal in the region image, and it is also effective to perform affine transformation such as rotating the photographed image (region image) 90 degrees or enlarging or reducing the image so as to be so. In addition, for a video taken at night, for example, as long as a certain pattern is reflected in the land as a result of infrared irradiation, nothing may be reflected in the flowing water, and the flowing water area can be detected.

  The region image is extracted after the user designates the extraction position at a certain point in time so that the water surface is always located near the center of the region image according to the water level obtained based on the detection result of the flowing water region. It may be performed automatically at time intervals.

(Frame adder 2)
The frame addition unit 2 synchronously adds a plurality of frames for the region image extracted by the region extraction unit 1. That is, the frame addition unit 2 integrates the region image extracted by the region extraction unit 1 in the time direction. As a result, an image in which the moving flowing water part is blurred or smooth is obtained. That is, the edge component (high frequency component) of the flowing water part is suppressed. On the other hand, the stationary land is not particularly changed. This can be confirmed, for example, by comparing FIG. 2 (a) and FIG. 2 (b). FIG. 2B is obtained by synchronously adding a plurality of frames by the frame adder 2.

  However, when adding region images of a plurality of frames, if the addition is simply performed, the pixel value simply increases and the required resources increase. For example, the pixel value is divided by the number of added frames. Therefore, it is desirable to prevent the range of pixel values from expanding. Further, for example, when adding images, the pixel value may be multiplied by a weighting factor, or a bit shift may be performed on the pixel value.

  For example, when adding four frames, the frame adding unit 2 multiplies the pixel value in each frame by 0.25 or shifts the pixel value to the right by 2 bits so as to be equivalent to it. The pixel value already stored in the frame memory is added, and the addition result is newly stored in the frame memory. Thus, frame addition can be realized with a small number of frame memories without preparing as many frame memories as the number of sheets to be added.

  Further, the pixel value stored in the frame memory and the pixel value of the region image extracted by the region extraction unit 1 are added and divided by 2, and then the addition result is newly stored in the frame memory. By repeating this process, an image is generated by weight-adding region images of a plurality of frames. Alternatively, when taking an image with the fixed camera CM, an effect equivalent to that obtained by adding a plurality of frames as described above can be obtained by opening the shutter for a relatively long time and making the exposure time relatively long. be able to.

  Further, before adding images over a plurality of frames, non-linear processing such as median filter processing in the time direction may be performed on the images to be added. In this way, by performing non-linear processing on the region image to be added, it is possible to remove the influence caused by disturbances such as birds, insects, rain and snow particles, or car lights and water drops that block the front of the fixed camera CM. This makes it possible to perform stable water level detection.

  Here, although details will be described later, in the present embodiment, the land portion and the flowing water portion are determined by setting a region including many edge pixels in the video as a land portion and a region including few edge pixels as a flowing portion. Then, by recognizing the position of the boundary between the land portion and the flowing water portion as the water surface, it becomes possible to calculate the water level as shown in FIG.

(Spatial filter processing unit 3)
The spatial filter processing unit 3 is a space for emphasizing the edge component that is small in the flowing water portion but large in the land portion, that is, the difference between the flowing water portion and the land portion, with respect to the image generated by the frame addition unit 2. Apply filtering. For example, the image shown in FIG. 2C is obtained by applying the filter processing by the spatial filter processing unit 3 to the image shown in FIG.

In the present embodiment, the spatial filter processing unit 3 enhances the edge component of the image by convolution processing of the pixel value of the image and the spatial filter coefficient value. As the coefficient values of the spatial filter, those corresponding to differential processing are effective.
Where the transfer function of the spatial filter is

In other words, the coefficient value of the spatial filter used for processing in the spatial filter processing unit 3 is T1 = T2 = 1 in the above equation (1).

Or Prewitt operator, or

The Sobel operator expressed as follows is effective. Both of these are equivalent to performing differential processing in the horizontal direction in the image and averaging processing in the vertical direction.
The transfer function of the spatial filter is

And a filter of H (z) = 1−z ^{−1 and} a filter of H (z) = 1 + z ⁻¹ are applied once in the horizontal direction in the image, and H (z) = 1 + z ^{−. By} applying the filter “ ^1” twice in the vertical direction, the processing is equivalent to the above-described Sobel operator. More effective processing may be possible by appropriately adjusting the combination and the number of times of application of these filters.

In addition, for example, in the above formula (1), the value of T1 or T2 is set to an integer value larger than ₁ , and h (k ₁ , k ₂ ) is arbitrarily given, so that the degree of freedom is increased, and thus more effective. Processing may be possible.
In particular, the filter coefficient value of the spatial filter may be calculated by the method of least squares so that the variance value as a result of applying the spatial filter to the flowing water portion is minimized.
Or you may make it determine parameters, such as a filter coefficient value of a spatial filter, and a tap number, so that the ratio of a flowing water part and a land part may become the maximum about the dispersion value after a spatial filter process. For example, the dispersion value σ _L ² of the land portion is maximized under the constraint that the dispersion value σ _W ² of the flowing water portion after the spatial filter processing is constant. That is, the parameter relating to the spatial filter may be determined so as to maximize the evaluation function L shown in the following formula (5).

It is known that this problem can be solved as an eigenvalue problem by Lagrange's undetermined multiplier method. Conversely, the parameter relating to the spatial filter may be determined so as to minimize the dispersion value of the flowing water part under the constraint that the dispersion value of the land part is constant.
Also, depending on the image, it may be more effective to perform differential processing in the vertical direction instead of the horizontal direction in the image as described above. In some cases, it is not necessary to perform an averaging process.

  It is desirable that the parameters such as the spatial filter direction, the coefficient value, and the number of taps as described above are updated as appropriate in real time in accordance with the shooting environment (situation) that changes every moment. As a result, it is possible to cope with changes in the photographed image due to changes in sunlight, changes in water quality, turbidity, flow velocity, etc., and highly accurate and stable detection of the flowing water region can be performed.

(Binarization processing unit 4)
The binarization processing unit 4 determines for each pixel whether or not each pixel in the image generated by the spatial filter unit 3 is an edge pixel, and determines each pixel as an edge pixel based on the determination result. Or not (non-edge pixels). Further, the binarization processing unit 4 binarizes the pixel value into, for example, white (edge pixel) or black (non-edge pixel) according to the classification, and an example is shown in FIG. A binary image is obtained.

  Here, the threshold value when the binarization processing unit 4 performs binarization processing may be calculated, for example, according to the pixel value of the image generated by the spatial filter unit 3, for example, an average value thereof And the centroid value of the histogram can be applied.

(Area division unit 5A)
The area dividing unit 5A determines an area including many edge pixels from the image generated by the binarization processing unit 4 as a land part (non-flowing area) and the other as a flowing part (flowing area). Is divided into two. This discrimination processing is performed based on the distribution of edge pixels or the distribution of non-edge pixels in the image generated by the binarization processing unit 4.

For example, by outputting the boundary between the two regions thus obtained, the water level is calculated as the boundary between the land portion and the flowing water portion as shown in FIG.
Here, the binarization processing unit 4 and the region dividing unit 5A constitute region discriminating means of the present invention.

  In the image generated by the binarization processing unit 4, various forms are conceivable for the processing in the region dividing unit 5 </ b> A that bisects the region into a land portion (non-flowing water region) and a flowing water portion (flowing water region). Hereinafter, an example of processing in the region dividing unit 5A will be described with reference to FIGS.

  FIG. 3 is a block diagram showing a configuration example of the area dividing unit 5A, and FIG. 4 is a diagram for explaining the principle of area division by the area dividing unit 5A shown in FIG.

(Horizontal histogram calculation unit 11)
The horizontal histogram calculation unit 11 counts how many edge pixels exist for each row in the binary image generated by the binarization processing unit 4 shown in FIG. That is, the horizontal histogram calculation unit 11 integrates the number of edge pixels for each row in the binary image, and generates a horizontal histogram of the edge pixels.

  For example, in the binary image shown in FIG. 4A, there are six edge pixels in the first row from the top and seven edge pixels in the second row. Therefore, in the horizontal histogram (FIG. 4B) generated by the horizontal histogram calculation unit 11, the number of edge pixels is plotted as 6 and 7 for each row, that is, the vertical position.

(Vertical Histogram Calculation Unit 12)
The vertical histogram calculation unit 12 refers to the horizontal histogram generated by the horizontal histogram calculation unit 11 and counts the number of corresponding vertical positions for each edge pixel value. That is, the vertical histogram calculation unit 12 generates a vertical histogram regarding the number of edge pixels in the horizontal histogram.

  For example, in the horizontal histogram shown in FIG. 4B, there are two edge images in the first column from the left, and one edge image in the second column. In the horizontal histogram generated by the vertical histogram calculation unit 12 (FIG. 4C), the vertical integrated values of the number of edge pixels are plotted as 2 and 1 for each column, that is, the number of edge pixels. .

(Boundary value determination unit 13)
The vertical histogram generated by the vertical histogram calculation unit 12 includes two clusters (distributions) of a histogram portion related to the land portion and a histogram portion related to the flowing water portion. Therefore, it is possible to determine the boundary portion that separates these two clusters. The boundary value determination unit 13 determines the boundary portion (number of boundary pixels). Various methods can be used as a method for determining the boundary portion.

  For example, the boundary value determination unit 13 may determine the boundary so that the variance within the class is small and the distance between the classes is large, or the boundary so that the intra-class variance / inter-class variance ratio is maximized. May be determined. Alternatively, the boundary value determination unit 13 may determine the boundary between the two classes by reducing the vertical histogram to a bimodal Gaussian distribution.

(Water level calculation unit 14)
Based on the two class boundaries in the vertical histogram determined by the boundary value determination unit 13, the water level calculation unit 14 determines the boundary in the corresponding horizontal histogram, and further determines the boundary of the corresponding binary image. . As a result, the image is divided into two regions, a land portion and a flowing water portion, and the boundary is output as a water level.

  Specifically, with the boundary determined by the boundary value determination unit 13 as a threshold value, the corresponding boundary P1 in the vertical histogram shown in FIG. 4C is the horizontal direction shown in FIG. 4B. Through the corresponding point P2 in the histogram, a water level P3 that is a boundary between the land portion and the flowing water portion in the binary image is obtained. The case where it applies to an actual river image is shown in FIG.

  In the above description, the case where the water surface is horizontal in the image (the boundary between the land portion and the flowing water portion extends in the lateral direction) is shown as an example, but the water surface is vertical in the image (the land portion and the flowing water). When the boundary of the portion extends in the vertical direction), the edge pixel number is added up for each column to generate a vertical histogram of the edge pixel, and the horizontal direction of each edge pixel number is referenced with reference to that. A histogram may be generated.

  As described above, according to the first embodiment, from the captured image captured using the fixed camera CM with a river or the like as a subject, the region extraction unit 1 uses the boundary between the land part and the flowing water part, that is, the land part. An area image including the flowing part is extracted, and the frame adding part 2 adds several frames for each area to generate an image in which the flowing part is smooth. Further, a spatial filter that enhances the edge component in the image is applied to the entire image by the spatial filter processing unit 3, and binarization processing for classifying each pixel of the obtained image as an edge component is binary. The region dividing unit 5A performs the region division by discriminating the region containing a lot of edge components as the land portion and the other as the flowing portion. As a result, the land part and the flowing water part can be detected, respectively, and the boundary between the two areas is determined as the water level, so that the water flow can be detected only from the video signal having the river as a subject without installing any object in the water. A region can be detected.

<Second Embodiment>
Next, a second embodiment of the present invention will be described.
The flowing water area detection system according to the second embodiment is based on the integration of the time direction (frame addition, etc.) and spatial filter processing from a video signal having a river or the like obtained by photographing using a fixed camera as a subject. Detect the flowing water area at.

FIG. 8 is a block diagram illustrating a configuration example of the flowing water region detection system according to the second embodiment. In FIG. 8, blocks having the same functions as the blocks shown in FIG. 1 are denoted by the same reference numerals, and redundant description is omitted.
As shown in FIG. 8, the flowing water region detection system according to the second embodiment includes a region extraction unit 1, a frame addition unit 2, a spatial filter processing unit 3, a line feature amount calculation unit 6, and a region division unit 5B.

(Spatial filter processing unit 3)
The spatial filter processing unit 3 includes a parameter calculation unit 7 and has an edge component that is small in the flowing water portion but large in the land portion, that is, the flowing water portion and the land portion with respect to the image generated by the frame addition unit 2. A spatial filter process for emphasizing the difference is performed. For example, the spatial image processing is performed on the region image shown in FIG. 9A extracted from the captured video by the region extraction unit 1 and the image shown in FIG. By performing the filtering process by the unit 3, an image shown in FIG. 9C is obtained.

  In the present embodiment, the spatial filter processing unit 3 enhances the edge component of the image by convolution processing of the pixel value of the image and the spatial filter coefficient value. As the coefficient value of the spatial filter, one corresponding to differential processing is effective.

  The coefficient value of the spatial filter is calculated by the parameter calculation unit 7 in the spatial filter processing unit 3. The parameter calculation unit 7 calculates parameters such as the direction of the spatial filter, the coefficient value, the number of taps, etc., and performs a process of updating to the optimum one in real time according to the shooting environment (situation) that changes every moment. Note that the method for determining parameters such as the coefficient value of the spatial filter and the number of taps by the parameter calculation unit 7 is the same as the method for determining the parameter related to the spatial filter in the first embodiment, and a description thereof will be omitted.

  In this way, the parameter calculation unit 7 calculates the parameters related to the optimal spatial filter in real time according to the shooting environment that changes from moment to moment, and updates it appropriately, so that changes in sunshine, water quality, turbidity, flow velocity Thus, it is possible to cope with fluctuations in the captured image accompanying changes such as high accuracy and stable water flow region detection. Further, for example, even if the installation position of the fixed camera CM is changed, the parameters relating to the spatial filter can be automatically optimized.

(Line feature calculation unit 6)
Here, the image shown in FIG. 9 (a) is synchronously added over a plurality of frames by the frame adder 2, so that the high-frequency component is reduced in the flowing water portion as shown in FIG. 9 (b). It becomes a smooth signal and a signal having a clear outline in which high-frequency components are maintained for a stationary land portion. In order to make this difference obvious, the contour (high frequency) component of the land portion is emphasized with respect to the flowing water portion by applying the spatial filter processing to the image shown in FIG. 9B by the spatial filter processing portion 3. The image shown in FIG. 9C is obtained.

  The line feature amount calculation unit 6 calculates a variance value for each line of the image as the feature amount of each line of the image processed by the spatial filter processing unit 3 in this way. The feature amount calculated by the line feature amount calculation unit 6 based on the image shown in FIG. 9C is shown in FIG. As shown in FIG. 9D, the calculated feature value is generally large in the land and small in the flowing water.

  The line feature amount calculation unit 6 calculates the variance value as the feature amount of each line of the image, but may calculate an absolute value sum for each line of the image. When the absolute value sum is calculated, the amount of calculation can be reduced because the multiplication process is not included as compared with the case where the variance value is calculated.

(Region division unit 5B)
The region dividing unit 5B discriminates the land portion (non-flowing region) and the flowing portion (flowing region) in the image based on the feature amount of each line calculated by the line feature amount calculating unit 6, and divides the region into two. To do.

Based on the feature amount calculated by the line feature amount calculation unit 6, various forms are considered for the processing in the region dividing unit 5B that divides the region into a land portion (non-flowing water region) and a flowing water portion (flowing water region). It is done. For example, the feature quantity shown in FIG. 9 (d) can be approximated to the key figure P11, and the constricted portion of this key can be used as the water level as the boundary between the land portion and the flowing water portion. Further, for example, a linear discriminant method in which the class is divided into two classes based on the maximum intra-class variance / inter-class variance ratio criterion can be applied. The boundary between the two regions obtained in this way is output as a water level.
Here, the line feature amount calculation unit 6 and the region division unit 5B constitute the region discrimination means of the present invention.

  As described above, according to the second embodiment, from the captured image captured using the fixed camera CM with a river or the like as a subject, the region extraction unit 1 uses the boundary between the land part and the flowing water part, that is, the land part. An area image including the flowing part is extracted, and the frame adding part 2 adds several frames for each area to generate an image in which the flowing part is smooth. Furthermore, the spatial filter processing unit 3 applies a spatial filter that enhances the edge component in the image while appropriately changing the parameters of the spatial filter according to the shooting situation by the parameter calculation unit 6, and the obtained image The feature amount is calculated by the line feature amount calculation unit 6 for each of the lines, and the region division unit 5B classifies the image into two classes of the flowing water portion and the land portion based on the feature amount of each line, and performs region division. As a result, the land part and the flowing water part can be detected, respectively, and the boundary between the two areas is determined as the water level, so that the water flow can be detected only from the video signal having the river as a subject without installing any object in the water. A region can be detected.

  Further, according to the second embodiment, by performing region division based on the feature amount of the line and detecting the water level, the binarization processing and the vertical and horizontal directions performed in the first embodiment are performed. Histogram calculation is not required, and processing is performed in units of lines rather than processing in units of pixels. As a result, the amount of calculation processing in the entire system is reduced, and power saving and miniaturization of a highly accurate water level calculation processing system (processing circuit, etc.) can be achieved. Also, in the binarization process, it is not easy to adjust the threshold value to be set, and the accuracy of the water level calculation varies depending on the determination method. In the histogram calculation, the binarization process is performed in order to accumulate the results of the binarization process. Although the value error is also accumulated, in the second embodiment, the water level can be detected with higher accuracy by not using such processing.

  In the first and second embodiments described above, the region extraction unit 1 extracts one region image from a captured image captured using the fixed camera CM. However, as illustrated in FIG. In addition, a plurality of area images (area 1, area 2, and area 3 in the example shown in FIG. 6) may be extracted for one frame. In that case, the partial areas may overlap in the plurality of area images. For each of these area images, the land part and the flowing water part are discriminated by the above-described processing, and the final division of the land part and the flowing water part is performed by comprehensively judging from the obtained results. May be. For example, rainwater adheres to the lens of the fixed camera CM by using the average value of multiple results as the boundary between the final land part and the flowing water part, or by determining the final land part and flowing water area by the majority method. Even when an image failure due to rainfall, snowfall or fog occurs and it is difficult to detect the flowing water portion, the flowing water portion can be detected with high accuracy and stability.

(Other embodiments of the present invention)
The above-described embodiment can be configured by a CPU or MPU of a computer, a RAM, a ROM, and the like, and can be realized by operating a program stored in the RAM or the ROM, and the program is an embodiment of the present invention. include. In addition, a program that causes a computer to operate so as to perform the functions of the above-described embodiments can be realized by recording the program on a recording medium such as a CD-ROM and causing the computer to read the program. A medium is included in an embodiment of the present invention. As a recording medium for recording the program, a flexible disk, a hard disk, a magnetic tape, a magneto-optical disk, a nonvolatile memory card, and the like can be used in addition to the CD-ROM.
In addition, a program product in which the functions of the above-described embodiments are realized by a computer executing a program and performing processing is included in the embodiments of the present invention. The program product includes the program itself that implements the functions of the above-described embodiments, a computer loaded with the program, a transmission device that can provide the program to a computer that is communicably connected via a network, and the transmission There are network systems equipped with devices.
Moreover, not only the functions of the above-described embodiments are realized by executing a program supplied by a computer, but the program is also shared with an OS (operating system) or other application software running on the computer. When the functions of the above-described embodiment are realized, or when all or part of the processing of the supplied program is performed by a function expansion board or a function expansion unit of the computer, the functions of the above-described embodiment are realized. Such a program is included in the embodiment of the present invention.

For example, a computer function 700 as shown in FIG. 7 is provided, and the CPU 701 performs the operation in the above-described embodiment.
As shown in FIG. 7, the computer function 700 includes a CPU 701, a ROM 702, a RAM 703, a keyboard controller (KBC) 705 of a keyboard (KB) 709, and a CRT controller (CRTC) of a CRT display (CRT) 710 as a display unit. ) 706, a disk controller (DKC) 707 of a hard disk (HD) 711 and a flexible disk (FD) 712, and a network interface card (NIC) 708 are communicably connected to each other via a system bus 704. Yes.
The CPU 701 comprehensively controls each component connected to the system bus 704 by executing software stored in the ROM 702 or the HD 711 or software supplied from the FD 712.
That is, the CPU 701 reads out a processing program for performing the above-described operation from the ROM 702, the HD 711, or the FD 712 and executes it, thereby performing control for realizing the operation in the above-described embodiment.
The RAM 703 functions as a main memory or work area for the CPU 701.
The KBC 705 controls an instruction input from the KB 709 or a pointing device (not shown).
The CRTC 706 controls display on the CRT 710.
The DKC 707 controls access to the HD 711 and the FD 712 that store a boot program, various applications, user files, a network management program, the processing program, and the like.
The NIC 708 exchanges data with other devices on the network 713 in both directions.

  The above-described embodiments are merely examples of implementation in carrying out the present invention, and the technical scope of the present invention should not be construed as being limited thereto. That is, the present invention can be implemented in various forms without departing from the technical idea or the main features thereof.

It is a figure which shows the structural example of the flowing water area | region detection system by the 1st Embodiment of this invention. It is a figure which shows an example of the image processed with the flowing water area | region detection system shown in FIG. It is a figure which shows the structural example of an area division part. It is a figure for demonstrating the principle of the area division by the area division part shown in FIG. It is a figure which shows the case where the area division by the area division part shown in FIG. 3 is applied to an actual river image. It is a figure which shows the other example of the area image extraction by an area extraction part. It is a block diagram which shows the computer function which can implement | achieve the flowing water area | region detection system in this embodiment. It is a figure which shows the structural example of the flowing water area | region detection system by the 2nd Embodiment of this invention. It is a figure for demonstrating the process in the flowing water area | region detection system by 2nd Embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Area extraction part 2 Frame addition part 3 Spatial filter process part 4 Binarization process part 5A, 5B Area division part 6 Line feature-value calculation part 7 Parameter calculation part 11 Horizontal direction histogram calculation part 12 Vertical direction histogram calculation part 13 Boundary value Decision part 14 Water level calculation part

Claims (14)

An integration unit that integrates the supplied image in the time direction, provided with an image including a flowing region and a non-flowing region captured using a fixed camera;
Spatial filter processing means for enhancing an edge component of the video obtained by the integration means;
A region discriminating unit that determines, for each pixel, whether each pixel in the image processed by the spatial filter processing unit is an edge pixel, and discriminates the flowing water region and the non-flowing water region based on the determination result. And a flowing water region detection system. The region discriminating means
Binarization processing means for determining whether each image is an edge pixel for the image processed by the spatial filter processing means and classifying the image into an edge pixel or a non-edge pixel;
A region dividing unit that divides a region in the image into the flowing water region and the non-flowing region based on the distribution of the edge pixels or the non-edge pixels classified by the binarization processing unit; The flowing water region detection system according to claim 1.   The area dividing means integrates the number of target pixels with respect to the direction in which the boundary between the flowing water area and the non-flowing area extends, with the edge pixel or the non-edge pixel as the target pixel, and the distribution of the obtained target pixel number 3. The water flow region detection according to claim 2, wherein the boundary pixel number is determined from the boundary pixels, and the boundary pixel number is used as a threshold value, and the water flow region and the non-water flow region are divided based on the obtained target pixel number. system. An integration unit that integrates the supplied image in the time direction, provided with an image including a flowing region and a non-flowing region captured using a fixed camera;
Spatial filter processing means for enhancing an edge component of the video obtained by the integration means;
A running water area detection system comprising: area discrimination means for discriminating between the running water area and the non-flowing water area based on a feature amount obtained for each line in the video processed by the spatial filter processing means. The region discriminating means
For each line of the video processed by the spatial filter processing means, feature quantity calculation means for calculating a variance value or an absolute value sum as the feature quantity;
5. The flowing water region detection according to claim 4, further comprising region dividing means for dividing the region in the image into the flowing water region and the non-flowing region based on the feature amount calculated by the feature amount calculating means. system.   The running water area detection system according to claim 1, wherein the integration unit adds the supplied video over a plurality of frames.   7. The flowing water region detection system according to claim 6, wherein before the video is added over a plurality of frames by the integrating means, nonlinear processing is performed on the video.   8. The apparatus according to claim 1, further comprising a region extracting unit that extracts a region image including the flowing region and the non-flowing region from an image captured using the fixed camera and supplies the region image to the integrating unit. The flowing water region detection system according to any one of the preceding claims.   A plurality of area videos having different areas are extracted from the video captured using the fixed camera, and the flowing area and the non-flowing area in each area video obtained by processing each extracted area video. 9. The flowing water region detection system according to claim 8, wherein the flowing water region and the non-flowing water region in the captured image are determined based on a determination result.   The spatial filter used in the spatial filter processing means is calculated and updated as needed so that a filter coefficient value is calculated so that a variance value obtained as a result of the filtering process on the flowing water region is minimized. The flowing water region detection system according to any one of the above. An integration step of integrating in a time direction an image including a flowing water region and a non-flowing region photographed using a fixed camera;
A spatial filter processing step for enhancing the edge component of the video obtained in the integration step;
A determination step of determining for each pixel whether or not each pixel in the image processed in the spatial filter processing step is an edge pixel;
A running water area detection method comprising: an area discriminating process for discriminating between the running water area and the non-flowing water area based on a determination result in the determining process. An integration step of integrating in a time direction an image including a flowing water region and a non-flowing region photographed using a fixed camera;
A spatial filter processing step for enhancing the edge component of the video obtained in the integration step;
A feature amount calculating step for calculating a feature amount for each line of the video processed in the spatial filter processing step;
A running water area detection method comprising: an area discrimination step for discriminating between the running water area and the non-flowing water area based on the feature quantity calculated in the feature quantity calculation step. An integration step of integrating in a time direction an image including a flowing water region and a non-flowing region photographed using a fixed camera;
A spatial filter processing step for enhancing the edge component of the video obtained in the integration step;
A determination step of determining for each pixel whether or not each pixel in the image processed in the spatial filter processing step is an edge pixel;
A program for causing a computer to execute an area determination step for determining the flowing water area and the non-flowing water area based on a determination result in the determination step. An integration step of integrating in a time direction an image including a flowing water region and a non-flowing region photographed using a fixed camera;
A spatial filter processing step for enhancing the edge component of the video obtained in the integration step;
A feature amount calculating step for calculating a feature amount for each line of the video processed in the spatial filter processing step;
A program for causing a computer to execute an area discrimination step for discriminating between the flowing water area and the non-flowing water area based on the feature quantity calculated in the feature quantity calculating step.

Images